From 02df1786d1da0b5bd73d2cb0bdb9851ec709182f Mon Sep 17 00:00:00 2001
From: Geoffrey Sneddon <me@gsnedders.com>
Date: Tue, 26 Jun 2018 02:42:25 +0000
Subject: [PATCH] Bug 1467516 [wpt PR 11380] - Update html5lib and six,
 a=testonly

Automatic update from web-platform-testsFix #7200: Update vendored html5lib to 1.0.1

This adds webencodings as another vendored package, and moves both to
third_party (part of #10922).

--
Fix #10922: move six into third_party and update to 1.11

--

wpt-commits: efdb898172298b29a50c2e39cd40ac191ee8b383, 7cd0b885a529734ef71afd3254df48f57f255512
wpt-pr: 11380

--HG--
rename : testing/web-platform/tests/tools/html5lib/.gitmodules => testing/web-platform/tests/tools/third_party/html5lib/.gitmodules
rename : testing/web-platform/tests/tools/html5lib/CONTRIBUTING.rst => testing/web-platform/tests/tools/third_party/html5lib/CONTRIBUTING.rst
rename : testing/web-platform/tests/tools/html5lib/LICENSE => testing/web-platform/tests/tools/third_party/html5lib/LICENSE
rename : testing/web-platform/tests/tools/html5lib/doc/Makefile => testing/web-platform/tests/tools/third_party/html5lib/doc/Makefile
rename : testing/web-platform/tests/tools/html5lib/doc/changes.rst => testing/web-platform/tests/tools/third_party/html5lib/doc/changes.rst
rename : testing/web-platform/tests/tools/html5lib/doc/license.rst => testing/web-platform/tests/tools/third_party/html5lib/doc/license.rst
rename : testing/web-platform/tests/tools/html5lib/doc/make.bat => testing/web-platform/tests/tools/third_party/html5lib/doc/make.bat
rename : testing/web-platform/tests/tools/html5lib/doc/modules.rst => testing/web-platform/tests/tools/third_party/html5lib/doc/modules.rst
rename : testing/web-platform/tests/tools/html5lib/html5lib/trie/datrie.py => testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/datrie.py
rename : testing/web-platform/tests/tools/html5lib/html5lib/trie/py.py => testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/py.py
rename : testing/web-platform/tests/tools/html5lib/html5lib/filters/_base.py => testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/base.py
rename : testing/web-platform/tests/tools/html5lib/html5lib/tests/__init__.py => testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/__init__.py
rename : testing/web-platform/tests/tools/html5lib/html5lib/tests/tokenizertotree.py => testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tokenizertotree.py
rename : testing/web-platform/tests/tools/html5lib/html5lib/tests/us-ascii.html => testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/us-ascii.html
rename : testing/web-platform/tests/tools/html5lib/html5lib/tests/utf-8-bom.html => testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/utf-8-bom.html
rename : testing/web-platform/tests/tools/six/MANIFEST.in => testing/web-platform/tests/tools/third_party/six/MANIFEST.in
rename : testing/web-platform/tests/tools/six/documentation/Makefile => testing/web-platform/tests/tools/third_party/six/documentation/Makefile
rename : testing/web-platform/tests/tools/html5lib/requirements.txt => testing/web-platform/tests/tools/third_party/six/six.egg-info/top_level.txt
---
 testing/web-platform/meta/MANIFEST.json       |    2 +-
 testing/web-platform/tests/.gitmodules        |    3 -
 .../tests/tools/html5lib/.gitignore           |   20 -
 .../tests/tools/html5lib/.travis.yml          |   37 -
 .../tests/tools/html5lib/CHANGES.rst          |  171 -
 .../tests/tools/html5lib/doc/html5lib.rst     |   77 -
 .../html5lib/doc/html5lib.serializer.rst      |   19 -
 .../html5lib/doc/html5lib.treewalkers.rst     |   59 -
 .../tests/tools/html5lib/flake8-run.sh        |   14 -
 .../tests/tools/html5lib/html5lib/__init__.py |   23 -
 .../filters/alphabeticalattributes.py         |   20 -
 .../tools/html5lib/html5lib/filters/lint.py   |   93 -
 .../html5lib/html5lib/filters/sanitizer.py    |   12 -
 .../tools/html5lib/html5lib/sanitizer.py      |  271 --
 .../html5lib/html5lib/serializer/__init__.py  |   16 -
 .../html5lib/serializer/htmlserializer.py     |  320 --
 .../tools/html5lib/html5lib/tests/README      |    1 -
 .../html5lib/html5lib/tests/mockParser.py     |   41 -
 .../tests/performance/concatenation.py        |   36 -
 .../html5lib/html5lib/tests/test_encoding.py  |   67 -
 .../html5lib/html5lib/tests/test_parser.py    |   96 -
 .../html5lib/html5lib/tests/test_parser2.py   |   64 -
 .../html5lib/html5lib/tests/test_sanitizer.py |  105 -
 .../html5lib/tests/test_serializer.py         |  178 -
 .../html5lib/html5lib/tests/test_stream.py    |  183 -
 .../html5lib/tests/test_treewalkers.py        |  353 --
 .../html5lib/tests/test_whitespace_filter.py  |  133 -
 .../html5lib/treeadapters/__init__.py         |    0
 .../html5lib/treebuilders/__init__.py         |   76 -
 .../html5lib/html5lib/treewalkers/__init__.py |   57 -
 .../html5lib/html5lib/treewalkers/pulldom.py  |   63 -
 .../tools/html5lib/requirements-install.sh    |   16 -
 .../html5lib/requirements-optional-2.6.txt    |    5 -
 .../requirements-optional-cpython.txt         |    5 -
 .../tools/html5lib/requirements-optional.txt  |   13 -
 .../tools/html5lib/requirements-test.txt      |    5 -
 .../tests/tools/html5lib/setup.py             |   44 -
 .../web-platform/tests/tools/html5lib/tox.ini |   30 -
 .../tests/tools/html5lib/utils/iana_parse.py  |   24 -
 .../tests/tools/html5lib/utils/spider.py      |  122 -
 .../web-platform/tests/tools/localpaths.py    |    5 +-
 .../web-platform/tests/tools/six/.gitignore   |    9 -
 .../web-platform/tests/tools/six/.hgignore    |    8 -
 .../web-platform/tests/tools/six/CONTRIBUTORS |   22 -
 testing/web-platform/tests/tools/six/README   |   16 -
 .../web-platform/tests/tools/six/setup.cfg    |    2 -
 testing/web-platform/tests/tools/six/setup.py |   32 -
 testing/web-platform/tests/tools/six/tox.ini  |   12 -
 .../tools/third_party/html5lib/.appveyor.yml  |   31 +
 .../tools/third_party/html5lib/.coveragerc    |    8 +
 .../tools/third_party/html5lib/.gitignore     |   85 +
 .../{ => third_party}/html5lib/.gitmodules    |    0
 .../third_party/html5lib/.prospector.yaml     |   21 +
 .../tools/third_party/html5lib/.pylintrc      |   10 +
 .../tools/third_party/html5lib/.pytest.expect | 1322 +++++++
 .../tools/third_party/html5lib/.travis.yml    |   32 +
 .../{ => third_party}/html5lib/AUTHORS.rst    |   38 +-
 .../tools/third_party/html5lib/CHANGES.rst    |  335 ++
 .../html5lib/CONTRIBUTING.rst                 |    0
 .../tools/{ => third_party}/html5lib/LICENSE  |    0
 .../{ => third_party}/html5lib/MANIFEST.in    |    4 +
 .../{ => third_party}/html5lib/README.rst     |   26 +-
 .../{ => third_party}/html5lib/debug-info.py  |    2 +-
 .../{ => third_party}/html5lib/doc/Makefile   |    0
 .../html5lib/doc/changes.rst                  |    0
 .../{ => third_party}/html5lib/doc/conf.py    |    2 +-
 .../html5lib/doc/html5lib.filters.rst         |   19 +-
 .../third_party/html5lib/doc/html5lib.rst     |   38 +
 .../html5lib/doc/html5lib.treeadapters.rst    |   20 +
 .../html5lib/doc/html5lib.treebuilders.rst    |   15 +-
 .../html5lib/doc/html5lib.treewalkers.rst     |   50 +
 .../{ => third_party}/html5lib/doc/index.rst  |    1 +
 .../html5lib/doc/license.rst                  |    0
 .../{ => third_party}/html5lib/doc/make.bat   |    0
 .../html5lib/doc/modules.rst                  |    0
 .../html5lib/doc/movingparts.rst              |  106 +-
 .../tools/third_party/html5lib/flake8-run.sh  |    9 +
 .../third_party/html5lib/html5lib/__init__.py |   35 +
 .../html5lib/html5lib/_ihatexml.py}           |   15 +-
 .../html5lib/html5lib/_inputstream.py}        |  231 +-
 .../html5lib/html5lib/_tokenizer.py}          |   36 +-
 .../html5lib/html5lib/_trie}/__init__.py      |    2 +
 .../html5lib/html5lib/_trie}/_base.py         |    6 +-
 .../html5lib/html5lib/_trie}/datrie.py        |    0
 .../html5lib/html5lib/_trie}/py.py            |    0
 .../html5lib/html5lib/_utils.py}              |   56 +-
 .../html5lib/html5lib/constants.py            |  697 ++--
 .../html5lib/html5lib/filters/__init__.py     |    0
 .../filters/alphabeticalattributes.py         |   29 +
 .../html5lib/html5lib/filters/base.py}        |    0
 .../html5lib/filters/inject_meta_charset.py   |   16 +-
 .../html5lib/html5lib/filters/lint.py         |   93 +
 .../html5lib/html5lib/filters/optionaltags.py |   12 +-
 .../html5lib/html5lib/filters/sanitizer.py    |  896 +++++
 .../html5lib/html5lib/filters/whitespace.py   |    8 +-
 .../html5lib/html5lib/html5parser.py          |  662 ++--
 .../html5lib/html5lib/serializer.py           |  409 +++
 .../html5lib/html5lib/tests/__init__.py       |    0
 .../html5lib/html5lib/tests/conftest.py       |  108 +
 .../tests/sanitizer-testdata/tests1.dat       |  433 +++
 .../html5lib/html5lib/tests/sanitizer.py      |   50 +
 .../tests/serializer-testdata/core.test       |  395 ++
 .../tests/serializer-testdata/injectmeta.test |  350 ++
 .../serializer-testdata/optionaltags.test     | 3254 +++++++++++++++++
 .../tests/serializer-testdata/options.test    |  334 ++
 .../tests/serializer-testdata/whitespace.test |  198 +
 .../html5lib/html5lib/tests/support.py        |   87 +-
 .../tests/test_alphabeticalattributes.py      |   78 +
 .../html5lib/html5lib/tests/test_encoding.py  |  116 +
 .../html5lib/html5lib/tests/test_meta.py      |   41 +
 .../tests/test_optionaltags_filter.py         |    7 +
 .../html5lib/html5lib/tests/test_parser2.py   |  130 +
 .../html5lib/html5lib/tests/test_sanitizer.py |  127 +
 .../html5lib/tests/test_serializer.py         |  225 ++
 .../html5lib/html5lib/tests/test_stream.py    |  323 ++
 .../html5lib/tests/test_treeadapters.py       |    4 +-
 .../html5lib/tests/test_treewalkers.py        |  136 +
 .../html5lib/tests/test_whitespace_filter.py  |  125 +
 .../html5lib/html5lib/tests/tokenizer.py}     |  144 +-
 .../html5lib/tests/tokenizertotree.py         |    0
 .../html5lib/tests/tree_construction.py       |  204 ++
 .../html5lib/html5lib/tests/us-ascii.html     |    0
 .../html5lib/html5lib/tests/utf-8-bom.html    |    0
 .../html5lib/treeadapters/__init__.py         |   30 +
 .../html5lib/html5lib/treeadapters/genshi.py  |   54 +
 .../html5lib/html5lib/treeadapters/sax.py     |    8 +-
 .../html5lib/treebuilders/__init__.py         |   88 +
 .../html5lib/html5lib/treebuilders/base.py}   |   82 +-
 .../html5lib/html5lib/treebuilders/dom.py     |   65 +-
 .../html5lib/html5lib/treebuilders/etree.py   |   21 +-
 .../html5lib/treebuilders/etree_lxml.py       |   43 +-
 .../html5lib/html5lib/treewalkers/__init__.py |  154 +
 .../html5lib/html5lib/treewalkers/base.py}    |  182 +-
 .../html5lib/html5lib/treewalkers/dom.py      |   19 +-
 .../html5lib/html5lib/treewalkers/etree.py    |   34 +-
 .../html5lib/treewalkers/etree_lxml.py}       |   69 +-
 .../html5lib/html5lib/treewalkers/genshi.py}  |   12 +-
 .../tools/{ => third_party}/html5lib/parse.py |   77 +-
 .../tools/third_party/html5lib/pytest.ini     |   17 +
 .../html5lib/requirements-install.sh          |   15 +
 .../html5lib/requirements-optional.txt        |   17 +
 .../html5lib/requirements-test.txt            |   10 +
 .../third_party/html5lib/requirements.txt     |    2 +
 .../tools/third_party/html5lib/setup.cfg      |   14 +
 .../tests/tools/third_party/html5lib/setup.py |  125 +
 .../tests/tools/third_party/html5lib/tox.ini  |   23 +
 .../html5lib/utils/entities.py                |   50 +-
 .../tests/tools/{ => third_party}/six/CHANGES |   51 +-
 .../tests/tools/{ => third_party}/six/LICENSE |    2 +-
 .../tools/{ => third_party}/six/MANIFEST.in   |    0
 .../tests/tools/third_party/six/PKG-INFO      |   41 +
 .../tests/tools/third_party/six/README.rst    |   25 +
 .../six/documentation/Makefile                |    0
 .../six/documentation/conf.py                 |    2 +-
 .../six/documentation/index.rst               |  351 +-
 .../tests/tools/third_party/six/setup.cfg     |   21 +
 .../tests/tools/third_party/six/setup.py      |   56 +
 .../third_party/six/six.egg-info/PKG-INFO     |   41 +
 .../third_party/six/six.egg-info/SOURCES.txt  |   15 +
 .../six/six.egg-info/dependency_links.txt     |    1 +
 .../six/six.egg-info/top_level.txt}           |    0
 .../tests/tools/{ => third_party}/six/six.py  |  170 +-
 .../tools/{ => third_party}/six/test_six.py   |  151 +-
 .../tools/third_party/webencodings/PKG-INFO   |   50 +
 .../tools/third_party/webencodings/README.rst |   25 +
 .../tools/third_party/webencodings/setup.cfg  |   14 +
 .../tools/third_party/webencodings/setup.py   |   47 +
 .../webencodings.egg-info/PKG-INFO            |   50 +
 .../webencodings.egg-info/SOURCES.txt         |   12 +
 .../dependency_links.txt                      |    1 +
 .../webencodings.egg-info/top_level.txt       |    1 +
 .../webencodings/webencodings/__init__.py     |  342 ++
 .../webencodings/webencodings/labels.py       |  231 ++
 .../webencodings/webencodings/mklabels.py     |   59 +
 .../webencodings/webencodings/tests.py        |  153 +
 .../webencodings/x_user_defined.py            |  325 ++
 176 files changed, 14187 insertions(+), 4487 deletions(-)
 delete mode 100644 testing/web-platform/tests/tools/html5lib/.gitignore
 delete mode 100644 testing/web-platform/tests/tools/html5lib/.travis.yml
 delete mode 100644 testing/web-platform/tests/tools/html5lib/CHANGES.rst
 delete mode 100644 testing/web-platform/tests/tools/html5lib/doc/html5lib.rst
 delete mode 100644 testing/web-platform/tests/tools/html5lib/doc/html5lib.serializer.rst
 delete mode 100644 testing/web-platform/tests/tools/html5lib/doc/html5lib.treewalkers.rst
 delete mode 100755 testing/web-platform/tests/tools/html5lib/flake8-run.sh
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/__init__.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/filters/alphabeticalattributes.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/filters/lint.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/filters/sanitizer.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/sanitizer.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/serializer/__init__.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/serializer/htmlserializer.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/README
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/mockParser.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/performance/concatenation.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/test_encoding.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/test_parser.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/test_parser2.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/test_sanitizer.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/test_serializer.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/test_stream.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/test_treewalkers.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/tests/test_whitespace_filter.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/treeadapters/__init__.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/__init__.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/__init__.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/pulldom.py
 delete mode 100755 testing/web-platform/tests/tools/html5lib/requirements-install.sh
 delete mode 100644 testing/web-platform/tests/tools/html5lib/requirements-optional-2.6.txt
 delete mode 100644 testing/web-platform/tests/tools/html5lib/requirements-optional-cpython.txt
 delete mode 100644 testing/web-platform/tests/tools/html5lib/requirements-optional.txt
 delete mode 100644 testing/web-platform/tests/tools/html5lib/requirements-test.txt
 delete mode 100644 testing/web-platform/tests/tools/html5lib/setup.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/tox.ini
 delete mode 100644 testing/web-platform/tests/tools/html5lib/utils/iana_parse.py
 delete mode 100644 testing/web-platform/tests/tools/html5lib/utils/spider.py
 delete mode 100644 testing/web-platform/tests/tools/six/.gitignore
 delete mode 100644 testing/web-platform/tests/tools/six/.hgignore
 delete mode 100644 testing/web-platform/tests/tools/six/CONTRIBUTORS
 delete mode 100644 testing/web-platform/tests/tools/six/README
 delete mode 100644 testing/web-platform/tests/tools/six/setup.cfg
 delete mode 100644 testing/web-platform/tests/tools/six/setup.py
 delete mode 100644 testing/web-platform/tests/tools/six/tox.ini
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/.appveyor.yml
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/.coveragerc
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/.gitignore
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/.gitmodules (100%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/.prospector.yaml
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/.pylintrc
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/.pytest.expect
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/.travis.yml
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/AUTHORS.rst (52%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/CHANGES.rst
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/CONTRIBUTING.rst (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/LICENSE (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/MANIFEST.in (65%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/README.rst (79%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/debug-info.py (88%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/Makefile (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/changes.rst (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/conf.py (99%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/html5lib.filters.rst (77%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.rst
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treeadapters.rst
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/html5lib.treebuilders.rst (73%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treewalkers.rst
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/index.rst (95%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/license.rst (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/make.bat (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/modules.rst (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/doc/movingparts.rst (56%)
 create mode 100755 testing/web-platform/tests/tools/third_party/html5lib/flake8-run.sh
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/__init__.py
 rename testing/web-platform/tests/tools/{html5lib/html5lib/ihatexml.py => third_party/html5lib/html5lib/_ihatexml.py} (97%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/inputstream.py => third_party/html5lib/html5lib/_inputstream.py} (80%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/tokenizer.py => third_party/html5lib/html5lib/_tokenizer.py} (98%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/trie => third_party/html5lib/html5lib/_trie}/__init__.py (73%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/trie => third_party/html5lib/html5lib/_trie}/_base.py (85%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/trie => third_party/html5lib/html5lib/_trie}/datrie.py (100%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/trie => third_party/html5lib/html5lib/_trie}/py.py (100%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/utils.py => third_party/html5lib/html5lib/_utils.py} (55%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/constants.py (81%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/filters/__init__.py (100%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/alphabeticalattributes.py
 rename testing/web-platform/tests/tools/{html5lib/html5lib/filters/_base.py => third_party/html5lib/html5lib/filters/base.py} (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/filters/inject_meta_charset.py (88%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/lint.py
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/filters/optionaltags.py (96%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/sanitizer.py
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/filters/whitespace.py (85%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/html5parser.py (85%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/serializer.py
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/tests/__init__.py (100%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/conftest.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/sanitizer-testdata/tests1.dat
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/sanitizer.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/core.test
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/injectmeta.test
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/optionaltags.test
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/options.test
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/whitespace.test
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/tests/support.py (70%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_alphabeticalattributes.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_encoding.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_meta.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_optionaltags_filter.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_parser2.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_sanitizer.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_serializer.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_stream.py
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/tests/test_treeadapters.py (93%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_treewalkers.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_whitespace_filter.py
 rename testing/web-platform/tests/tools/{html5lib/html5lib/tests/test_tokenizer.py => third_party/html5lib/html5lib/tests/tokenizer.py} (52%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/tests/tokenizertotree.py (100%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tree_construction.py
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/tests/us-ascii.html (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/tests/utf-8-bom.html (100%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/__init__.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/genshi.py
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/treeadapters/sax.py (89%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/__init__.py
 rename testing/web-platform/tests/tools/{html5lib/html5lib/treebuilders/_base.py => third_party/html5lib/html5lib/treebuilders/base.py} (86%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/treebuilders/dom.py (85%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/treebuilders/etree.py (96%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/treebuilders/etree_lxml.py (93%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/__init__.py
 rename testing/web-platform/tests/tools/{html5lib/html5lib/treewalkers/_base.py => third_party/html5lib/html5lib/treewalkers/base.py} (52%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/treewalkers/dom.py (70%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/html5lib/treewalkers/etree.py (84%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/treewalkers/lxmletree.py => third_party/html5lib/html5lib/treewalkers/etree_lxml.py} (72%)
 rename testing/web-platform/tests/tools/{html5lib/html5lib/treewalkers/genshistream.py => third_party/html5lib/html5lib/treewalkers/genshi.py} (90%)
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/parse.py (78%)
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/pytest.ini
 create mode 100755 testing/web-platform/tests/tools/third_party/html5lib/requirements-install.sh
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/requirements-optional.txt
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/requirements-test.txt
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/requirements.txt
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/setup.cfg
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/setup.py
 create mode 100644 testing/web-platform/tests/tools/third_party/html5lib/tox.ini
 rename testing/web-platform/tests/tools/{ => third_party}/html5lib/utils/entities.py (67%)
 rename testing/web-platform/tests/tools/{ => third_party}/six/CHANGES (82%)
 rename testing/web-platform/tests/tools/{ => third_party}/six/LICENSE (96%)
 rename testing/web-platform/tests/tools/{ => third_party}/six/MANIFEST.in (100%)
 create mode 100644 testing/web-platform/tests/tools/third_party/six/PKG-INFO
 create mode 100644 testing/web-platform/tests/tools/third_party/six/README.rst
 rename testing/web-platform/tests/tools/{ => third_party}/six/documentation/Makefile (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/six/documentation/conf.py (99%)
 rename testing/web-platform/tests/tools/{ => third_party}/six/documentation/index.rst (73%)
 create mode 100644 testing/web-platform/tests/tools/third_party/six/setup.cfg
 create mode 100644 testing/web-platform/tests/tools/third_party/six/setup.py
 create mode 100644 testing/web-platform/tests/tools/third_party/six/six.egg-info/PKG-INFO
 create mode 100644 testing/web-platform/tests/tools/third_party/six/six.egg-info/SOURCES.txt
 create mode 100644 testing/web-platform/tests/tools/third_party/six/six.egg-info/dependency_links.txt
 rename testing/web-platform/tests/tools/{html5lib/requirements.txt => third_party/six/six.egg-info/top_level.txt} (100%)
 rename testing/web-platform/tests/tools/{ => third_party}/six/six.py (87%)
 rename testing/web-platform/tests/tools/{ => third_party}/six/test_six.py (82%)
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/PKG-INFO
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/README.rst
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/setup.cfg
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/setup.py
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/PKG-INFO
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/SOURCES.txt
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/dependency_links.txt
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/top_level.txt
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings/__init__.py
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings/labels.py
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings/mklabels.py
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings/tests.py
 create mode 100644 testing/web-platform/tests/tools/third_party/webencodings/webencodings/x_user_defined.py

diff --git a/testing/web-platform/meta/MANIFEST.json b/testing/web-platform/meta/MANIFEST.json
index 2b42766a8579..e885533838bf 100644
--- a/testing/web-platform/meta/MANIFEST.json
+++ b/testing/web-platform/meta/MANIFEST.json
@@ -405432,7 +405432,7 @@
    "support"
   ],
   "./.gitmodules": [
-   "6a203e28d43909d7513daf8761281b351d2b2bd7",
+   "9e008399bdce736c7c03f7db0c3e8d624083c6b9",
    "support"
   ],
   "./.pyup.yml": [
diff --git a/testing/web-platform/tests/.gitmodules b/testing/web-platform/tests/.gitmodules
index 90c91af579f8..f40c77f6331e 100644
--- a/testing/web-platform/tests/.gitmodules
+++ b/testing/web-platform/tests/.gitmodules
@@ -1,6 +1,3 @@
-[submodule "tools/html5lib/html5lib/tests/testdata"]
-	path = tools/html5lib/html5lib/tests/testdata
-	url = https://github.com/html5lib/html5lib-tests.git
 [submodule "resources/webidl2/test/widlproc"]
 	path = resources/webidl2/test/widlproc
 	url = https://github.com/dontcallmedom/widlproc.git
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/html5lib/.gitignore b/testing/web-platform/tests/tools/html5lib/.gitignore
deleted file mode 100644
index 73d97fec0733..000000000000
--- a/testing/web-platform/tests/tools/html5lib/.gitignore
+++ /dev/null
@@ -1,20 +0,0 @@
-# Because we never want compiled Python
-__pycache__/
-*.pyc
-
-# Ignore stuff produced by distutils
-/build/
-/dist/
-/MANIFEST
-
-# Generated by parse.py -p
-stats.prof
-
-# From cover (esp. in combination with nose)
-.coverage
-
-# Because tox's data is inherently local
-/.tox/
-
-# We have no interest in built Sphinx files
-/doc/_build
diff --git a/testing/web-platform/tests/tools/html5lib/.travis.yml b/testing/web-platform/tests/tools/html5lib/.travis.yml
deleted file mode 100644
index dd3130019e7a..000000000000
--- a/testing/web-platform/tests/tools/html5lib/.travis.yml
+++ /dev/null
@@ -1,37 +0,0 @@
-language: python
-python:
-  - "2.6"
-  - "2.7"
-  - "3.2"
-  - "3.3"
-  - "3.4"
-  - "pypy"
-
-env:
-  - USE_OPTIONAL=true
-  - USE_OPTIONAL=false
-
-matrix:
-  exclude:
-    - python: "2.7"
-      env: USE_OPTIONAL=false
-    - python: "3.4"
-      env: USE_OPTIONAL=false
-  include:
-    - python: "2.7"
-      env: USE_OPTIONAL=false FLAKE=true
-    - python: "3.4"
-      env: USE_OPTIONAL=false FLAKE=true
-
-before_install:
-  - git submodule update --init --recursive
-
-install:
-  - bash requirements-install.sh
-
-script:
-  - nosetests
-  - bash flake8-run.sh
-
-after_script:
-  - python debug-info.py
diff --git a/testing/web-platform/tests/tools/html5lib/CHANGES.rst b/testing/web-platform/tests/tools/html5lib/CHANGES.rst
deleted file mode 100644
index 1431b3c9b8fa..000000000000
--- a/testing/web-platform/tests/tools/html5lib/CHANGES.rst
+++ /dev/null
@@ -1,171 +0,0 @@
-Change Log
-----------
-
-0.9999
-~~~~~~
-
-Released on XXX, 2014
-
-* XXX
-
-
-0.999
-~~~~~
-
-Released on December 23, 2013
-
-* Fix #127: add work-around for CPython issue #20007: .read(0) on
-  http.client.HTTPResponse drops the rest of the content.
-
-* Fix #115: lxml treewalker can now deal with fragments containing, at
-  their root level, text nodes with non-ASCII characters on Python 2.
-
-
-0.99
-~~~~
-
-Released on September 10, 2013
-
-* No library changes from 1.0b3; released as 0.99 as pip has changed
-  behaviour from 1.4 to avoid installing pre-release versions per
-  PEP 440.
-
-
-1.0b3
-~~~~~
-
-Released on July 24, 2013
-
-* Removed ``RecursiveTreeWalker`` from ``treewalkers._base``. Any
-  implementation using it should be moved to
-  ``NonRecursiveTreeWalker``, as everything bundled with html5lib has
-  for years.
-
-* Fix #67 so that ``BufferedStream`` to correctly returns a bytes
-  object, thereby fixing any case where html5lib is passed a
-  non-seekable RawIOBase-like object.
-
-
-1.0b2
-~~~~~
-
-Released on June 27, 2013
-
-* Removed reordering of attributes within the serializer. There is now
-  an ``alphabetical_attributes`` option which preserves the previous
-  behaviour through a new filter. This allows attribute order to be
-  preserved through html5lib if the tree builder preserves order.
-
-* Removed ``dom2sax`` from DOM treebuilders. It has been replaced by
-  ``treeadapters.sax.to_sax`` which is generic and supports any
-  treewalker; it also resolves all known bugs with ``dom2sax``.
-
-* Fix treewalker assertions on hitting bytes strings on
-  Python 2. Previous to 1.0b1, treewalkers coped with mixed
-  bytes/unicode data on Python 2; this reintroduces this prior
-  behaviour on Python 2. Behaviour is unchanged on Python 3.
-
-
-1.0b1
-~~~~~
-
-Released on May 17, 2013
-
-* Implementation updated to implement the `HTML specification
-  <http://www.whatwg.org/specs/web-apps/current-work/>`_ as of 5th May
-  2013 (`SVN <http://svn.whatwg.org/webapps/>`_ revision r7867).
-
-* Python 3.2+ supported in a single codebase using the ``six`` library.
-
-* Removed support for Python 2.5 and older.
-
-* Removed the deprecated Beautiful Soup 3 treebuilder.
-  ``beautifulsoup4`` can use ``html5lib`` as a parser instead. Note that
-  since it doesn't support namespaces, foreign content like SVG and
-  MathML is parsed incorrectly.
-
-* Removed ``simpletree`` from the package. The default tree builder is
-  now ``etree`` (using the ``xml.etree.cElementTree`` implementation if
-  available, and ``xml.etree.ElementTree`` otherwise).
-
-* Removed the ``XHTMLSerializer`` as it never actually guaranteed its
-  output was well-formed XML, and hence provided little of use.
-
-* Removed default DOM treebuilder, so ``html5lib.treebuilders.dom`` is no
-  longer supported. ``html5lib.treebuilders.getTreeBuilder("dom")`` will
-  return the default DOM treebuilder, which uses ``xml.dom.minidom``.
-
-* Optional heuristic character encoding detection now based on
-  ``charade`` for Python 2.6 - 3.3 compatibility.
-
-* Optional ``Genshi`` treewalker support fixed.
-
-* Many bugfixes, including:
-
-  * #33: null in attribute value breaks XML AttValue;
-
-  * #4: nested, indirect descendant, <button> causes infinite loop;
-
-  * `Google Code 215
-    <http://code.google.com/p/html5lib/issues/detail?id=215>`_: Properly
-    detect seekable streams;
-
-  * `Google Code 206
-    <http://code.google.com/p/html5lib/issues/detail?id=206>`_: add
-    support for <video preload=...>, <audio preload=...>;
-
-  * `Google Code 205
-    <http://code.google.com/p/html5lib/issues/detail?id=205>`_: add
-    support for <video poster=...>;
-
-  * `Google Code 202
-    <http://code.google.com/p/html5lib/issues/detail?id=202>`_: Unicode
-    file breaks InputStream.
-
-* Source code is now mostly PEP 8 compliant.
-
-* Test harness has been improved and now depends on ``nose``.
-
-* Documentation updated and moved to http://html5lib.readthedocs.org/.
-
-
-0.95
-~~~~
-
-Released on February 11, 2012
-
-
-0.90
-~~~~
-
-Released on January 17, 2010
-
-
-0.11.1
-~~~~~~
-
-Released on June 12, 2008
-
-
-0.11
-~~~~
-
-Released on June 10, 2008
-
-
-0.10
-~~~~
-
-Released on October 7, 2007
-
-
-0.9
-~~~
-
-Released on March 11, 2007
-
-
-0.2
-~~~
-
-Released on January 8, 2007
diff --git a/testing/web-platform/tests/tools/html5lib/doc/html5lib.rst b/testing/web-platform/tests/tools/html5lib/doc/html5lib.rst
deleted file mode 100644
index d4ed12b46469..000000000000
--- a/testing/web-platform/tests/tools/html5lib/doc/html5lib.rst
+++ /dev/null
@@ -1,77 +0,0 @@
-html5lib Package
-================
-
-:mod:`html5lib` Package
------------------------
-
-.. automodule:: html5lib.__init__
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`constants` Module
------------------------
-
-.. automodule:: html5lib.constants
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`html5parser` Module
--------------------------
-
-.. automodule:: html5lib.html5parser
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`ihatexml` Module
-----------------------
-
-.. automodule:: html5lib.ihatexml
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`inputstream` Module
--------------------------
-
-.. automodule:: html5lib.inputstream
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`sanitizer` Module
------------------------
-
-.. automodule:: html5lib.sanitizer
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`tokenizer` Module
------------------------
-
-.. automodule:: html5lib.tokenizer
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`utils` Module
--------------------
-
-.. automodule:: html5lib.utils
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-Subpackages
------------
-
-.. toctree::
-
-    html5lib.filters
-    html5lib.serializer
-    html5lib.treebuilders
-    html5lib.treewalkers
-
diff --git a/testing/web-platform/tests/tools/html5lib/doc/html5lib.serializer.rst b/testing/web-platform/tests/tools/html5lib/doc/html5lib.serializer.rst
deleted file mode 100644
index fa9547421b13..000000000000
--- a/testing/web-platform/tests/tools/html5lib/doc/html5lib.serializer.rst
+++ /dev/null
@@ -1,19 +0,0 @@
-serializer Package
-==================
-
-:mod:`serializer` Package
--------------------------
-
-.. automodule:: html5lib.serializer
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`htmlserializer` Module
-----------------------------
-
-.. automodule:: html5lib.serializer.htmlserializer
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
diff --git a/testing/web-platform/tests/tools/html5lib/doc/html5lib.treewalkers.rst b/testing/web-platform/tests/tools/html5lib/doc/html5lib.treewalkers.rst
deleted file mode 100644
index 80595e2d7d0e..000000000000
--- a/testing/web-platform/tests/tools/html5lib/doc/html5lib.treewalkers.rst
+++ /dev/null
@@ -1,59 +0,0 @@
-treewalkers Package
-===================
-
-:mod:`treewalkers` Package
---------------------------
-
-.. automodule:: html5lib.treewalkers
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`_base` Module
--------------------
-
-.. automodule:: html5lib.treewalkers._base
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`dom` Module
------------------
-
-.. automodule:: html5lib.treewalkers.dom
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`etree` Module
--------------------
-
-.. automodule:: html5lib.treewalkers.etree
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`genshistream` Module
---------------------------
-
-.. automodule:: html5lib.treewalkers.genshistream
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`lxmletree` Module
------------------------
-
-.. automodule:: html5lib.treewalkers.lxmletree
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
-:mod:`pulldom` Module
----------------------
-
-.. automodule:: html5lib.treewalkers.pulldom
-    :members:
-    :undoc-members:
-    :show-inheritance:
-
diff --git a/testing/web-platform/tests/tools/html5lib/flake8-run.sh b/testing/web-platform/tests/tools/html5lib/flake8-run.sh
deleted file mode 100755
index d1a587d35067..000000000000
--- a/testing/web-platform/tests/tools/html5lib/flake8-run.sh
+++ /dev/null
@@ -1,14 +0,0 @@
-#!/bin/bash -e
-
-if [[ ! -x $(which flake8) ]]; then
-  echo "fatal: flake8 not found on $PATH. Exiting."
-  exit 1
-fi
-
-if [[ $TRAVIS != "true" || $FLAKE == "true" ]]; then
-  find html5lib/ -name '*.py' -and -not -name 'constants.py' -print0 | xargs -0 flake8 --ignore=E501
-  flake1=$?
-  flake8 --max-line-length=99 --ignore=E126 html5lib/constants.py
-  flake2=$?
-  exit $[$flake1 || $flake2]
-fi
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/__init__.py b/testing/web-platform/tests/tools/html5lib/html5lib/__init__.py
deleted file mode 100644
index a67a652b9990..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/__init__.py
+++ /dev/null
@@ -1,23 +0,0 @@
-"""
-HTML parsing library based on the WHATWG "HTML5"
-specification. The parser is designed to be compatible with existing
-HTML found in the wild and implements well-defined error recovery that
-is largely compatible with modern desktop web browsers.
-
-Example usage:
-
-import html5lib
-f = open("my_document.html")
-tree = html5lib.parse(f)
-"""
-
-from __future__ import absolute_import, division, unicode_literals
-
-from .html5parser import HTMLParser, parse, parseFragment
-from .treebuilders import getTreeBuilder
-from .treewalkers import getTreeWalker
-from .serializer import serialize
-
-__all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder",
-           "getTreeWalker", "serialize"]
-__version__ = "0.9999-dev"
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/filters/alphabeticalattributes.py b/testing/web-platform/tests/tools/html5lib/html5lib/filters/alphabeticalattributes.py
deleted file mode 100644
index fed6996c1d9b..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/filters/alphabeticalattributes.py
+++ /dev/null
@@ -1,20 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from . import _base
-
-try:
-    from collections import OrderedDict
-except ImportError:
-    from ordereddict import OrderedDict
-
-
-class Filter(_base.Filter):
-    def __iter__(self):
-        for token in _base.Filter.__iter__(self):
-            if token["type"] in ("StartTag", "EmptyTag"):
-                attrs = OrderedDict()
-                for name, value in sorted(token["data"].items(),
-                                          key=lambda x: x[0]):
-                    attrs[name] = value
-                token["data"] = attrs
-            yield token
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/filters/lint.py b/testing/web-platform/tests/tools/html5lib/html5lib/filters/lint.py
deleted file mode 100644
index 7cc99a4ba7c0..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/filters/lint.py
+++ /dev/null
@@ -1,93 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from gettext import gettext
-_ = gettext
-
-from . import _base
-from ..constants import cdataElements, rcdataElements, voidElements
-
-from ..constants import spaceCharacters
-spaceCharacters = "".join(spaceCharacters)
-
-
-class LintError(Exception):
-    pass
-
-
-class Filter(_base.Filter):
-    def __iter__(self):
-        open_elements = []
-        contentModelFlag = "PCDATA"
-        for token in _base.Filter.__iter__(self):
-            type = token["type"]
-            if type in ("StartTag", "EmptyTag"):
-                name = token["name"]
-                if contentModelFlag != "PCDATA":
-                    raise LintError(_("StartTag not in PCDATA content model flag: %(tag)s") % {"tag": name})
-                if not isinstance(name, str):
-                    raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
-                if not name:
-                    raise LintError(_("Empty tag name"))
-                if type == "StartTag" and name in voidElements:
-                    raise LintError(_("Void element reported as StartTag token: %(tag)s") % {"tag": name})
-                elif type == "EmptyTag" and name not in voidElements:
-                    raise LintError(_("Non-void element reported as EmptyTag token: %(tag)s") % {"tag": token["name"]})
-                if type == "StartTag":
-                    open_elements.append(name)
-                for name, value in token["data"]:
-                    if not isinstance(name, str):
-                        raise LintError(_("Attribute name is not a string: %(name)r") % {"name": name})
-                    if not name:
-                        raise LintError(_("Empty attribute name"))
-                    if not isinstance(value, str):
-                        raise LintError(_("Attribute value is not a string: %(value)r") % {"value": value})
-                if name in cdataElements:
-                    contentModelFlag = "CDATA"
-                elif name in rcdataElements:
-                    contentModelFlag = "RCDATA"
-                elif name == "plaintext":
-                    contentModelFlag = "PLAINTEXT"
-
-            elif type == "EndTag":
-                name = token["name"]
-                if not isinstance(name, str):
-                    raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
-                if not name:
-                    raise LintError(_("Empty tag name"))
-                if name in voidElements:
-                    raise LintError(_("Void element reported as EndTag token: %(tag)s") % {"tag": name})
-                start_name = open_elements.pop()
-                if start_name != name:
-                    raise LintError(_("EndTag (%(end)s) does not match StartTag (%(start)s)") % {"end": name, "start": start_name})
-                contentModelFlag = "PCDATA"
-
-            elif type == "Comment":
-                if contentModelFlag != "PCDATA":
-                    raise LintError(_("Comment not in PCDATA content model flag"))
-
-            elif type in ("Characters", "SpaceCharacters"):
-                data = token["data"]
-                if not isinstance(data, str):
-                    raise LintError(_("Attribute name is not a string: %(name)r") % {"name": data})
-                if not data:
-                    raise LintError(_("%(type)s token with empty data") % {"type": type})
-                if type == "SpaceCharacters":
-                    data = data.strip(spaceCharacters)
-                    if data:
-                        raise LintError(_("Non-space character(s) found in SpaceCharacters token: %(token)r") % {"token": data})
-
-            elif type == "Doctype":
-                name = token["name"]
-                if contentModelFlag != "PCDATA":
-                    raise LintError(_("Doctype not in PCDATA content model flag: %(name)s") % {"name": name})
-                if not isinstance(name, str):
-                    raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
-                # XXX: what to do with token["data"] ?
-
-            elif type in ("ParseError", "SerializeError"):
-                pass
-
-            else:
-                raise LintError(_("Unknown token type: %(type)s") % {"type": type})
-
-            yield token
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/filters/sanitizer.py b/testing/web-platform/tests/tools/html5lib/html5lib/filters/sanitizer.py
deleted file mode 100644
index b206b54e7a74..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/filters/sanitizer.py
+++ /dev/null
@@ -1,12 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from . import _base
-from ..sanitizer import HTMLSanitizerMixin
-
-
-class Filter(_base.Filter, HTMLSanitizerMixin):
-    def __iter__(self):
-        for token in _base.Filter.__iter__(self):
-            token = self.sanitize_token(token)
-            if token:
-                yield token
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/sanitizer.py b/testing/web-platform/tests/tools/html5lib/html5lib/sanitizer.py
deleted file mode 100644
index 469d9b40c966..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/sanitizer.py
+++ /dev/null
@@ -1,271 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-import re
-from xml.sax.saxutils import escape, unescape
-
-from .tokenizer import HTMLTokenizer
-from .constants import tokenTypes
-
-
-class HTMLSanitizerMixin(object):
-    """ sanitization of XHTML+MathML+SVG and of inline style attributes."""
-
-    acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area',
-                           'article', 'aside', 'audio', 'b', 'big', 'blockquote', 'br', 'button',
-                           'canvas', 'caption', 'center', 'cite', 'code', 'col', 'colgroup',
-                           'command', 'datagrid', 'datalist', 'dd', 'del', 'details', 'dfn',
-                           'dialog', 'dir', 'div', 'dl', 'dt', 'em', 'event-source', 'fieldset',
-                           'figcaption', 'figure', 'footer', 'font', 'form', 'header', 'h1',
-                           'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', 'ins',
-                           'keygen', 'kbd', 'label', 'legend', 'li', 'm', 'map', 'menu', 'meter',
-                           'multicol', 'nav', 'nextid', 'ol', 'output', 'optgroup', 'option',
-                           'p', 'pre', 'progress', 'q', 's', 'samp', 'section', 'select',
-                           'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong',
-                           'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot',
-                           'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video']
-
-    mathml_elements = ['maction', 'math', 'merror', 'mfrac', 'mi',
-                       'mmultiscripts', 'mn', 'mo', 'mover', 'mpadded', 'mphantom',
-                       'mprescripts', 'mroot', 'mrow', 'mspace', 'msqrt', 'mstyle', 'msub',
-                       'msubsup', 'msup', 'mtable', 'mtd', 'mtext', 'mtr', 'munder',
-                       'munderover', 'none']
-
-    svg_elements = ['a', 'animate', 'animateColor', 'animateMotion',
-                    'animateTransform', 'clipPath', 'circle', 'defs', 'desc', 'ellipse',
-                    'font-face', 'font-face-name', 'font-face-src', 'g', 'glyph', 'hkern',
-                    'linearGradient', 'line', 'marker', 'metadata', 'missing-glyph',
-                    'mpath', 'path', 'polygon', 'polyline', 'radialGradient', 'rect',
-                    'set', 'stop', 'svg', 'switch', 'text', 'title', 'tspan', 'use']
-
-    acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey',
-                             'action', 'align', 'alt', 'autocomplete', 'autofocus', 'axis',
-                             'background', 'balance', 'bgcolor', 'bgproperties', 'border',
-                             'bordercolor', 'bordercolordark', 'bordercolorlight', 'bottompadding',
-                             'cellpadding', 'cellspacing', 'ch', 'challenge', 'char', 'charoff',
-                             'choff', 'charset', 'checked', 'cite', 'class', 'clear', 'color',
-                             'cols', 'colspan', 'compact', 'contenteditable', 'controls', 'coords',
-                             'data', 'datafld', 'datapagesize', 'datasrc', 'datetime', 'default',
-                             'delay', 'dir', 'disabled', 'draggable', 'dynsrc', 'enctype', 'end',
-                             'face', 'for', 'form', 'frame', 'galleryimg', 'gutter', 'headers',
-                             'height', 'hidefocus', 'hidden', 'high', 'href', 'hreflang', 'hspace',
-                             'icon', 'id', 'inputmode', 'ismap', 'keytype', 'label', 'leftspacing',
-                             'lang', 'list', 'longdesc', 'loop', 'loopcount', 'loopend',
-                             'loopstart', 'low', 'lowsrc', 'max', 'maxlength', 'media', 'method',
-                             'min', 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'open',
-                             'optimum', 'pattern', 'ping', 'point-size', 'poster', 'pqg', 'preload',
-                             'prompt', 'radiogroup', 'readonly', 'rel', 'repeat-max', 'repeat-min',
-                             'replace', 'required', 'rev', 'rightspacing', 'rows', 'rowspan',
-                             'rules', 'scope', 'selected', 'shape', 'size', 'span', 'src', 'start',
-                             'step', 'style', 'summary', 'suppress', 'tabindex', 'target',
-                             'template', 'title', 'toppadding', 'type', 'unselectable', 'usemap',
-                             'urn', 'valign', 'value', 'variable', 'volume', 'vspace', 'vrml',
-                             'width', 'wrap', 'xml:lang']
-
-    mathml_attributes = ['actiontype', 'align', 'columnalign', 'columnalign',
-                         'columnalign', 'columnlines', 'columnspacing', 'columnspan', 'depth',
-                         'display', 'displaystyle', 'equalcolumns', 'equalrows', 'fence',
-                         'fontstyle', 'fontweight', 'frame', 'height', 'linethickness', 'lspace',
-                         'mathbackground', 'mathcolor', 'mathvariant', 'mathvariant', 'maxsize',
-                         'minsize', 'other', 'rowalign', 'rowalign', 'rowalign', 'rowlines',
-                         'rowspacing', 'rowspan', 'rspace', 'scriptlevel', 'selection',
-                         'separator', 'stretchy', 'width', 'width', 'xlink:href', 'xlink:show',
-                         'xlink:type', 'xmlns', 'xmlns:xlink']
-
-    svg_attributes = ['accent-height', 'accumulate', 'additive', 'alphabetic',
-                      'arabic-form', 'ascent', 'attributeName', 'attributeType',
-                      'baseProfile', 'bbox', 'begin', 'by', 'calcMode', 'cap-height',
-                      'class', 'clip-path', 'color', 'color-rendering', 'content', 'cx',
-                      'cy', 'd', 'dx', 'dy', 'descent', 'display', 'dur', 'end', 'fill',
-                      'fill-opacity', 'fill-rule', 'font-family', 'font-size',
-                      'font-stretch', 'font-style', 'font-variant', 'font-weight', 'from',
-                      'fx', 'fy', 'g1', 'g2', 'glyph-name', 'gradientUnits', 'hanging',
-                      'height', 'horiz-adv-x', 'horiz-origin-x', 'id', 'ideographic', 'k',
-                      'keyPoints', 'keySplines', 'keyTimes', 'lang', 'marker-end',
-                      'marker-mid', 'marker-start', 'markerHeight', 'markerUnits',
-                      'markerWidth', 'mathematical', 'max', 'min', 'name', 'offset',
-                      'opacity', 'orient', 'origin', 'overline-position',
-                      'overline-thickness', 'panose-1', 'path', 'pathLength', 'points',
-                      'preserveAspectRatio', 'r', 'refX', 'refY', 'repeatCount',
-                      'repeatDur', 'requiredExtensions', 'requiredFeatures', 'restart',
-                      'rotate', 'rx', 'ry', 'slope', 'stemh', 'stemv', 'stop-color',
-                      'stop-opacity', 'strikethrough-position', 'strikethrough-thickness',
-                      'stroke', 'stroke-dasharray', 'stroke-dashoffset', 'stroke-linecap',
-                      'stroke-linejoin', 'stroke-miterlimit', 'stroke-opacity',
-                      'stroke-width', 'systemLanguage', 'target', 'text-anchor', 'to',
-                      'transform', 'type', 'u1', 'u2', 'underline-position',
-                      'underline-thickness', 'unicode', 'unicode-range', 'units-per-em',
-                      'values', 'version', 'viewBox', 'visibility', 'width', 'widths', 'x',
-                      'x-height', 'x1', 'x2', 'xlink:actuate', 'xlink:arcrole',
-                      'xlink:href', 'xlink:role', 'xlink:show', 'xlink:title', 'xlink:type',
-                      'xml:base', 'xml:lang', 'xml:space', 'xmlns', 'xmlns:xlink', 'y',
-                      'y1', 'y2', 'zoomAndPan']
-
-    attr_val_is_uri = ['href', 'src', 'cite', 'action', 'longdesc', 'poster',
-                       'xlink:href', 'xml:base']
-
-    svg_attr_val_allows_ref = ['clip-path', 'color-profile', 'cursor', 'fill',
-                               'filter', 'marker', 'marker-start', 'marker-mid', 'marker-end',
-                               'mask', 'stroke']
-
-    svg_allow_local_href = ['altGlyph', 'animate', 'animateColor',
-                            'animateMotion', 'animateTransform', 'cursor', 'feImage', 'filter',
-                            'linearGradient', 'pattern', 'radialGradient', 'textpath', 'tref',
-                            'set', 'use']
-
-    acceptable_css_properties = ['azimuth', 'background-color',
-                                 'border-bottom-color', 'border-collapse', 'border-color',
-                                 'border-left-color', 'border-right-color', 'border-top-color', 'clear',
-                                 'color', 'cursor', 'direction', 'display', 'elevation', 'float', 'font',
-                                 'font-family', 'font-size', 'font-style', 'font-variant', 'font-weight',
-                                 'height', 'letter-spacing', 'line-height', 'overflow', 'pause',
-                                 'pause-after', 'pause-before', 'pitch', 'pitch-range', 'richness',
-                                 'speak', 'speak-header', 'speak-numeral', 'speak-punctuation',
-                                 'speech-rate', 'stress', 'text-align', 'text-decoration', 'text-indent',
-                                 'unicode-bidi', 'vertical-align', 'voice-family', 'volume',
-                                 'white-space', 'width']
-
-    acceptable_css_keywords = ['auto', 'aqua', 'black', 'block', 'blue',
-                               'bold', 'both', 'bottom', 'brown', 'center', 'collapse', 'dashed',
-                               'dotted', 'fuchsia', 'gray', 'green', '!important', 'italic', 'left',
-                               'lime', 'maroon', 'medium', 'none', 'navy', 'normal', 'nowrap', 'olive',
-                               'pointer', 'purple', 'red', 'right', 'solid', 'silver', 'teal', 'top',
-                               'transparent', 'underline', 'white', 'yellow']
-
-    acceptable_svg_properties = ['fill', 'fill-opacity', 'fill-rule',
-                                 'stroke', 'stroke-width', 'stroke-linecap', 'stroke-linejoin',
-                                 'stroke-opacity']
-
-    acceptable_protocols = ['ed2k', 'ftp', 'http', 'https', 'irc',
-                            'mailto', 'news', 'gopher', 'nntp', 'telnet', 'webcal',
-                            'xmpp', 'callto', 'feed', 'urn', 'aim', 'rsync', 'tag',
-                            'ssh', 'sftp', 'rtsp', 'afs']
-
-    # subclasses may define their own versions of these constants
-    allowed_elements = acceptable_elements + mathml_elements + svg_elements
-    allowed_attributes = acceptable_attributes + mathml_attributes + svg_attributes
-    allowed_css_properties = acceptable_css_properties
-    allowed_css_keywords = acceptable_css_keywords
-    allowed_svg_properties = acceptable_svg_properties
-    allowed_protocols = acceptable_protocols
-
-    # Sanitize the +html+, escaping all elements not in ALLOWED_ELEMENTS, and
-    # stripping out all # attributes not in ALLOWED_ATTRIBUTES. Style
-    # attributes are parsed, and a restricted set, # specified by
-    # ALLOWED_CSS_PROPERTIES and ALLOWED_CSS_KEYWORDS, are allowed through.
-    # attributes in ATTR_VAL_IS_URI are scanned, and only URI schemes specified
-    # in ALLOWED_PROTOCOLS are allowed.
-    #
-    #   sanitize_html('<script> do_nasty_stuff() </script>')
-    #    => &lt;script> do_nasty_stuff() &lt;/script>
-    #   sanitize_html('<a href="javascript: sucker();">Click here for $100</a>')
-    #    => <a>Click here for $100</a>
-    def sanitize_token(self, token):
-
-        # accommodate filters which use token_type differently
-        token_type = token["type"]
-        if token_type in list(tokenTypes.keys()):
-            token_type = tokenTypes[token_type]
-
-        if token_type in (tokenTypes["StartTag"], tokenTypes["EndTag"],
-                          tokenTypes["EmptyTag"]):
-            if token["name"] in self.allowed_elements:
-                return self.allowed_token(token, token_type)
-            else:
-                return self.disallowed_token(token, token_type)
-        elif token_type == tokenTypes["Comment"]:
-            pass
-        else:
-            return token
-
-    def allowed_token(self, token, token_type):
-        if "data" in token:
-            attrs = dict([(name, val) for name, val in
-                          token["data"][::-1]
-                          if name in self.allowed_attributes])
-            for attr in self.attr_val_is_uri:
-                if attr not in attrs:
-                    continue
-                val_unescaped = re.sub("[`\000-\040\177-\240\s]+", '',
-                                       unescape(attrs[attr])).lower()
-                # remove replacement characters from unescaped characters
-                val_unescaped = val_unescaped.replace("\ufffd", "")
-                if (re.match("^[a-z0-9][-+.a-z0-9]*:", val_unescaped) and
-                    (val_unescaped.split(':')[0] not in
-                     self.allowed_protocols)):
-                    del attrs[attr]
-            for attr in self.svg_attr_val_allows_ref:
-                if attr in attrs:
-                    attrs[attr] = re.sub(r'url\s*\(\s*[^#\s][^)]+?\)',
-                                         ' ',
-                                         unescape(attrs[attr]))
-            if (token["name"] in self.svg_allow_local_href and
-                'xlink:href' in attrs and re.search('^\s*[^#\s].*',
-                                                    attrs['xlink:href'])):
-                del attrs['xlink:href']
-            if 'style' in attrs:
-                attrs['style'] = self.sanitize_css(attrs['style'])
-            token["data"] = [[name, val] for name, val in list(attrs.items())]
-        return token
-
-    def disallowed_token(self, token, token_type):
-        if token_type == tokenTypes["EndTag"]:
-            token["data"] = "</%s>" % token["name"]
-        elif token["data"]:
-            attrs = ''.join([' %s="%s"' % (k, escape(v)) for k, v in token["data"]])
-            token["data"] = "<%s%s>" % (token["name"], attrs)
-        else:
-            token["data"] = "<%s>" % token["name"]
-        if token.get("selfClosing"):
-            token["data"] = token["data"][:-1] + "/>"
-
-        if token["type"] in list(tokenTypes.keys()):
-            token["type"] = "Characters"
-        else:
-            token["type"] = tokenTypes["Characters"]
-
-        del token["name"]
-        return token
-
-    def sanitize_css(self, style):
-        # disallow urls
-        style = re.compile('url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style)
-
-        # gauntlet
-        if not re.match("""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style):
-            return ''
-        if not re.match("^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style):
-            return ''
-
-        clean = []
-        for prop, value in re.findall("([-\w]+)\s*:\s*([^:;]*)", style):
-            if not value:
-                continue
-            if prop.lower() in self.allowed_css_properties:
-                clean.append(prop + ': ' + value + ';')
-            elif prop.split('-')[0].lower() in ['background', 'border', 'margin',
-                                                'padding']:
-                for keyword in value.split():
-                    if keyword not in self.acceptable_css_keywords and \
-                            not re.match("^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword):
-                        break
-                else:
-                    clean.append(prop + ': ' + value + ';')
-            elif prop.lower() in self.allowed_svg_properties:
-                clean.append(prop + ': ' + value + ';')
-
-        return ' '.join(clean)
-
-
-class HTMLSanitizer(HTMLTokenizer, HTMLSanitizerMixin):
-    def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
-                 lowercaseElementName=False, lowercaseAttrName=False, parser=None):
-        # Change case matching defaults as we only output lowercase html anyway
-        # This solution doesn't seem ideal...
-        HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
-                               lowercaseElementName, lowercaseAttrName, parser=parser)
-
-    def __iter__(self):
-        for token in HTMLTokenizer.__iter__(self):
-            token = self.sanitize_token(token)
-            if token:
-                yield token
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/serializer/__init__.py b/testing/web-platform/tests/tools/html5lib/html5lib/serializer/__init__.py
deleted file mode 100644
index 8380839a6d3e..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/serializer/__init__.py
+++ /dev/null
@@ -1,16 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from .. import treewalkers
-
-from .htmlserializer import HTMLSerializer
-
-
-def serialize(input, tree="etree", format="html", encoding=None,
-              **serializer_opts):
-    # XXX: Should we cache this?
-    walker = treewalkers.getTreeWalker(tree)
-    if format == "html":
-        s = HTMLSerializer(**serializer_opts)
-    else:
-        raise ValueError("type must be html")
-    return s.render(walker(input), encoding)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/serializer/htmlserializer.py b/testing/web-platform/tests/tools/html5lib/html5lib/serializer/htmlserializer.py
deleted file mode 100644
index 4a891ff56c4e..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/serializer/htmlserializer.py
+++ /dev/null
@@ -1,320 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-from six import text_type
-
-import gettext
-_ = gettext.gettext
-
-try:
-    from functools import reduce
-except ImportError:
-    pass
-
-from ..constants import voidElements, booleanAttributes, spaceCharacters
-from ..constants import rcdataElements, entities, xmlEntities
-from .. import utils
-from xml.sax.saxutils import escape
-
-spaceCharacters = "".join(spaceCharacters)
-
-try:
-    from codecs import register_error, xmlcharrefreplace_errors
-except ImportError:
-    unicode_encode_errors = "strict"
-else:
-    unicode_encode_errors = "htmlentityreplace"
-
-    encode_entity_map = {}
-    is_ucs4 = len("\U0010FFFF") == 1
-    for k, v in list(entities.items()):
-        # skip multi-character entities
-        if ((is_ucs4 and len(v) > 1) or
-                (not is_ucs4 and len(v) > 2)):
-            continue
-        if v != "&":
-            if len(v) == 2:
-                v = utils.surrogatePairToCodepoint(v)
-            else:
-                v = ord(v)
-            if v not in encode_entity_map or k.islower():
-                # prefer &lt; over &LT; and similarly for &amp;, &gt;, etc.
-                encode_entity_map[v] = k
-
-    def htmlentityreplace_errors(exc):
-        if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
-            res = []
-            codepoints = []
-            skip = False
-            for i, c in enumerate(exc.object[exc.start:exc.end]):
-                if skip:
-                    skip = False
-                    continue
-                index = i + exc.start
-                if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
-                    codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
-                    skip = True
-                else:
-                    codepoint = ord(c)
-                codepoints.append(codepoint)
-            for cp in codepoints:
-                e = encode_entity_map.get(cp)
-                if e:
-                    res.append("&")
-                    res.append(e)
-                    if not e.endswith(";"):
-                        res.append(";")
-                else:
-                    res.append("&#x%s;" % (hex(cp)[2:]))
-            return ("".join(res), exc.end)
-        else:
-            return xmlcharrefreplace_errors(exc)
-
-    register_error(unicode_encode_errors, htmlentityreplace_errors)
-
-    del register_error
-
-
-class HTMLSerializer(object):
-
-    # attribute quoting options
-    quote_attr_values = False
-    quote_char = '"'
-    use_best_quote_char = True
-
-    # tag syntax options
-    omit_optional_tags = True
-    minimize_boolean_attributes = True
-    use_trailing_solidus = False
-    space_before_trailing_solidus = True
-
-    # escaping options
-    escape_lt_in_attrs = False
-    escape_rcdata = False
-    resolve_entities = True
-
-    # miscellaneous options
-    alphabetical_attributes = False
-    inject_meta_charset = True
-    strip_whitespace = False
-    sanitize = False
-
-    options = ("quote_attr_values", "quote_char", "use_best_quote_char",
-               "omit_optional_tags", "minimize_boolean_attributes",
-               "use_trailing_solidus", "space_before_trailing_solidus",
-               "escape_lt_in_attrs", "escape_rcdata", "resolve_entities",
-               "alphabetical_attributes", "inject_meta_charset",
-               "strip_whitespace", "sanitize")
-
-    def __init__(self, **kwargs):
-        """Initialize HTMLSerializer.
-
-        Keyword options (default given first unless specified) include:
-
-        inject_meta_charset=True|False
-          Whether it insert a meta element to define the character set of the
-          document.
-        quote_attr_values=True|False
-          Whether to quote attribute values that don't require quoting
-          per HTML5 parsing rules.
-        quote_char=u'"'|u"'"
-          Use given quote character for attribute quoting. Default is to
-          use double quote unless attribute value contains a double quote,
-          in which case single quotes are used instead.
-        escape_lt_in_attrs=False|True
-          Whether to escape < in attribute values.
-        escape_rcdata=False|True
-          Whether to escape characters that need to be escaped within normal
-          elements within rcdata elements such as style.
-        resolve_entities=True|False
-          Whether to resolve named character entities that appear in the
-          source tree. The XML predefined entities &lt; &gt; &amp; &quot; &apos;
-          are unaffected by this setting.
-        strip_whitespace=False|True
-          Whether to remove semantically meaningless whitespace. (This
-          compresses all whitespace to a single space except within pre.)
-        minimize_boolean_attributes=True|False
-          Shortens boolean attributes to give just the attribute value,
-          for example <input disabled="disabled"> becomes <input disabled>.
-        use_trailing_solidus=False|True
-          Includes a close-tag slash at the end of the start tag of void
-          elements (empty elements whose end tag is forbidden). E.g. <hr/>.
-        space_before_trailing_solidus=True|False
-          Places a space immediately before the closing slash in a tag
-          using a trailing solidus. E.g. <hr />. Requires use_trailing_solidus.
-        sanitize=False|True
-          Strip all unsafe or unknown constructs from output.
-          See `html5lib user documentation`_
-        omit_optional_tags=True|False
-          Omit start/end tags that are optional.
-        alphabetical_attributes=False|True
-          Reorder attributes to be in alphabetical order.
-
-        .. _html5lib user documentation: http://code.google.com/p/html5lib/wiki/UserDocumentation
-        """
-        if 'quote_char' in kwargs:
-            self.use_best_quote_char = False
-        for attr in self.options:
-            setattr(self, attr, kwargs.get(attr, getattr(self, attr)))
-        self.errors = []
-        self.strict = False
-
-    def encode(self, string):
-        assert(isinstance(string, text_type))
-        if self.encoding:
-            return string.encode(self.encoding, unicode_encode_errors)
-        else:
-            return string
-
-    def encodeStrict(self, string):
-        assert(isinstance(string, text_type))
-        if self.encoding:
-            return string.encode(self.encoding, "strict")
-        else:
-            return string
-
-    def serialize(self, treewalker, encoding=None):
-        self.encoding = encoding
-        in_cdata = False
-        self.errors = []
-
-        if encoding and self.inject_meta_charset:
-            from ..filters.inject_meta_charset import Filter
-            treewalker = Filter(treewalker, encoding)
-        # WhitespaceFilter should be used before OptionalTagFilter
-        # for maximum efficiently of this latter filter
-        if self.strip_whitespace:
-            from ..filters.whitespace import Filter
-            treewalker = Filter(treewalker)
-        if self.sanitize:
-            from ..filters.sanitizer import Filter
-            treewalker = Filter(treewalker)
-        if self.omit_optional_tags:
-            from ..filters.optionaltags import Filter
-            treewalker = Filter(treewalker)
-        # Alphabetical attributes must be last, as other filters
-        # could add attributes and alter the order
-        if self.alphabetical_attributes:
-            from ..filters.alphabeticalattributes import Filter
-            treewalker = Filter(treewalker)
-
-        for token in treewalker:
-            type = token["type"]
-            if type == "Doctype":
-                doctype = "<!DOCTYPE %s" % token["name"]
-
-                if token["publicId"]:
-                    doctype += ' PUBLIC "%s"' % token["publicId"]
-                elif token["systemId"]:
-                    doctype += " SYSTEM"
-                if token["systemId"]:
-                    if token["systemId"].find('"') >= 0:
-                        if token["systemId"].find("'") >= 0:
-                            self.serializeError(_("System identifer contains both single and double quote characters"))
-                        quote_char = "'"
-                    else:
-                        quote_char = '"'
-                    doctype += " %s%s%s" % (quote_char, token["systemId"], quote_char)
-
-                doctype += ">"
-                yield self.encodeStrict(doctype)
-
-            elif type in ("Characters", "SpaceCharacters"):
-                if type == "SpaceCharacters" or in_cdata:
-                    if in_cdata and token["data"].find("</") >= 0:
-                        self.serializeError(_("Unexpected </ in CDATA"))
-                    yield self.encode(token["data"])
-                else:
-                    yield self.encode(escape(token["data"]))
-
-            elif type in ("StartTag", "EmptyTag"):
-                name = token["name"]
-                yield self.encodeStrict("<%s" % name)
-                if name in rcdataElements and not self.escape_rcdata:
-                    in_cdata = True
-                elif in_cdata:
-                    self.serializeError(_("Unexpected child element of a CDATA element"))
-                for (attr_namespace, attr_name), attr_value in token["data"].items():
-                    # TODO: Add namespace support here
-                    k = attr_name
-                    v = attr_value
-                    yield self.encodeStrict(' ')
-
-                    yield self.encodeStrict(k)
-                    if not self.minimize_boolean_attributes or \
-                        (k not in booleanAttributes.get(name, tuple())
-                         and k not in booleanAttributes.get("", tuple())):
-                        yield self.encodeStrict("=")
-                        if self.quote_attr_values or not v:
-                            quote_attr = True
-                        else:
-                            quote_attr = reduce(lambda x, y: x or (y in v),
-                                                spaceCharacters + ">\"'=", False)
-                        v = v.replace("&", "&amp;")
-                        if self.escape_lt_in_attrs:
-                            v = v.replace("<", "&lt;")
-                        if quote_attr:
-                            quote_char = self.quote_char
-                            if self.use_best_quote_char:
-                                if "'" in v and '"' not in v:
-                                    quote_char = '"'
-                                elif '"' in v and "'" not in v:
-                                    quote_char = "'"
-                            if quote_char == "'":
-                                v = v.replace("'", "&#39;")
-                            else:
-                                v = v.replace('"', "&quot;")
-                            yield self.encodeStrict(quote_char)
-                            yield self.encode(v)
-                            yield self.encodeStrict(quote_char)
-                        else:
-                            yield self.encode(v)
-                if name in voidElements and self.use_trailing_solidus:
-                    if self.space_before_trailing_solidus:
-                        yield self.encodeStrict(" /")
-                    else:
-                        yield self.encodeStrict("/")
-                yield self.encode(">")
-
-            elif type == "EndTag":
-                name = token["name"]
-                if name in rcdataElements:
-                    in_cdata = False
-                elif in_cdata:
-                    self.serializeError(_("Unexpected child element of a CDATA element"))
-                yield self.encodeStrict("</%s>" % name)
-
-            elif type == "Comment":
-                data = token["data"]
-                if data.find("--") >= 0:
-                    self.serializeError(_("Comment contains --"))
-                yield self.encodeStrict("<!--%s-->" % token["data"])
-
-            elif type == "Entity":
-                name = token["name"]
-                key = name + ";"
-                if key not in entities:
-                    self.serializeError(_("Entity %s not recognized" % name))
-                if self.resolve_entities and key not in xmlEntities:
-                    data = entities[key]
-                else:
-                    data = "&%s;" % name
-                yield self.encodeStrict(data)
-
-            else:
-                self.serializeError(token["data"])
-
-    def render(self, treewalker, encoding=None):
-        if encoding:
-            return b"".join(list(self.serialize(treewalker, encoding)))
-        else:
-            return "".join(list(self.serialize(treewalker)))
-
-    def serializeError(self, data="XXX ERROR MESSAGE NEEDED"):
-        # XXX The idea is to make data mandatory.
-        self.errors.append(data)
-        if self.strict:
-            raise SerializeError
-
-
-def SerializeError(Exception):
-    """Error in serialized tree"""
-    pass
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/README b/testing/web-platform/tests/tools/html5lib/html5lib/tests/README
deleted file mode 100644
index c564b6836e46..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/README
+++ /dev/null
@@ -1 +0,0 @@
-Each testcase file can be run through nose (using ``nosetests``).
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/mockParser.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/mockParser.py
deleted file mode 100644
index ef31527e82df..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/mockParser.py
+++ /dev/null
@@ -1,41 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-import sys
-import os
-
-if __name__ == '__main__':
-    # Allow us to import from the src directory
-    os.chdir(os.path.split(os.path.abspath(__file__))[0])
-    sys.path.insert(0, os.path.abspath(os.path.join(os.pardir, "src")))
-
-from html5lib.tokenizer import HTMLTokenizer
-
-
-class HTMLParser(object):
-    """ Fake parser to test tokenizer output """
-    def parse(self, stream, output=True):
-        tokenizer = HTMLTokenizer(stream)
-        for token in tokenizer:
-            if output:
-                print(token)
-
-if __name__ == "__main__":
-    x = HTMLParser()
-    if len(sys.argv) > 1:
-        if len(sys.argv) > 2:
-            import hotshot
-            import hotshot.stats
-            prof = hotshot.Profile('stats.prof')
-            prof.runcall(x.parse, sys.argv[1], False)
-            prof.close()
-            stats = hotshot.stats.load('stats.prof')
-            stats.strip_dirs()
-            stats.sort_stats('time')
-            stats.print_stats()
-        else:
-            x.parse(sys.argv[1])
-    else:
-        print("""Usage: python mockParser.py filename [stats]
-        If stats is specified the hotshots profiler will run and output the
-        stats instead.
-        """)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/performance/concatenation.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/performance/concatenation.py
deleted file mode 100644
index a1465036e52b..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/performance/concatenation.py
+++ /dev/null
@@ -1,36 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-
-def f1():
-    x = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    y = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    z = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    x += y + z
-
-
-def f2():
-    x = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    y = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    z = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    x = x + y + z
-
-
-def f3():
-    x = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    y = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    z = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    x = "".join((x, y, z))
-
-
-def f4():
-    x = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    y = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    z = "ABCDEFGHIJKLMNOPQRSTUVWXYZABCDEFGHIJKLMNOPQRSTUVWXYZ"
-    x = "%s%s%s" % (x, y, z)
-
-import timeit
-for x in range(4):
-    statement = "f%s" % (x + 1)
-    t = timeit.Timer(statement, "from __main__ import " + statement)
-    r = t.repeat(3, 1000000)
-    print(r, min(r))
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_encoding.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_encoding.py
deleted file mode 100644
index d774ce0f600f..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_encoding.py
+++ /dev/null
@@ -1,67 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-import os
-import unittest
-
-try:
-    unittest.TestCase.assertEqual
-except AttributeError:
-    unittest.TestCase.assertEqual = unittest.TestCase.assertEquals
-
-from .support import get_data_files, TestData, test_dir, errorMessage
-from html5lib import HTMLParser, inputstream
-
-
-class Html5EncodingTestCase(unittest.TestCase):
-    def test_codec_name_a(self):
-        self.assertEqual(inputstream.codecName("utf-8"), "utf-8")
-
-    def test_codec_name_b(self):
-        self.assertEqual(inputstream.codecName("utf8"), "utf-8")
-
-    def test_codec_name_c(self):
-        self.assertEqual(inputstream.codecName("  utf8  "), "utf-8")
-
-    def test_codec_name_d(self):
-        self.assertEqual(inputstream.codecName("ISO_8859--1"), "windows-1252")
-
-
-def runParserEncodingTest(data, encoding):
-    p = HTMLParser()
-    assert p.documentEncoding is None
-    p.parse(data, useChardet=False)
-    encoding = encoding.lower().decode("ascii")
-
-    assert encoding == p.documentEncoding, errorMessage(data, encoding, p.documentEncoding)
-
-
-def runPreScanEncodingTest(data, encoding):
-    stream = inputstream.HTMLBinaryInputStream(data, chardet=False)
-    encoding = encoding.lower().decode("ascii")
-
-    # Very crude way to ignore irrelevant tests
-    if len(data) > stream.numBytesMeta:
-        return
-
-    assert encoding == stream.charEncoding[0], errorMessage(data, encoding, stream.charEncoding[0])
-
-
-def test_encoding():
-    for filename in get_data_files("encoding"):
-        tests = TestData(filename, b"data", encoding=None)
-        for idx, test in enumerate(tests):
-            yield (runParserEncodingTest, test[b'data'], test[b'encoding'])
-            yield (runPreScanEncodingTest, test[b'data'], test[b'encoding'])
-
-try:
-    try:
-        import charade  # flake8: noqa
-    except ImportError:
-        import chardet  # flake8: noqa
-except ImportError:
-    print("charade/chardet not found, skipping chardet tests")
-else:
-    def test_chardet():
-        with open(os.path.join(test_dir, "encoding" , "chardet", "test_big5.txt"), "rb") as fp:
-            encoding = inputstream.HTMLInputStream(fp.read()).charEncoding
-            assert encoding[0].lower() == "big5"
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_parser.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_parser.py
deleted file mode 100644
index 230cdb42d59c..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_parser.py
+++ /dev/null
@@ -1,96 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-import os
-import sys
-import traceback
-import warnings
-import re
-
-warnings.simplefilter("error")
-
-from .support import get_data_files
-from .support import TestData, convert, convertExpected, treeTypes
-from html5lib import html5parser, constants
-
-# Run the parse error checks
-checkParseErrors = False
-
-# XXX - There should just be one function here but for some reason the testcase
-# format differs from the treedump format by a single space character
-
-
-def convertTreeDump(data):
-    return "\n".join(convert(3)(data).split("\n")[1:])
-
-namespaceExpected = re.compile(r"^(\s*)<(\S+)>", re.M).sub
-
-
-def runParserTest(innerHTML, input, expected, errors, treeClass,
-                  namespaceHTMLElements):
-    with warnings.catch_warnings(record=True) as caughtWarnings:
-        warnings.simplefilter("always")
-        p = html5parser.HTMLParser(tree=treeClass,
-                                   namespaceHTMLElements=namespaceHTMLElements)
-
-        try:
-            if innerHTML:
-                document = p.parseFragment(input, innerHTML)
-            else:
-                document = p.parse(input)
-        except:
-            errorMsg = "\n".join(["\n\nInput:", input, "\nExpected:", expected,
-                                  "\nTraceback:", traceback.format_exc()])
-            assert False, errorMsg
-
-    otherWarnings = [x for x in caughtWarnings
-                     if not issubclass(x.category, constants.DataLossWarning)]
-    assert len(otherWarnings) == 0, [(x.category, x.message) for x in otherWarnings]
-    if len(caughtWarnings):
-        return
-
-    output = convertTreeDump(p.tree.testSerializer(document))
-
-    expected = convertExpected(expected)
-    if namespaceHTMLElements:
-        expected = namespaceExpected(r"\1<html \2>", expected)
-
-    errorMsg = "\n".join(["\n\nInput:", input, "\nExpected:", expected,
-                          "\nReceived:", output])
-    assert expected == output, errorMsg
-
-    errStr = []
-    for (line, col), errorcode, datavars in p.errors:
-        assert isinstance(datavars, dict), "%s, %s" % (errorcode, repr(datavars))
-        errStr.append("Line: %i Col: %i %s" % (line, col,
-                                               constants.E[errorcode] % datavars))
-
-    errorMsg2 = "\n".join(["\n\nInput:", input,
-                           "\nExpected errors (" + str(len(errors)) + "):\n" + "\n".join(errors),
-                           "\nActual errors (" + str(len(p.errors)) + "):\n" + "\n".join(errStr)])
-    if checkParseErrors:
-            assert len(p.errors) == len(errors), errorMsg2
-
-
-def test_parser():
-    sys.stderr.write('Testing tree builders ' + " ".join(list(treeTypes.keys())) + "\n")
-    files = get_data_files('tree-construction')
-
-    for filename in files:
-        testName = os.path.basename(filename).replace(".dat", "")
-        if testName in ("template",):
-            continue
-
-        tests = TestData(filename, "data")
-
-        for index, test in enumerate(tests):
-            input, errors, innerHTML, expected = [test[key] for key in
-                                                  ('data', 'errors',
-                                                   'document-fragment',
-                                                   'document')]
-            if errors:
-                errors = errors.split("\n")
-
-            for treeName, treeCls in treeTypes.items():
-                for namespaceHTMLElements in (True, False):
-                    yield (runParserTest, innerHTML, input, expected, errors, treeCls,
-                           namespaceHTMLElements)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_parser2.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_parser2.py
deleted file mode 100644
index 20bbdf3179c9..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_parser2.py
+++ /dev/null
@@ -1,64 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-import io
-
-from . import support  # flake8: noqa
-from html5lib import html5parser
-from html5lib.constants import namespaces
-from html5lib import treebuilders
-
-import unittest
-
-# tests that aren't autogenerated from text files
-
-
-class MoreParserTests(unittest.TestCase):
-
-    def setUp(self):
-        self.dom_tree = treebuilders.getTreeBuilder("dom")
-
-    def test_assertDoctypeCloneable(self):
-        parser = html5parser.HTMLParser(tree=self.dom_tree)
-        doc = parser.parse('<!DOCTYPE HTML>')
-        self.assertTrue(doc.cloneNode(True))
-
-    def test_line_counter(self):
-        # http://groups.google.com/group/html5lib-discuss/browse_frm/thread/f4f00e4a2f26d5c0
-        parser = html5parser.HTMLParser(tree=self.dom_tree)
-        parser.parse("<pre>\nx\n&gt;\n</pre>")
-
-    def test_namespace_html_elements_0_dom(self):
-        parser = html5parser.HTMLParser(tree=self.dom_tree, namespaceHTMLElements=True)
-        doc = parser.parse("<html></html>")
-        self.assertTrue(doc.childNodes[0].namespaceURI == namespaces["html"])
-
-    def test_namespace_html_elements_1_dom(self):
-        parser = html5parser.HTMLParser(tree=self.dom_tree, namespaceHTMLElements=False)
-        doc = parser.parse("<html></html>")
-        self.assertTrue(doc.childNodes[0].namespaceURI is None)
-
-    def test_namespace_html_elements_0_etree(self):
-        parser = html5parser.HTMLParser(namespaceHTMLElements=True)
-        doc = parser.parse("<html></html>")
-        self.assertTrue(list(doc)[0].tag == "{%s}html" % (namespaces["html"],))
-
-    def test_namespace_html_elements_1_etree(self):
-        parser = html5parser.HTMLParser(namespaceHTMLElements=False)
-        doc = parser.parse("<html></html>")
-        self.assertTrue(list(doc)[0].tag == "html")
-
-    def test_unicode_file(self):
-        parser = html5parser.HTMLParser()
-        parser.parse(io.StringIO("a"))
-
-
-def buildTestSuite():
-    return unittest.defaultTestLoader.loadTestsFromName(__name__)
-
-
-def main():
-    buildTestSuite()
-    unittest.main()
-
-if __name__ == '__main__':
-    main()
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_sanitizer.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_sanitizer.py
deleted file mode 100644
index 1cc687dfcad7..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_sanitizer.py
+++ /dev/null
@@ -1,105 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-try:
-    import json
-except ImportError:
-    import simplejson as json
-
-from html5lib import html5parser, sanitizer, constants, treebuilders
-
-
-def toxmlFactory():
-    tree = treebuilders.getTreeBuilder("etree")
-
-    def toxml(element):
-        # encode/decode roundtrip required for Python 2.6 compatibility
-        result_bytes = tree.implementation.tostring(element, encoding="utf-8")
-        return result_bytes.decode("utf-8")
-
-    return toxml
-
-
-def runSanitizerTest(name, expected, input, toxml=None):
-    if toxml is None:
-        toxml = toxmlFactory()
-    expected = ''.join([toxml(token) for token in html5parser.HTMLParser().
-                        parseFragment(expected)])
-    expected = json.loads(json.dumps(expected))
-    assert expected == sanitize_html(input)
-
-
-def sanitize_html(stream, toxml=None):
-    if toxml is None:
-        toxml = toxmlFactory()
-    return ''.join([toxml(token) for token in
-                    html5parser.HTMLParser(tokenizer=sanitizer.HTMLSanitizer).
-                    parseFragment(stream)])
-
-
-def test_should_handle_astral_plane_characters():
-    assert '<html:p xmlns:html="http://www.w3.org/1999/xhtml">\U0001d4b5 \U0001d538</html:p>' == sanitize_html("<p>&#x1d4b5; &#x1d538;</p>")
-
-
-def test_sanitizer():
-    toxml = toxmlFactory()
-    for tag_name in sanitizer.HTMLSanitizer.allowed_elements:
-        if tag_name in ['caption', 'col', 'colgroup', 'optgroup', 'option', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead', 'tr']:
-            continue  # TODO
-        if tag_name != tag_name.lower():
-            continue  # TODO
-        if tag_name == 'image':
-            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
-                   "<img title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz",
-                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name),
-                   toxml)
-        elif tag_name == 'br':
-            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
-                   "<br title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz<br/>",
-                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name),
-                   toxml)
-        elif tag_name in constants.voidElements:
-            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
-                   "<%s title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz" % tag_name,
-                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name),
-                   toxml)
-        else:
-            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
-                   "<%s title=\"1\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</%s>" % (tag_name, tag_name),
-                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name),
-                   toxml)
-
-    for tag_name in sanitizer.HTMLSanitizer.allowed_elements:
-        tag_name = tag_name.upper()
-        yield (runSanitizerTest, "test_should_forbid_%s_tag" % tag_name,
-               "&lt;%s title=\"1\"&gt;foo &lt;bad&gt;bar&lt;/bad&gt; baz&lt;/%s&gt;" % (tag_name, tag_name),
-               "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name),
-               toxml)
-
-    for attribute_name in sanitizer.HTMLSanitizer.allowed_attributes:
-        if attribute_name != attribute_name.lower():
-            continue  # TODO
-        if attribute_name == 'style':
-            continue
-        yield (runSanitizerTest, "test_should_allow_%s_attribute" % attribute_name,
-               "<p %s=\"foo\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</p>" % attribute_name,
-               "<p %s='foo'>foo <bad>bar</bad> baz</p>" % attribute_name,
-               toxml)
-
-    for attribute_name in sanitizer.HTMLSanitizer.allowed_attributes:
-        attribute_name = attribute_name.upper()
-        yield (runSanitizerTest, "test_should_forbid_%s_attribute" % attribute_name,
-               "<p>foo &lt;bad&gt;bar&lt;/bad&gt; baz</p>",
-               "<p %s='display: none;'>foo <bad>bar</bad> baz</p>" % attribute_name,
-               toxml)
-
-    for protocol in sanitizer.HTMLSanitizer.allowed_protocols:
-        yield (runSanitizerTest, "test_should_allow_%s_uris" % protocol,
-               "<a href=\"%s\">foo</a>" % protocol,
-               """<a href="%s">foo</a>""" % protocol,
-               toxml)
-
-    for protocol in sanitizer.HTMLSanitizer.allowed_protocols:
-        yield (runSanitizerTest, "test_should_allow_uppercase_%s_uris" % protocol,
-               "<a href=\"%s\">foo</a>" % protocol,
-               """<a href="%s">foo</a>""" % protocol,
-               toxml)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_serializer.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_serializer.py
deleted file mode 100644
index 3c37feff70b2..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_serializer.py
+++ /dev/null
@@ -1,178 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-import json
-import unittest
-
-from .support import get_data_files
-
-try:
-    unittest.TestCase.assertEqual
-except AttributeError:
-    unittest.TestCase.assertEqual = unittest.TestCase.assertEquals
-
-import html5lib
-from html5lib import constants
-from html5lib.serializer import HTMLSerializer, serialize
-from html5lib.treewalkers._base import TreeWalker
-
-optionals_loaded = []
-
-try:
-    from lxml import etree
-    optionals_loaded.append("lxml")
-except ImportError:
-    pass
-
-default_namespace = constants.namespaces["html"]
-
-
-class JsonWalker(TreeWalker):
-    def __iter__(self):
-        for token in self.tree:
-            type = token[0]
-            if type == "StartTag":
-                if len(token) == 4:
-                    namespace, name, attrib = token[1:4]
-                else:
-                    namespace = default_namespace
-                    name, attrib = token[1:3]
-                yield self.startTag(namespace, name, self._convertAttrib(attrib))
-            elif type == "EndTag":
-                if len(token) == 3:
-                    namespace, name = token[1:3]
-                else:
-                    namespace = default_namespace
-                    name = token[1]
-                yield self.endTag(namespace, name)
-            elif type == "EmptyTag":
-                if len(token) == 4:
-                    namespace, name, attrib = token[1:]
-                else:
-                    namespace = default_namespace
-                    name, attrib = token[1:]
-                for token in self.emptyTag(namespace, name, self._convertAttrib(attrib)):
-                    yield token
-            elif type == "Comment":
-                yield self.comment(token[1])
-            elif type in ("Characters", "SpaceCharacters"):
-                for token in self.text(token[1]):
-                    yield token
-            elif type == "Doctype":
-                if len(token) == 4:
-                    yield self.doctype(token[1], token[2], token[3])
-                elif len(token) == 3:
-                    yield self.doctype(token[1], token[2])
-                else:
-                    yield self.doctype(token[1])
-            else:
-                raise ValueError("Unknown token type: " + type)
-
-    def _convertAttrib(self, attribs):
-        """html5lib tree-walkers use a dict of (namespace, name): value for
-        attributes, but JSON cannot represent this. Convert from the format
-        in the serializer tests (a list of dicts with "namespace", "name",
-        and "value" as keys) to html5lib's tree-walker format."""
-        attrs = {}
-        for attrib in attribs:
-            name = (attrib["namespace"], attrib["name"])
-            assert(name not in attrs)
-            attrs[name] = attrib["value"]
-        return attrs
-
-
-def serialize_html(input, options):
-    options = dict([(str(k), v) for k, v in options.items()])
-    stream = JsonWalker(input)
-    serializer = HTMLSerializer(alphabetical_attributes=True, **options)
-    return serializer.render(stream, options.get("encoding", None))
-
-
-def runSerializerTest(input, expected, options):
-    encoding = options.get("encoding", None)
-
-    if encoding:
-        encode = lambda x: x.encode(encoding)
-        expected = list(map(encode, expected))
-
-    result = serialize_html(input, options)
-    if len(expected) == 1:
-        assert expected[0] == result, "Expected:\n%s\nActual:\n%s\nOptions:\n%s" % (expected[0], result, str(options))
-    elif result not in expected:
-        assert False, "Expected: %s, Received: %s" % (expected, result)
-
-
-class EncodingTestCase(unittest.TestCase):
-    def throwsWithLatin1(self, input):
-        self.assertRaises(UnicodeEncodeError, serialize_html, input, {"encoding": "iso-8859-1"})
-
-    def testDoctypeName(self):
-        self.throwsWithLatin1([["Doctype", "\u0101"]])
-
-    def testDoctypePublicId(self):
-        self.throwsWithLatin1([["Doctype", "potato", "\u0101"]])
-
-    def testDoctypeSystemId(self):
-        self.throwsWithLatin1([["Doctype", "potato", "potato", "\u0101"]])
-
-    def testCdataCharacters(self):
-        runSerializerTest([["StartTag", "http://www.w3.org/1999/xhtml", "style", {}], ["Characters", "\u0101"]],
-                          ["<style>&amacr;"], {"encoding": "iso-8859-1"})
-
-    def testCharacters(self):
-        runSerializerTest([["Characters", "\u0101"]],
-                          ["&amacr;"], {"encoding": "iso-8859-1"})
-
-    def testStartTagName(self):
-        self.throwsWithLatin1([["StartTag", "http://www.w3.org/1999/xhtml", "\u0101", []]])
-
-    def testEmptyTagName(self):
-        self.throwsWithLatin1([["EmptyTag", "http://www.w3.org/1999/xhtml", "\u0101", []]])
-
-    def testAttributeName(self):
-        self.throwsWithLatin1([["StartTag", "http://www.w3.org/1999/xhtml", "span", [{"namespace": None, "name": "\u0101", "value": "potato"}]]])
-
-    def testAttributeValue(self):
-        runSerializerTest([["StartTag", "http://www.w3.org/1999/xhtml", "span",
-                            [{"namespace": None, "name": "potato", "value": "\u0101"}]]],
-                          ["<span potato=&amacr;>"], {"encoding": "iso-8859-1"})
-
-    def testEndTagName(self):
-        self.throwsWithLatin1([["EndTag", "http://www.w3.org/1999/xhtml", "\u0101"]])
-
-    def testComment(self):
-        self.throwsWithLatin1([["Comment", "\u0101"]])
-
-
-if "lxml" in optionals_loaded:
-    class LxmlTestCase(unittest.TestCase):
-        def setUp(self):
-            self.parser = etree.XMLParser(resolve_entities=False)
-            self.treewalker = html5lib.getTreeWalker("lxml")
-            self.serializer = HTMLSerializer()
-
-        def testEntityReplacement(self):
-            doc = """<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>"""
-            tree = etree.fromstring(doc, parser=self.parser).getroottree()
-            result = serialize(tree, tree="lxml", omit_optional_tags=False)
-            self.assertEqual("""<!DOCTYPE html SYSTEM "about:legacy-compat"><html>\u03B2</html>""", result)
-
-        def testEntityXML(self):
-            doc = """<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&gt;</html>"""
-            tree = etree.fromstring(doc, parser=self.parser).getroottree()
-            result = serialize(tree, tree="lxml", omit_optional_tags=False)
-            self.assertEqual("""<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&gt;</html>""", result)
-
-        def testEntityNoResolve(self):
-            doc = """<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>"""
-            tree = etree.fromstring(doc, parser=self.parser).getroottree()
-            result = serialize(tree, tree="lxml", omit_optional_tags=False,
-                                          resolve_entities=False)
-            self.assertEqual("""<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>""", result)
-
-
-def test_serializer():
-    for filename in get_data_files('serializer', '*.test'):
-        with open(filename) as fp:
-            tests = json.load(fp)
-            for index, test in enumerate(tests['tests']):
-                yield runSerializerTest, test["input"], test["expected"], test.get("options", {})
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_stream.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_stream.py
deleted file mode 100644
index 2a876c1dbfdb..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_stream.py
+++ /dev/null
@@ -1,183 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from . import support  # flake8: noqa
-import unittest
-import codecs
-from io import BytesIO
-
-from six.moves import http_client
-
-from html5lib.inputstream import (BufferedStream, HTMLInputStream,
-                                  HTMLUnicodeInputStream, HTMLBinaryInputStream)
-
-class BufferedStreamTest(unittest.TestCase):
-    def test_basic(self):
-        s = b"abc"
-        fp = BufferedStream(BytesIO(s))
-        read = fp.read(10)
-        assert read == s
-
-    def test_read_length(self):
-        fp = BufferedStream(BytesIO(b"abcdef"))
-        read1 = fp.read(1)
-        assert read1 == b"a"
-        read2 = fp.read(2)
-        assert read2 == b"bc"
-        read3 = fp.read(3)
-        assert read3 == b"def"
-        read4 = fp.read(4)
-        assert read4 == b""
-
-    def test_tell(self):
-        fp = BufferedStream(BytesIO(b"abcdef"))
-        read1 = fp.read(1)
-        assert fp.tell() == 1
-        read2 = fp.read(2)
-        assert fp.tell() == 3
-        read3 = fp.read(3)
-        assert fp.tell() == 6
-        read4 = fp.read(4)
-        assert fp.tell() == 6
-
-    def test_seek(self):
-        fp = BufferedStream(BytesIO(b"abcdef"))
-        read1 = fp.read(1)
-        assert read1 == b"a"
-        fp.seek(0)
-        read2 = fp.read(1)
-        assert read2 == b"a"
-        read3 = fp.read(2)
-        assert read3 == b"bc"
-        fp.seek(2)
-        read4 = fp.read(2)
-        assert read4 == b"cd"
-        fp.seek(4)
-        read5 = fp.read(2)
-        assert read5 == b"ef"
-
-    def test_seek_tell(self):
-        fp = BufferedStream(BytesIO(b"abcdef"))
-        read1 = fp.read(1)
-        assert fp.tell() == 1
-        fp.seek(0)
-        read2 = fp.read(1)
-        assert fp.tell() == 1
-        read3 = fp.read(2)
-        assert fp.tell() == 3
-        fp.seek(2)
-        read4 = fp.read(2)
-        assert fp.tell() == 4
-        fp.seek(4)
-        read5 = fp.read(2)
-        assert fp.tell() == 6
-
-
-class HTMLUnicodeInputStreamShortChunk(HTMLUnicodeInputStream):
-    _defaultChunkSize = 2
-
-
-class HTMLBinaryInputStreamShortChunk(HTMLBinaryInputStream):
-    _defaultChunkSize = 2
-
-
-class HTMLInputStreamTest(unittest.TestCase):
-
-    def test_char_ascii(self):
-        stream = HTMLInputStream(b"'", encoding='ascii')
-        self.assertEqual(stream.charEncoding[0], 'ascii')
-        self.assertEqual(stream.char(), "'")
-
-    def test_char_utf8(self):
-        stream = HTMLInputStream('\u2018'.encode('utf-8'), encoding='utf-8')
-        self.assertEqual(stream.charEncoding[0], 'utf-8')
-        self.assertEqual(stream.char(), '\u2018')
-
-    def test_char_win1252(self):
-        stream = HTMLInputStream("\xa9\xf1\u2019".encode('windows-1252'))
-        self.assertEqual(stream.charEncoding[0], 'windows-1252')
-        self.assertEqual(stream.char(), "\xa9")
-        self.assertEqual(stream.char(), "\xf1")
-        self.assertEqual(stream.char(), "\u2019")
-
-    def test_bom(self):
-        stream = HTMLInputStream(codecs.BOM_UTF8 + b"'")
-        self.assertEqual(stream.charEncoding[0], 'utf-8')
-        self.assertEqual(stream.char(), "'")
-
-    def test_utf_16(self):
-        stream = HTMLInputStream((' ' * 1025).encode('utf-16'))
-        self.assertTrue(stream.charEncoding[0] in ['utf-16-le', 'utf-16-be'], stream.charEncoding)
-        self.assertEqual(len(stream.charsUntil(' ', True)), 1025)
-
-    def test_newlines(self):
-        stream = HTMLBinaryInputStreamShortChunk(codecs.BOM_UTF8 + b"a\nbb\r\nccc\rddddxe")
-        self.assertEqual(stream.position(), (1, 0))
-        self.assertEqual(stream.charsUntil('c'), "a\nbb\n")
-        self.assertEqual(stream.position(), (3, 0))
-        self.assertEqual(stream.charsUntil('x'), "ccc\ndddd")
-        self.assertEqual(stream.position(), (4, 4))
-        self.assertEqual(stream.charsUntil('e'), "x")
-        self.assertEqual(stream.position(), (4, 5))
-
-    def test_newlines2(self):
-        size = HTMLUnicodeInputStream._defaultChunkSize
-        stream = HTMLInputStream("\r" * size + "\n")
-        self.assertEqual(stream.charsUntil('x'), "\n" * size)
-
-    def test_position(self):
-        stream = HTMLBinaryInputStreamShortChunk(codecs.BOM_UTF8 + b"a\nbb\nccc\nddde\nf\ngh")
-        self.assertEqual(stream.position(), (1, 0))
-        self.assertEqual(stream.charsUntil('c'), "a\nbb\n")
-        self.assertEqual(stream.position(), (3, 0))
-        stream.unget("\n")
-        self.assertEqual(stream.position(), (2, 2))
-        self.assertEqual(stream.charsUntil('c'), "\n")
-        self.assertEqual(stream.position(), (3, 0))
-        stream.unget("\n")
-        self.assertEqual(stream.position(), (2, 2))
-        self.assertEqual(stream.char(), "\n")
-        self.assertEqual(stream.position(), (3, 0))
-        self.assertEqual(stream.charsUntil('e'), "ccc\nddd")
-        self.assertEqual(stream.position(), (4, 3))
-        self.assertEqual(stream.charsUntil('h'), "e\nf\ng")
-        self.assertEqual(stream.position(), (6, 1))
-
-    def test_position2(self):
-        stream = HTMLUnicodeInputStreamShortChunk("abc\nd")
-        self.assertEqual(stream.position(), (1, 0))
-        self.assertEqual(stream.char(), "a")
-        self.assertEqual(stream.position(), (1, 1))
-        self.assertEqual(stream.char(), "b")
-        self.assertEqual(stream.position(), (1, 2))
-        self.assertEqual(stream.char(), "c")
-        self.assertEqual(stream.position(), (1, 3))
-        self.assertEqual(stream.char(), "\n")
-        self.assertEqual(stream.position(), (2, 0))
-        self.assertEqual(stream.char(), "d")
-        self.assertEqual(stream.position(), (2, 1))
-
-    def test_python_issue_20007(self):
-        """
-        Make sure we have a work-around for Python bug #20007
-        http://bugs.python.org/issue20007
-        """
-        class FakeSocket(object):
-            def makefile(self, _mode, _bufsize=None):
-                return BytesIO(b"HTTP/1.1 200 Ok\r\n\r\nText")
-
-        source = http_client.HTTPResponse(FakeSocket())
-        source.begin()
-        stream = HTMLInputStream(source)
-        self.assertEqual(stream.charsUntil(" "), "Text")
-
-
-def buildTestSuite():
-    return unittest.defaultTestLoader.loadTestsFromName(__name__)
-
-
-def main():
-    buildTestSuite()
-    unittest.main()
-
-if __name__ == '__main__':
-    main()
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_treewalkers.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_treewalkers.py
deleted file mode 100644
index b7756035c263..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_treewalkers.py
+++ /dev/null
@@ -1,353 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-import os
-import sys
-import unittest
-import warnings
-from difflib import unified_diff
-
-try:
-    unittest.TestCase.assertEqual
-except AttributeError:
-    unittest.TestCase.assertEqual = unittest.TestCase.assertEquals
-
-from .support import get_data_files, TestData, convertExpected
-
-from html5lib import html5parser, treewalkers, treebuilders, constants
-
-
-def PullDOMAdapter(node):
-    from xml.dom import Node
-    from xml.dom.pulldom import START_ELEMENT, END_ELEMENT, COMMENT, CHARACTERS
-
-    if node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
-        for childNode in node.childNodes:
-            for event in PullDOMAdapter(childNode):
-                yield event
-
-    elif node.nodeType == Node.DOCUMENT_TYPE_NODE:
-        raise NotImplementedError("DOCTYPE nodes are not supported by PullDOM")
-
-    elif node.nodeType == Node.COMMENT_NODE:
-        yield COMMENT, node
-
-    elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
-        yield CHARACTERS, node
-
-    elif node.nodeType == Node.ELEMENT_NODE:
-        yield START_ELEMENT, node
-        for childNode in node.childNodes:
-            for event in PullDOMAdapter(childNode):
-                yield event
-        yield END_ELEMENT, node
-
-    else:
-        raise NotImplementedError("Node type not supported: " + str(node.nodeType))
-
-treeTypes = {
-    "DOM": {"builder": treebuilders.getTreeBuilder("dom"),
-            "walker": treewalkers.getTreeWalker("dom")},
-    "PullDOM": {"builder": treebuilders.getTreeBuilder("dom"),
-                "adapter": PullDOMAdapter,
-                "walker": treewalkers.getTreeWalker("pulldom")},
-}
-
-# Try whatever etree implementations are available from a list that are
-#"supposed" to work
-try:
-    import xml.etree.ElementTree as ElementTree
-except ImportError:
-    pass
-else:
-    treeTypes['ElementTree'] = \
-        {"builder": treebuilders.getTreeBuilder("etree", ElementTree),
-         "walker": treewalkers.getTreeWalker("etree", ElementTree)}
-
-try:
-    import xml.etree.cElementTree as ElementTree
-except ImportError:
-    pass
-else:
-    treeTypes['cElementTree'] = \
-        {"builder": treebuilders.getTreeBuilder("etree", ElementTree),
-         "walker": treewalkers.getTreeWalker("etree", ElementTree)}
-
-
-try:
-    import lxml.etree as ElementTree  # flake8: noqa
-except ImportError:
-    pass
-else:
-    treeTypes['lxml_native'] = \
-        {"builder": treebuilders.getTreeBuilder("lxml"),
-         "walker": treewalkers.getTreeWalker("lxml")}
-
-
-try:
-    from genshi.core import QName, Attrs
-    from genshi.core import START, END, TEXT, COMMENT, DOCTYPE
-except ImportError:
-    pass
-else:
-    def GenshiAdapter(tree):
-        text = None
-        for token in treewalkers.getTreeWalker("dom")(tree):
-            type = token["type"]
-            if type in ("Characters", "SpaceCharacters"):
-                if text is None:
-                    text = token["data"]
-                else:
-                    text += token["data"]
-            elif text is not None:
-                yield TEXT, text, (None, -1, -1)
-                text = None
-
-            if type in ("StartTag", "EmptyTag"):
-                if token["namespace"]:
-                    name = "{%s}%s" % (token["namespace"], token["name"])
-                else:
-                    name = token["name"]
-                attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
-                               for attr, value in token["data"].items()])
-                yield (START, (QName(name), attrs), (None, -1, -1))
-                if type == "EmptyTag":
-                    type = "EndTag"
-
-            if type == "EndTag":
-                if token["namespace"]:
-                    name = "{%s}%s" % (token["namespace"], token["name"])
-                else:
-                    name = token["name"]
-
-                yield END, QName(name), (None, -1, -1)
-
-            elif type == "Comment":
-                yield COMMENT, token["data"], (None, -1, -1)
-
-            elif type == "Doctype":
-                yield DOCTYPE, (token["name"], token["publicId"],
-                                token["systemId"]), (None, -1, -1)
-
-            else:
-                pass  # FIXME: What to do?
-
-        if text is not None:
-            yield TEXT, text, (None, -1, -1)
-
-    treeTypes["genshi"] = \
-        {"builder": treebuilders.getTreeBuilder("dom"),
-         "adapter": GenshiAdapter,
-         "walker": treewalkers.getTreeWalker("genshi")}
-
-
-def concatenateCharacterTokens(tokens):
-    charactersToken = None
-    for token in tokens:
-        type = token["type"]
-        if type in ("Characters", "SpaceCharacters"):
-            if charactersToken is None:
-                charactersToken = {"type": "Characters", "data": token["data"]}
-            else:
-                charactersToken["data"] += token["data"]
-        else:
-            if charactersToken is not None:
-                yield charactersToken
-                charactersToken = None
-            yield token
-    if charactersToken is not None:
-        yield charactersToken
-
-
-def convertTokens(tokens):
-    output = []
-    indent = 0
-    for token in concatenateCharacterTokens(tokens):
-        type = token["type"]
-        if type in ("StartTag", "EmptyTag"):
-            if (token["namespace"] and
-                    token["namespace"] != constants.namespaces["html"]):
-                if token["namespace"] in constants.prefixes:
-                    name = constants.prefixes[token["namespace"]]
-                else:
-                    name = token["namespace"]
-                name += " " + token["name"]
-            else:
-                name = token["name"]
-            output.append("%s<%s>" % (" " * indent, name))
-            indent += 2
-            attrs = token["data"]
-            if attrs:
-                # TODO: Remove this if statement, attrs should always exist
-                for (namespace, name), value in sorted(attrs.items()):
-                    if namespace:
-                        if namespace in constants.prefixes:
-                            outputname = constants.prefixes[namespace]
-                        else:
-                            outputname = namespace
-                        outputname += " " + name
-                    else:
-                        outputname = name
-                    output.append("%s%s=\"%s\"" % (" " * indent, outputname, value))
-            if type == "EmptyTag":
-                indent -= 2
-        elif type == "EndTag":
-            indent -= 2
-        elif type == "Comment":
-            output.append("%s<!-- %s -->" % (" " * indent, token["data"]))
-        elif type == "Doctype":
-            if token["name"]:
-                if token["publicId"]:
-                    output.append("""%s<!DOCTYPE %s "%s" "%s">""" %
-                                  (" " * indent, token["name"],
-                                   token["publicId"],
-                                   token["systemId"] and token["systemId"] or ""))
-                elif token["systemId"]:
-                    output.append("""%s<!DOCTYPE %s "" "%s">""" %
-                                  (" " * indent, token["name"],
-                                   token["systemId"]))
-                else:
-                    output.append("%s<!DOCTYPE %s>" % (" " * indent,
-                                                       token["name"]))
-            else:
-                output.append("%s<!DOCTYPE >" % (" " * indent,))
-        elif type in ("Characters", "SpaceCharacters"):
-            output.append("%s\"%s\"" % (" " * indent, token["data"]))
-        else:
-            pass  # TODO: what to do with errors?
-    return "\n".join(output)
-
-import re
-attrlist = re.compile(r"^(\s+)\w+=.*(\n\1\w+=.*)+", re.M)
-
-
-def sortattrs(x):
-    lines = x.group(0).split("\n")
-    lines.sort()
-    return "\n".join(lines)
-
-
-class TokenTestCase(unittest.TestCase):
-    def test_all_tokens(self):
-        expected = [
-            {'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'html'},
-            {'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'head'},
-            {'data': {}, 'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'head'},
-            {'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'body'},
-            {'data': 'a', 'type': 'Characters'},
-            {'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'div'},
-            {'data': 'b', 'type': 'Characters'},
-            {'data': {}, 'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'div'},
-            {'data': 'c', 'type': 'Characters'},
-            {'data': {}, 'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'body'},
-            {'data': {}, 'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'html'}
-        ]
-        for treeName, treeCls in treeTypes.items():
-            p = html5parser.HTMLParser(tree=treeCls["builder"])
-            document = p.parse("<html><head></head><body>a<div>b</div>c</body></html>")
-            document = treeCls.get("adapter", lambda x: x)(document)
-            output = treeCls["walker"](document)
-            for expectedToken, outputToken in zip(expected, output):
-                self.assertEqual(expectedToken, outputToken)
-
-
-def runTreewalkerTest(innerHTML, input, expected, errors, treeClass):
-    warnings.resetwarnings()
-    warnings.simplefilter("error")
-    try:
-        p = html5parser.HTMLParser(tree=treeClass["builder"])
-        if innerHTML:
-            document = p.parseFragment(input, innerHTML)
-        else:
-            document = p.parse(input)
-    except constants.DataLossWarning:
-        # Ignore testcases we know we don't pass
-        return
-
-    document = treeClass.get("adapter", lambda x: x)(document)
-    try:
-        output = convertTokens(treeClass["walker"](document))
-        output = attrlist.sub(sortattrs, output)
-        expected = attrlist.sub(sortattrs, convertExpected(expected))
-        diff = "".join(unified_diff([line + "\n" for line in expected.splitlines()],
-                                    [line + "\n" for line in output.splitlines()],
-                                    "Expected", "Received"))
-        assert expected == output, "\n".join([
-            "", "Input:", input,
-                "", "Expected:", expected,
-                "", "Received:", output,
-                "", "Diff:", diff,
-        ])
-    except NotImplementedError:
-        pass  # Amnesty for those that confess...
-
-
-def test_treewalker():
-    sys.stdout.write('Testing tree walkers ' + " ".join(list(treeTypes.keys())) + "\n")
-
-    for treeName, treeCls in treeTypes.items():
-        files = get_data_files('tree-construction')
-        for filename in files:
-            testName = os.path.basename(filename).replace(".dat", "")
-            if testName in ("template",):
-                continue
-
-            tests = TestData(filename, "data")
-
-            for index, test in enumerate(tests):
-                (input, errors,
-                 innerHTML, expected) = [test[key] for key in ("data", "errors",
-                                                               "document-fragment",
-                                                               "document")]
-                errors = errors.split("\n")
-                yield runTreewalkerTest, innerHTML, input, expected, errors, treeCls
-
-
-def set_attribute_on_first_child(docfrag, name, value, treeName):
-    """naively sets an attribute on the first child of the document
-    fragment passed in"""
-    setter = {'ElementTree': lambda d: d[0].set,
-              'DOM': lambda d: d.firstChild.setAttribute}
-    setter['cElementTree'] = setter['ElementTree']
-    try:
-        setter.get(treeName, setter['DOM'])(docfrag)(name, value)
-    except AttributeError:
-        setter['ElementTree'](docfrag)(name, value)
-
-
-def runTreewalkerEditTest(intext, expected, attrs_to_add, tree):
-    """tests what happens when we add attributes to the intext"""
-    treeName, treeClass = tree
-    parser = html5parser.HTMLParser(tree=treeClass["builder"])
-    document = parser.parseFragment(intext)
-    for nom, val in attrs_to_add:
-        set_attribute_on_first_child(document, nom, val, treeName)
-
-    document = treeClass.get("adapter", lambda x: x)(document)
-    output = convertTokens(treeClass["walker"](document))
-    output = attrlist.sub(sortattrs, output)
-    if not output in expected:
-        raise AssertionError("TreewalkerEditTest: %s\nExpected:\n%s\nReceived:\n%s" % (treeName, expected, output))
-
-
-def test_treewalker_six_mix():
-    """Str/Unicode mix. If str attrs added to tree"""
-
-    # On Python 2.x string literals are of type str. Unless, like this
-    # file, the programmer imports unicode_literals from __future__.
-    # In that case, string literals become objects of type unicode.
-
-    # This test simulates a Py2 user, modifying attributes on a document
-    # fragment but not using the u'' syntax nor importing unicode_literals
-    sm_tests = [
-        ('<a href="http://example.com">Example</a>',
-         [(str('class'), str('test123'))],
-         '<a>\n  class="test123"\n  href="http://example.com"\n  "Example"'),
-
-        ('<link href="http://example.com/cow">',
-         [(str('rel'), str('alternate'))],
-         '<link>\n  href="http://example.com/cow"\n  rel="alternate"\n  "Example"')
-    ]
-
-    for tree in treeTypes.items():
-        for intext, attrs, expected in sm_tests:
-            yield runTreewalkerEditTest, intext, expected, attrs, tree
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_whitespace_filter.py b/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_whitespace_filter.py
deleted file mode 100644
index 9ed27fd6ac0a..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_whitespace_filter.py
+++ /dev/null
@@ -1,133 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-import unittest
-
-from html5lib.filters.whitespace import Filter
-from html5lib.constants import spaceCharacters
-spaceCharacters = "".join(spaceCharacters)
-
-try:
-    unittest.TestCase.assertEqual
-except AttributeError:
-    unittest.TestCase.assertEqual = unittest.TestCase.assertEquals
-
-
-class TestCase(unittest.TestCase):
-    def runTest(self, input, expected):
-        output = list(Filter(input))
-        errorMsg = "\n".join(["\n\nInput:", str(input),
-                              "\nExpected:", str(expected),
-                              "\nReceived:", str(output)])
-        self.assertEqual(output, expected, errorMsg)
-
-    def runTestUnmodifiedOutput(self, input):
-        self.runTest(input, input)
-
-    def testPhrasingElements(self):
-        self.runTestUnmodifiedOutput(
-            [{"type": "Characters", "data": "This is a "},
-             {"type": "StartTag", "name": "span", "data": []},
-             {"type": "Characters", "data": "phrase"},
-             {"type": "EndTag", "name": "span", "data": []},
-             {"type": "SpaceCharacters", "data": " "},
-             {"type": "Characters", "data": "with"},
-             {"type": "SpaceCharacters", "data": " "},
-             {"type": "StartTag", "name": "em", "data": []},
-             {"type": "Characters", "data": "emphasised text"},
-             {"type": "EndTag", "name": "em", "data": []},
-             {"type": "Characters", "data": " and an "},
-             {"type": "StartTag", "name": "img", "data": [["alt", "image"]]},
-             {"type": "Characters", "data": "."}])
-
-    def testLeadingWhitespace(self):
-        self.runTest(
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "SpaceCharacters", "data": spaceCharacters},
-             {"type": "Characters", "data": "foo"},
-             {"type": "EndTag", "name": "p", "data": []}],
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "SpaceCharacters", "data": " "},
-             {"type": "Characters", "data": "foo"},
-             {"type": "EndTag", "name": "p", "data": []}])
-
-    def testLeadingWhitespaceAsCharacters(self):
-        self.runTest(
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "Characters", "data": spaceCharacters + "foo"},
-             {"type": "EndTag", "name": "p", "data": []}],
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "Characters", "data": " foo"},
-             {"type": "EndTag", "name": "p", "data": []}])
-
-    def testTrailingWhitespace(self):
-        self.runTest(
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "Characters", "data": "foo"},
-             {"type": "SpaceCharacters", "data": spaceCharacters},
-             {"type": "EndTag", "name": "p", "data": []}],
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "Characters", "data": "foo"},
-             {"type": "SpaceCharacters", "data": " "},
-             {"type": "EndTag", "name": "p", "data": []}])
-
-    def testTrailingWhitespaceAsCharacters(self):
-        self.runTest(
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "Characters", "data": "foo" + spaceCharacters},
-             {"type": "EndTag", "name": "p", "data": []}],
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "Characters", "data": "foo "},
-             {"type": "EndTag", "name": "p", "data": []}])
-
-    def testWhitespace(self):
-        self.runTest(
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "Characters", "data": "foo" + spaceCharacters + "bar"},
-             {"type": "EndTag", "name": "p", "data": []}],
-            [{"type": "StartTag", "name": "p", "data": []},
-             {"type": "Characters", "data": "foo bar"},
-             {"type": "EndTag", "name": "p", "data": []}])
-
-    def testLeadingWhitespaceInPre(self):
-        self.runTestUnmodifiedOutput(
-            [{"type": "StartTag", "name": "pre", "data": []},
-             {"type": "SpaceCharacters", "data": spaceCharacters},
-             {"type": "Characters", "data": "foo"},
-             {"type": "EndTag", "name": "pre", "data": []}])
-
-    def testLeadingWhitespaceAsCharactersInPre(self):
-        self.runTestUnmodifiedOutput(
-            [{"type": "StartTag", "name": "pre", "data": []},
-             {"type": "Characters", "data": spaceCharacters + "foo"},
-             {"type": "EndTag", "name": "pre", "data": []}])
-
-    def testTrailingWhitespaceInPre(self):
-        self.runTestUnmodifiedOutput(
-            [{"type": "StartTag", "name": "pre", "data": []},
-             {"type": "Characters", "data": "foo"},
-             {"type": "SpaceCharacters", "data": spaceCharacters},
-             {"type": "EndTag", "name": "pre", "data": []}])
-
-    def testTrailingWhitespaceAsCharactersInPre(self):
-        self.runTestUnmodifiedOutput(
-            [{"type": "StartTag", "name": "pre", "data": []},
-             {"type": "Characters", "data": "foo" + spaceCharacters},
-             {"type": "EndTag", "name": "pre", "data": []}])
-
-    def testWhitespaceInPre(self):
-        self.runTestUnmodifiedOutput(
-            [{"type": "StartTag", "name": "pre", "data": []},
-             {"type": "Characters", "data": "foo" + spaceCharacters + "bar"},
-             {"type": "EndTag", "name": "pre", "data": []}])
-
-
-def buildTestSuite():
-    return unittest.defaultTestLoader.loadTestsFromName(__name__)
-
-
-def main():
-    buildTestSuite()
-    unittest.main()
-
-if __name__ == "__main__":
-    main()
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treeadapters/__init__.py b/testing/web-platform/tests/tools/html5lib/html5lib/treeadapters/__init__.py
deleted file mode 100644
index e69de29bb2d1..000000000000
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/__init__.py b/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/__init__.py
deleted file mode 100644
index 6a6b2a4c45c0..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/__init__.py
+++ /dev/null
@@ -1,76 +0,0 @@
-"""A collection of modules for building different kinds of tree from
-HTML documents.
-
-To create a treebuilder for a new type of tree, you need to do
-implement several things:
-
-1) A set of classes for various types of elements: Document, Doctype,
-Comment, Element. These must implement the interface of
-_base.treebuilders.Node (although comment nodes have a different
-signature for their constructor, see treebuilders.etree.Comment)
-Textual content may also be implemented as another node type, or not, as
-your tree implementation requires.
-
-2) A treebuilder object (called TreeBuilder by convention) that
-inherits from treebuilders._base.TreeBuilder. This has 4 required attributes:
-documentClass - the class to use for the bottommost node of a document
-elementClass - the class to use for HTML Elements
-commentClass - the class to use for comments
-doctypeClass - the class to use for doctypes
-It also has one required method:
-getDocument - Returns the root node of the complete document tree
-
-3) If you wish to run the unit tests, you must also create a
-testSerializer method on your treebuilder which accepts a node and
-returns a string containing Node and its children serialized according
-to the format used in the unittests
-"""
-
-from __future__ import absolute_import, division, unicode_literals
-
-from ..utils import default_etree
-
-treeBuilderCache = {}
-
-
-def getTreeBuilder(treeType, implementation=None, **kwargs):
-    """Get a TreeBuilder class for various types of tree with built-in support
-
-    treeType - the name of the tree type required (case-insensitive). Supported
-               values are:
-
-               "dom" - A generic builder for DOM implementations, defaulting to
-                       a xml.dom.minidom based implementation.
-               "etree" - A generic builder for tree implementations exposing an
-                         ElementTree-like interface, defaulting to
-                         xml.etree.cElementTree if available and
-                         xml.etree.ElementTree if not.
-               "lxml" - A etree-based builder for lxml.etree, handling
-                        limitations of lxml's implementation.
-
-    implementation - (Currently applies to the "etree" and "dom" tree types). A
-                      module implementing the tree type e.g.
-                      xml.etree.ElementTree or xml.etree.cElementTree."""
-
-    treeType = treeType.lower()
-    if treeType not in treeBuilderCache:
-        if treeType == "dom":
-            from . import dom
-            # Come up with a sane default (pref. from the stdlib)
-            if implementation is None:
-                from xml.dom import minidom
-                implementation = minidom
-            # NEVER cache here, caching is done in the dom submodule
-            return dom.getDomModule(implementation, **kwargs).TreeBuilder
-        elif treeType == "lxml":
-            from . import etree_lxml
-            treeBuilderCache[treeType] = etree_lxml.TreeBuilder
-        elif treeType == "etree":
-            from . import etree
-            if implementation is None:
-                implementation = default_etree
-            # NEVER cache here, caching is done in the etree submodule
-            return etree.getETreeModule(implementation, **kwargs).TreeBuilder
-        else:
-            raise ValueError("""Unrecognised treebuilder "%s" """ % treeType)
-    return treeBuilderCache.get(treeType)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/__init__.py b/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/__init__.py
deleted file mode 100644
index 18124e75f3b9..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/__init__.py
+++ /dev/null
@@ -1,57 +0,0 @@
-"""A collection of modules for iterating through different kinds of
-tree, generating tokens identical to those produced by the tokenizer
-module.
-
-To create a tree walker for a new type of tree, you need to do
-implement a tree walker object (called TreeWalker by convention) that
-implements a 'serialize' method taking a tree as sole argument and
-returning an iterator generating tokens.
-"""
-
-from __future__ import absolute_import, division, unicode_literals
-
-import sys
-
-from ..utils import default_etree
-
-treeWalkerCache = {}
-
-
-def getTreeWalker(treeType, implementation=None, **kwargs):
-    """Get a TreeWalker class for various types of tree with built-in support
-
-    treeType - the name of the tree type required (case-insensitive). Supported
-               values are:
-
-                "dom" - The xml.dom.minidom DOM implementation
-                "pulldom" - The xml.dom.pulldom event stream
-                "etree" - A generic walker for tree implementations exposing an
-                          elementtree-like interface (known to work with
-                          ElementTree, cElementTree and lxml.etree).
-                "lxml" - Optimized walker for lxml.etree
-                "genshi" - a Genshi stream
-
-    implementation - (Currently applies to the "etree" tree type only). A module
-                      implementing the tree type e.g. xml.etree.ElementTree or
-                      cElementTree."""
-
-    treeType = treeType.lower()
-    if treeType not in treeWalkerCache:
-        if treeType in ("dom", "pulldom"):
-            name = "%s.%s" % (__name__, treeType)
-            __import__(name)
-            mod = sys.modules[name]
-            treeWalkerCache[treeType] = mod.TreeWalker
-        elif treeType == "genshi":
-            from . import genshistream
-            treeWalkerCache[treeType] = genshistream.TreeWalker
-        elif treeType == "lxml":
-            from . import lxmletree
-            treeWalkerCache[treeType] = lxmletree.TreeWalker
-        elif treeType == "etree":
-            from . import etree
-            if implementation is None:
-                implementation = default_etree
-            # XXX: NEVER cache here, caching is done in the etree submodule
-            return etree.getETreeModule(implementation, **kwargs).TreeWalker
-    return treeWalkerCache.get(treeType)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/pulldom.py b/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/pulldom.py
deleted file mode 100644
index 0b0f515fec7e..000000000000
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/pulldom.py
+++ /dev/null
@@ -1,63 +0,0 @@
-from __future__ import absolute_import, division, unicode_literals
-
-from xml.dom.pulldom import START_ELEMENT, END_ELEMENT, \
-    COMMENT, IGNORABLE_WHITESPACE, CHARACTERS
-
-from . import _base
-
-from ..constants import voidElements
-
-
-class TreeWalker(_base.TreeWalker):
-    def __iter__(self):
-        ignore_until = None
-        previous = None
-        for event in self.tree:
-            if previous is not None and \
-                    (ignore_until is None or previous[1] is ignore_until):
-                if previous[1] is ignore_until:
-                    ignore_until = None
-                for token in self.tokens(previous, event):
-                    yield token
-                    if token["type"] == "EmptyTag":
-                        ignore_until = previous[1]
-            previous = event
-        if ignore_until is None or previous[1] is ignore_until:
-            for token in self.tokens(previous, None):
-                yield token
-        elif ignore_until is not None:
-            raise ValueError("Illformed DOM event stream: void element without END_ELEMENT")
-
-    def tokens(self, event, next):
-        type, node = event
-        if type == START_ELEMENT:
-            name = node.nodeName
-            namespace = node.namespaceURI
-            attrs = {}
-            for attr in list(node.attributes.keys()):
-                attr = node.getAttributeNode(attr)
-                attrs[(attr.namespaceURI, attr.localName)] = attr.value
-            if name in voidElements:
-                for token in self.emptyTag(namespace,
-                                           name,
-                                           attrs,
-                                           not next or next[1] is not node):
-                    yield token
-            else:
-                yield self.startTag(namespace, name, attrs)
-
-        elif type == END_ELEMENT:
-            name = node.nodeName
-            namespace = node.namespaceURI
-            if name not in voidElements:
-                yield self.endTag(namespace, name)
-
-        elif type == COMMENT:
-            yield self.comment(node.nodeValue)
-
-        elif type in (IGNORABLE_WHITESPACE, CHARACTERS):
-            for token in self.text(node.nodeValue):
-                yield token
-
-        else:
-            yield self.unknown(type)
diff --git a/testing/web-platform/tests/tools/html5lib/requirements-install.sh b/testing/web-platform/tests/tools/html5lib/requirements-install.sh
deleted file mode 100755
index 5f8ba50645f9..000000000000
--- a/testing/web-platform/tests/tools/html5lib/requirements-install.sh
+++ /dev/null
@@ -1,16 +0,0 @@
-#!/bin/bash -e
-
-if [[ $USE_OPTIONAL != "true" && $USE_OPTIONAL != "false" ]]; then
-  echo "fatal: \$USE_OPTIONAL not set to true or false. Exiting."
-  exit 1
-fi
-
-pip install -r requirements-test.txt
-
-if [[ $USE_OPTIONAL == "true" && $TRAVIS_PYTHON_VERSION != "pypy" ]]; then
-  if [[ $TRAVIS_PYTHON_VERSION == "2.6" ]]; then
-    pip install --allow-external Genshi --allow-insecure Genshi -r requirements-optional-2.6.txt
-  else
-    pip install --allow-external Genshi --allow-insecure Genshi -r requirements-optional-cpython.txt
-  fi
-fi
diff --git a/testing/web-platform/tests/tools/html5lib/requirements-optional-2.6.txt b/testing/web-platform/tests/tools/html5lib/requirements-optional-2.6.txt
deleted file mode 100644
index 37557ac403df..000000000000
--- a/testing/web-platform/tests/tools/html5lib/requirements-optional-2.6.txt
+++ /dev/null
@@ -1,5 +0,0 @@
--r requirements-optional-cpython.txt
-
-# Can be used to force attributes to be serialized in alphabetical
-# order.
-ordereddict
diff --git a/testing/web-platform/tests/tools/html5lib/requirements-optional-cpython.txt b/testing/web-platform/tests/tools/html5lib/requirements-optional-cpython.txt
deleted file mode 100644
index 35ed3529c2c3..000000000000
--- a/testing/web-platform/tests/tools/html5lib/requirements-optional-cpython.txt
+++ /dev/null
@@ -1,5 +0,0 @@
--r requirements-optional.txt
-
-# lxml is supported with its own treebuilder ("lxml") and otherwise
-# uses the standard ElementTree support
-lxml
diff --git a/testing/web-platform/tests/tools/html5lib/requirements-optional.txt b/testing/web-platform/tests/tools/html5lib/requirements-optional.txt
deleted file mode 100644
index c6355270127e..000000000000
--- a/testing/web-platform/tests/tools/html5lib/requirements-optional.txt
+++ /dev/null
@@ -1,13 +0,0 @@
--r requirements.txt
-
-# We support a Genshi treewalker that can be used to serialize Genshi
-# streams.
-genshi
-
-# DATrie can be used in place of our Python trie implementation for
-# slightly better parsing performance.
-datrie
-
-# charade can be used as a fallback in case we are unable to determine
-# the encoding of a document.
-charade
diff --git a/testing/web-platform/tests/tools/html5lib/requirements-test.txt b/testing/web-platform/tests/tools/html5lib/requirements-test.txt
deleted file mode 100644
index d5f8088c1c13..000000000000
--- a/testing/web-platform/tests/tools/html5lib/requirements-test.txt
+++ /dev/null
@@ -1,5 +0,0 @@
--r requirements.txt
-
-flake8
-nose
-ordereddict # Python 2.6
diff --git a/testing/web-platform/tests/tools/html5lib/setup.py b/testing/web-platform/tests/tools/html5lib/setup.py
deleted file mode 100644
index f75910eaf210..000000000000
--- a/testing/web-platform/tests/tools/html5lib/setup.py
+++ /dev/null
@@ -1,44 +0,0 @@
-from distutils.core import setup
-import os
-import codecs
-
-classifiers=[
-    'Development Status :: 5 - Production/Stable',
-    'Intended Audience :: Developers',
-    'License :: OSI Approved :: MIT License',
-    'Operating System :: OS Independent',
-    'Programming Language :: Python',
-    'Programming Language :: Python :: 2',
-    'Programming Language :: Python :: 2.6',
-    'Programming Language :: Python :: 2.7',
-    'Programming Language :: Python :: 3',
-    'Programming Language :: Python :: 3.2',
-    'Programming Language :: Python :: 3.3',
-    'Topic :: Software Development :: Libraries :: Python Modules',
-    'Topic :: Text Processing :: Markup :: HTML'
-    ]
-
-packages = ['html5lib'] + ['html5lib.'+name
-                           for name in os.listdir(os.path.join('html5lib'))
-                           if os.path.isdir(os.path.join('html5lib', name)) and
-                           not name.startswith('.') and name != 'tests']
-
-current_dir = os.path.dirname(__file__)
-with codecs.open(os.path.join(current_dir, 'README.rst'), 'r', 'utf8') as readme_file:
-    with codecs.open(os.path.join(current_dir, 'CHANGES.rst'), 'r', 'utf8') as changes_file:
-        long_description = readme_file.read() + '\n' + changes_file.read()
-
-setup(name='html5lib',
-      version='0.9999-dev',
-      url='https://github.com/html5lib/html5lib-python',
-      license="MIT License",
-      description='HTML parser based on the WHATWG HTML specifcation',
-      long_description=long_description,
-      classifiers=classifiers,
-      maintainer='James Graham',
-      maintainer_email='james@hoppipolla.co.uk',
-      packages=packages,
-      install_requires=[
-          'six',
-      ],
-      )
diff --git a/testing/web-platform/tests/tools/html5lib/tox.ini b/testing/web-platform/tests/tools/html5lib/tox.ini
deleted file mode 100644
index 479f9e1f7323..000000000000
--- a/testing/web-platform/tests/tools/html5lib/tox.ini
+++ /dev/null
@@ -1,30 +0,0 @@
-[tox]
-envlist = py26,py27,py32,py33,py34,pypy
-
-[testenv]
-deps =
-  -r{toxinidir}/requirements-optional-cpython.txt
-  flake8
-  nose
-commands =
-  {envbindir}/nosetests -q
-  {toxinidir}/flake8-run.sh
-install_command =
-  pip install {opts} {packages}
-
-[testenv:pypy]
-# lxml doesn't work and datrie doesn't make sense
-# (it's slower than the pure-python version)
-deps =
-  charade
-  flake8
-  Genshi
-  nose
-  six
-
-[testenv:py26]
-basepython = python2.6
-deps =
-  -r{toxinidir}/requirements-optional-2.6.txt
-  flake8
-  nose
diff --git a/testing/web-platform/tests/tools/html5lib/utils/iana_parse.py b/testing/web-platform/tests/tools/html5lib/utils/iana_parse.py
deleted file mode 100644
index 6dde94c28292..000000000000
--- a/testing/web-platform/tests/tools/html5lib/utils/iana_parse.py
+++ /dev/null
@@ -1,24 +0,0 @@
-#!/usr/bin/env python
-import sys
-import urllib.request, urllib.error, urllib.parse
-import codecs
-
-def main():
-    encodings = []
-    f = urllib.request.urlopen(sys.argv[1])
-    for line in f:
-        if line.startswith("Name: ") or line.startswith("Alias: "):
-            enc = line.split()[1]
-            try:
-                codecs.lookup(enc)
-                if enc.lower not in encodings:
-                    encodings.append(enc.lower())
-            except LookupError:
-                pass
-    sys.stdout.write("encodings = frozenset((\n")
-    for enc in encodings:
-        sys.stdout.write('    "%s",\n'%enc)
-    sys.stdout.write('    ))')
-
-if __name__ == "__main__":
-    main()
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/html5lib/utils/spider.py b/testing/web-platform/tests/tools/html5lib/utils/spider.py
deleted file mode 100644
index a7b8031974b1..000000000000
--- a/testing/web-platform/tests/tools/html5lib/utils/spider.py
+++ /dev/null
@@ -1,122 +0,0 @@
-#!/usr/bin/env python
-"""Spider to try and find bugs in the parser. Requires httplib2 and elementtree
-
-usage:
-import spider
-s = spider.Spider()
-s.spider("http://www.google.com", maxURLs=100)
-"""
-
-import urllib.request, urllib.error, urllib.parse
-import urllib.robotparser
-import md5
-
-import httplib2
-
-import html5lib
-from html5lib.treebuilders import etree
-
-class Spider(object):
-    def __init__(self):
-        self.unvisitedURLs = set()
-        self.visitedURLs = set()
-        self.buggyURLs=set()
-        self.robotParser = urllib.robotparser.RobotFileParser()
-        self.contentDigest = {}
-        self.http = httplib2.Http(".cache")
-
-    def run(self, initialURL, maxURLs=1000):
-        urlNumber = 0
-        self.visitedURLs.add(initialURL)
-        content = self.loadURL(initialURL)
-        while maxURLs is None or urlNumber < maxURLs:
-            if content is not None:
-                self.parse(content)
-                urlNumber += 1
-            if not self.unvisitedURLs:
-                break
-            content = self.loadURL(self.unvisitedURLs.pop())
-
-    def parse(self, content):
-        failed = False
-        p = html5lib.HTMLParser(tree=etree.TreeBuilder)
-        try:
-            tree = p.parse(content)
-        except:
-            self.buggyURLs.add(self.currentURL)
-            failed = True
-            print("BUGGY:", self.currentURL)
-        self.visitedURLs.add(self.currentURL)
-        if not failed:
-            self.updateURLs(tree)
-
-    def loadURL(self, url):
-        resp, content = self.http.request(url, "GET")
-        self.currentURL = url
-        digest = md5.md5(content).hexdigest()
-        if digest in self.contentDigest:
-            content = None
-            self.visitedURLs.add(url)
-        else:
-            self.contentDigest[digest] = url
-
-        if resp['status'] != "200":
-            content = None
-
-        return content
-
-    def updateURLs(self, tree):
-        """Take all the links in the current document, extract the URLs and
-        update the list of visited and unvisited URLs according to whether we
-        have seen them before or not"""
-        urls = set()
-        #Remove all links we have already visited
-        for link in tree.findall(".//a"):
-                try:
-                    url = urllib.parse.urldefrag(link.attrib['href'])[0]
-                    if (url and url not in self.unvisitedURLs and url
-                        not in self.visitedURLs):
-                        urls.add(url)
-                except KeyError:
-                    pass
-
-        #Remove all non-http URLs and a dd a sutiable base URL where that is
-        #missing
-        newUrls = set()
-        for url in urls:
-            splitURL = list(urllib.parse.urlsplit(url))
-            if splitURL[0] != "http":
-                continue
-            if splitURL[1] == "":
-                splitURL[1] = urllib.parse.urlsplit(self.currentURL)[1]
-            newUrls.add(urllib.parse.urlunsplit(splitURL))
-        urls = newUrls
-
-        responseHeaders = {}
-        #Now we want to find the content types of the links we haven't visited
-        for url in urls:
-            try:
-                resp, content = self.http.request(url, "HEAD")
-                responseHeaders[url] = resp
-            except AttributeError as KeyError:
-                #Don't know why this happens
-                pass
-
-
-        #Remove links not of content-type html or pages not found
-        #XXX - need to deal with other status codes?
-        toVisit = set([url for url in urls if url in responseHeaders and
-                      "html" in responseHeaders[url]['content-type'] and
-                      responseHeaders[url]['status'] == "200"])
-
-        #Now check we are allowed to spider the page
-        for url in toVisit:
-            robotURL = list(urllib.parse.urlsplit(url)[:2])
-            robotURL.extend(["robots.txt", "", ""])
-            robotURL = urllib.parse.urlunsplit(robotURL)
-            self.robotParser.set_url(robotURL)
-            if not self.robotParser.can_fetch("*", url):
-                toVisit.remove(url)
-
-        self.visitedURLs.update(urls)
-        self.unvisitedURLs.update(toVisit)
diff --git a/testing/web-platform/tests/tools/localpaths.py b/testing/web-platform/tests/tools/localpaths.py
index 8509114b939c..0c4f018ae684 100644
--- a/testing/web-platform/tests/tools/localpaths.py
+++ b/testing/web-platform/tests/tools/localpaths.py
@@ -5,14 +5,15 @@ here = os.path.abspath(os.path.split(__file__)[0])
 repo_root = os.path.abspath(os.path.join(here, os.pardir))
 
 sys.path.insert(0, os.path.join(here))
-sys.path.insert(0, os.path.join(here, "six"))
-sys.path.insert(0, os.path.join(here, "html5lib"))
 sys.path.insert(0, os.path.join(here, "wptserve"))
 sys.path.insert(0, os.path.join(here, "pywebsocket"))
 sys.path.insert(0, os.path.join(here, "third_party", "attrs", "src"))
 sys.path.insert(0, os.path.join(here, "third_party", "funcsigs"))
+sys.path.insert(0, os.path.join(here, "third_party", "html5lib"))
 sys.path.insert(0, os.path.join(here, "third_party", "pluggy"))
 sys.path.insert(0, os.path.join(here, "third_party", "py"))
 sys.path.insert(0, os.path.join(here, "third_party", "pytest"))
+sys.path.insert(0, os.path.join(here, "third_party", "six"))
+sys.path.insert(0, os.path.join(here, "third_party", "webencodings"))
 sys.path.insert(0, os.path.join(here, "webdriver"))
 sys.path.insert(0, os.path.join(here, "wptrunner"))
diff --git a/testing/web-platform/tests/tools/six/.gitignore b/testing/web-platform/tests/tools/six/.gitignore
deleted file mode 100644
index 809b2e84eefc..000000000000
--- a/testing/web-platform/tests/tools/six/.gitignore
+++ /dev/null
@@ -1,9 +0,0 @@
-*#
-*.py[co]
-*.sw[po]
-*~
-MANIFEST
-documentation/_build
-\#*
-.tox
-six.egg-info
diff --git a/testing/web-platform/tests/tools/six/.hgignore b/testing/web-platform/tests/tools/six/.hgignore
deleted file mode 100644
index 37232e733825..000000000000
--- a/testing/web-platform/tests/tools/six/.hgignore
+++ /dev/null
@@ -1,8 +0,0 @@
-syntax: glob
-*.pyc
-dist
-MANIFEST
-documentation/_build
-.tox
-.gitignore
-six.egg-info
diff --git a/testing/web-platform/tests/tools/six/CONTRIBUTORS b/testing/web-platform/tests/tools/six/CONTRIBUTORS
deleted file mode 100644
index 0cbd0a4026e6..000000000000
--- a/testing/web-platform/tests/tools/six/CONTRIBUTORS
+++ /dev/null
@@ -1,22 +0,0 @@
-The primary author and maintainer of six is Benjamin Peterson. He would like to
-acknowledge the following people who submitted bug reports, pull requests, and
-otherwise worked to improve six:
-
-Marc Abramowitz
-Alexander Artemenko
-Aymeric Augustin
-Ned Batchelder
-Jason R. Coombs
-Julien Danjou
-Ben Darnell
-Ben Davis
-Joshua Harlow
-Anselm Kruis
-Alexander Lukanin
-James Mills
-Sridhar Ratnakumar
-Erik Rose
-Peter Ruibal
-Miroslav Shubernetskiy
-
-If you think you belong on this list, please let me know! --Benjamin
diff --git a/testing/web-platform/tests/tools/six/README b/testing/web-platform/tests/tools/six/README
deleted file mode 100644
index 32bab7ceecf6..000000000000
--- a/testing/web-platform/tests/tools/six/README
+++ /dev/null
@@ -1,16 +0,0 @@
-Six is a Python 2 and 3 compatibility library.  It provides utility functions
-for smoothing over the differences between the Python versions with the goal of
-writing Python code that is compatible on both Python versions.  See the
-documentation for more information on what is provided.
-
-Six supports every Python version since 2.5.  It is contained in only one Python
-file, so it can be easily copied into your project. (The copyright and license
-notice must be retained.)
-
-Online documentation is at http://pythonhosted.org/six/.
-
-Bugs can be reported to https://bitbucket.org/gutworth/six.  The code can also
-be found there.
-
-For questions about six or porting in general, email the python-porting mailing
-list: http://mail.python.org/mailman/listinfo/python-porting
diff --git a/testing/web-platform/tests/tools/six/setup.cfg b/testing/web-platform/tests/tools/six/setup.cfg
deleted file mode 100644
index 5e4090017a9b..000000000000
--- a/testing/web-platform/tests/tools/six/setup.cfg
+++ /dev/null
@@ -1,2 +0,0 @@
-[wheel]
-universal = 1
diff --git a/testing/web-platform/tests/tools/six/setup.py b/testing/web-platform/tests/tools/six/setup.py
deleted file mode 100644
index b0cca52d4a85..000000000000
--- a/testing/web-platform/tests/tools/six/setup.py
+++ /dev/null
@@ -1,32 +0,0 @@
-from __future__ import with_statement
-
-try:
-    from setuptools import setup
-except ImportError:
-    from distutils.core import setup
-
-import six
-
-six_classifiers = [
-    "Programming Language :: Python :: 2",
-    "Programming Language :: Python :: 3",
-    "Intended Audience :: Developers",
-    "License :: OSI Approved :: MIT License",
-    "Topic :: Software Development :: Libraries",
-    "Topic :: Utilities",
-]
-
-with open("README", "r") as fp:
-    six_long_description = fp.read()
-
-setup(name="six",
-      version=six.__version__,
-      author="Benjamin Peterson",
-      author_email="benjamin@python.org",
-      url="http://pypi.python.org/pypi/six/",
-      py_modules=["six"],
-      description="Python 2 and 3 compatibility utilities",
-      long_description=six_long_description,
-      license="MIT",
-      classifiers=six_classifiers
-      )
diff --git a/testing/web-platform/tests/tools/six/tox.ini b/testing/web-platform/tests/tools/six/tox.ini
deleted file mode 100644
index b29b31a69e9d..000000000000
--- a/testing/web-platform/tests/tools/six/tox.ini
+++ /dev/null
@@ -1,12 +0,0 @@
-[tox]
-envlist=py25,py26,py27,py31,py32,py33,py34,pypy
-indexserver=
-    default = http://pypi.python.org/simple
-    testrun = http://pypi.testrun.org
-
-[testenv]
-deps=pytest
-commands= py.test -rfsxX {posargs}
-
-[pytest]
-minversion=2.2.0
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/.appveyor.yml b/testing/web-platform/tests/tools/third_party/html5lib/.appveyor.yml
new file mode 100644
index 000000000000..984e2b7fa5e6
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/.appveyor.yml
@@ -0,0 +1,31 @@
+# To activate, change the Appveyor settings to use `.appveyor.yml`.
+environment:
+  global:
+    PATH: "C:\\Python27\\Scripts\\;%PATH%"
+    PYTEST_COMMAND: "coverage run -m pytest"
+  matrix:
+    - TOXENV: py27-base
+    - TOXENV: py27-optional
+    - TOXENV: py33-base
+    - TOXENV: py33-optional
+    - TOXENV: py34-base
+    - TOXENV: py34-optional
+    - TOXENV: py35-base
+    - TOXENV: py35-optional
+    - TOXENV: py36-base
+    - TOXENV: py36-optional
+
+install:
+  - git submodule update --init --recursive
+  - python -m pip install tox codecov
+
+build: off
+
+test_script:
+  - tox
+
+after_test:
+  - python debug-info.py
+
+on_success:
+  - codecov
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/.coveragerc b/testing/web-platform/tests/tools/third_party/html5lib/.coveragerc
new file mode 100644
index 000000000000..6facf35239fa
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/.coveragerc
@@ -0,0 +1,8 @@
+[run]
+branch = True
+source = html5lib
+
+[paths]
+source =
+   html5lib
+   .tox/*/lib/python*/site-packages/html5lib
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/.gitignore b/testing/web-platform/tests/tools/third_party/html5lib/.gitignore
new file mode 100644
index 000000000000..ecd62df31b91
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/.gitignore
@@ -0,0 +1,85 @@
+# Copyright (c) 2014 GitHub, Inc.
+#
+# Permission is hereby granted,  free of charge,  to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to  use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+# DEALINGS IN THE SOFTWARE.
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+doc/_build/
+
+# PyBuilder
+target/
+
+# Generated by parse.py -p
+stats.prof
+
+# IDE
+.idea
diff --git a/testing/web-platform/tests/tools/html5lib/.gitmodules b/testing/web-platform/tests/tools/third_party/html5lib/.gitmodules
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/.gitmodules
rename to testing/web-platform/tests/tools/third_party/html5lib/.gitmodules
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/.prospector.yaml b/testing/web-platform/tests/tools/third_party/html5lib/.prospector.yaml
new file mode 100644
index 000000000000..7e8efe1a629e
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/.prospector.yaml
@@ -0,0 +1,21 @@
+strictness: veryhigh
+doc-warnings: false
+test-warnings: false
+
+max-line-length: 139
+
+requirements:
+  - requirements.txt
+  - requirements-test.txt
+  - requirements-optional.txt
+
+ignore-paths:
+  - parse.py
+  - utils/
+
+python-targets:
+  - 2
+  - 3
+
+mccabe:
+  run: false
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/.pylintrc b/testing/web-platform/tests/tools/third_party/html5lib/.pylintrc
new file mode 100644
index 000000000000..ea74d5db3ff3
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/.pylintrc
@@ -0,0 +1,10 @@
+[MASTER]
+ignore=tests
+
+[MESSAGES CONTROL]
+# messages up to fixme should probably be fixed somehow
+disable = redefined-builtin,attribute-defined-outside-init,anomalous-backslash-in-string,no-self-use,redefined-outer-name,bad-continuation,wrong-import-order,superfluous-parens,no-member,duplicate-code,super-init-not-called,abstract-method,property-on-old-class,wrong-import-position,no-name-in-module,no-init,bad-mcs-classmethod-argument,bad-classmethod-argument,fixme,invalid-name,import-error,too-few-public-methods,too-many-ancestors,too-many-arguments,too-many-boolean-expressions,too-many-branches,too-many-instance-attributes,too-many-locals,too-many-lines,too-many-public-methods,too-many-return-statements,too-many-statements,missing-docstring,line-too-long,locally-disabled,locally-enabled,bad-builtin,deprecated-lambda
+
+[FORMAT]
+max-line-length=139
+single-line-if-stmt=no
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/.pytest.expect b/testing/web-platform/tests/tools/third_party/html5lib/.pytest.expect
new file mode 100644
index 000000000000..0fa326f0354f
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/.pytest.expect
@@ -0,0 +1,1322 @@
+pytest-expect file v1
+(2, 7, 11, 'final', 0)
+b'html5lib/tests/test_encoding.py::test_encoding::[110]': FAIL
+b'html5lib/tests/test_encoding.py::test_encoding::[111]': FAIL
+u'html5lib/tests/testdata/tokenizer/test2.test::0::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::228::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::231::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::232::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::234::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::235::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::237::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::240::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::241::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::243::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::244::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::246::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::258::dataState': FAIL
+u'html5lib/tests/testdata/tokenizer/test3.test::656::dataState': FAIL
+u'html5lib/tests/testdata/tree-construction/adoption01.dat::17::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/adoption01.dat::17::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/adoption01.dat::17::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/adoption01.dat::17::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/adoption01.dat::17::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/adoption01.dat::17::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/adoption01.dat::17::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/adoption01.dat::17::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::0::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::0::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::0::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::0::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::0::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::0::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::0::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::0::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::18::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::18::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::18::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::18::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::18::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::18::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::18::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::18::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::19::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::19::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::19::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::19::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::19::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::19::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::19::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::19::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::1::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::1::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::1::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::1::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::1::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::1::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::1::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::1::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::22::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::22::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::22::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::22::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::22::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::22::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::22::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::22::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::23::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::23::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::23::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::23::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::23::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::23::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::23::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::23::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::26::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::26::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::26::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::26::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::26::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::26::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::26::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::26::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::27::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::27::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::27::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::27::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::27::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::27::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::27::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::27::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::2::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::2::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::2::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::2::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::2::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::2::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::2::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::2::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::30::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::30::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::30::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::30::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::30::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::30::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::30::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::30::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::31::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::31::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::31::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::31::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::31::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::31::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::31::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::31::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::34::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::34::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::34::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::34::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::34::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::34::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::34::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::34::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::35::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::35::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::35::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::35::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::35::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::35::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::35::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::35::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::38::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::38::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::38::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::38::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::38::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::38::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::38::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::38::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::39::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::39::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::39::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::39::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::39::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::39::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::39::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::39::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::3::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::3::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::3::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::3::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::3::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::3::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::3::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::3::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::40::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::40::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::40::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::40::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::40::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::40::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::40::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::40::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::41::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::41::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::41::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::41::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::41::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::41::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::41::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::41::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::47::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::47::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::47::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::47::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::47::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::47::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::47::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::47::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::48::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::48::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::48::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::48::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::48::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::48::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::48::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/foreign-fragment.dat::48::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::0::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::0::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::0::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::0::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::0::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::0::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::0::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::0::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::1::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::1::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::1::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::1::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::1::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::1::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::1::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::1::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::2::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::2::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::2::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::2::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::2::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::2::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::2::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::2::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::3::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::3::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::3::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::3::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::3::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::3::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::3::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/isindex.dat::3::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::3::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::3::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::3::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::3::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::3::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::3::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::3::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::3::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::4::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::4::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::4::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::4::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::4::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::4::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::4::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::4::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::5::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::5::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::5::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::5::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::5::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::5::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::5::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/menuitem-element.dat::5::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/namespace-sensitivity.dat::0::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/namespace-sensitivity.dat::0::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/namespace-sensitivity.dat::0::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/namespace-sensitivity.dat::0::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/namespace-sensitivity.dat::0::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/namespace-sensitivity.dat::0::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/namespace-sensitivity.dat::0::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/namespace-sensitivity.dat::0::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::0::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::0::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::0::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::0::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::0::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::0::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::0::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::0::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::10::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::10::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::10::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::10::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::10::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::10::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::10::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::10::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::12::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::12::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::12::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::12::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::12::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::12::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::12::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::12::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::15::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::15::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::15::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::15::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::15::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::15::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::15::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::15::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::17::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::17::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::17::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::17::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::17::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::17::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::17::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::17::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::1::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::1::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::1::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::1::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::1::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::1::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::1::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::1::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::20::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::20::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::20::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::20::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::20::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::20::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::20::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::20::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::2::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::2::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::2::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::2::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::2::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::2::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::2::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::2::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::3::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::3::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::3::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::3::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::3::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::3::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::3::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::3::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::5::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::5::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::5::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::5::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::5::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::5::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::5::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::5::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::7::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::7::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::7::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::7::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::7::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::7::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::7::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/ruby.dat::7::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/adoption01.dat::0::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/adoption01.dat::0::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/adoption01.dat::0::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/adoption01.dat::0::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/adoption01.dat::0::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/adoption01.dat::0::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/adoption01.dat::0::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/adoption01.dat::0::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/ark.dat::0::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/ark.dat::0::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/ark.dat::0::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/ark.dat::0::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/ark.dat::0::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/ark.dat::0::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/ark.dat::0::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/ark.dat::0::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::0::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::0::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::0::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::0::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::0::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::0::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::0::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::0::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::1::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::1::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::1::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::1::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::1::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::1::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::1::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/scripted/webkit01.dat::1::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::0::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::0::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::0::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::0::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::0::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::0::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::0::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::0::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::100::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::100::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::100::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::100::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::100::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::100::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::100::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::100::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::101::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::101::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::101::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::101::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::101::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::101::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::101::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::101::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::102::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::102::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::102::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::102::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::102::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::102::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::102::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::102::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::103::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::103::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::103::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::103::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::103::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::103::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::103::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::103::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::104::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::104::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::104::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::104::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::104::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::104::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::104::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::104::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::105::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::105::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::105::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::105::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::105::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::105::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::105::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::105::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::106::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::106::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::106::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::106::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::106::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::106::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::106::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::106::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::107::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::107::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::107::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::107::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::107::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::107::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::107::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::107::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::10::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::10::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::10::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::10::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::10::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::10::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::10::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::10::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::11::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::11::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::11::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::11::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::11::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::11::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::11::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::11::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::12::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::12::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::12::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::12::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::12::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::12::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::12::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::12::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::13::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::13::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::13::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::13::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::13::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::13::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::13::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::13::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::14::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::14::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::14::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::14::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::14::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::14::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::14::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::14::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::15::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::15::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::15::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::15::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::15::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::15::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::15::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::15::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::16::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::16::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::16::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::16::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::16::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::16::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::16::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::16::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::17::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::17::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::17::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::17::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::17::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::17::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::17::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::17::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::18::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::18::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::18::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::18::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::18::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::18::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::18::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::18::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::19::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::19::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::19::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::19::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::19::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::19::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::19::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::19::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::1::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::1::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::1::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::1::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::1::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::1::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::1::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::1::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::20::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::20::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::20::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::20::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::20::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::20::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::20::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::20::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::21::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::21::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::21::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::21::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::21::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::21::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::21::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::21::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::22::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::22::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::22::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::22::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::22::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::22::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::22::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::22::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::23::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::23::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::23::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::23::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::23::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::23::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::23::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::23::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::24::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::24::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::24::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::24::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::24::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::24::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::24::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::24::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::25::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::25::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::25::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::25::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::25::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::25::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::25::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::25::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::26::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::26::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::26::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::26::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::26::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::26::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::26::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::26::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::27::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::27::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::27::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::27::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::27::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::27::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::27::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::27::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::28::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::28::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::28::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::28::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::28::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::28::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::28::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::28::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::29::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::29::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::29::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::29::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::29::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::29::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::29::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::29::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::2::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::2::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::2::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::2::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::2::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::2::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::2::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::2::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::30::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::30::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::30::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::30::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::30::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::30::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::30::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::30::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::31::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::31::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::31::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::31::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::31::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::31::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::31::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::31::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::32::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::32::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::32::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::32::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::32::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::32::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::32::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::32::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::33::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::33::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::33::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::33::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::33::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::33::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::33::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::33::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::34::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::34::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::34::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::34::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::34::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::34::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::34::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::34::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::35::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::35::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::35::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::35::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::35::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::35::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::35::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::35::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::36::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::36::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::36::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::36::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::36::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::36::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::36::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::36::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::37::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::37::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::37::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::37::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::37::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::37::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::37::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::37::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::38::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::38::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::38::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::38::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::38::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::38::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::38::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::38::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::3::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::3::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::3::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::3::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::3::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::3::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::3::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::3::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::40::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::40::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::40::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::40::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::40::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::40::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::40::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::40::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::41::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::41::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::41::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::41::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::41::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::41::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::41::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::41::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::42::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::42::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::42::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::42::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::42::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::42::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::42::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::42::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::43::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::43::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::43::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::43::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::43::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::43::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::43::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::43::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::44::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::44::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::44::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::44::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::44::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::44::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::44::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::44::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::45::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::45::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::45::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::45::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::45::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::45::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::45::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::45::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::46::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::46::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::46::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::46::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::46::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::46::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::46::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::46::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::47::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::47::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::47::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::47::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::47::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::47::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::47::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::47::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::48::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::48::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::48::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::48::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::48::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::48::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::48::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::48::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::49::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::49::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::49::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::49::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::49::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::49::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::49::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::49::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::4::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::4::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::4::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::4::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::4::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::4::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::4::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::4::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::50::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::50::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::50::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::50::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::50::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::50::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::50::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::50::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::51::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::51::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::51::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::51::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::51::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::51::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::51::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::51::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::52::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::52::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::52::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::52::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::52::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::52::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::52::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::52::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::53::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::53::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::53::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::53::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::53::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::53::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::53::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::53::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::54::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::54::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::54::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::54::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::54::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::54::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::54::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::54::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::55::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::55::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::55::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::55::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::55::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::55::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::55::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::55::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::56::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::56::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::56::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::56::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::56::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::56::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::56::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::56::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::57::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::57::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::57::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::57::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::57::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::57::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::57::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::57::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::58::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::58::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::58::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::58::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::58::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::58::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::58::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::58::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::59::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::59::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::59::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::59::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::59::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::59::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::59::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::59::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::5::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::5::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::5::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::5::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::5::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::5::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::5::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::5::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::60::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::60::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::60::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::60::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::60::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::60::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::60::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::60::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::61::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::61::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::61::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::61::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::61::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::61::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::61::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::61::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::62::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::62::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::62::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::62::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::62::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::62::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::62::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::62::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::63::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::63::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::63::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::63::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::63::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::63::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::63::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::63::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::64::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::64::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::64::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::64::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::64::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::64::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::64::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::64::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::65::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::65::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::65::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::65::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::65::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::65::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::65::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::65::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::66::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::66::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::66::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::66::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::66::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::66::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::66::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::66::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::67::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::67::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::67::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::67::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::67::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::67::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::67::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::67::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::68::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::68::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::68::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::68::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::68::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::68::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::68::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::68::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::69::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::69::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::69::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::69::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::69::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::69::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::69::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::69::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::6::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::6::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::6::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::6::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::6::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::6::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::6::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::6::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::70::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::70::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::70::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::70::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::70::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::70::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::70::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::70::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::71::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::71::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::71::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::71::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::71::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::71::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::71::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::71::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::72::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::72::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::72::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::72::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::72::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::72::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::72::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::72::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::73::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::73::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::73::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::73::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::73::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::73::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::73::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::73::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::74::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::74::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::74::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::74::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::74::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::74::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::74::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::74::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::75::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::75::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::75::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::75::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::75::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::75::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::75::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::75::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::76::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::76::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::76::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::76::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::76::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::76::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::76::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::76::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::77::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::77::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::77::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::77::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::77::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::77::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::77::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::77::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::78::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::78::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::78::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::78::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::78::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::78::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::78::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::78::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::79::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::79::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::79::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::79::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::79::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::79::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::79::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::79::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::80::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::80::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::80::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::80::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::80::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::80::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::80::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::80::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::81::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::81::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::81::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::81::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::81::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::81::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::81::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::81::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::82::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::82::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::82::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::82::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::82::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::82::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::82::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::82::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::83::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::83::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::83::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::83::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::83::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::83::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::83::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::83::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::84::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::84::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::84::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::84::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::84::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::84::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::84::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::84::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::85::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::85::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::85::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::85::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::85::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::85::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::85::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::85::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::86::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::86::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::86::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::86::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::86::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::86::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::86::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::86::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::87::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::87::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::87::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::87::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::87::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::87::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::87::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::87::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::88::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::88::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::88::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::88::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::88::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::88::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::88::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::88::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::89::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::89::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::89::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::89::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::89::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::89::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::89::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::89::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::8::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::8::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::8::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::8::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::8::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::8::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::8::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::8::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::90::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::90::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::90::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::90::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::90::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::90::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::90::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::90::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::91::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::91::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::91::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::91::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::91::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::91::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::91::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::91::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::92::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::92::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::92::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::92::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::92::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::92::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::92::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::92::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::93::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::93::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::93::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::93::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::93::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::93::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::93::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::93::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::94::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::94::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::94::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::94::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::94::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::94::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::94::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::94::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::95::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::95::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::95::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::95::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::95::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::95::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::95::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::95::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::96::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::96::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::96::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::96::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::96::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::96::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::96::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::96::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::97::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::97::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::97::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::97::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::97::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::97::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::97::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::97::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::98::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::98::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::98::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::98::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::98::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::98::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::98::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::98::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::99::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::99::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::99::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::99::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::99::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::99::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::99::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::99::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::9::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::9::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::9::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::9::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::9::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::9::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::9::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/template.dat::9::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::2::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::2::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::2::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::2::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::2::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::2::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::2::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::2::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::4::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::4::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::4::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::4::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::4::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::4::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::4::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::4::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::5::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::5::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::5::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::5::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::5::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::5::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::5::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::5::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::6::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::6::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::6::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::6::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::6::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::6::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::6::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests11.dat::6::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::14::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::14::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::14::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::14::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::14::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::14::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::14::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::14::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::17::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::17::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::17::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::17::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::17::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::17::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::17::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::17::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::7::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::7::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::7::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::7::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::7::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::7::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::7::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests19.dat::7::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::6::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::6::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::6::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::6::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::6::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::6::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::6::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::6::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::7::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::7::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::7::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::7::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::7::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::7::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::7::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests2.dat::7::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests25.dat::7::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests25.dat::7::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests25.dat::7::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests25.dat::7::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests25.dat::7::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests25.dat::7::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/tests25.dat::7::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/tests25.dat::7::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::14::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::14::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::14::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::14::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::14::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::14::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::14::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::14::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::15::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::15::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::15::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::15::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::15::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::15::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::15::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::15::lxml::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::16::DOM::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::16::DOM::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::16::ElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::16::ElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::16::cElementTree::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::16::cElementTree::parser::void-namespace': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::16::lxml::parser::namespaced': FAIL
+u'html5lib/tests/testdata/tree-construction/webkit02.dat::16::lxml::parser::void-namespace': FAIL
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/.travis.yml b/testing/web-platform/tests/tools/third_party/html5lib/.travis.yml
new file mode 100644
index 000000000000..5727e0947e2e
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/.travis.yml
@@ -0,0 +1,32 @@
+language: python
+python:
+  - "pypy"
+  - "3.6"
+  - "3.5"
+  - "3.4"
+  - "3.3"
+  - "2.7"
+
+sudo: false
+
+cache: pip
+
+env:
+  global:
+    - PYTEST_COMMAND="coverage run -m pytest"
+  matrix:
+    - TOXENV=optional
+    - TOXENV=base
+    - TOXENV=six19-optional
+
+install:
+  - pip install tox codecov
+
+script:
+  - tox
+
+after_script:
+  - python debug-info.py
+
+after_success:
+  - codecov
diff --git a/testing/web-platform/tests/tools/html5lib/AUTHORS.rst b/testing/web-platform/tests/tools/third_party/html5lib/AUTHORS.rst
similarity index 52%
rename from testing/web-platform/tests/tools/html5lib/AUTHORS.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/AUTHORS.rst
index 4148a6ed262d..fc635dea75b6 100644
--- a/testing/web-platform/tests/tools/html5lib/AUTHORS.rst
+++ b/testing/web-platform/tests/tools/third_party/html5lib/AUTHORS.rst
@@ -6,6 +6,7 @@ Credits
 - James Graham
 - Geoffrey Sneddon
 - Łukasz Langa
+- Will Kahn-Greene
 
 
 Patches and suggestions
@@ -16,19 +17,50 @@ Patches and suggestions
 - Lachlan Hunt
 - lantis63
 - Sam Ruby
-- Tim Fletcher
 - Thomas Broyer
+- Tim Fletcher
 - Mark Pilgrim
-- Philip Taylor
 - Ryan King
+- Philip Taylor
 - Edward Z. Yang
 - fantasai
 - Philip Jägenstedt
 - Ms2ger
+- Mohammad Taha Jahangir
 - Andy Wingo
 - Andreas Madsack
 - Karim Valiev
-- Mohammad Taha Jahangir
 - Juan Carlos Garcia Segovia
 - Mike West
 - Marc DM
+- Simon Sapin
+- Michael[tm] Smith
+- Ritwik Gupta
+- Marc Abramowitz
+- Tony Lopes
+- lilbludevil
+- Kevin
+- Drew Hubl
+- Austin Kumbera
+- Jim Baker
+- Jon Dufresne
+- Donald Stufft
+- Alex Gaynor
+- Nik Nyby
+- Jakub Wilk
+- Sigmund Cherem
+- Gabi Davar
+- Florian Mounier
+- neumond
+- Vitalik Verhovodov
+- Kovid Goyal
+- Adam Chainz
+- John Vandenberg
+- Eric Amorde
+- Benedikt Morbach
+- Jonathan Vanasco
+- Tom Most
+- Ville Skyttä
+- Hugo van Kemenade
+- Mark Vasilkov
+
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/CHANGES.rst b/testing/web-platform/tests/tools/third_party/html5lib/CHANGES.rst
new file mode 100644
index 000000000000..82605a216b27
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/CHANGES.rst
@@ -0,0 +1,335 @@
+Change Log
+----------
+
+1.0.1
+~~~~~
+
+Released on December 7, 2017
+
+Breaking changes:
+
+* Drop support for Python 2.6. (#330) (Thank you, Hugo, Will Kahn-Greene!)
+* Remove ``utils/spider.py`` (#353) (Thank you, Jon Dufresne!)
+
+Features:
+
+* Improve documentation. (#300, #307) (Thank you, Jon Dufresne, Tom Most,
+  Will Kahn-Greene!)
+* Add iframe seamless boolean attribute. (Thank you, Ritwik Gupta!)
+* Add itemscope as a boolean attribute. (#194) (Thank you, Jonathan Vanasco!)
+* Support Python 3.6. (#333) (Thank you, Jon Dufresne!)
+* Add CI support for Windows using AppVeyor. (Thank you, John Vandenberg!)
+* Improve testing and CI and add code coverage (#323, #334), (Thank you, Jon
+  Dufresne, John Vandenberg, Geoffrey Sneddon, Will Kahn-Greene!)
+* Semver-compliant version number.
+
+Bug fixes:
+
+* Add support for setuptools < 18.5 to support environment markers. (Thank you,
+  John Vandenberg!)
+* Add explicit dependency for six >= 1.9. (Thank you, Eric Amorde!)
+* Fix regexes to work with Python 3.7 regex adjustments. (#318, #379) (Thank
+  you, Benedikt Morbach, Ville Skyttä, Mark Vasilkov!)
+* Fix alphabeticalattributes filter namespace bug. (#324) (Thank you, Will
+  Kahn-Greene!)
+* Include license file in generated wheel package. (#350) (Thank you, Jon
+  Dufresne!)
+* Fix annotation-xml typo. (#339) (Thank you, Will Kahn-Greene!)
+* Allow uppercase hex chararcters in CSS colour check. (#377) (Thank you,
+  Komal Dembla, Hugo!)
+
+
+1.0
+~~~
+
+Released and unreleased on December 7, 2017. Badly packaged release.
+
+
+0.999999999/1.0b10
+~~~~~~~~~~~~~~~~~~
+
+Released on July 15, 2016
+
+* Fix attribute order going to the tree builder to be document order
+  instead of reverse document order(!).
+
+
+0.99999999/1.0b9
+~~~~~~~~~~~~~~~~
+
+Released on July 14, 2016
+
+* **Added ordereddict as a mandatory dependency on Python 2.6.**
+
+* Added ``lxml``, ``genshi``, ``datrie``, ``charade``, and ``all``
+  extras that will do the right thing based on the specific
+  interpreter implementation.
+
+* Now requires the ``mock`` package for the testsuite.
+
+* Cease supporting DATrie under PyPy.
+
+* **Remove PullDOM support, as this hasn't ever been properly
+  tested, doesn't entirely work, and as far as I can tell is
+  completely unused by anyone.**
+
+* Move testsuite to ``py.test``.
+
+* **Fix #124: move to webencodings for decoding the input byte stream;
+  this makes html5lib compliant with the Encoding Standard, and
+  introduces a required dependency on webencodings.**
+
+* **Cease supporting Python 3.2 (in both CPython and PyPy forms).**
+
+* **Fix comments containing double-dash with lxml 3.5 and above.**
+
+* **Use scripting disabled by default (as we don't implement
+  scripting).**
+
+* **Fix #11, avoiding the XSS bug potentially caused by serializer
+  allowing attribute values to be escaped out of in old browser versions,
+  changing the quote_attr_values option on serializer to take one of
+  three values, "always" (the old True value), "legacy" (the new option,
+  and the new default), and "spec" (the old False value, and the old
+  default).**
+
+* **Fix #72 by rewriting the sanitizer to apply only to treewalkers
+  (instead of the tokenizer); as such, this will require amending all
+  callers of it to use it via the treewalker API.**
+
+* **Drop support of charade, now that chardet is supported once more.**
+
+* **Replace the charset keyword argument on parse and related methods
+  with a set of keyword arguments: override_encoding, transport_encoding,
+  same_origin_parent_encoding, likely_encoding, and default_encoding.**
+
+* **Move filters._base, treebuilder._base, and treewalkers._base to .base
+  to clarify their status as public.**
+
+* **Get rid of the sanitizer package. Merge sanitizer.sanitize into the
+  sanitizer.htmlsanitizer module and move that to sanitizer. This means
+  anyone who used sanitizer.sanitize or sanitizer.HTMLSanitizer needs no
+  code changes.**
+
+* **Rename treewalkers.lxmletree to .etree_lxml and
+  treewalkers.genshistream to .genshi to have a consistent API.**
+
+* Move a whole load of stuff (inputstream, ihatexml, trie, tokenizer,
+  utils) to be underscore prefixed to clarify their status as private.
+
+
+0.9999999/1.0b8
+~~~~~~~~~~~~~~~
+
+Released on September 10, 2015
+
+* Fix #195: fix the sanitizer to drop broken URLs (it threw an
+  exception between 0.9999 and 0.999999).
+
+
+0.999999/1.0b7
+~~~~~~~~~~~~~~
+
+Released on July 7, 2015
+
+* Fix #189: fix the sanitizer to allow relative URLs again (as it did
+  prior to 0.9999/1.0b5).
+
+
+0.99999/1.0b6
+~~~~~~~~~~~~~
+
+Released on April 30, 2015
+
+* Fix #188: fix the sanitizer to not throw an exception when sanitizing
+  bogus data URLs.
+
+
+0.9999/1.0b5
+~~~~~~~~~~~~
+
+Released on April 29, 2015
+
+* Fix #153: Sanitizer fails to treat some attributes as URLs. Despite how
+  this sounds, this has no known security implications.  No known version
+  of IE (5.5 to current), Firefox (3 to current), Safari (6 to current),
+  Chrome (1 to current), or Opera (12 to current) will run any script
+  provided in these attributes.
+
+* Pass error message to the ParseError exception in strict parsing mode.
+
+* Allow data URIs in the sanitizer, with a whitelist of content-types.
+
+* Add support for Python implementations that don't support lone
+  surrogates (read: Jython). Fixes #2.
+
+* Remove localization of error messages. This functionality was totally
+  unused (and untested that everything was localizable), so we may as
+  well follow numerous browsers in not supporting translating technical
+  strings.
+
+* Expose treewalkers.pprint as a public API.
+
+* Add a documentEncoding property to HTML5Parser, fix #121.
+
+
+0.999
+~~~~~
+
+Released on December 23, 2013
+
+* Fix #127: add work-around for CPython issue #20007: .read(0) on
+  http.client.HTTPResponse drops the rest of the content.
+
+* Fix #115: lxml treewalker can now deal with fragments containing, at
+  their root level, text nodes with non-ASCII characters on Python 2.
+
+
+0.99
+~~~~
+
+Released on September 10, 2013
+
+* No library changes from 1.0b3; released as 0.99 as pip has changed
+  behaviour from 1.4 to avoid installing pre-release versions per
+  PEP 440.
+
+
+1.0b3
+~~~~~
+
+Released on July 24, 2013
+
+* Removed ``RecursiveTreeWalker`` from ``treewalkers._base``. Any
+  implementation using it should be moved to
+  ``NonRecursiveTreeWalker``, as everything bundled with html5lib has
+  for years.
+
+* Fix #67 so that ``BufferedStream`` to correctly returns a bytes
+  object, thereby fixing any case where html5lib is passed a
+  non-seekable RawIOBase-like object.
+
+
+1.0b2
+~~~~~
+
+Released on June 27, 2013
+
+* Removed reordering of attributes within the serializer. There is now
+  an ``alphabetical_attributes`` option which preserves the previous
+  behaviour through a new filter. This allows attribute order to be
+  preserved through html5lib if the tree builder preserves order.
+
+* Removed ``dom2sax`` from DOM treebuilders. It has been replaced by
+  ``treeadapters.sax.to_sax`` which is generic and supports any
+  treewalker; it also resolves all known bugs with ``dom2sax``.
+
+* Fix treewalker assertions on hitting bytes strings on
+  Python 2. Previous to 1.0b1, treewalkers coped with mixed
+  bytes/unicode data on Python 2; this reintroduces this prior
+  behaviour on Python 2. Behaviour is unchanged on Python 3.
+
+
+1.0b1
+~~~~~
+
+Released on May 17, 2013
+
+* Implementation updated to implement the `HTML specification
+  <http://www.whatwg.org/specs/web-apps/current-work/>`_ as of 5th May
+  2013 (`SVN <http://svn.whatwg.org/webapps/>`_ revision r7867).
+
+* Python 3.2+ supported in a single codebase using the ``six`` library.
+
+* Removed support for Python 2.5 and older.
+
+* Removed the deprecated Beautiful Soup 3 treebuilder.
+  ``beautifulsoup4`` can use ``html5lib`` as a parser instead. Note that
+  since it doesn't support namespaces, foreign content like SVG and
+  MathML is parsed incorrectly.
+
+* Removed ``simpletree`` from the package. The default tree builder is
+  now ``etree`` (using the ``xml.etree.cElementTree`` implementation if
+  available, and ``xml.etree.ElementTree`` otherwise).
+
+* Removed the ``XHTMLSerializer`` as it never actually guaranteed its
+  output was well-formed XML, and hence provided little of use.
+
+* Removed default DOM treebuilder, so ``html5lib.treebuilders.dom`` is no
+  longer supported. ``html5lib.treebuilders.getTreeBuilder("dom")`` will
+  return the default DOM treebuilder, which uses ``xml.dom.minidom``.
+
+* Optional heuristic character encoding detection now based on
+  ``charade`` for Python 2.6 - 3.3 compatibility.
+
+* Optional ``Genshi`` treewalker support fixed.
+
+* Many bugfixes, including:
+
+  * #33: null in attribute value breaks XML AttValue;
+
+  * #4: nested, indirect descendant, <button> causes infinite loop;
+
+  * `Google Code 215
+    <http://code.google.com/p/html5lib/issues/detail?id=215>`_: Properly
+    detect seekable streams;
+
+  * `Google Code 206
+    <http://code.google.com/p/html5lib/issues/detail?id=206>`_: add
+    support for <video preload=...>, <audio preload=...>;
+
+  * `Google Code 205
+    <http://code.google.com/p/html5lib/issues/detail?id=205>`_: add
+    support for <video poster=...>;
+
+  * `Google Code 202
+    <http://code.google.com/p/html5lib/issues/detail?id=202>`_: Unicode
+    file breaks InputStream.
+
+* Source code is now mostly PEP 8 compliant.
+
+* Test harness has been improved and now depends on ``nose``.
+
+* Documentation updated and moved to https://html5lib.readthedocs.io/.
+
+
+0.95
+~~~~
+
+Released on February 11, 2012
+
+
+0.90
+~~~~
+
+Released on January 17, 2010
+
+
+0.11.1
+~~~~~~
+
+Released on June 12, 2008
+
+
+0.11
+~~~~
+
+Released on June 10, 2008
+
+
+0.10
+~~~~
+
+Released on October 7, 2007
+
+
+0.9
+~~~
+
+Released on March 11, 2007
+
+
+0.2
+~~~
+
+Released on January 8, 2007
diff --git a/testing/web-platform/tests/tools/html5lib/CONTRIBUTING.rst b/testing/web-platform/tests/tools/third_party/html5lib/CONTRIBUTING.rst
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/CONTRIBUTING.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/CONTRIBUTING.rst
diff --git a/testing/web-platform/tests/tools/html5lib/LICENSE b/testing/web-platform/tests/tools/third_party/html5lib/LICENSE
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/LICENSE
rename to testing/web-platform/tests/tools/third_party/html5lib/LICENSE
diff --git a/testing/web-platform/tests/tools/html5lib/MANIFEST.in b/testing/web-platform/tests/tools/third_party/html5lib/MANIFEST.in
similarity index 65%
rename from testing/web-platform/tests/tools/html5lib/MANIFEST.in
rename to testing/web-platform/tests/tools/third_party/html5lib/MANIFEST.in
index 1edd0b7deea5..4b3ffe3ed9f5 100644
--- a/testing/web-platform/tests/tools/html5lib/MANIFEST.in
+++ b/testing/web-platform/tests/tools/third_party/html5lib/MANIFEST.in
@@ -1,6 +1,10 @@
 include LICENSE
+include AUTHORS.rst
 include CHANGES.rst
 include README.rst
 include requirements*.txt
+include .pytest.expect
+include tox.ini
+include pytest.ini
 graft html5lib/tests/testdata
 recursive-include html5lib/tests *.py
diff --git a/testing/web-platform/tests/tools/html5lib/README.rst b/testing/web-platform/tests/tools/third_party/html5lib/README.rst
similarity index 79%
rename from testing/web-platform/tests/tools/html5lib/README.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/README.rst
index 9e0a0f740485..8c151328b3da 100644
--- a/testing/web-platform/tests/tools/html5lib/README.rst
+++ b/testing/web-platform/tests/tools/third_party/html5lib/README.rst
@@ -51,7 +51,7 @@ pass into html5lib as follows:
   import html5lib
 
   with closing(urlopen("http://example.com/")) as f:
-      document = html5lib.parse(f, encoding=f.info().getparam("charset"))
+      document = html5lib.parse(f, transport_encoding=f.info().getparam("charset"))
 
 When using with ``urllib.request`` (Python 3), the charset from HTTP
 should be pass into html5lib as follows:
@@ -62,7 +62,7 @@ should be pass into html5lib as follows:
   import html5lib
 
   with urlopen("http://example.com/") as f:
-      document = html5lib.parse(f, encoding=f.info().get_content_charset())
+      document = html5lib.parse(f, transport_encoding=f.info().get_content_charset())
 
 To have more control over the parser, create a parser object explicitly.
 For instance, to make the parser raise exceptions on parse errors, use:
@@ -84,13 +84,13 @@ format:
   parser = html5lib.HTMLParser(tree=html5lib.getTreeBuilder("dom"))
   minidom_document = parser.parse("<p>Hello World!")
 
-More documentation is available at http://html5lib.readthedocs.org/.
+More documentation is available at https://html5lib.readthedocs.io/.
 
 
 Installation
 ------------
 
-html5lib works on CPython 2.6+, CPython 3.2+ and PyPy.  To install it,
+html5lib works on CPython 2.7+, CPython 3.3+ and PyPy.  To install it,
 use:
 
 .. code-block:: bash
@@ -104,8 +104,8 @@ Optional Dependencies
 The following third-party libraries may be used for additional
 functionality:
 
-- ``datrie`` can be used to improve parsing performance (though in
-  almost all cases the improvement is marginal);
+- ``datrie`` can be used under CPython to improve parsing performance
+  (though in almost all cases the improvement is marginal);
 
 - ``lxml`` is supported as a tree format (for both building and
   walking) under CPython (but *not* PyPy where it is known to cause
@@ -113,13 +113,8 @@ functionality:
 
 - ``genshi`` has a treewalker (but not builder); and
 
-- ``charade`` can be used as a fallback when character encoding cannot
-  be determined; ``chardet``, from which it was forked, can also be used
-  on Python 2.
-
-- ``ordereddict`` can be used under Python 2.6
-  (``collections.OrderedDict`` is used instead on later versions) to
-  serialize attributes in alphabetical order.
+- ``chardet`` can be used as a fallback when character encoding cannot
+  be determined.
 
 
 Bugs
@@ -132,9 +127,8 @@ Please report any bugs on the `issue tracker
 Tests
 -----
 
-Unit tests require the ``nose`` library and can be run using the
-``nosetests`` command in the root directory; ``ordereddict`` is
-required under Python 2.6. All should pass.
+Unit tests require the ``pytest`` and ``mock`` libraries and can be
+run using the ``py.test`` command in the root directory.
 
 Test data are contained in a separate `html5lib-tests
 <https://github.com/html5lib/html5lib-tests>`_ repository and included
diff --git a/testing/web-platform/tests/tools/html5lib/debug-info.py b/testing/web-platform/tests/tools/third_party/html5lib/debug-info.py
similarity index 88%
rename from testing/web-platform/tests/tools/html5lib/debug-info.py
rename to testing/web-platform/tests/tools/third_party/html5lib/debug-info.py
index b5d2bb6a3057..f93fbdbeaec1 100644
--- a/testing/web-platform/tests/tools/html5lib/debug-info.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/debug-info.py
@@ -12,7 +12,7 @@ info = {
     "maxsize": sys.maxsize
 }
 
-search_modules = ["charade", "chardet", "datrie", "genshi", "html5lib", "lxml", "six"]
+search_modules = ["chardet", "datrie", "genshi", "html5lib", "lxml", "six"]
 found_modules = []
 
 for m in search_modules:
diff --git a/testing/web-platform/tests/tools/html5lib/doc/Makefile b/testing/web-platform/tests/tools/third_party/html5lib/doc/Makefile
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/doc/Makefile
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/Makefile
diff --git a/testing/web-platform/tests/tools/html5lib/doc/changes.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/changes.rst
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/doc/changes.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/changes.rst
diff --git a/testing/web-platform/tests/tools/html5lib/doc/conf.py b/testing/web-platform/tests/tools/third_party/html5lib/doc/conf.py
similarity index 99%
rename from testing/web-platform/tests/tools/html5lib/doc/conf.py
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/conf.py
index 434f21c42ebc..e02218b8ad39 100644
--- a/testing/web-platform/tests/tools/html5lib/doc/conf.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/doc/conf.py
@@ -126,7 +126,7 @@ html_theme = 'default'
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+#html_static_path = ['_static']
 
 # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
 # using the given strftime format.
diff --git a/testing/web-platform/tests/tools/html5lib/doc/html5lib.filters.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.filters.rst
similarity index 77%
rename from testing/web-platform/tests/tools/html5lib/doc/html5lib.filters.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.filters.rst
index 1fda38a735a1..d70e4552f028 100644
--- a/testing/web-platform/tests/tools/html5lib/doc/html5lib.filters.rst
+++ b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.filters.rst
@@ -1,59 +1,58 @@
 filters Package
 ===============
 
-:mod:`_base` Module
+:mod:`base` Module
 -------------------
 
-.. automodule:: html5lib.filters._base
+.. automodule:: html5lib.filters.base
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`alphabeticalattributes` Module
 ------------------------------------
 
 .. automodule:: html5lib.filters.alphabeticalattributes
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`inject_meta_charset` Module
 ---------------------------------
 
 .. automodule:: html5lib.filters.inject_meta_charset
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`lint` Module
 ------------------
 
 .. automodule:: html5lib.filters.lint
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`optionaltags` Module
 --------------------------
 
 .. automodule:: html5lib.filters.optionaltags
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`sanitizer` Module
 -----------------------
 
 .. automodule:: html5lib.filters.sanitizer
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`whitespace` Module
 ------------------------
 
 .. automodule:: html5lib.filters.whitespace
     :members:
-    :undoc-members:
     :show-inheritance:
-
+    :special-members: __init__
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.rst
new file mode 100644
index 000000000000..d7c75c5842ff
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.rst
@@ -0,0 +1,38 @@
+html5lib Package
+================
+
+.. automodule:: html5lib
+    :members: __version__
+
+:mod:`constants` Module
+-----------------------
+
+.. automodule:: html5lib.constants
+    :members:
+    :show-inheritance:
+
+:mod:`html5parser` Module
+-------------------------
+
+.. automodule:: html5lib.html5parser
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+:mod:`serializer` Module
+------------------------
+
+.. automodule:: html5lib.serializer
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+Subpackages
+-----------
+
+.. toctree::
+
+    html5lib.filters
+    html5lib.treebuilders
+    html5lib.treewalkers
+    html5lib.treeadapters
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treeadapters.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treeadapters.rst
new file mode 100644
index 000000000000..1d3a9fba2ff3
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treeadapters.rst
@@ -0,0 +1,20 @@
+treeadapters Package
+====================
+
+:mod:`~html5lib.treeadapters` Package
+-------------------------------------
+
+.. automodule:: html5lib.treeadapters
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+.. automodule:: html5lib.treeadapters.genshi
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+.. automodule:: html5lib.treeadapters.sax
+    :members:
+    :show-inheritance:
+    :special-members: __init__
diff --git a/testing/web-platform/tests/tools/html5lib/doc/html5lib.treebuilders.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treebuilders.rst
similarity index 73%
rename from testing/web-platform/tests/tools/html5lib/doc/html5lib.treebuilders.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treebuilders.rst
index 9911983948de..1a051e50bd8e 100644
--- a/testing/web-platform/tests/tools/html5lib/doc/html5lib.treebuilders.rst
+++ b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treebuilders.rst
@@ -6,38 +6,37 @@ treebuilders Package
 
 .. automodule:: html5lib.treebuilders
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
-:mod:`_base` Module
+:mod:`base` Module
 -------------------
 
-.. automodule:: html5lib.treebuilders._base
+.. automodule:: html5lib.treebuilders.base
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`dom` Module
 -----------------
 
 .. automodule:: html5lib.treebuilders.dom
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`etree` Module
 -------------------
 
 .. automodule:: html5lib.treebuilders.etree
     :members:
-    :undoc-members:
     :show-inheritance:
+    :special-members: __init__
 
 :mod:`etree_lxml` Module
 ------------------------
 
 .. automodule:: html5lib.treebuilders.etree_lxml
     :members:
-    :undoc-members:
     :show-inheritance:
-
+    :special-members: __init__
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treewalkers.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treewalkers.rst
new file mode 100644
index 000000000000..4afef47609b5
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/doc/html5lib.treewalkers.rst
@@ -0,0 +1,50 @@
+treewalkers Package
+===================
+
+:mod:`treewalkers` Package
+--------------------------
+
+.. automodule:: html5lib.treewalkers
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+:mod:`base` Module
+------------------
+
+.. automodule:: html5lib.treewalkers.base
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+:mod:`dom` Module
+-----------------
+
+.. automodule:: html5lib.treewalkers.dom
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+:mod:`etree` Module
+-------------------
+
+.. automodule:: html5lib.treewalkers.etree
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+:mod:`etree_lxml` Module
+------------------------
+
+.. automodule:: html5lib.treewalkers.etree_lxml
+    :members:
+    :show-inheritance:
+    :special-members: __init__
+
+:mod:`genshi` Module
+--------------------
+
+.. automodule:: html5lib.treewalkers.genshi
+    :members:
+    :show-inheritance:
+    :special-members: __init__
diff --git a/testing/web-platform/tests/tools/html5lib/doc/index.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/index.rst
similarity index 95%
rename from testing/web-platform/tests/tools/html5lib/doc/index.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/index.rst
index ca2e1b969cdc..27104b14697d 100644
--- a/testing/web-platform/tests/tools/html5lib/doc/index.rst
+++ b/testing/web-platform/tests/tools/third_party/html5lib/doc/index.rst
@@ -8,6 +8,7 @@ Overview
    :maxdepth: 2
 
    movingparts
+   modules
    changes
    License <license>
 
diff --git a/testing/web-platform/tests/tools/html5lib/doc/license.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/license.rst
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/doc/license.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/license.rst
diff --git a/testing/web-platform/tests/tools/html5lib/doc/make.bat b/testing/web-platform/tests/tools/third_party/html5lib/doc/make.bat
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/doc/make.bat
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/make.bat
diff --git a/testing/web-platform/tests/tools/html5lib/doc/modules.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/modules.rst
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/doc/modules.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/modules.rst
diff --git a/testing/web-platform/tests/tools/html5lib/doc/movingparts.rst b/testing/web-platform/tests/tools/third_party/html5lib/doc/movingparts.rst
similarity index 56%
rename from testing/web-platform/tests/tools/html5lib/doc/movingparts.rst
rename to testing/web-platform/tests/tools/third_party/html5lib/doc/movingparts.rst
index 36539785a7ec..6ba367a27ae4 100644
--- a/testing/web-platform/tests/tools/html5lib/doc/movingparts.rst
+++ b/testing/web-platform/tests/tools/third_party/html5lib/doc/movingparts.rst
@@ -4,22 +4,25 @@ The moving parts
 html5lib consists of a number of components, which are responsible for
 handling its features.
 
+Parsing uses a *tree builder* to generate a *tree*, the in-memory representation of the document.
+Several tree representations are supported, as are translations to other formats via *tree adapters*.
+The tree may be translated to a token stream with a *tree walker*, from which :class:`~html5lib.serializer.HTMLSerializer` produces a stream of bytes.
+The token stream may also be transformed by use of *filters* to accomplish tasks like sanitization.
 
 Tree builders
 -------------
 
 The parser reads HTML by tokenizing the content and building a tree that
-the user can later access. There are three main types of trees that
-html5lib can build:
+the user can later access. html5lib can build three types of trees:
 
-* ``etree`` - this is the default; builds a tree based on ``xml.etree``,
+* ``etree`` - this is the default; builds a tree based on :mod:`xml.etree`,
   which can be found in the standard library. Whenever possible, the
   accelerated ``ElementTree`` implementation (i.e.
   ``xml.etree.cElementTree`` on Python 2.x) is used.
 
-* ``dom`` - builds a tree based on ``xml.dom.minidom``.
+* ``dom`` - builds a tree based on :mod:`xml.dom.minidom`.
 
-* ``lxml.etree`` - uses lxml's implementation of the ``ElementTree``
+* ``lxml`` - uses the :mod:`lxml.etree` implementation of the ``ElementTree``
   API.  The performance gains are relatively small compared to using the
   accelerated ``ElementTree`` module.
 
@@ -31,21 +34,15 @@ You can specify the builder by name when using the shorthand API:
   with open("mydocument.html", "rb") as f:
       lxml_etree_document = html5lib.parse(f, treebuilder="lxml")
 
-When instantiating a parser object, you have to pass a tree builder
-class in the ``tree`` keyword attribute:
+To get a builder class by name, use the :func:`~html5lib.treebuilders.getTreeBuilder` function.
+
+When instantiating a :class:`~html5lib.html5parser.HTMLParser` object, you must pass a tree builder class via the ``tree`` keyword attribute:
 
 .. code-block:: python
 
   import html5lib
-  parser = html5lib.HTMLParser(tree=SomeTreeBuilder)
-  document = parser.parse("<p>Hello World!")
-
-To get a builder class by name, use the ``getTreeBuilder`` function:
-
-.. code-block:: python
-
-  import html5lib
-  parser = html5lib.HTMLParser(tree=html5lib.getTreeBuilder("dom"))
+  TreeBuilder = html5lib.getTreeBuilder("dom")
+  parser = html5lib.HTMLParser(tree=TreeBuilder)
   minidom_document = parser.parse("<p>Hello World!")
 
 The implementation of builders can be found in `html5lib/treebuilders/
@@ -55,17 +52,13 @@ The implementation of builders can be found in `html5lib/treebuilders/
 Tree walkers
 ------------
 
-Once a tree is ready, you can work on it either manually, or using
-a tree walker, which provides a streaming view of the tree. html5lib
-provides walkers for all three supported types of trees (``etree``,
-``dom`` and ``lxml``).
+In addition to manipulating a tree directly, you can use a tree walker to generate a streaming view of it.
+html5lib provides walkers for ``etree``, ``dom``, and ``lxml`` trees, as well as ``genshi`` `markup streams <https://genshi.edgewall.org/wiki/Documentation/streams.html>`_.
 
 The implementation of walkers can be found in `html5lib/treewalkers/
 <https://github.com/html5lib/html5lib-python/tree/master/html5lib/treewalkers>`_.
 
-Walkers make consuming HTML easier. html5lib uses them to provide you
-with has a couple of handy tools.
-
+html5lib provides :class:`~html5lib.serializer.HTMLSerializer` for generating a stream of bytes from a token stream, and several filters which manipulate the stream.
 
 HTMLSerializer
 ~~~~~~~~~~~~~~
@@ -90,15 +83,14 @@ The serializer lets you write HTML back as a stream of bytes.
   '>'
   'Witam wszystkich'
 
-You can customize the serializer behaviour in a variety of ways, consult
-the :class:`~html5lib.serializer.htmlserializer.HTMLSerializer`
-documentation.
+You can customize the serializer behaviour in a variety of ways. Consult
+the :class:`~html5lib.serializer.HTMLSerializer` documentation.
 
 
 Filters
 ~~~~~~~
 
-You can alter the stream content with filters provided by html5lib:
+html5lib provides several filters:
 
 * :class:`alphabeticalattributes.Filter
   <html5lib.filters.alphabeticalattributes.Filter>` sorts attributes on
@@ -110,11 +102,11 @@ You can alter the stream content with filters provided by html5lib:
   the document
 
 * :class:`lint.Filter <html5lib.filters.lint.Filter>` raises
-  ``LintError`` exceptions on invalid tag and attribute names, invalid
+  :exc:`AssertionError` exceptions on invalid tag and attribute names, invalid
   PCDATA, etc.
 
 * :class:`optionaltags.Filter <html5lib.filters.optionaltags.Filter>`
-  removes tags from the stream which are not necessary to produce valid
+  removes tags from the token stream which are not necessary to produce valid
   HTML
 
 * :class:`sanitizer.Filter <html5lib.filters.sanitizer.Filter>` removes
@@ -125,9 +117,9 @@ You can alter the stream content with filters provided by html5lib:
 
 * :class:`whitespace.Filter <html5lib.filters.whitespace.Filter>`
   collapses all whitespace characters to single spaces unless they're in
-  ``<pre/>`` or ``textarea`` tags.
+  ``<pre/>`` or ``<textarea/>`` tags.
 
-To use a filter, simply wrap it around a stream:
+To use a filter, simply wrap it around a token stream:
 
 .. code-block:: python
 
@@ -136,15 +128,17 @@ To use a filter, simply wrap it around a stream:
   >>> dom = html5lib.parse("<p><script>alert('Boo!')", treebuilder="dom")
   >>> walker = html5lib.getTreeWalker("dom")
   >>> stream = walker(dom)
-  >>> sane_stream = sanitizer.Filter(stream) clean_stream = sanitizer.Filter(stream)
+  >>> clean_stream = sanitizer.Filter(stream)
 
 
 Tree adapters
 -------------
 
-Used to translate one type of tree to another. More documentation
-pending, sorry.
+Tree adapters can be used to translate between tree formats.
+Two adapters are provided by html5lib:
 
+* :func:`html5lib.treeadapters.genshi.to_genshi()` generates a `Genshi markup stream <https://genshi.edgewall.org/wiki/Documentation/streams.html>`_.
+* :func:`html5lib.treeadapters.sax.to_sax()` calls a SAX handler based on the tree.
 
 Encoding discovery
 ------------------
@@ -156,54 +150,16 @@ the following way:
 * The encoding may be explicitly specified by passing the name of the
   encoding as the encoding parameter to the
   :meth:`~html5lib.html5parser.HTMLParser.parse` method on
-  ``HTMLParser`` objects.
+  :class:`~html5lib.html5parser.HTMLParser` objects.
 
 * If no encoding is specified, the parser will attempt to detect the
   encoding from a ``<meta>``  element in the first 512 bytes of the
   document (this is only a partial implementation of the current HTML
-  5 specification).
+  specification).
 
-* If no encoding can be found and the chardet library is available, an
+* If no encoding can be found and the :mod:`chardet` library is available, an
   attempt will be made to sniff the encoding from the byte pattern.
 
 * If all else fails, the default encoding will be used. This is usually
   `Windows-1252 <http://en.wikipedia.org/wiki/Windows-1252>`_, which is
   a common fallback used by Web browsers.
-
-
-Tokenizers
-----------
-
-The part of the parser responsible for translating a raw input stream
-into meaningful tokens is the tokenizer. Currently html5lib provides
-two.
-
-To set up a tokenizer, simply pass it when instantiating
-a :class:`~html5lib.html5parser.HTMLParser`:
-
-.. code-block:: python
-
-  import html5lib
-  from html5lib import sanitizer
-
-  p = html5lib.HTMLParser(tokenizer=sanitizer.HTMLSanitizer)
-  p.parse("<p>Surprise!<script>alert('Boo!');</script>")
-
-HTMLTokenizer
-~~~~~~~~~~~~~
-
-This is the default tokenizer, the heart of html5lib. The implementation
-can be found in `html5lib/tokenizer.py
-<https://github.com/html5lib/html5lib-python/blob/master/html5lib/tokenizer.py>`_.
-
-HTMLSanitizer
-~~~~~~~~~~~~~
-
-This is a tokenizer that removes unsafe markup and CSS styles from the
-input. Elements that are known to be safe are passed through and the
-rest is converted to visible text. The default configuration of the
-sanitizer follows the `WHATWG Sanitization Rules
-<http://wiki.whatwg.org/wiki/Sanitization_rules>`_.
-
-The implementation can be found in `html5lib/sanitizer.py
-<https://github.com/html5lib/html5lib-python/blob/master/html5lib/sanitizer.py>`_.
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/flake8-run.sh b/testing/web-platform/tests/tools/third_party/html5lib/flake8-run.sh
new file mode 100755
index 000000000000..d926494699b9
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/flake8-run.sh
@@ -0,0 +1,9 @@
+#!/bin/bash -e
+
+if [[ ! -x $(which flake8) ]]; then
+  echo "fatal: flake8 not found on $PATH. Exiting."
+  exit 1
+fi
+
+flake8 `dirname $0`
+exit $?
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/__init__.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/__init__.py
new file mode 100644
index 000000000000..ba01065ef63a
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/__init__.py
@@ -0,0 +1,35 @@
+"""
+HTML parsing library based on the `WHATWG HTML specification
+<https://whatwg.org/html>`_. The parser is designed to be compatible with
+existing HTML found in the wild and implements well-defined error recovery that
+is largely compatible with modern desktop web browsers.
+
+Example usage::
+
+    import html5lib
+    with open("my_document.html", "rb") as f:
+        tree = html5lib.parse(f)
+
+For convenience, this module re-exports the following names:
+
+* :func:`~.html5parser.parse`
+* :func:`~.html5parser.parseFragment`
+* :class:`~.html5parser.HTMLParser`
+* :func:`~.treebuilders.getTreeBuilder`
+* :func:`~.treewalkers.getTreeWalker`
+* :func:`~.serializer.serialize`
+"""
+
+from __future__ import absolute_import, division, unicode_literals
+
+from .html5parser import HTMLParser, parse, parseFragment
+from .treebuilders import getTreeBuilder
+from .treewalkers import getTreeWalker
+from .serializer import serialize
+
+__all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder",
+           "getTreeWalker", "serialize"]
+
+# this has to be at the top level, see how setup.py parses this
+#: Distribution version number.
+__version__ = "1.0.1"
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/ihatexml.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_ihatexml.py
similarity index 97%
rename from testing/web-platform/tests/tools/html5lib/html5lib/ihatexml.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/_ihatexml.py
index 0fc79308ef4c..4c77717bbc02 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/ihatexml.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_ihatexml.py
@@ -175,18 +175,18 @@ def escapeRegexp(string):
     return string
 
 # output from the above
-nonXmlNameBMPRegexp = re.compile('[\x00-,/:-@\\[-\\^`\\{-\xb6\xb8-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u02cf\u02d2-\u02ff\u0346-\u035f\u0362-\u0385\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482\u0487-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u0590\u05a2\u05ba\u05be\u05c0\u05c3\u05c5-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u063f\u0653-\u065f\u066a-\u066f\u06b8-\u06b9\u06bf\u06cf\u06d4\u06e9\u06ee-\u06ef\u06fa-\u0900\u0904\u093a-\u093b\u094e-\u0950\u0955-\u0957\u0964-\u0965\u0970-\u0980\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09bb\u09bd\u09c5-\u09c6\u09c9-\u09ca\u09ce-\u09d6\u09d8-\u09db\u09de\u09e4-\u09e5\u09f2-\u0a01\u0a03-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a3b\u0a3d\u0a43-\u0a46\u0a49-\u0a4a\u0a4e-\u0a58\u0a5d\u0a5f-\u0a65\u0a75-\u0a80\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abb\u0ac6\u0aca\u0ace-\u0adf\u0ae1-\u0ae5\u0af0-\u0b00\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3b\u0b44-\u0b46\u0b49-\u0b4a\u0b4e-\u0b55\u0b58-\u0b5b\u0b5e\u0b62-\u0b65\u0b70-\u0b81\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0bbd\u0bc3-\u0bc5\u0bc9\u0bce-\u0bd6\u0bd8-\u0be6\u0bf0-\u0c00\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c3d\u0c45\u0c49\u0c4e-\u0c54\u0c57-\u0c5f\u0c62-\u0c65\u0c70-\u0c81\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cbd\u0cc5\u0cc9\u0cce-\u0cd4\u0cd7-\u0cdd\u0cdf\u0ce2-\u0ce5\u0cf0-\u0d01\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d3d\u0d44-\u0d45\u0d49\u0d4e-\u0d56\u0d58-\u0d5f\u0d62-\u0d65\u0d70-\u0e00\u0e2f\u0e3b-\u0e3f\u0e4f\u0e5a-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eba\u0ebe-\u0ebf\u0ec5\u0ec7\u0ece-\u0ecf\u0eda-\u0f17\u0f1a-\u0f1f\u0f2a-\u0f34\u0f36\u0f38\u0f3a-\u0f3d\u0f48\u0f6a-\u0f70\u0f85\u0f8c-\u0f8f\u0f96\u0f98\u0fae-\u0fb0\u0fb8\u0fba-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u20cf\u20dd-\u20e0\u20e2-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3004\u3006\u3008-\u3020\u3030\u3036-\u3040\u3095-\u3098\u309b-\u309c\u309f-\u30a0\u30fb\u30ff-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]')
+nonXmlNameBMPRegexp = re.compile('[\x00-,/:-@\\[-\\^`\\{-\xb6\xb8-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u02cf\u02d2-\u02ff\u0346-\u035f\u0362-\u0385\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482\u0487-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u0590\u05a2\u05ba\u05be\u05c0\u05c3\u05c5-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u063f\u0653-\u065f\u066a-\u066f\u06b8-\u06b9\u06bf\u06cf\u06d4\u06e9\u06ee-\u06ef\u06fa-\u0900\u0904\u093a-\u093b\u094e-\u0950\u0955-\u0957\u0964-\u0965\u0970-\u0980\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09bb\u09bd\u09c5-\u09c6\u09c9-\u09ca\u09ce-\u09d6\u09d8-\u09db\u09de\u09e4-\u09e5\u09f2-\u0a01\u0a03-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a3b\u0a3d\u0a43-\u0a46\u0a49-\u0a4a\u0a4e-\u0a58\u0a5d\u0a5f-\u0a65\u0a75-\u0a80\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abb\u0ac6\u0aca\u0ace-\u0adf\u0ae1-\u0ae5\u0af0-\u0b00\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3b\u0b44-\u0b46\u0b49-\u0b4a\u0b4e-\u0b55\u0b58-\u0b5b\u0b5e\u0b62-\u0b65\u0b70-\u0b81\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0bbd\u0bc3-\u0bc5\u0bc9\u0bce-\u0bd6\u0bd8-\u0be6\u0bf0-\u0c00\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c3d\u0c45\u0c49\u0c4e-\u0c54\u0c57-\u0c5f\u0c62-\u0c65\u0c70-\u0c81\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cbd\u0cc5\u0cc9\u0cce-\u0cd4\u0cd7-\u0cdd\u0cdf\u0ce2-\u0ce5\u0cf0-\u0d01\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d3d\u0d44-\u0d45\u0d49\u0d4e-\u0d56\u0d58-\u0d5f\u0d62-\u0d65\u0d70-\u0e00\u0e2f\u0e3b-\u0e3f\u0e4f\u0e5a-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eba\u0ebe-\u0ebf\u0ec5\u0ec7\u0ece-\u0ecf\u0eda-\u0f17\u0f1a-\u0f1f\u0f2a-\u0f34\u0f36\u0f38\u0f3a-\u0f3d\u0f48\u0f6a-\u0f70\u0f85\u0f8c-\u0f8f\u0f96\u0f98\u0fae-\u0fb0\u0fb8\u0fba-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u20cf\u20dd-\u20e0\u20e2-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3004\u3006\u3008-\u3020\u3030\u3036-\u3040\u3095-\u3098\u309b-\u309c\u309f-\u30a0\u30fb\u30ff-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]')  # noqa
 
-nonXmlNameFirstBMPRegexp = re.compile('[\x00-@\\[-\\^`\\{-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u0385\u0387\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u0640\u064b-\u0670\u06b8-\u06b9\u06bf\u06cf\u06d4\u06d6-\u06e4\u06e7-\u0904\u093a-\u093c\u093e-\u0957\u0962-\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09db\u09de\u09e2-\u09ef\u09f2-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a58\u0a5d\u0a5f-\u0a71\u0a75-\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abc\u0abe-\u0adf\u0ae1-\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3c\u0b3e-\u0b5b\u0b5e\u0b62-\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c5f\u0c62-\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cdd\u0cdf\u0ce2-\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d5f\u0d62-\u0e00\u0e2f\u0e31\u0e34-\u0e3f\u0e46-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eb1\u0eb4-\u0ebc\u0ebe-\u0ebf\u0ec5-\u0f3f\u0f48\u0f6a-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3006\u3008-\u3020\u302a-\u3040\u3095-\u30a0\u30fb-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]')
+nonXmlNameFirstBMPRegexp = re.compile('[\x00-@\\[-\\^`\\{-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u0385\u0387\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u0640\u064b-\u0670\u06b8-\u06b9\u06bf\u06cf\u06d4\u06d6-\u06e4\u06e7-\u0904\u093a-\u093c\u093e-\u0957\u0962-\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09db\u09de\u09e2-\u09ef\u09f2-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a58\u0a5d\u0a5f-\u0a71\u0a75-\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abc\u0abe-\u0adf\u0ae1-\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3c\u0b3e-\u0b5b\u0b5e\u0b62-\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c5f\u0c62-\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cdd\u0cdf\u0ce2-\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d5f\u0d62-\u0e00\u0e2f\u0e31\u0e34-\u0e3f\u0e46-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eb1\u0eb4-\u0ebc\u0ebe-\u0ebf\u0ec5-\u0f3f\u0f48\u0f6a-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3006\u3008-\u3020\u302a-\u3040\u3095-\u30a0\u30fb-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]')  # noqa
 
 # Simpler things
-nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\-\'()+,./:=?;!*#@$_%]")
+nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\\-'()+,./:=?;!*#@$_%]")
 
 
 class InfosetFilter(object):
     replacementRegexp = re.compile(r"U[\dA-F]{5,5}")
 
-    def __init__(self, replaceChars=None,
+    def __init__(self,
                  dropXmlnsLocalName=False,
                  dropXmlnsAttrNs=False,
                  preventDoubleDashComments=False,
@@ -217,7 +217,7 @@ class InfosetFilter(object):
         else:
             return self.toXmlName(name)
 
-    def coerceElement(self, name, namespace=None):
+    def coerceElement(self, name):
         return self.toXmlName(name)
 
     def coerceComment(self, data):
@@ -225,11 +225,14 @@ class InfosetFilter(object):
             while "--" in data:
                 warnings.warn("Comments cannot contain adjacent dashes", DataLossWarning)
                 data = data.replace("--", "- -")
+            if data.endswith("-"):
+                warnings.warn("Comments cannot end in a dash", DataLossWarning)
+                data += " "
         return data
 
     def coerceCharacters(self, data):
         if self.replaceFormFeedCharacters:
-            for i in range(data.count("\x0C")):
+            for _ in range(data.count("\x0C")):
                 warnings.warn("Text cannot contain U+000C", DataLossWarning)
             data = data.replace("\x0C", " ")
         # Other non-xml characters
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/inputstream.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_inputstream.py
similarity index 80%
rename from testing/web-platform/tests/tools/html5lib/html5lib/inputstream.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/_inputstream.py
index 9e03b9313d7f..177f0ab9ee34 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/inputstream.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_inputstream.py
@@ -1,13 +1,16 @@
 from __future__ import absolute_import, division, unicode_literals
-from six import text_type
-from six.moves import http_client
+
+from six import text_type, binary_type
+from six.moves import http_client, urllib
 
 import codecs
 import re
 
+import webencodings
+
 from .constants import EOF, spaceCharacters, asciiLetters, asciiUppercase
-from .constants import encodings, ReparseException
-from . import utils
+from .constants import _ReparseException
+from . import _utils
 
 from io import StringIO
 
@@ -16,19 +19,26 @@ try:
 except ImportError:
     BytesIO = StringIO
 
-try:
-    from io import BufferedIOBase
-except ImportError:
-    class BufferedIOBase(object):
-        pass
-
 # Non-unicode versions of constants for use in the pre-parser
 spaceCharactersBytes = frozenset([item.encode("ascii") for item in spaceCharacters])
 asciiLettersBytes = frozenset([item.encode("ascii") for item in asciiLetters])
 asciiUppercaseBytes = frozenset([item.encode("ascii") for item in asciiUppercase])
 spacesAngleBrackets = spaceCharactersBytes | frozenset([b">", b"<"])
 
-invalid_unicode_re = re.compile("[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uD800-\uDFFF\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]")
+
+invalid_unicode_no_surrogate = "[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]"  # noqa
+
+if _utils.supports_lone_surrogates:
+    # Use one extra step of indirection and create surrogates with
+    # eval. Not using this indirection would introduce an illegal
+    # unicode literal on platforms not supporting such lone
+    # surrogates.
+    assert invalid_unicode_no_surrogate[-1] == "]" and invalid_unicode_no_surrogate.count("]") == 1
+    invalid_unicode_re = re.compile(invalid_unicode_no_surrogate[:-1] +
+                                    eval('"\\uD800-\\uDFFF"') +  # pylint:disable=eval-used
+                                    "]")
+else:
+    invalid_unicode_re = re.compile(invalid_unicode_no_surrogate)
 
 non_bmp_invalid_codepoints = set([0x1FFFE, 0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE,
                                   0x3FFFF, 0x4FFFE, 0x4FFFF, 0x5FFFE, 0x5FFFF,
@@ -38,7 +48,7 @@ non_bmp_invalid_codepoints = set([0x1FFFE, 0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE,
                                   0xDFFFF, 0xEFFFE, 0xEFFFF, 0xFFFFE, 0xFFFFF,
                                   0x10FFFE, 0x10FFFF])
 
-ascii_punctuation_re = re.compile("[\u0009-\u000D\u0020-\u002F\u003A-\u0040\u005B-\u0060\u007B-\u007E]")
+ascii_punctuation_re = re.compile("[\u0009-\u000D\u0020-\u002F\u003A-\u0040\u005C\u005B-\u0060\u007B-\u007E]")
 
 # Cache for charsUntil()
 charsUntilRegEx = {}
@@ -118,10 +128,13 @@ class BufferedStream(object):
         return b"".join(rv)
 
 
-def HTMLInputStream(source, encoding=None, parseMeta=True, chardet=True):
-    if isinstance(source, http_client.HTTPResponse):
-        # Work around Python bug #20007: read(0) closes the connection.
-        # http://bugs.python.org/issue20007
+def HTMLInputStream(source, **kwargs):
+    # Work around Python bug #20007: read(0) closes the connection.
+    # http://bugs.python.org/issue20007
+    if (isinstance(source, http_client.HTTPResponse) or
+        # Also check for addinfourl wrapping HTTPResponse
+        (isinstance(source, urllib.response.addbase) and
+         isinstance(source.fp, http_client.HTTPResponse))):
         isUnicode = False
     elif hasattr(source, "read"):
         isUnicode = isinstance(source.read(0), text_type)
@@ -129,12 +142,13 @@ def HTMLInputStream(source, encoding=None, parseMeta=True, chardet=True):
         isUnicode = isinstance(source, text_type)
 
     if isUnicode:
-        if encoding is not None:
-            raise TypeError("Cannot explicitly set an encoding with a unicode string")
+        encodings = [x for x in kwargs if x.endswith("_encoding")]
+        if encodings:
+            raise TypeError("Cannot set an encoding with a unicode input, set %r" % encodings)
 
-        return HTMLUnicodeInputStream(source)
+        return HTMLUnicodeInputStream(source, **kwargs)
     else:
-        return HTMLBinaryInputStream(source, encoding, parseMeta, chardet)
+        return HTMLBinaryInputStream(source, **kwargs)
 
 
 class HTMLUnicodeInputStream(object):
@@ -160,22 +174,21 @@ class HTMLUnicodeInputStream(object):
         regardless of any BOM or later declaration (such as in a meta
         element)
 
-        parseMeta - Look for a <meta> element containing encoding information
-
         """
 
-        # Craziness
-        if len("\U0010FFFF") == 1:
+        if not _utils.supports_lone_surrogates:
+            # Such platforms will have already checked for such
+            # surrogate errors, so no need to do this checking.
+            self.reportCharacterErrors = None
+        elif len("\U0010FFFF") == 1:
             self.reportCharacterErrors = self.characterErrorsUCS4
-            self.replaceCharactersRegexp = re.compile("[\uD800-\uDFFF]")
         else:
             self.reportCharacterErrors = self.characterErrorsUCS2
-            self.replaceCharactersRegexp = re.compile("([\uD800-\uDBFF](?![\uDC00-\uDFFF])|(?<![\uD800-\uDBFF])[\uDC00-\uDFFF])")
 
         # List of where new lines occur
         self.newLines = [0]
 
-        self.charEncoding = ("utf-8", "certain")
+        self.charEncoding = (lookupEncoding("utf-8"), "certain")
         self.dataStream = self.openStream(source)
 
         self.reset()
@@ -265,12 +278,10 @@ class HTMLUnicodeInputStream(object):
                 self._bufferedCharacter = data[-1]
                 data = data[:-1]
 
-        self.reportCharacterErrors(data)
+        if self.reportCharacterErrors:
+            self.reportCharacterErrors(data)
 
         # Replace invalid characters
-        # Note U+0000 is dealt with in the tokenizer
-        data = self.replaceCharactersRegexp.sub("\ufffd", data)
-
         data = data.replace("\r\n", "\n")
         data = data.replace("\r", "\n")
 
@@ -280,7 +291,7 @@ class HTMLUnicodeInputStream(object):
         return True
 
     def characterErrorsUCS4(self, data):
-        for i in range(len(invalid_unicode_re.findall(data))):
+        for _ in range(len(invalid_unicode_re.findall(data))):
             self.errors.append("invalid-codepoint")
 
     def characterErrorsUCS2(self, data):
@@ -293,9 +304,9 @@ class HTMLUnicodeInputStream(object):
             codepoint = ord(match.group())
             pos = match.start()
             # Pretty sure there should be endianness issues here
-            if utils.isSurrogatePair(data[pos:pos + 2]):
+            if _utils.isSurrogatePair(data[pos:pos + 2]):
                 # We have a surrogate pair!
-                char_val = utils.surrogatePairToCodepoint(data[pos:pos + 2])
+                char_val = _utils.surrogatePairToCodepoint(data[pos:pos + 2])
                 if char_val in non_bmp_invalid_codepoints:
                     self.errors.append("invalid-codepoint")
                 skip = True
@@ -378,7 +389,9 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
 
     """
 
-    def __init__(self, source, encoding=None, parseMeta=True, chardet=True):
+    def __init__(self, source, override_encoding=None, transport_encoding=None,
+                 same_origin_parent_encoding=None, likely_encoding=None,
+                 default_encoding="windows-1252", useChardet=True):
         """Initialises the HTMLInputStream.
 
         HTMLInputStream(source, [encoding]) -> Normalized stream from source
@@ -391,8 +404,6 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
         regardless of any BOM or later declaration (such as in a meta
         element)
 
-        parseMeta - Look for a <meta> element containing encoding information
-
         """
         # Raw Stream - for unicode objects this will encode to utf-8 and set
         #              self.charEncoding as appropriate
@@ -400,27 +411,28 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
 
         HTMLUnicodeInputStream.__init__(self, self.rawStream)
 
-        self.charEncoding = (codecName(encoding), "certain")
-
         # Encoding Information
         # Number of bytes to use when looking for a meta element with
         # encoding information
-        self.numBytesMeta = 512
+        self.numBytesMeta = 1024
         # Number of bytes to use when using detecting encoding using chardet
         self.numBytesChardet = 100
-        # Encoding to use if no other information can be found
-        self.defaultEncoding = "windows-1252"
+        # Things from args
+        self.override_encoding = override_encoding
+        self.transport_encoding = transport_encoding
+        self.same_origin_parent_encoding = same_origin_parent_encoding
+        self.likely_encoding = likely_encoding
+        self.default_encoding = default_encoding
 
-        # Detect encoding iff no explicit "transport level" encoding is supplied
-        if (self.charEncoding[0] is None):
-            self.charEncoding = self.detectEncoding(parseMeta, chardet)
+        # Determine encoding
+        self.charEncoding = self.determineEncoding(useChardet)
+        assert self.charEncoding[0] is not None
 
         # Call superclass
         self.reset()
 
     def reset(self):
-        self.dataStream = codecs.getreader(self.charEncoding[0])(self.rawStream,
-                                                                 'replace')
+        self.dataStream = self.charEncoding[0].codec_info.streamreader(self.rawStream, 'replace')
         HTMLUnicodeInputStream.reset(self)
 
     def openStream(self, source):
@@ -437,29 +449,50 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
 
         try:
             stream.seek(stream.tell())
-        except:
+        except:  # pylint:disable=bare-except
             stream = BufferedStream(stream)
 
         return stream
 
-    def detectEncoding(self, parseMeta=True, chardet=True):
-        # First look for a BOM
+    def determineEncoding(self, chardet=True):
+        # BOMs take precedence over everything
         # This will also read past the BOM if present
-        encoding = self.detectBOM()
-        confidence = "certain"
-        # If there is no BOM need to look for meta elements with encoding
-        # information
-        if encoding is None and parseMeta:
-            encoding = self.detectEncodingMeta()
-            confidence = "tentative"
-        # Guess with chardet, if avaliable
-        if encoding is None and chardet:
-            confidence = "tentative"
+        charEncoding = self.detectBOM(), "certain"
+        if charEncoding[0] is not None:
+            return charEncoding
+
+        # If we've been overriden, we've been overriden
+        charEncoding = lookupEncoding(self.override_encoding), "certain"
+        if charEncoding[0] is not None:
+            return charEncoding
+
+        # Now check the transport layer
+        charEncoding = lookupEncoding(self.transport_encoding), "certain"
+        if charEncoding[0] is not None:
+            return charEncoding
+
+        # Look for meta elements with encoding information
+        charEncoding = self.detectEncodingMeta(), "tentative"
+        if charEncoding[0] is not None:
+            return charEncoding
+
+        # Parent document encoding
+        charEncoding = lookupEncoding(self.same_origin_parent_encoding), "tentative"
+        if charEncoding[0] is not None and not charEncoding[0].name.startswith("utf-16"):
+            return charEncoding
+
+        # "likely" encoding
+        charEncoding = lookupEncoding(self.likely_encoding), "tentative"
+        if charEncoding[0] is not None:
+            return charEncoding
+
+        # Guess with chardet, if available
+        if chardet:
             try:
-                try:
-                    from charade.universaldetector import UniversalDetector
-                except ImportError:
-                    from chardet.universaldetector import UniversalDetector
+                from chardet.universaldetector import UniversalDetector
+            except ImportError:
+                pass
+            else:
                 buffers = []
                 detector = UniversalDetector()
                 while not detector.done:
@@ -470,37 +503,34 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
                     buffers.append(buffer)
                     detector.feed(buffer)
                 detector.close()
-                encoding = detector.result['encoding']
+                encoding = lookupEncoding(detector.result['encoding'])
                 self.rawStream.seek(0)
-            except ImportError:
-                pass
-        # If all else fails use the default encoding
-        if encoding is None:
-            confidence = "tentative"
-            encoding = self.defaultEncoding
+                if encoding is not None:
+                    return encoding, "tentative"
 
-        # Substitute for equivalent encodings:
-        encodingSub = {"iso-8859-1": "windows-1252"}
+        # Try the default encoding
+        charEncoding = lookupEncoding(self.default_encoding), "tentative"
+        if charEncoding[0] is not None:
+            return charEncoding
 
-        if encoding.lower() in encodingSub:
-            encoding = encodingSub[encoding.lower()]
-
-        return encoding, confidence
+        # Fallback to html5lib's default if even that hasn't worked
+        return lookupEncoding("windows-1252"), "tentative"
 
     def changeEncoding(self, newEncoding):
         assert self.charEncoding[1] != "certain"
-        newEncoding = codecName(newEncoding)
-        if newEncoding in ("utf-16", "utf-16-be", "utf-16-le"):
-            newEncoding = "utf-8"
+        newEncoding = lookupEncoding(newEncoding)
         if newEncoding is None:
             return
+        if newEncoding.name in ("utf-16be", "utf-16le"):
+            newEncoding = lookupEncoding("utf-8")
+            assert newEncoding is not None
         elif newEncoding == self.charEncoding[0]:
             self.charEncoding = (self.charEncoding[0], "certain")
         else:
             self.rawStream.seek(0)
-            self.reset()
             self.charEncoding = (newEncoding, "certain")
-            raise ReparseException("Encoding changed from %s to %s" % (self.charEncoding[0], newEncoding))
+            self.reset()
+            raise _ReparseException("Encoding changed from %s to %s" % (self.charEncoding[0], newEncoding))
 
     def detectBOM(self):
         """Attempts to detect at BOM at the start of the stream. If
@@ -508,8 +538,8 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
         encoding otherwise return None"""
         bomDict = {
             codecs.BOM_UTF8: 'utf-8',
-            codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
-            codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
+            codecs.BOM_UTF16_LE: 'utf-16le', codecs.BOM_UTF16_BE: 'utf-16be',
+            codecs.BOM_UTF32_LE: 'utf-32le', codecs.BOM_UTF32_BE: 'utf-32be'
         }
 
         # Go to beginning of file and read in 4 bytes
@@ -529,9 +559,12 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
 
         # Set the read position past the BOM if one was found, otherwise
         # set it to the start of the stream
-        self.rawStream.seek(encoding and seek or 0)
-
-        return encoding
+        if encoding:
+            self.rawStream.seek(seek)
+            return lookupEncoding(encoding)
+        else:
+            self.rawStream.seek(0)
+            return None
 
     def detectEncodingMeta(self):
         """Report the encoding declared by the meta element
@@ -542,8 +575,8 @@ class HTMLBinaryInputStream(HTMLUnicodeInputStream):
         self.rawStream.seek(0)
         encoding = parser.getEncoding()
 
-        if encoding in ("utf-16", "utf-16-be", "utf-16-le"):
-            encoding = "utf-8"
+        if encoding is not None and encoding.name in ("utf-16be", "utf-16le"):
+            encoding = lookupEncoding("utf-8")
 
         return encoding
 
@@ -557,6 +590,7 @@ class EncodingBytes(bytes):
         return bytes.__new__(self, value.lower())
 
     def __init__(self, value):
+        # pylint:disable=unused-argument
         self._position = -1
 
     def __iter__(self):
@@ -667,7 +701,7 @@ class EncodingParser(object):
             (b"<!", self.handleOther),
             (b"<?", self.handleOther),
             (b"<", self.handlePossibleStartTag))
-        for byte in self.data:
+        for _ in self.data:
             keepParsing = True
             for key, method in methodDispatch:
                 if self.data.matchBytes(key):
@@ -706,7 +740,7 @@ class EncodingParser(object):
                         return False
                 elif attr[0] == b"charset":
                     tentativeEncoding = attr[1]
-                    codec = codecName(tentativeEncoding)
+                    codec = lookupEncoding(tentativeEncoding)
                     if codec is not None:
                         self.encoding = codec
                         return False
@@ -714,7 +748,7 @@ class EncodingParser(object):
                     contentParser = ContentAttrParser(EncodingBytes(attr[1]))
                     tentativeEncoding = contentParser.parse()
                     if tentativeEncoding is not None:
-                        codec = codecName(tentativeEncoding)
+                        codec = lookupEncoding(tentativeEncoding)
                         if codec is not None:
                             if hasPragma:
                                 self.encoding = codec
@@ -871,16 +905,19 @@ class ContentAttrParser(object):
             return None
 
 
-def codecName(encoding):
+def lookupEncoding(encoding):
     """Return the python codec name corresponding to an encoding or None if the
     string doesn't correspond to a valid encoding."""
-    if isinstance(encoding, bytes):
+    if isinstance(encoding, binary_type):
         try:
             encoding = encoding.decode("ascii")
         except UnicodeDecodeError:
             return None
-    if encoding:
-        canonicalName = ascii_punctuation_re.sub("", encoding).lower()
-        return encodings.get(canonicalName, None)
+
+    if encoding is not None:
+        try:
+            return webencodings.lookup(encoding)
+        except AttributeError:
+            return None
     else:
         return None
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tokenizer.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_tokenizer.py
similarity index 98%
rename from testing/web-platform/tests/tools/html5lib/html5lib/tokenizer.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/_tokenizer.py
index 797745787a49..6078f66aa0d3 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tokenizer.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_tokenizer.py
@@ -1,9 +1,6 @@
 from __future__ import absolute_import, division, unicode_literals
 
-try:
-    chr = unichr # flake8: noqa
-except NameError:
-    pass
+from six import unichr as chr
 
 from collections import deque
 
@@ -14,9 +11,9 @@ from .constants import digits, hexDigits, EOF
 from .constants import tokenTypes, tagTokenTypes
 from .constants import replacementCharacters
 
-from .inputstream import HTMLInputStream
+from ._inputstream import HTMLInputStream
 
-from .trie import Trie
+from ._trie import Trie
 
 entitiesTrie = Trie(entities)
 
@@ -34,16 +31,11 @@ class HTMLTokenizer(object):
       Points to HTMLInputStream object.
     """
 
-    def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
-                 lowercaseElementName=True, lowercaseAttrName=True, parser=None):
+    def __init__(self, stream, parser=None, **kwargs):
 
-        self.stream = HTMLInputStream(stream, encoding, parseMeta, useChardet)
+        self.stream = HTMLInputStream(stream, **kwargs)
         self.parser = parser
 
-        # Perform case conversions?
-        self.lowercaseElementName = lowercaseElementName
-        self.lowercaseAttrName = lowercaseAttrName
-
         # Setup the initial tokenizer state
         self.escapeFlag = False
         self.lastFourChars = []
@@ -147,8 +139,8 @@ class HTMLTokenizer(object):
         output = "&"
 
         charStack = [self.stream.char()]
-        if (charStack[0] in spaceCharacters or charStack[0] in (EOF, "<", "&")
-                or (allowedChar is not None and allowedChar == charStack[0])):
+        if (charStack[0] in spaceCharacters or charStack[0] in (EOF, "<", "&") or
+                (allowedChar is not None and allowedChar == charStack[0])):
             self.stream.unget(charStack[0])
 
         elif charStack[0] == "#":
@@ -235,8 +227,7 @@ class HTMLTokenizer(object):
         token = self.currentToken
         # Add token to the queue to be yielded
         if (token["type"] in tagTokenTypes):
-            if self.lowercaseElementName:
-                token["name"] = token["name"].translate(asciiUpper2Lower)
+            token["name"] = token["name"].translate(asciiUpper2Lower)
             if token["type"] == tokenTypes["EndTag"]:
                 if token["data"]:
                     self.tokenQueue.append({"type": tokenTypes["ParseError"],
@@ -921,10 +912,9 @@ class HTMLTokenizer(object):
             # Attributes are not dropped at this stage. That happens when the
             # start tag token is emitted so values can still be safely appended
             # to attributes, but we do want to report the parse error in time.
-            if self.lowercaseAttrName:
-                self.currentToken["data"][-1][0] = (
-                    self.currentToken["data"][-1][0].translate(asciiUpper2Lower))
-            for name, value in self.currentToken["data"][:-1]:
+            self.currentToken["data"][-1][0] = (
+                self.currentToken["data"][-1][0].translate(asciiUpper2Lower))
+            for name, _ in self.currentToken["data"][:-1]:
                 if self.currentToken["data"][-1][0] == name:
                     self.tokenQueue.append({"type": tokenTypes["ParseError"], "data":
                                             "duplicate-attribute"})
@@ -1716,11 +1706,11 @@ class HTMLTokenizer(object):
                 else:
                     data.append(char)
 
-        data = "".join(data)
+        data = "".join(data)  # pylint:disable=redefined-variable-type
         # Deal with null here rather than in the parser
         nullCount = data.count("\u0000")
         if nullCount > 0:
-            for i in range(nullCount):
+            for _ in range(nullCount):
                 self.tokenQueue.append({"type": tokenTypes["ParseError"],
                                         "data": "invalid-codepoint"})
             data = data.replace("\u0000", "\uFFFD")
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/trie/__init__.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/__init__.py
similarity index 73%
rename from testing/web-platform/tests/tools/html5lib/html5lib/trie/__init__.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/__init__.py
index a8cca8a9acf8..a5ba4bf123aa 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/trie/__init__.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/__init__.py
@@ -4,9 +4,11 @@ from .py import Trie as PyTrie
 
 Trie = PyTrie
 
+# pylint:disable=wrong-import-position
 try:
     from .datrie import Trie as DATrie
 except ImportError:
     pass
 else:
     Trie = DATrie
+# pylint:enable=wrong-import-position
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/trie/_base.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/_base.py
similarity index 85%
rename from testing/web-platform/tests/tools/html5lib/html5lib/trie/_base.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/_base.py
index 724486b16eb7..a1158bbbfa5b 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/trie/_base.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/_base.py
@@ -7,13 +7,13 @@ class Trie(Mapping):
     """Abstract base class for tries"""
 
     def keys(self, prefix=None):
-        keys = super().keys()
+        # pylint:disable=arguments-differ
+        keys = super(Trie, self).keys()
 
         if prefix is None:
             return set(keys)
 
-        # Python 2.6: no set comprehensions
-        return set([x for x in keys if x.startswith(prefix)])
+        return {x for x in keys if x.startswith(prefix)}
 
     def has_keys_with_prefix(self, prefix):
         for key in self.keys():
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/trie/datrie.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/datrie.py
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/html5lib/trie/datrie.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/datrie.py
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/trie/py.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/py.py
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/html5lib/trie/py.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/_trie/py.py
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/utils.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_utils.py
similarity index 55%
rename from testing/web-platform/tests/tools/html5lib/html5lib/utils.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/_utils.py
index 2f41f4dfa608..91252f2c0a8f 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/utils.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/_utils.py
@@ -2,6 +2,8 @@ from __future__ import absolute_import, division, unicode_literals
 
 from types import ModuleType
 
+from six import text_type
+
 try:
     import xml.etree.cElementTree as default_etree
 except ImportError:
@@ -9,7 +11,26 @@ except ImportError:
 
 
 __all__ = ["default_etree", "MethodDispatcher", "isSurrogatePair",
-           "surrogatePairToCodepoint", "moduleFactoryFactory"]
+           "surrogatePairToCodepoint", "moduleFactoryFactory",
+           "supports_lone_surrogates"]
+
+
+# Platforms not supporting lone surrogates (\uD800-\uDFFF) should be
+# caught by the below test. In general this would be any platform
+# using UTF-16 as its encoding of unicode strings, such as
+# Jython. This is because UTF-16 itself is based on the use of such
+# surrogates, and there is no mechanism to further escape such
+# escapes.
+try:
+    _x = eval('"\\uD800"')  # pylint:disable=eval-used
+    if not isinstance(_x, text_type):
+        # We need this with u"" because of http://bugs.jython.org/issue2039
+        _x = eval('u"\\uD800"')  # pylint:disable=eval-used
+        assert isinstance(_x, text_type)
+except:  # pylint:disable=bare-except
+    supports_lone_surrogates = False
+else:
+    supports_lone_surrogates = True
 
 
 class MethodDispatcher(dict):
@@ -31,19 +52,20 @@ class MethodDispatcher(dict):
         # anything here.
         _dictEntries = []
         for name, value in items:
-            if type(name) in (list, tuple, frozenset, set):
+            if isinstance(name, (list, tuple, frozenset, set)):
                 for item in name:
                     _dictEntries.append((item, value))
             else:
                 _dictEntries.append((name, value))
         dict.__init__(self, _dictEntries)
+        assert len(self) == len(_dictEntries)
         self.default = None
 
     def __getitem__(self, key):
         return dict.get(self, key, self.default)
 
 
-# Some utility functions to dal with weirdness around UCS2 vs UCS4
+# Some utility functions to deal with weirdness around UCS2 vs UCS4
 # python builds
 
 def isSurrogatePair(data):
@@ -70,13 +92,33 @@ def moduleFactoryFactory(factory):
         else:
             name = b"_%s_factory" % baseModule.__name__
 
-        if name in moduleCache:
-            return moduleCache[name]
-        else:
+        kwargs_tuple = tuple(kwargs.items())
+
+        try:
+            return moduleCache[name][args][kwargs_tuple]
+        except KeyError:
             mod = ModuleType(name)
             objs = factory(baseModule, *args, **kwargs)
             mod.__dict__.update(objs)
-            moduleCache[name] = mod
+            if "name" not in moduleCache:
+                moduleCache[name] = {}
+            if "args" not in moduleCache[name]:
+                moduleCache[name][args] = {}
+            if "kwargs" not in moduleCache[name][args]:
+                moduleCache[name][args][kwargs_tuple] = {}
+            moduleCache[name][args][kwargs_tuple] = mod
             return mod
 
     return moduleFactory
+
+
+def memoize(func):
+    cache = {}
+
+    def wrapped(*args, **kwargs):
+        key = (tuple(args), tuple(kwargs.items()))
+        if key not in cache:
+            cache[key] = func(*args, **kwargs)
+        return cache[key]
+
+    return wrapped
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/constants.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/constants.py
similarity index 81%
rename from testing/web-platform/tests/tools/html5lib/html5lib/constants.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/constants.py
index e7089846d59f..1ff804190cd8 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/constants.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/constants.py
@@ -1,292 +1,296 @@
 from __future__ import absolute_import, division, unicode_literals
 
 import string
-import gettext
-_ = gettext.gettext
 
 EOF = None
 
 E = {
     "null-character":
-        _("Null character in input stream, replaced with U+FFFD."),
+        "Null character in input stream, replaced with U+FFFD.",
     "invalid-codepoint":
-        _("Invalid codepoint in stream."),
+        "Invalid codepoint in stream.",
     "incorrectly-placed-solidus":
-        _("Solidus (/) incorrectly placed in tag."),
+        "Solidus (/) incorrectly placed in tag.",
     "incorrect-cr-newline-entity":
-        _("Incorrect CR newline entity, replaced with LF."),
+        "Incorrect CR newline entity, replaced with LF.",
     "illegal-windows-1252-entity":
-        _("Entity used with illegal number (windows-1252 reference)."),
+        "Entity used with illegal number (windows-1252 reference).",
     "cant-convert-numeric-entity":
-        _("Numeric entity couldn't be converted to character "
-          "(codepoint U+%(charAsInt)08x)."),
+        "Numeric entity couldn't be converted to character "
+        "(codepoint U+%(charAsInt)08x).",
     "illegal-codepoint-for-numeric-entity":
-        _("Numeric entity represents an illegal codepoint: "
-          "U+%(charAsInt)08x."),
+        "Numeric entity represents an illegal codepoint: "
+        "U+%(charAsInt)08x.",
     "numeric-entity-without-semicolon":
-        _("Numeric entity didn't end with ';'."),
+        "Numeric entity didn't end with ';'.",
     "expected-numeric-entity-but-got-eof":
-        _("Numeric entity expected. Got end of file instead."),
+        "Numeric entity expected. Got end of file instead.",
     "expected-numeric-entity":
-        _("Numeric entity expected but none found."),
+        "Numeric entity expected but none found.",
     "named-entity-without-semicolon":
-        _("Named entity didn't end with ';'."),
+        "Named entity didn't end with ';'.",
     "expected-named-entity":
-        _("Named entity expected. Got none."),
+        "Named entity expected. Got none.",
     "attributes-in-end-tag":
-        _("End tag contains unexpected attributes."),
+        "End tag contains unexpected attributes.",
     'self-closing-flag-on-end-tag':
-        _("End tag contains unexpected self-closing flag."),
+        "End tag contains unexpected self-closing flag.",
     "expected-tag-name-but-got-right-bracket":
-        _("Expected tag name. Got '>' instead."),
+        "Expected tag name. Got '>' instead.",
     "expected-tag-name-but-got-question-mark":
-        _("Expected tag name. Got '?' instead. (HTML doesn't "
-          "support processing instructions.)"),
+        "Expected tag name. Got '?' instead. (HTML doesn't "
+        "support processing instructions.)",
     "expected-tag-name":
-        _("Expected tag name. Got something else instead"),
+        "Expected tag name. Got something else instead",
     "expected-closing-tag-but-got-right-bracket":
-        _("Expected closing tag. Got '>' instead. Ignoring '</>'."),
+        "Expected closing tag. Got '>' instead. Ignoring '</>'.",
     "expected-closing-tag-but-got-eof":
-        _("Expected closing tag. Unexpected end of file."),
+        "Expected closing tag. Unexpected end of file.",
     "expected-closing-tag-but-got-char":
-        _("Expected closing tag. Unexpected character '%(data)s' found."),
+        "Expected closing tag. Unexpected character '%(data)s' found.",
     "eof-in-tag-name":
-        _("Unexpected end of file in the tag name."),
+        "Unexpected end of file in the tag name.",
     "expected-attribute-name-but-got-eof":
-        _("Unexpected end of file. Expected attribute name instead."),
+        "Unexpected end of file. Expected attribute name instead.",
     "eof-in-attribute-name":
-        _("Unexpected end of file in attribute name."),
+        "Unexpected end of file in attribute name.",
     "invalid-character-in-attribute-name":
-        _("Invalid character in attribute name"),
+        "Invalid character in attribute name",
     "duplicate-attribute":
-        _("Dropped duplicate attribute on tag."),
+        "Dropped duplicate attribute on tag.",
     "expected-end-of-tag-name-but-got-eof":
-        _("Unexpected end of file. Expected = or end of tag."),
+        "Unexpected end of file. Expected = or end of tag.",
     "expected-attribute-value-but-got-eof":
-        _("Unexpected end of file. Expected attribute value."),
+        "Unexpected end of file. Expected attribute value.",
     "expected-attribute-value-but-got-right-bracket":
-        _("Expected attribute value. Got '>' instead."),
+        "Expected attribute value. Got '>' instead.",
     'equals-in-unquoted-attribute-value':
-        _("Unexpected = in unquoted attribute"),
+        "Unexpected = in unquoted attribute",
     'unexpected-character-in-unquoted-attribute-value':
-        _("Unexpected character in unquoted attribute"),
+        "Unexpected character in unquoted attribute",
     "invalid-character-after-attribute-name":
-        _("Unexpected character after attribute name."),
+        "Unexpected character after attribute name.",
     "unexpected-character-after-attribute-value":
-        _("Unexpected character after attribute value."),
+        "Unexpected character after attribute value.",
     "eof-in-attribute-value-double-quote":
-        _("Unexpected end of file in attribute value (\")."),
+        "Unexpected end of file in attribute value (\").",
     "eof-in-attribute-value-single-quote":
-        _("Unexpected end of file in attribute value (')."),
+        "Unexpected end of file in attribute value (').",
     "eof-in-attribute-value-no-quotes":
-        _("Unexpected end of file in attribute value."),
+        "Unexpected end of file in attribute value.",
     "unexpected-EOF-after-solidus-in-tag":
-        _("Unexpected end of file in tag. Expected >"),
+        "Unexpected end of file in tag. Expected >",
     "unexpected-character-after-solidus-in-tag":
-        _("Unexpected character after / in tag. Expected >"),
+        "Unexpected character after / in tag. Expected >",
     "expected-dashes-or-doctype":
-        _("Expected '--' or 'DOCTYPE'. Not found."),
+        "Expected '--' or 'DOCTYPE'. Not found.",
     "unexpected-bang-after-double-dash-in-comment":
-        _("Unexpected ! after -- in comment"),
+        "Unexpected ! after -- in comment",
     "unexpected-space-after-double-dash-in-comment":
-        _("Unexpected space after -- in comment"),
+        "Unexpected space after -- in comment",
     "incorrect-comment":
-        _("Incorrect comment."),
+        "Incorrect comment.",
     "eof-in-comment":
-        _("Unexpected end of file in comment."),
+        "Unexpected end of file in comment.",
     "eof-in-comment-end-dash":
-        _("Unexpected end of file in comment (-)"),
+        "Unexpected end of file in comment (-)",
     "unexpected-dash-after-double-dash-in-comment":
-        _("Unexpected '-' after '--' found in comment."),
+        "Unexpected '-' after '--' found in comment.",
     "eof-in-comment-double-dash":
-        _("Unexpected end of file in comment (--)."),
+        "Unexpected end of file in comment (--).",
     "eof-in-comment-end-space-state":
-        _("Unexpected end of file in comment."),
+        "Unexpected end of file in comment.",
     "eof-in-comment-end-bang-state":
-        _("Unexpected end of file in comment."),
+        "Unexpected end of file in comment.",
     "unexpected-char-in-comment":
-        _("Unexpected character in comment found."),
+        "Unexpected character in comment found.",
     "need-space-after-doctype":
-        _("No space after literal string 'DOCTYPE'."),
+        "No space after literal string 'DOCTYPE'.",
     "expected-doctype-name-but-got-right-bracket":
-        _("Unexpected > character. Expected DOCTYPE name."),
+        "Unexpected > character. Expected DOCTYPE name.",
     "expected-doctype-name-but-got-eof":
-        _("Unexpected end of file. Expected DOCTYPE name."),
+        "Unexpected end of file. Expected DOCTYPE name.",
     "eof-in-doctype-name":
-        _("Unexpected end of file in DOCTYPE name."),
+        "Unexpected end of file in DOCTYPE name.",
     "eof-in-doctype":
-        _("Unexpected end of file in DOCTYPE."),
+        "Unexpected end of file in DOCTYPE.",
     "expected-space-or-right-bracket-in-doctype":
-        _("Expected space or '>'. Got '%(data)s'"),
+        "Expected space or '>'. Got '%(data)s'",
     "unexpected-end-of-doctype":
-        _("Unexpected end of DOCTYPE."),
+        "Unexpected end of DOCTYPE.",
     "unexpected-char-in-doctype":
-        _("Unexpected character in DOCTYPE."),
+        "Unexpected character in DOCTYPE.",
     "eof-in-innerhtml":
-        _("XXX innerHTML EOF"),
+        "XXX innerHTML EOF",
     "unexpected-doctype":
-        _("Unexpected DOCTYPE. Ignored."),
+        "Unexpected DOCTYPE. Ignored.",
     "non-html-root":
-        _("html needs to be the first start tag."),
+        "html needs to be the first start tag.",
     "expected-doctype-but-got-eof":
-        _("Unexpected End of file. Expected DOCTYPE."),
+        "Unexpected End of file. Expected DOCTYPE.",
     "unknown-doctype":
-        _("Erroneous DOCTYPE."),
+        "Erroneous DOCTYPE.",
     "expected-doctype-but-got-chars":
-        _("Unexpected non-space characters. Expected DOCTYPE."),
+        "Unexpected non-space characters. Expected DOCTYPE.",
     "expected-doctype-but-got-start-tag":
-        _("Unexpected start tag (%(name)s). Expected DOCTYPE."),
+        "Unexpected start tag (%(name)s). Expected DOCTYPE.",
     "expected-doctype-but-got-end-tag":
-        _("Unexpected end tag (%(name)s). Expected DOCTYPE."),
+        "Unexpected end tag (%(name)s). Expected DOCTYPE.",
     "end-tag-after-implied-root":
-        _("Unexpected end tag (%(name)s) after the (implied) root element."),
+        "Unexpected end tag (%(name)s) after the (implied) root element.",
     "expected-named-closing-tag-but-got-eof":
-        _("Unexpected end of file. Expected end tag (%(name)s)."),
+        "Unexpected end of file. Expected end tag (%(name)s).",
     "two-heads-are-not-better-than-one":
-        _("Unexpected start tag head in existing head. Ignored."),
+        "Unexpected start tag head in existing head. Ignored.",
     "unexpected-end-tag":
-        _("Unexpected end tag (%(name)s). Ignored."),
+        "Unexpected end tag (%(name)s). Ignored.",
     "unexpected-start-tag-out-of-my-head":
-        _("Unexpected start tag (%(name)s) that can be in head. Moved."),
+        "Unexpected start tag (%(name)s) that can be in head. Moved.",
     "unexpected-start-tag":
-        _("Unexpected start tag (%(name)s)."),
+        "Unexpected start tag (%(name)s).",
     "missing-end-tag":
-        _("Missing end tag (%(name)s)."),
+        "Missing end tag (%(name)s).",
     "missing-end-tags":
-        _("Missing end tags (%(name)s)."),
+        "Missing end tags (%(name)s).",
     "unexpected-start-tag-implies-end-tag":
-        _("Unexpected start tag (%(startName)s) "
-          "implies end tag (%(endName)s)."),
+        "Unexpected start tag (%(startName)s) "
+        "implies end tag (%(endName)s).",
     "unexpected-start-tag-treated-as":
-        _("Unexpected start tag (%(originalName)s). Treated as %(newName)s."),
+        "Unexpected start tag (%(originalName)s). Treated as %(newName)s.",
     "deprecated-tag":
-        _("Unexpected start tag %(name)s. Don't use it!"),
+        "Unexpected start tag %(name)s. Don't use it!",
     "unexpected-start-tag-ignored":
-        _("Unexpected start tag %(name)s. Ignored."),
+        "Unexpected start tag %(name)s. Ignored.",
     "expected-one-end-tag-but-got-another":
-        _("Unexpected end tag (%(gotName)s). "
-          "Missing end tag (%(expectedName)s)."),
+        "Unexpected end tag (%(gotName)s). "
+        "Missing end tag (%(expectedName)s).",
     "end-tag-too-early":
-        _("End tag (%(name)s) seen too early. Expected other end tag."),
+        "End tag (%(name)s) seen too early. Expected other end tag.",
     "end-tag-too-early-named":
-        _("Unexpected end tag (%(gotName)s). Expected end tag (%(expectedName)s)."),
+        "Unexpected end tag (%(gotName)s). Expected end tag (%(expectedName)s).",
     "end-tag-too-early-ignored":
-        _("End tag (%(name)s) seen too early. Ignored."),
+        "End tag (%(name)s) seen too early. Ignored.",
     "adoption-agency-1.1":
-        _("End tag (%(name)s) violates step 1, "
-          "paragraph 1 of the adoption agency algorithm."),
+        "End tag (%(name)s) violates step 1, "
+        "paragraph 1 of the adoption agency algorithm.",
     "adoption-agency-1.2":
-        _("End tag (%(name)s) violates step 1, "
-          "paragraph 2 of the adoption agency algorithm."),
+        "End tag (%(name)s) violates step 1, "
+        "paragraph 2 of the adoption agency algorithm.",
     "adoption-agency-1.3":
-        _("End tag (%(name)s) violates step 1, "
-          "paragraph 3 of the adoption agency algorithm."),
+        "End tag (%(name)s) violates step 1, "
+        "paragraph 3 of the adoption agency algorithm.",
     "adoption-agency-4.4":
-        _("End tag (%(name)s) violates step 4, "
-          "paragraph 4 of the adoption agency algorithm."),
+        "End tag (%(name)s) violates step 4, "
+        "paragraph 4 of the adoption agency algorithm.",
     "unexpected-end-tag-treated-as":
-        _("Unexpected end tag (%(originalName)s). Treated as %(newName)s."),
+        "Unexpected end tag (%(originalName)s). Treated as %(newName)s.",
     "no-end-tag":
-        _("This element (%(name)s) has no end tag."),
+        "This element (%(name)s) has no end tag.",
     "unexpected-implied-end-tag-in-table":
-        _("Unexpected implied end tag (%(name)s) in the table phase."),
+        "Unexpected implied end tag (%(name)s) in the table phase.",
     "unexpected-implied-end-tag-in-table-body":
-        _("Unexpected implied end tag (%(name)s) in the table body phase."),
+        "Unexpected implied end tag (%(name)s) in the table body phase.",
     "unexpected-char-implies-table-voodoo":
-        _("Unexpected non-space characters in "
-          "table context caused voodoo mode."),
+        "Unexpected non-space characters in "
+        "table context caused voodoo mode.",
     "unexpected-hidden-input-in-table":
-        _("Unexpected input with type hidden in table context."),
+        "Unexpected input with type hidden in table context.",
     "unexpected-form-in-table":
-        _("Unexpected form in table context."),
+        "Unexpected form in table context.",
     "unexpected-start-tag-implies-table-voodoo":
-        _("Unexpected start tag (%(name)s) in "
-          "table context caused voodoo mode."),
+        "Unexpected start tag (%(name)s) in "
+        "table context caused voodoo mode.",
     "unexpected-end-tag-implies-table-voodoo":
-        _("Unexpected end tag (%(name)s) in "
-          "table context caused voodoo mode."),
+        "Unexpected end tag (%(name)s) in "
+        "table context caused voodoo mode.",
     "unexpected-cell-in-table-body":
-        _("Unexpected table cell start tag (%(name)s) "
-          "in the table body phase."),
+        "Unexpected table cell start tag (%(name)s) "
+        "in the table body phase.",
     "unexpected-cell-end-tag":
-        _("Got table cell end tag (%(name)s) "
-          "while required end tags are missing."),
+        "Got table cell end tag (%(name)s) "
+        "while required end tags are missing.",
     "unexpected-end-tag-in-table-body":
-        _("Unexpected end tag (%(name)s) in the table body phase. Ignored."),
+        "Unexpected end tag (%(name)s) in the table body phase. Ignored.",
     "unexpected-implied-end-tag-in-table-row":
-        _("Unexpected implied end tag (%(name)s) in the table row phase."),
+        "Unexpected implied end tag (%(name)s) in the table row phase.",
     "unexpected-end-tag-in-table-row":
-        _("Unexpected end tag (%(name)s) in the table row phase. Ignored."),
+        "Unexpected end tag (%(name)s) in the table row phase. Ignored.",
     "unexpected-select-in-select":
-        _("Unexpected select start tag in the select phase "
-          "treated as select end tag."),
+        "Unexpected select start tag in the select phase "
+        "treated as select end tag.",
     "unexpected-input-in-select":
-        _("Unexpected input start tag in the select phase."),
+        "Unexpected input start tag in the select phase.",
     "unexpected-start-tag-in-select":
-        _("Unexpected start tag token (%(name)s in the select phase. "
-          "Ignored."),
+        "Unexpected start tag token (%(name)s in the select phase. "
+        "Ignored.",
     "unexpected-end-tag-in-select":
-        _("Unexpected end tag (%(name)s) in the select phase. Ignored."),
+        "Unexpected end tag (%(name)s) in the select phase. Ignored.",
     "unexpected-table-element-start-tag-in-select-in-table":
-        _("Unexpected table element start tag (%(name)s) in the select in table phase."),
+        "Unexpected table element start tag (%(name)s) in the select in table phase.",
     "unexpected-table-element-end-tag-in-select-in-table":
-        _("Unexpected table element end tag (%(name)s) in the select in table phase."),
+        "Unexpected table element end tag (%(name)s) in the select in table phase.",
     "unexpected-char-after-body":
-        _("Unexpected non-space characters in the after body phase."),
+        "Unexpected non-space characters in the after body phase.",
     "unexpected-start-tag-after-body":
-        _("Unexpected start tag token (%(name)s)"
-          " in the after body phase."),
+        "Unexpected start tag token (%(name)s)"
+        " in the after body phase.",
     "unexpected-end-tag-after-body":
-        _("Unexpected end tag token (%(name)s)"
-          " in the after body phase."),
+        "Unexpected end tag token (%(name)s)"
+        " in the after body phase.",
     "unexpected-char-in-frameset":
-        _("Unexpected characters in the frameset phase. Characters ignored."),
+        "Unexpected characters in the frameset phase. Characters ignored.",
     "unexpected-start-tag-in-frameset":
-        _("Unexpected start tag token (%(name)s)"
-          " in the frameset phase. Ignored."),
+        "Unexpected start tag token (%(name)s)"
+        " in the frameset phase. Ignored.",
     "unexpected-frameset-in-frameset-innerhtml":
-        _("Unexpected end tag token (frameset) "
-          "in the frameset phase (innerHTML)."),
+        "Unexpected end tag token (frameset) "
+        "in the frameset phase (innerHTML).",
     "unexpected-end-tag-in-frameset":
-        _("Unexpected end tag token (%(name)s)"
-          " in the frameset phase. Ignored."),
+        "Unexpected end tag token (%(name)s)"
+        " in the frameset phase. Ignored.",
     "unexpected-char-after-frameset":
-        _("Unexpected non-space characters in the "
-          "after frameset phase. Ignored."),
+        "Unexpected non-space characters in the "
+        "after frameset phase. Ignored.",
     "unexpected-start-tag-after-frameset":
-        _("Unexpected start tag (%(name)s)"
-          " in the after frameset phase. Ignored."),
+        "Unexpected start tag (%(name)s)"
+        " in the after frameset phase. Ignored.",
     "unexpected-end-tag-after-frameset":
-        _("Unexpected end tag (%(name)s)"
-          " in the after frameset phase. Ignored."),
+        "Unexpected end tag (%(name)s)"
+        " in the after frameset phase. Ignored.",
     "unexpected-end-tag-after-body-innerhtml":
-        _("Unexpected end tag after body(innerHtml)"),
+        "Unexpected end tag after body(innerHtml)",
     "expected-eof-but-got-char":
-        _("Unexpected non-space characters. Expected end of file."),
+        "Unexpected non-space characters. Expected end of file.",
     "expected-eof-but-got-start-tag":
-        _("Unexpected start tag (%(name)s)"
-          ". Expected end of file."),
+        "Unexpected start tag (%(name)s)"
+        ". Expected end of file.",
     "expected-eof-but-got-end-tag":
-        _("Unexpected end tag (%(name)s)"
-          ". Expected end of file."),
+        "Unexpected end tag (%(name)s)"
+        ". Expected end of file.",
     "eof-in-table":
-        _("Unexpected end of file. Expected table content."),
+        "Unexpected end of file. Expected table content.",
     "eof-in-select":
-        _("Unexpected end of file. Expected select content."),
+        "Unexpected end of file. Expected select content.",
     "eof-in-frameset":
-        _("Unexpected end of file. Expected frameset content."),
+        "Unexpected end of file. Expected frameset content.",
     "eof-in-script-in-script":
-        _("Unexpected end of file. Expected script content."),
+        "Unexpected end of file. Expected script content.",
     "eof-in-foreign-lands":
-        _("Unexpected end of file. Expected foreign content"),
+        "Unexpected end of file. Expected foreign content",
     "non-void-element-with-trailing-solidus":
-        _("Trailing solidus not allowed on element %(name)s"),
+        "Trailing solidus not allowed on element %(name)s",
     "unexpected-html-element-in-foreign-content":
-        _("Element %(name)s not allowed in a non-html context"),
+        "Element %(name)s not allowed in a non-html context",
     "unexpected-end-tag-before-html":
-        _("Unexpected end tag (%(name)s) before html."),
+        "Unexpected end tag (%(name)s) before html.",
+    "unexpected-inhead-noscript-tag":
+        "Element %(name)s not allowed in a inhead-noscript context",
+    "eof-in-head-noscript":
+        "Unexpected end of file. Expected inhead-noscript content",
+    "char-in-head-noscript":
+        "Unexpected non-space character. Expected inhead-noscript content",
     "XXX-undefined-error":
-        _("Undefined error (this sucks and should be fixed)"),
+        "Undefined error (this sucks and should be fixed)",
 }
 
 namespaces = {
@@ -298,7 +302,7 @@ namespaces = {
     "xmlns": "http://www.w3.org/2000/xmlns/"
 }
 
-scopingElements = frozenset((
+scopingElements = frozenset([
     (namespaces["html"], "applet"),
     (namespaces["html"], "caption"),
     (namespaces["html"], "html"),
@@ -316,9 +320,9 @@ scopingElements = frozenset((
     (namespaces["svg"], "foreignObject"),
     (namespaces["svg"], "desc"),
     (namespaces["svg"], "title"),
-))
+])
 
-formattingElements = frozenset((
+formattingElements = frozenset([
     (namespaces["html"], "a"),
     (namespaces["html"], "b"),
     (namespaces["html"], "big"),
@@ -333,9 +337,9 @@ formattingElements = frozenset((
     (namespaces["html"], "strong"),
     (namespaces["html"], "tt"),
     (namespaces["html"], "u")
-))
+])
 
-specialElements = frozenset((
+specialElements = frozenset([
     (namespaces["html"], "address"),
     (namespaces["html"], "applet"),
     (namespaces["html"], "area"),
@@ -416,22 +420,89 @@ specialElements = frozenset((
     (namespaces["html"], "wbr"),
     (namespaces["html"], "xmp"),
     (namespaces["svg"], "foreignObject")
-))
+])
 
-htmlIntegrationPointElements = frozenset((
-    (namespaces["mathml"], "annotaion-xml"),
+htmlIntegrationPointElements = frozenset([
+    (namespaces["mathml"], "annotation-xml"),
     (namespaces["svg"], "foreignObject"),
     (namespaces["svg"], "desc"),
     (namespaces["svg"], "title")
-))
+])
 
-mathmlTextIntegrationPointElements = frozenset((
+mathmlTextIntegrationPointElements = frozenset([
     (namespaces["mathml"], "mi"),
     (namespaces["mathml"], "mo"),
     (namespaces["mathml"], "mn"),
     (namespaces["mathml"], "ms"),
     (namespaces["mathml"], "mtext")
-))
+])
+
+adjustSVGAttributes = {
+    "attributename": "attributeName",
+    "attributetype": "attributeType",
+    "basefrequency": "baseFrequency",
+    "baseprofile": "baseProfile",
+    "calcmode": "calcMode",
+    "clippathunits": "clipPathUnits",
+    "contentscripttype": "contentScriptType",
+    "contentstyletype": "contentStyleType",
+    "diffuseconstant": "diffuseConstant",
+    "edgemode": "edgeMode",
+    "externalresourcesrequired": "externalResourcesRequired",
+    "filterres": "filterRes",
+    "filterunits": "filterUnits",
+    "glyphref": "glyphRef",
+    "gradienttransform": "gradientTransform",
+    "gradientunits": "gradientUnits",
+    "kernelmatrix": "kernelMatrix",
+    "kernelunitlength": "kernelUnitLength",
+    "keypoints": "keyPoints",
+    "keysplines": "keySplines",
+    "keytimes": "keyTimes",
+    "lengthadjust": "lengthAdjust",
+    "limitingconeangle": "limitingConeAngle",
+    "markerheight": "markerHeight",
+    "markerunits": "markerUnits",
+    "markerwidth": "markerWidth",
+    "maskcontentunits": "maskContentUnits",
+    "maskunits": "maskUnits",
+    "numoctaves": "numOctaves",
+    "pathlength": "pathLength",
+    "patterncontentunits": "patternContentUnits",
+    "patterntransform": "patternTransform",
+    "patternunits": "patternUnits",
+    "pointsatx": "pointsAtX",
+    "pointsaty": "pointsAtY",
+    "pointsatz": "pointsAtZ",
+    "preservealpha": "preserveAlpha",
+    "preserveaspectratio": "preserveAspectRatio",
+    "primitiveunits": "primitiveUnits",
+    "refx": "refX",
+    "refy": "refY",
+    "repeatcount": "repeatCount",
+    "repeatdur": "repeatDur",
+    "requiredextensions": "requiredExtensions",
+    "requiredfeatures": "requiredFeatures",
+    "specularconstant": "specularConstant",
+    "specularexponent": "specularExponent",
+    "spreadmethod": "spreadMethod",
+    "startoffset": "startOffset",
+    "stddeviation": "stdDeviation",
+    "stitchtiles": "stitchTiles",
+    "surfacescale": "surfaceScale",
+    "systemlanguage": "systemLanguage",
+    "tablevalues": "tableValues",
+    "targetx": "targetX",
+    "targety": "targetY",
+    "textlength": "textLength",
+    "viewbox": "viewBox",
+    "viewtarget": "viewTarget",
+    "xchannelselector": "xChannelSelector",
+    "ychannelselector": "yChannelSelector",
+    "zoomandpan": "zoomAndPan"
+}
+
+adjustMathMLAttributes = {"definitionurl": "definitionURL"}
 
 adjustForeignAttributes = {
     "xlink:actuate": ("xlink", "actuate", namespaces["xlink"]),
@@ -451,21 +522,21 @@ adjustForeignAttributes = {
 unadjustForeignAttributes = dict([((ns, local), qname) for qname, (prefix, local, ns) in
                                   adjustForeignAttributes.items()])
 
-spaceCharacters = frozenset((
+spaceCharacters = frozenset([
     "\t",
     "\n",
     "\u000C",
     " ",
     "\r"
-))
+])
 
-tableInsertModeElements = frozenset((
+tableInsertModeElements = frozenset([
     "table",
     "tbody",
     "tfoot",
     "thead",
     "tr"
-))
+])
 
 asciiLowercase = frozenset(string.ascii_lowercase)
 asciiUppercase = frozenset(string.ascii_uppercase)
@@ -486,7 +557,7 @@ headingElements = (
     "h6"
 )
 
-voidElements = frozenset((
+voidElements = frozenset([
     "base",
     "command",
     "event-source",
@@ -502,11 +573,11 @@ voidElements = frozenset((
     "input",
     "source",
     "track"
-))
+])
 
-cdataElements = frozenset(('title', 'textarea'))
+cdataElements = frozenset(['title', 'textarea'])
 
-rcdataElements = frozenset((
+rcdataElements = frozenset([
     'style',
     'script',
     'xmp',
@@ -514,27 +585,28 @@ rcdataElements = frozenset((
     'noembed',
     'noframes',
     'noscript'
-))
+])
 
 booleanAttributes = {
-    "": frozenset(("irrelevant",)),
-    "style": frozenset(("scoped",)),
-    "img": frozenset(("ismap",)),
-    "audio": frozenset(("autoplay", "controls")),
-    "video": frozenset(("autoplay", "controls")),
-    "script": frozenset(("defer", "async")),
-    "details": frozenset(("open",)),
-    "datagrid": frozenset(("multiple", "disabled")),
-    "command": frozenset(("hidden", "disabled", "checked", "default")),
-    "hr": frozenset(("noshade")),
-    "menu": frozenset(("autosubmit",)),
-    "fieldset": frozenset(("disabled", "readonly")),
-    "option": frozenset(("disabled", "readonly", "selected")),
-    "optgroup": frozenset(("disabled", "readonly")),
-    "button": frozenset(("disabled", "autofocus")),
-    "input": frozenset(("disabled", "readonly", "required", "autofocus", "checked", "ismap")),
-    "select": frozenset(("disabled", "readonly", "autofocus", "multiple")),
-    "output": frozenset(("disabled", "readonly")),
+    "": frozenset(["irrelevant", "itemscope"]),
+    "style": frozenset(["scoped"]),
+    "img": frozenset(["ismap"]),
+    "audio": frozenset(["autoplay", "controls"]),
+    "video": frozenset(["autoplay", "controls"]),
+    "script": frozenset(["defer", "async"]),
+    "details": frozenset(["open"]),
+    "datagrid": frozenset(["multiple", "disabled"]),
+    "command": frozenset(["hidden", "disabled", "checked", "default"]),
+    "hr": frozenset(["noshade"]),
+    "menu": frozenset(["autosubmit"]),
+    "fieldset": frozenset(["disabled", "readonly"]),
+    "option": frozenset(["disabled", "readonly", "selected"]),
+    "optgroup": frozenset(["disabled", "readonly"]),
+    "button": frozenset(["disabled", "autofocus"]),
+    "input": frozenset(["disabled", "readonly", "required", "autofocus", "checked", "ismap"]),
+    "select": frozenset(["disabled", "readonly", "autofocus", "multiple"]),
+    "output": frozenset(["disabled", "readonly"]),
+    "iframe": frozenset(["seamless"]),
 }
 
 # entitiesWindows1252 has to be _ordered_ and needs to have an index. It
@@ -574,7 +646,7 @@ entitiesWindows1252 = (
     376     # 0x9F  0x0178  LATIN CAPITAL LETTER Y WITH DIAERESIS
 )
 
-xmlEntities = frozenset(('lt;', 'gt;', 'amp;', 'apos;', 'quot;'))
+xmlEntities = frozenset(['lt;', 'gt;', 'amp;', 'apos;', 'quot;'])
 
 entities = {
     "AElig": "\xc6",
@@ -2815,7 +2887,6 @@ replacementCharacters = {
     0x0d: "\u000D",
     0x80: "\u20AC",
     0x81: "\u0081",
-    0x81: "\u0081",
     0x82: "\u201A",
     0x83: "\u0192",
     0x84: "\u201E",
@@ -2848,235 +2919,6 @@ replacementCharacters = {
     0x9F: "\u0178",
 }
 
-encodings = {
-    '437': 'cp437',
-    '850': 'cp850',
-    '852': 'cp852',
-    '855': 'cp855',
-    '857': 'cp857',
-    '860': 'cp860',
-    '861': 'cp861',
-    '862': 'cp862',
-    '863': 'cp863',
-    '865': 'cp865',
-    '866': 'cp866',
-    '869': 'cp869',
-    'ansix341968': 'ascii',
-    'ansix341986': 'ascii',
-    'arabic': 'iso8859-6',
-    'ascii': 'ascii',
-    'asmo708': 'iso8859-6',
-    'big5': 'big5',
-    'big5hkscs': 'big5hkscs',
-    'chinese': 'gbk',
-    'cp037': 'cp037',
-    'cp1026': 'cp1026',
-    'cp154': 'ptcp154',
-    'cp367': 'ascii',
-    'cp424': 'cp424',
-    'cp437': 'cp437',
-    'cp500': 'cp500',
-    'cp775': 'cp775',
-    'cp819': 'windows-1252',
-    'cp850': 'cp850',
-    'cp852': 'cp852',
-    'cp855': 'cp855',
-    'cp857': 'cp857',
-    'cp860': 'cp860',
-    'cp861': 'cp861',
-    'cp862': 'cp862',
-    'cp863': 'cp863',
-    'cp864': 'cp864',
-    'cp865': 'cp865',
-    'cp866': 'cp866',
-    'cp869': 'cp869',
-    'cp936': 'gbk',
-    'cpgr': 'cp869',
-    'cpis': 'cp861',
-    'csascii': 'ascii',
-    'csbig5': 'big5',
-    'cseuckr': 'cp949',
-    'cseucpkdfmtjapanese': 'euc_jp',
-    'csgb2312': 'gbk',
-    'cshproman8': 'hp-roman8',
-    'csibm037': 'cp037',
-    'csibm1026': 'cp1026',
-    'csibm424': 'cp424',
-    'csibm500': 'cp500',
-    'csibm855': 'cp855',
-    'csibm857': 'cp857',
-    'csibm860': 'cp860',
-    'csibm861': 'cp861',
-    'csibm863': 'cp863',
-    'csibm864': 'cp864',
-    'csibm865': 'cp865',
-    'csibm866': 'cp866',
-    'csibm869': 'cp869',
-    'csiso2022jp': 'iso2022_jp',
-    'csiso2022jp2': 'iso2022_jp_2',
-    'csiso2022kr': 'iso2022_kr',
-    'csiso58gb231280': 'gbk',
-    'csisolatin1': 'windows-1252',
-    'csisolatin2': 'iso8859-2',
-    'csisolatin3': 'iso8859-3',
-    'csisolatin4': 'iso8859-4',
-    'csisolatin5': 'windows-1254',
-    'csisolatin6': 'iso8859-10',
-    'csisolatinarabic': 'iso8859-6',
-    'csisolatincyrillic': 'iso8859-5',
-    'csisolatingreek': 'iso8859-7',
-    'csisolatinhebrew': 'iso8859-8',
-    'cskoi8r': 'koi8-r',
-    'csksc56011987': 'cp949',
-    'cspc775baltic': 'cp775',
-    'cspc850multilingual': 'cp850',
-    'cspc862latinhebrew': 'cp862',
-    'cspc8codepage437': 'cp437',
-    'cspcp852': 'cp852',
-    'csptcp154': 'ptcp154',
-    'csshiftjis': 'shift_jis',
-    'csunicode11utf7': 'utf-7',
-    'cyrillic': 'iso8859-5',
-    'cyrillicasian': 'ptcp154',
-    'ebcdiccpbe': 'cp500',
-    'ebcdiccpca': 'cp037',
-    'ebcdiccpch': 'cp500',
-    'ebcdiccphe': 'cp424',
-    'ebcdiccpnl': 'cp037',
-    'ebcdiccpus': 'cp037',
-    'ebcdiccpwt': 'cp037',
-    'ecma114': 'iso8859-6',
-    'ecma118': 'iso8859-7',
-    'elot928': 'iso8859-7',
-    'eucjp': 'euc_jp',
-    'euckr': 'cp949',
-    'extendedunixcodepackedformatforjapanese': 'euc_jp',
-    'gb18030': 'gb18030',
-    'gb2312': 'gbk',
-    'gb231280': 'gbk',
-    'gbk': 'gbk',
-    'greek': 'iso8859-7',
-    'greek8': 'iso8859-7',
-    'hebrew': 'iso8859-8',
-    'hproman8': 'hp-roman8',
-    'hzgb2312': 'hz',
-    'ibm037': 'cp037',
-    'ibm1026': 'cp1026',
-    'ibm367': 'ascii',
-    'ibm424': 'cp424',
-    'ibm437': 'cp437',
-    'ibm500': 'cp500',
-    'ibm775': 'cp775',
-    'ibm819': 'windows-1252',
-    'ibm850': 'cp850',
-    'ibm852': 'cp852',
-    'ibm855': 'cp855',
-    'ibm857': 'cp857',
-    'ibm860': 'cp860',
-    'ibm861': 'cp861',
-    'ibm862': 'cp862',
-    'ibm863': 'cp863',
-    'ibm864': 'cp864',
-    'ibm865': 'cp865',
-    'ibm866': 'cp866',
-    'ibm869': 'cp869',
-    'iso2022jp': 'iso2022_jp',
-    'iso2022jp2': 'iso2022_jp_2',
-    'iso2022kr': 'iso2022_kr',
-    'iso646irv1991': 'ascii',
-    'iso646us': 'ascii',
-    'iso88591': 'windows-1252',
-    'iso885910': 'iso8859-10',
-    'iso8859101992': 'iso8859-10',
-    'iso885911987': 'windows-1252',
-    'iso885913': 'iso8859-13',
-    'iso885914': 'iso8859-14',
-    'iso8859141998': 'iso8859-14',
-    'iso885915': 'iso8859-15',
-    'iso885916': 'iso8859-16',
-    'iso8859162001': 'iso8859-16',
-    'iso88592': 'iso8859-2',
-    'iso885921987': 'iso8859-2',
-    'iso88593': 'iso8859-3',
-    'iso885931988': 'iso8859-3',
-    'iso88594': 'iso8859-4',
-    'iso885941988': 'iso8859-4',
-    'iso88595': 'iso8859-5',
-    'iso885951988': 'iso8859-5',
-    'iso88596': 'iso8859-6',
-    'iso885961987': 'iso8859-6',
-    'iso88597': 'iso8859-7',
-    'iso885971987': 'iso8859-7',
-    'iso88598': 'iso8859-8',
-    'iso885981988': 'iso8859-8',
-    'iso88599': 'windows-1254',
-    'iso885991989': 'windows-1254',
-    'isoceltic': 'iso8859-14',
-    'isoir100': 'windows-1252',
-    'isoir101': 'iso8859-2',
-    'isoir109': 'iso8859-3',
-    'isoir110': 'iso8859-4',
-    'isoir126': 'iso8859-7',
-    'isoir127': 'iso8859-6',
-    'isoir138': 'iso8859-8',
-    'isoir144': 'iso8859-5',
-    'isoir148': 'windows-1254',
-    'isoir149': 'cp949',
-    'isoir157': 'iso8859-10',
-    'isoir199': 'iso8859-14',
-    'isoir226': 'iso8859-16',
-    'isoir58': 'gbk',
-    'isoir6': 'ascii',
-    'koi8r': 'koi8-r',
-    'koi8u': 'koi8-u',
-    'korean': 'cp949',
-    'ksc5601': 'cp949',
-    'ksc56011987': 'cp949',
-    'ksc56011989': 'cp949',
-    'l1': 'windows-1252',
-    'l10': 'iso8859-16',
-    'l2': 'iso8859-2',
-    'l3': 'iso8859-3',
-    'l4': 'iso8859-4',
-    'l5': 'windows-1254',
-    'l6': 'iso8859-10',
-    'l8': 'iso8859-14',
-    'latin1': 'windows-1252',
-    'latin10': 'iso8859-16',
-    'latin2': 'iso8859-2',
-    'latin3': 'iso8859-3',
-    'latin4': 'iso8859-4',
-    'latin5': 'windows-1254',
-    'latin6': 'iso8859-10',
-    'latin8': 'iso8859-14',
-    'latin9': 'iso8859-15',
-    'ms936': 'gbk',
-    'mskanji': 'shift_jis',
-    'pt154': 'ptcp154',
-    'ptcp154': 'ptcp154',
-    'r8': 'hp-roman8',
-    'roman8': 'hp-roman8',
-    'shiftjis': 'shift_jis',
-    'tis620': 'cp874',
-    'unicode11utf7': 'utf-7',
-    'us': 'ascii',
-    'usascii': 'ascii',
-    'utf16': 'utf-16',
-    'utf16be': 'utf-16-be',
-    'utf16le': 'utf-16-le',
-    'utf8': 'utf-8',
-    'windows1250': 'cp1250',
-    'windows1251': 'cp1251',
-    'windows1252': 'cp1252',
-    'windows1253': 'cp1253',
-    'windows1254': 'cp1254',
-    'windows1255': 'cp1255',
-    'windows1256': 'cp1256',
-    'windows1257': 'cp1257',
-    'windows1258': 'cp1258',
-    'windows936': 'gbk',
-    'x-x-big5': 'big5'}
-
 tokenTypes = {
     "Doctype": 0,
     "Characters": 1,
@@ -3088,8 +2930,8 @@ tokenTypes = {
     "ParseError": 7
 }
 
-tagTokenTypes = frozenset((tokenTypes["StartTag"], tokenTypes["EndTag"],
-                           tokenTypes["EmptyTag"]))
+tagTokenTypes = frozenset([tokenTypes["StartTag"], tokenTypes["EndTag"],
+                           tokenTypes["EmptyTag"]])
 
 
 prefixes = dict([(v, k) for k, v in namespaces.items()])
@@ -3097,8 +2939,9 @@ prefixes["http://www.w3.org/1998/Math/MathML"] = "math"
 
 
 class DataLossWarning(UserWarning):
+    """Raised when the current tree is unable to represent the input data"""
     pass
 
 
-class ReparseException(Exception):
+class _ReparseException(Exception):
     pass
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/filters/__init__.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/__init__.py
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/html5lib/filters/__init__.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/__init__.py
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/alphabeticalattributes.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/alphabeticalattributes.py
new file mode 100644
index 000000000000..5ba926e3b09a
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/alphabeticalattributes.py
@@ -0,0 +1,29 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from . import base
+
+from collections import OrderedDict
+
+
+def _attr_key(attr):
+    """Return an appropriate key for an attribute for sorting
+
+    Attributes have a namespace that can be either ``None`` or a string. We
+    can't compare the two because they're different types, so we convert
+    ``None`` to an empty string first.
+
+    """
+    return (attr[0][0] or ''), attr[0][1]
+
+
+class Filter(base.Filter):
+    """Alphabetizes attributes for elements"""
+    def __iter__(self):
+        for token in base.Filter.__iter__(self):
+            if token["type"] in ("StartTag", "EmptyTag"):
+                attrs = OrderedDict()
+                for name, value in sorted(token["data"].items(),
+                                          key=_attr_key):
+                    attrs[name] = value
+                token["data"] = attrs
+            yield token
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/filters/_base.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/base.py
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/html5lib/filters/_base.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/base.py
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/filters/inject_meta_charset.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/inject_meta_charset.py
similarity index 88%
rename from testing/web-platform/tests/tools/html5lib/html5lib/filters/inject_meta_charset.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/inject_meta_charset.py
index ca33b70b5307..aefb5c842c2f 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/filters/inject_meta_charset.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/inject_meta_charset.py
@@ -1,11 +1,19 @@
 from __future__ import absolute_import, division, unicode_literals
 
-from . import _base
+from . import base
 
 
-class Filter(_base.Filter):
+class Filter(base.Filter):
+    """Injects ``<meta charset=ENCODING>`` tag into head of document"""
     def __init__(self, source, encoding):
-        _base.Filter.__init__(self, source)
+        """Creates a Filter
+
+        :arg source: the source token stream
+
+        :arg encoding: the encoding to set
+
+        """
+        base.Filter.__init__(self, source)
         self.encoding = encoding
 
     def __iter__(self):
@@ -13,7 +21,7 @@ class Filter(_base.Filter):
         meta_found = (self.encoding is None)
         pending = []
 
-        for token in _base.Filter.__iter__(self):
+        for token in base.Filter.__iter__(self):
             type = token["type"]
             if type == "StartTag":
                 if token["name"].lower() == "head":
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/lint.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/lint.py
new file mode 100644
index 000000000000..acd4d7a2af1f
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/lint.py
@@ -0,0 +1,93 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from six import text_type
+
+from . import base
+from ..constants import namespaces, voidElements
+
+from ..constants import spaceCharacters
+spaceCharacters = "".join(spaceCharacters)
+
+
+class Filter(base.Filter):
+    """Lints the token stream for errors
+
+    If it finds any errors, it'll raise an ``AssertionError``.
+
+    """
+    def __init__(self, source, require_matching_tags=True):
+        """Creates a Filter
+
+        :arg source: the source token stream
+
+        :arg require_matching_tags: whether or not to require matching tags
+
+        """
+        super(Filter, self).__init__(source)
+        self.require_matching_tags = require_matching_tags
+
+    def __iter__(self):
+        open_elements = []
+        for token in base.Filter.__iter__(self):
+            type = token["type"]
+            if type in ("StartTag", "EmptyTag"):
+                namespace = token["namespace"]
+                name = token["name"]
+                assert namespace is None or isinstance(namespace, text_type)
+                assert namespace != ""
+                assert isinstance(name, text_type)
+                assert name != ""
+                assert isinstance(token["data"], dict)
+                if (not namespace or namespace == namespaces["html"]) and name in voidElements:
+                    assert type == "EmptyTag"
+                else:
+                    assert type == "StartTag"
+                if type == "StartTag" and self.require_matching_tags:
+                    open_elements.append((namespace, name))
+                for (namespace, name), value in token["data"].items():
+                    assert namespace is None or isinstance(namespace, text_type)
+                    assert namespace != ""
+                    assert isinstance(name, text_type)
+                    assert name != ""
+                    assert isinstance(value, text_type)
+
+            elif type == "EndTag":
+                namespace = token["namespace"]
+                name = token["name"]
+                assert namespace is None or isinstance(namespace, text_type)
+                assert namespace != ""
+                assert isinstance(name, text_type)
+                assert name != ""
+                if (not namespace or namespace == namespaces["html"]) and name in voidElements:
+                    assert False, "Void element reported as EndTag token: %(tag)s" % {"tag": name}
+                elif self.require_matching_tags:
+                    start = open_elements.pop()
+                    assert start == (namespace, name)
+
+            elif type == "Comment":
+                data = token["data"]
+                assert isinstance(data, text_type)
+
+            elif type in ("Characters", "SpaceCharacters"):
+                data = token["data"]
+                assert isinstance(data, text_type)
+                assert data != ""
+                if type == "SpaceCharacters":
+                    assert data.strip(spaceCharacters) == ""
+
+            elif type == "Doctype":
+                name = token["name"]
+                assert name is None or isinstance(name, text_type)
+                assert token["publicId"] is None or isinstance(name, text_type)
+                assert token["systemId"] is None or isinstance(name, text_type)
+
+            elif type == "Entity":
+                assert isinstance(token["name"], text_type)
+
+            elif type == "SerializerError":
+                assert isinstance(token["data"], text_type)
+
+            else:
+                assert False, "Unknown token type: %(type)s" % {"type": type}
+
+            yield token
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/filters/optionaltags.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/optionaltags.py
similarity index 96%
rename from testing/web-platform/tests/tools/html5lib/html5lib/filters/optionaltags.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/optionaltags.py
index fefe0b3097bd..4a865012c162 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/filters/optionaltags.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/optionaltags.py
@@ -1,9 +1,10 @@
 from __future__ import absolute_import, division, unicode_literals
 
-from . import _base
+from . import base
 
 
-class Filter(_base.Filter):
+class Filter(base.Filter):
+    """Removes optional tags from the token stream"""
     def slider(self):
         previous1 = previous2 = None
         for token in self.source:
@@ -11,7 +12,8 @@ class Filter(_base.Filter):
                 yield previous2, previous1, token
             previous2 = previous1
             previous1 = token
-        yield previous2, previous1, None
+        if previous1 is not None:
+            yield previous2, previous1, None
 
     def __iter__(self):
         for previous, token, next in self.slider():
@@ -58,7 +60,7 @@ class Filter(_base.Filter):
         elif tagname == 'colgroup':
             # A colgroup element's start tag may be omitted if the first thing
             # inside the colgroup element is a col element, and if the element
-            # is not immediately preceeded by another colgroup element whose
+            # is not immediately preceded by another colgroup element whose
             # end tag has been omitted.
             if type in ("StartTag", "EmptyTag"):
                 # XXX: we do not look at the preceding event, so instead we never
@@ -70,7 +72,7 @@ class Filter(_base.Filter):
         elif tagname == 'tbody':
             # A tbody element's start tag may be omitted if the first thing
             # inside the tbody element is a tr element, and if the element is
-            # not immediately preceeded by a tbody, thead, or tfoot element
+            # not immediately preceded by a tbody, thead, or tfoot element
             # whose end tag has been omitted.
             if type == "StartTag":
                 # omit the thead and tfoot elements' end tag when they are
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/sanitizer.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/sanitizer.py
new file mode 100644
index 000000000000..e852f53be8af
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/sanitizer.py
@@ -0,0 +1,896 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import re
+from xml.sax.saxutils import escape, unescape
+
+from six.moves import urllib_parse as urlparse
+
+from . import base
+from ..constants import namespaces, prefixes
+
+__all__ = ["Filter"]
+
+
+allowed_elements = frozenset((
+    (namespaces['html'], 'a'),
+    (namespaces['html'], 'abbr'),
+    (namespaces['html'], 'acronym'),
+    (namespaces['html'], 'address'),
+    (namespaces['html'], 'area'),
+    (namespaces['html'], 'article'),
+    (namespaces['html'], 'aside'),
+    (namespaces['html'], 'audio'),
+    (namespaces['html'], 'b'),
+    (namespaces['html'], 'big'),
+    (namespaces['html'], 'blockquote'),
+    (namespaces['html'], 'br'),
+    (namespaces['html'], 'button'),
+    (namespaces['html'], 'canvas'),
+    (namespaces['html'], 'caption'),
+    (namespaces['html'], 'center'),
+    (namespaces['html'], 'cite'),
+    (namespaces['html'], 'code'),
+    (namespaces['html'], 'col'),
+    (namespaces['html'], 'colgroup'),
+    (namespaces['html'], 'command'),
+    (namespaces['html'], 'datagrid'),
+    (namespaces['html'], 'datalist'),
+    (namespaces['html'], 'dd'),
+    (namespaces['html'], 'del'),
+    (namespaces['html'], 'details'),
+    (namespaces['html'], 'dfn'),
+    (namespaces['html'], 'dialog'),
+    (namespaces['html'], 'dir'),
+    (namespaces['html'], 'div'),
+    (namespaces['html'], 'dl'),
+    (namespaces['html'], 'dt'),
+    (namespaces['html'], 'em'),
+    (namespaces['html'], 'event-source'),
+    (namespaces['html'], 'fieldset'),
+    (namespaces['html'], 'figcaption'),
+    (namespaces['html'], 'figure'),
+    (namespaces['html'], 'footer'),
+    (namespaces['html'], 'font'),
+    (namespaces['html'], 'form'),
+    (namespaces['html'], 'header'),
+    (namespaces['html'], 'h1'),
+    (namespaces['html'], 'h2'),
+    (namespaces['html'], 'h3'),
+    (namespaces['html'], 'h4'),
+    (namespaces['html'], 'h5'),
+    (namespaces['html'], 'h6'),
+    (namespaces['html'], 'hr'),
+    (namespaces['html'], 'i'),
+    (namespaces['html'], 'img'),
+    (namespaces['html'], 'input'),
+    (namespaces['html'], 'ins'),
+    (namespaces['html'], 'keygen'),
+    (namespaces['html'], 'kbd'),
+    (namespaces['html'], 'label'),
+    (namespaces['html'], 'legend'),
+    (namespaces['html'], 'li'),
+    (namespaces['html'], 'm'),
+    (namespaces['html'], 'map'),
+    (namespaces['html'], 'menu'),
+    (namespaces['html'], 'meter'),
+    (namespaces['html'], 'multicol'),
+    (namespaces['html'], 'nav'),
+    (namespaces['html'], 'nextid'),
+    (namespaces['html'], 'ol'),
+    (namespaces['html'], 'output'),
+    (namespaces['html'], 'optgroup'),
+    (namespaces['html'], 'option'),
+    (namespaces['html'], 'p'),
+    (namespaces['html'], 'pre'),
+    (namespaces['html'], 'progress'),
+    (namespaces['html'], 'q'),
+    (namespaces['html'], 's'),
+    (namespaces['html'], 'samp'),
+    (namespaces['html'], 'section'),
+    (namespaces['html'], 'select'),
+    (namespaces['html'], 'small'),
+    (namespaces['html'], 'sound'),
+    (namespaces['html'], 'source'),
+    (namespaces['html'], 'spacer'),
+    (namespaces['html'], 'span'),
+    (namespaces['html'], 'strike'),
+    (namespaces['html'], 'strong'),
+    (namespaces['html'], 'sub'),
+    (namespaces['html'], 'sup'),
+    (namespaces['html'], 'table'),
+    (namespaces['html'], 'tbody'),
+    (namespaces['html'], 'td'),
+    (namespaces['html'], 'textarea'),
+    (namespaces['html'], 'time'),
+    (namespaces['html'], 'tfoot'),
+    (namespaces['html'], 'th'),
+    (namespaces['html'], 'thead'),
+    (namespaces['html'], 'tr'),
+    (namespaces['html'], 'tt'),
+    (namespaces['html'], 'u'),
+    (namespaces['html'], 'ul'),
+    (namespaces['html'], 'var'),
+    (namespaces['html'], 'video'),
+    (namespaces['mathml'], 'maction'),
+    (namespaces['mathml'], 'math'),
+    (namespaces['mathml'], 'merror'),
+    (namespaces['mathml'], 'mfrac'),
+    (namespaces['mathml'], 'mi'),
+    (namespaces['mathml'], 'mmultiscripts'),
+    (namespaces['mathml'], 'mn'),
+    (namespaces['mathml'], 'mo'),
+    (namespaces['mathml'], 'mover'),
+    (namespaces['mathml'], 'mpadded'),
+    (namespaces['mathml'], 'mphantom'),
+    (namespaces['mathml'], 'mprescripts'),
+    (namespaces['mathml'], 'mroot'),
+    (namespaces['mathml'], 'mrow'),
+    (namespaces['mathml'], 'mspace'),
+    (namespaces['mathml'], 'msqrt'),
+    (namespaces['mathml'], 'mstyle'),
+    (namespaces['mathml'], 'msub'),
+    (namespaces['mathml'], 'msubsup'),
+    (namespaces['mathml'], 'msup'),
+    (namespaces['mathml'], 'mtable'),
+    (namespaces['mathml'], 'mtd'),
+    (namespaces['mathml'], 'mtext'),
+    (namespaces['mathml'], 'mtr'),
+    (namespaces['mathml'], 'munder'),
+    (namespaces['mathml'], 'munderover'),
+    (namespaces['mathml'], 'none'),
+    (namespaces['svg'], 'a'),
+    (namespaces['svg'], 'animate'),
+    (namespaces['svg'], 'animateColor'),
+    (namespaces['svg'], 'animateMotion'),
+    (namespaces['svg'], 'animateTransform'),
+    (namespaces['svg'], 'clipPath'),
+    (namespaces['svg'], 'circle'),
+    (namespaces['svg'], 'defs'),
+    (namespaces['svg'], 'desc'),
+    (namespaces['svg'], 'ellipse'),
+    (namespaces['svg'], 'font-face'),
+    (namespaces['svg'], 'font-face-name'),
+    (namespaces['svg'], 'font-face-src'),
+    (namespaces['svg'], 'g'),
+    (namespaces['svg'], 'glyph'),
+    (namespaces['svg'], 'hkern'),
+    (namespaces['svg'], 'linearGradient'),
+    (namespaces['svg'], 'line'),
+    (namespaces['svg'], 'marker'),
+    (namespaces['svg'], 'metadata'),
+    (namespaces['svg'], 'missing-glyph'),
+    (namespaces['svg'], 'mpath'),
+    (namespaces['svg'], 'path'),
+    (namespaces['svg'], 'polygon'),
+    (namespaces['svg'], 'polyline'),
+    (namespaces['svg'], 'radialGradient'),
+    (namespaces['svg'], 'rect'),
+    (namespaces['svg'], 'set'),
+    (namespaces['svg'], 'stop'),
+    (namespaces['svg'], 'svg'),
+    (namespaces['svg'], 'switch'),
+    (namespaces['svg'], 'text'),
+    (namespaces['svg'], 'title'),
+    (namespaces['svg'], 'tspan'),
+    (namespaces['svg'], 'use'),
+))
+
+allowed_attributes = frozenset((
+    # HTML attributes
+    (None, 'abbr'),
+    (None, 'accept'),
+    (None, 'accept-charset'),
+    (None, 'accesskey'),
+    (None, 'action'),
+    (None, 'align'),
+    (None, 'alt'),
+    (None, 'autocomplete'),
+    (None, 'autofocus'),
+    (None, 'axis'),
+    (None, 'background'),
+    (None, 'balance'),
+    (None, 'bgcolor'),
+    (None, 'bgproperties'),
+    (None, 'border'),
+    (None, 'bordercolor'),
+    (None, 'bordercolordark'),
+    (None, 'bordercolorlight'),
+    (None, 'bottompadding'),
+    (None, 'cellpadding'),
+    (None, 'cellspacing'),
+    (None, 'ch'),
+    (None, 'challenge'),
+    (None, 'char'),
+    (None, 'charoff'),
+    (None, 'choff'),
+    (None, 'charset'),
+    (None, 'checked'),
+    (None, 'cite'),
+    (None, 'class'),
+    (None, 'clear'),
+    (None, 'color'),
+    (None, 'cols'),
+    (None, 'colspan'),
+    (None, 'compact'),
+    (None, 'contenteditable'),
+    (None, 'controls'),
+    (None, 'coords'),
+    (None, 'data'),
+    (None, 'datafld'),
+    (None, 'datapagesize'),
+    (None, 'datasrc'),
+    (None, 'datetime'),
+    (None, 'default'),
+    (None, 'delay'),
+    (None, 'dir'),
+    (None, 'disabled'),
+    (None, 'draggable'),
+    (None, 'dynsrc'),
+    (None, 'enctype'),
+    (None, 'end'),
+    (None, 'face'),
+    (None, 'for'),
+    (None, 'form'),
+    (None, 'frame'),
+    (None, 'galleryimg'),
+    (None, 'gutter'),
+    (None, 'headers'),
+    (None, 'height'),
+    (None, 'hidefocus'),
+    (None, 'hidden'),
+    (None, 'high'),
+    (None, 'href'),
+    (None, 'hreflang'),
+    (None, 'hspace'),
+    (None, 'icon'),
+    (None, 'id'),
+    (None, 'inputmode'),
+    (None, 'ismap'),
+    (None, 'keytype'),
+    (None, 'label'),
+    (None, 'leftspacing'),
+    (None, 'lang'),
+    (None, 'list'),
+    (None, 'longdesc'),
+    (None, 'loop'),
+    (None, 'loopcount'),
+    (None, 'loopend'),
+    (None, 'loopstart'),
+    (None, 'low'),
+    (None, 'lowsrc'),
+    (None, 'max'),
+    (None, 'maxlength'),
+    (None, 'media'),
+    (None, 'method'),
+    (None, 'min'),
+    (None, 'multiple'),
+    (None, 'name'),
+    (None, 'nohref'),
+    (None, 'noshade'),
+    (None, 'nowrap'),
+    (None, 'open'),
+    (None, 'optimum'),
+    (None, 'pattern'),
+    (None, 'ping'),
+    (None, 'point-size'),
+    (None, 'poster'),
+    (None, 'pqg'),
+    (None, 'preload'),
+    (None, 'prompt'),
+    (None, 'radiogroup'),
+    (None, 'readonly'),
+    (None, 'rel'),
+    (None, 'repeat-max'),
+    (None, 'repeat-min'),
+    (None, 'replace'),
+    (None, 'required'),
+    (None, 'rev'),
+    (None, 'rightspacing'),
+    (None, 'rows'),
+    (None, 'rowspan'),
+    (None, 'rules'),
+    (None, 'scope'),
+    (None, 'selected'),
+    (None, 'shape'),
+    (None, 'size'),
+    (None, 'span'),
+    (None, 'src'),
+    (None, 'start'),
+    (None, 'step'),
+    (None, 'style'),
+    (None, 'summary'),
+    (None, 'suppress'),
+    (None, 'tabindex'),
+    (None, 'target'),
+    (None, 'template'),
+    (None, 'title'),
+    (None, 'toppadding'),
+    (None, 'type'),
+    (None, 'unselectable'),
+    (None, 'usemap'),
+    (None, 'urn'),
+    (None, 'valign'),
+    (None, 'value'),
+    (None, 'variable'),
+    (None, 'volume'),
+    (None, 'vspace'),
+    (None, 'vrml'),
+    (None, 'width'),
+    (None, 'wrap'),
+    (namespaces['xml'], 'lang'),
+    # MathML attributes
+    (None, 'actiontype'),
+    (None, 'align'),
+    (None, 'columnalign'),
+    (None, 'columnalign'),
+    (None, 'columnalign'),
+    (None, 'columnlines'),
+    (None, 'columnspacing'),
+    (None, 'columnspan'),
+    (None, 'depth'),
+    (None, 'display'),
+    (None, 'displaystyle'),
+    (None, 'equalcolumns'),
+    (None, 'equalrows'),
+    (None, 'fence'),
+    (None, 'fontstyle'),
+    (None, 'fontweight'),
+    (None, 'frame'),
+    (None, 'height'),
+    (None, 'linethickness'),
+    (None, 'lspace'),
+    (None, 'mathbackground'),
+    (None, 'mathcolor'),
+    (None, 'mathvariant'),
+    (None, 'mathvariant'),
+    (None, 'maxsize'),
+    (None, 'minsize'),
+    (None, 'other'),
+    (None, 'rowalign'),
+    (None, 'rowalign'),
+    (None, 'rowalign'),
+    (None, 'rowlines'),
+    (None, 'rowspacing'),
+    (None, 'rowspan'),
+    (None, 'rspace'),
+    (None, 'scriptlevel'),
+    (None, 'selection'),
+    (None, 'separator'),
+    (None, 'stretchy'),
+    (None, 'width'),
+    (None, 'width'),
+    (namespaces['xlink'], 'href'),
+    (namespaces['xlink'], 'show'),
+    (namespaces['xlink'], 'type'),
+    # SVG attributes
+    (None, 'accent-height'),
+    (None, 'accumulate'),
+    (None, 'additive'),
+    (None, 'alphabetic'),
+    (None, 'arabic-form'),
+    (None, 'ascent'),
+    (None, 'attributeName'),
+    (None, 'attributeType'),
+    (None, 'baseProfile'),
+    (None, 'bbox'),
+    (None, 'begin'),
+    (None, 'by'),
+    (None, 'calcMode'),
+    (None, 'cap-height'),
+    (None, 'class'),
+    (None, 'clip-path'),
+    (None, 'color'),
+    (None, 'color-rendering'),
+    (None, 'content'),
+    (None, 'cx'),
+    (None, 'cy'),
+    (None, 'd'),
+    (None, 'dx'),
+    (None, 'dy'),
+    (None, 'descent'),
+    (None, 'display'),
+    (None, 'dur'),
+    (None, 'end'),
+    (None, 'fill'),
+    (None, 'fill-opacity'),
+    (None, 'fill-rule'),
+    (None, 'font-family'),
+    (None, 'font-size'),
+    (None, 'font-stretch'),
+    (None, 'font-style'),
+    (None, 'font-variant'),
+    (None, 'font-weight'),
+    (None, 'from'),
+    (None, 'fx'),
+    (None, 'fy'),
+    (None, 'g1'),
+    (None, 'g2'),
+    (None, 'glyph-name'),
+    (None, 'gradientUnits'),
+    (None, 'hanging'),
+    (None, 'height'),
+    (None, 'horiz-adv-x'),
+    (None, 'horiz-origin-x'),
+    (None, 'id'),
+    (None, 'ideographic'),
+    (None, 'k'),
+    (None, 'keyPoints'),
+    (None, 'keySplines'),
+    (None, 'keyTimes'),
+    (None, 'lang'),
+    (None, 'marker-end'),
+    (None, 'marker-mid'),
+    (None, 'marker-start'),
+    (None, 'markerHeight'),
+    (None, 'markerUnits'),
+    (None, 'markerWidth'),
+    (None, 'mathematical'),
+    (None, 'max'),
+    (None, 'min'),
+    (None, 'name'),
+    (None, 'offset'),
+    (None, 'opacity'),
+    (None, 'orient'),
+    (None, 'origin'),
+    (None, 'overline-position'),
+    (None, 'overline-thickness'),
+    (None, 'panose-1'),
+    (None, 'path'),
+    (None, 'pathLength'),
+    (None, 'points'),
+    (None, 'preserveAspectRatio'),
+    (None, 'r'),
+    (None, 'refX'),
+    (None, 'refY'),
+    (None, 'repeatCount'),
+    (None, 'repeatDur'),
+    (None, 'requiredExtensions'),
+    (None, 'requiredFeatures'),
+    (None, 'restart'),
+    (None, 'rotate'),
+    (None, 'rx'),
+    (None, 'ry'),
+    (None, 'slope'),
+    (None, 'stemh'),
+    (None, 'stemv'),
+    (None, 'stop-color'),
+    (None, 'stop-opacity'),
+    (None, 'strikethrough-position'),
+    (None, 'strikethrough-thickness'),
+    (None, 'stroke'),
+    (None, 'stroke-dasharray'),
+    (None, 'stroke-dashoffset'),
+    (None, 'stroke-linecap'),
+    (None, 'stroke-linejoin'),
+    (None, 'stroke-miterlimit'),
+    (None, 'stroke-opacity'),
+    (None, 'stroke-width'),
+    (None, 'systemLanguage'),
+    (None, 'target'),
+    (None, 'text-anchor'),
+    (None, 'to'),
+    (None, 'transform'),
+    (None, 'type'),
+    (None, 'u1'),
+    (None, 'u2'),
+    (None, 'underline-position'),
+    (None, 'underline-thickness'),
+    (None, 'unicode'),
+    (None, 'unicode-range'),
+    (None, 'units-per-em'),
+    (None, 'values'),
+    (None, 'version'),
+    (None, 'viewBox'),
+    (None, 'visibility'),
+    (None, 'width'),
+    (None, 'widths'),
+    (None, 'x'),
+    (None, 'x-height'),
+    (None, 'x1'),
+    (None, 'x2'),
+    (namespaces['xlink'], 'actuate'),
+    (namespaces['xlink'], 'arcrole'),
+    (namespaces['xlink'], 'href'),
+    (namespaces['xlink'], 'role'),
+    (namespaces['xlink'], 'show'),
+    (namespaces['xlink'], 'title'),
+    (namespaces['xlink'], 'type'),
+    (namespaces['xml'], 'base'),
+    (namespaces['xml'], 'lang'),
+    (namespaces['xml'], 'space'),
+    (None, 'y'),
+    (None, 'y1'),
+    (None, 'y2'),
+    (None, 'zoomAndPan'),
+))
+
+attr_val_is_uri = frozenset((
+    (None, 'href'),
+    (None, 'src'),
+    (None, 'cite'),
+    (None, 'action'),
+    (None, 'longdesc'),
+    (None, 'poster'),
+    (None, 'background'),
+    (None, 'datasrc'),
+    (None, 'dynsrc'),
+    (None, 'lowsrc'),
+    (None, 'ping'),
+    (namespaces['xlink'], 'href'),
+    (namespaces['xml'], 'base'),
+))
+
+svg_attr_val_allows_ref = frozenset((
+    (None, 'clip-path'),
+    (None, 'color-profile'),
+    (None, 'cursor'),
+    (None, 'fill'),
+    (None, 'filter'),
+    (None, 'marker'),
+    (None, 'marker-start'),
+    (None, 'marker-mid'),
+    (None, 'marker-end'),
+    (None, 'mask'),
+    (None, 'stroke'),
+))
+
+svg_allow_local_href = frozenset((
+    (None, 'altGlyph'),
+    (None, 'animate'),
+    (None, 'animateColor'),
+    (None, 'animateMotion'),
+    (None, 'animateTransform'),
+    (None, 'cursor'),
+    (None, 'feImage'),
+    (None, 'filter'),
+    (None, 'linearGradient'),
+    (None, 'pattern'),
+    (None, 'radialGradient'),
+    (None, 'textpath'),
+    (None, 'tref'),
+    (None, 'set'),
+    (None, 'use')
+))
+
+allowed_css_properties = frozenset((
+    'azimuth',
+    'background-color',
+    'border-bottom-color',
+    'border-collapse',
+    'border-color',
+    'border-left-color',
+    'border-right-color',
+    'border-top-color',
+    'clear',
+    'color',
+    'cursor',
+    'direction',
+    'display',
+    'elevation',
+    'float',
+    'font',
+    'font-family',
+    'font-size',
+    'font-style',
+    'font-variant',
+    'font-weight',
+    'height',
+    'letter-spacing',
+    'line-height',
+    'overflow',
+    'pause',
+    'pause-after',
+    'pause-before',
+    'pitch',
+    'pitch-range',
+    'richness',
+    'speak',
+    'speak-header',
+    'speak-numeral',
+    'speak-punctuation',
+    'speech-rate',
+    'stress',
+    'text-align',
+    'text-decoration',
+    'text-indent',
+    'unicode-bidi',
+    'vertical-align',
+    'voice-family',
+    'volume',
+    'white-space',
+    'width',
+))
+
+allowed_css_keywords = frozenset((
+    'auto',
+    'aqua',
+    'black',
+    'block',
+    'blue',
+    'bold',
+    'both',
+    'bottom',
+    'brown',
+    'center',
+    'collapse',
+    'dashed',
+    'dotted',
+    'fuchsia',
+    'gray',
+    'green',
+    '!important',
+    'italic',
+    'left',
+    'lime',
+    'maroon',
+    'medium',
+    'none',
+    'navy',
+    'normal',
+    'nowrap',
+    'olive',
+    'pointer',
+    'purple',
+    'red',
+    'right',
+    'solid',
+    'silver',
+    'teal',
+    'top',
+    'transparent',
+    'underline',
+    'white',
+    'yellow',
+))
+
+allowed_svg_properties = frozenset((
+    'fill',
+    'fill-opacity',
+    'fill-rule',
+    'stroke',
+    'stroke-width',
+    'stroke-linecap',
+    'stroke-linejoin',
+    'stroke-opacity',
+))
+
+allowed_protocols = frozenset((
+    'ed2k',
+    'ftp',
+    'http',
+    'https',
+    'irc',
+    'mailto',
+    'news',
+    'gopher',
+    'nntp',
+    'telnet',
+    'webcal',
+    'xmpp',
+    'callto',
+    'feed',
+    'urn',
+    'aim',
+    'rsync',
+    'tag',
+    'ssh',
+    'sftp',
+    'rtsp',
+    'afs',
+    'data',
+))
+
+allowed_content_types = frozenset((
+    'image/png',
+    'image/jpeg',
+    'image/gif',
+    'image/webp',
+    'image/bmp',
+    'text/plain',
+))
+
+
+data_content_type = re.compile(r'''
+                                ^
+                                # Match a content type <application>/<type>
+                                (?P<content_type>[-a-zA-Z0-9.]+/[-a-zA-Z0-9.]+)
+                                # Match any character set and encoding
+                                (?:(?:;charset=(?:[-a-zA-Z0-9]+)(?:;(?:base64))?)
+                                  |(?:;(?:base64))?(?:;charset=(?:[-a-zA-Z0-9]+))?)
+                                # Assume the rest is data
+                                ,.*
+                                $
+                                ''',
+                               re.VERBOSE)
+
+
+class Filter(base.Filter):
+    """Sanitizes token stream of XHTML+MathML+SVG and of inline style attributes"""
+    def __init__(self,
+                 source,
+                 allowed_elements=allowed_elements,
+                 allowed_attributes=allowed_attributes,
+                 allowed_css_properties=allowed_css_properties,
+                 allowed_css_keywords=allowed_css_keywords,
+                 allowed_svg_properties=allowed_svg_properties,
+                 allowed_protocols=allowed_protocols,
+                 allowed_content_types=allowed_content_types,
+                 attr_val_is_uri=attr_val_is_uri,
+                 svg_attr_val_allows_ref=svg_attr_val_allows_ref,
+                 svg_allow_local_href=svg_allow_local_href):
+        """Creates a Filter
+
+        :arg allowed_elements: set of elements to allow--everything else will
+            be escaped
+
+        :arg allowed_attributes: set of attributes to allow in
+            elements--everything else will be stripped
+
+        :arg allowed_css_properties: set of CSS properties to allow--everything
+            else will be stripped
+
+        :arg allowed_css_keywords: set of CSS keywords to allow--everything
+            else will be stripped
+
+        :arg allowed_svg_properties: set of SVG properties to allow--everything
+            else will be removed
+
+        :arg allowed_protocols: set of allowed protocols for URIs
+
+        :arg allowed_content_types: set of allowed content types for ``data`` URIs.
+
+        :arg attr_val_is_uri: set of attributes that have URI values--values
+            that have a scheme not listed in ``allowed_protocols`` are removed
+
+        :arg svg_attr_val_allows_ref: set of SVG attributes that can have
+            references
+
+        :arg svg_allow_local_href: set of SVG elements that can have local
+            hrefs--these are removed
+
+        """
+        super(Filter, self).__init__(source)
+        self.allowed_elements = allowed_elements
+        self.allowed_attributes = allowed_attributes
+        self.allowed_css_properties = allowed_css_properties
+        self.allowed_css_keywords = allowed_css_keywords
+        self.allowed_svg_properties = allowed_svg_properties
+        self.allowed_protocols = allowed_protocols
+        self.allowed_content_types = allowed_content_types
+        self.attr_val_is_uri = attr_val_is_uri
+        self.svg_attr_val_allows_ref = svg_attr_val_allows_ref
+        self.svg_allow_local_href = svg_allow_local_href
+
+    def __iter__(self):
+        for token in base.Filter.__iter__(self):
+            token = self.sanitize_token(token)
+            if token:
+                yield token
+
+    # Sanitize the +html+, escaping all elements not in ALLOWED_ELEMENTS, and
+    # stripping out all attributes not in ALLOWED_ATTRIBUTES. Style attributes
+    # are parsed, and a restricted set, specified by ALLOWED_CSS_PROPERTIES and
+    # ALLOWED_CSS_KEYWORDS, are allowed through. attributes in ATTR_VAL_IS_URI
+    # are scanned, and only URI schemes specified in ALLOWED_PROTOCOLS are
+    # allowed.
+    #
+    #   sanitize_html('<script> do_nasty_stuff() </script>')
+    #    => &lt;script> do_nasty_stuff() &lt;/script>
+    #   sanitize_html('<a href="javascript: sucker();">Click here for $100</a>')
+    #    => <a>Click here for $100</a>
+    def sanitize_token(self, token):
+
+        # accommodate filters which use token_type differently
+        token_type = token["type"]
+        if token_type in ("StartTag", "EndTag", "EmptyTag"):
+            name = token["name"]
+            namespace = token["namespace"]
+            if ((namespace, name) in self.allowed_elements or
+                (namespace is None and
+                 (namespaces["html"], name) in self.allowed_elements)):
+                return self.allowed_token(token)
+            else:
+                return self.disallowed_token(token)
+        elif token_type == "Comment":
+            pass
+        else:
+            return token
+
+    def allowed_token(self, token):
+        if "data" in token:
+            attrs = token["data"]
+            attr_names = set(attrs.keys())
+
+            # Remove forbidden attributes
+            for to_remove in (attr_names - self.allowed_attributes):
+                del token["data"][to_remove]
+                attr_names.remove(to_remove)
+
+            # Remove attributes with disallowed URL values
+            for attr in (attr_names & self.attr_val_is_uri):
+                assert attr in attrs
+                # I don't have a clue where this regexp comes from or why it matches those
+                # characters, nor why we call unescape. I just know it's always been here.
+                # Should you be worried by this comment in a sanitizer? Yes. On the other hand, all
+                # this will do is remove *more* than it otherwise would.
+                val_unescaped = re.sub("[`\x00-\x20\x7f-\xa0\\s]+", '',
+                                       unescape(attrs[attr])).lower()
+                # remove replacement characters from unescaped characters
+                val_unescaped = val_unescaped.replace("\ufffd", "")
+                try:
+                    uri = urlparse.urlparse(val_unescaped)
+                except ValueError:
+                    uri = None
+                    del attrs[attr]
+                if uri and uri.scheme:
+                    if uri.scheme not in self.allowed_protocols:
+                        del attrs[attr]
+                    if uri.scheme == 'data':
+                        m = data_content_type.match(uri.path)
+                        if not m:
+                            del attrs[attr]
+                        elif m.group('content_type') not in self.allowed_content_types:
+                            del attrs[attr]
+
+            for attr in self.svg_attr_val_allows_ref:
+                if attr in attrs:
+                    attrs[attr] = re.sub(r'url\s*\(\s*[^#\s][^)]+?\)',
+                                         ' ',
+                                         unescape(attrs[attr]))
+            if (token["name"] in self.svg_allow_local_href and
+                (namespaces['xlink'], 'href') in attrs and re.search(r'^\s*[^#\s].*',
+                                                                     attrs[(namespaces['xlink'], 'href')])):
+                del attrs[(namespaces['xlink'], 'href')]
+            if (None, 'style') in attrs:
+                attrs[(None, 'style')] = self.sanitize_css(attrs[(None, 'style')])
+            token["data"] = attrs
+        return token
+
+    def disallowed_token(self, token):
+        token_type = token["type"]
+        if token_type == "EndTag":
+            token["data"] = "</%s>" % token["name"]
+        elif token["data"]:
+            assert token_type in ("StartTag", "EmptyTag")
+            attrs = []
+            for (ns, name), v in token["data"].items():
+                attrs.append(' %s="%s"' % (name if ns is None else "%s:%s" % (prefixes[ns], name), escape(v)))
+            token["data"] = "<%s%s>" % (token["name"], ''.join(attrs))
+        else:
+            token["data"] = "<%s>" % token["name"]
+        if token.get("selfClosing"):
+            token["data"] = token["data"][:-1] + "/>"
+
+        token["type"] = "Characters"
+
+        del token["name"]
+        return token
+
+    def sanitize_css(self, style):
+        # disallow urls
+        style = re.compile(r'url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style)
+
+        # gauntlet
+        if not re.match(r"""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style):
+            return ''
+        if not re.match(r"^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style):
+            return ''
+
+        clean = []
+        for prop, value in re.findall(r"([-\w]+)\s*:\s*([^:;]*)", style):
+            if not value:
+                continue
+            if prop.lower() in self.allowed_css_properties:
+                clean.append(prop + ': ' + value + ';')
+            elif prop.split('-')[0].lower() in ['background', 'border', 'margin',
+                                                'padding']:
+                for keyword in value.split():
+                    if keyword not in self.allowed_css_keywords and \
+                            not re.match(r"^(#[0-9a-fA-F]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword):  # noqa
+                        break
+                else:
+                    clean.append(prop + ': ' + value + ';')
+            elif prop.lower() in self.allowed_svg_properties:
+                clean.append(prop + ': ' + value + ';')
+
+        return ' '.join(clean)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/filters/whitespace.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/whitespace.py
similarity index 85%
rename from testing/web-platform/tests/tools/html5lib/html5lib/filters/whitespace.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/whitespace.py
index dfc60eebd35b..0d12584b4599 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/filters/whitespace.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/filters/whitespace.py
@@ -2,20 +2,20 @@ from __future__ import absolute_import, division, unicode_literals
 
 import re
 
-from . import _base
+from . import base
 from ..constants import rcdataElements, spaceCharacters
 spaceCharacters = "".join(spaceCharacters)
 
 SPACES_REGEX = re.compile("[%s]+" % spaceCharacters)
 
 
-class Filter(_base.Filter):
-
+class Filter(base.Filter):
+    """Collapses whitespace except in pre, textarea, and script elements"""
     spacePreserveElements = frozenset(["pre", "textarea"] + list(rcdataElements))
 
     def __iter__(self):
         preserve = 0
-        for token in _base.Filter.__iter__(self):
+        for token in base.Filter.__iter__(self):
             type = token["type"]
             if type == "StartTag" \
                     and (preserve or token["name"] in self.spacePreserveElements):
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/html5parser.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/html5parser.py
similarity index 85%
rename from testing/web-platform/tests/tools/html5lib/html5lib/html5parser.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/html5parser.py
index 5b9ce7d72068..9d39b9d41da7 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/html5parser.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/html5parser.py
@@ -1,38 +1,75 @@
 from __future__ import absolute_import, division, unicode_literals
-from six import with_metaclass
+from six import with_metaclass, viewkeys
 
 import types
+from collections import OrderedDict
 
-from . import inputstream
-from . import tokenizer
+from . import _inputstream
+from . import _tokenizer
 
 from . import treebuilders
-from .treebuilders._base import Marker
+from .treebuilders.base import Marker
 
-from . import utils
-from . import constants
-from .constants import spaceCharacters, asciiUpper2Lower
-from .constants import specialElements
-from .constants import headingElements
-from .constants import cdataElements, rcdataElements
-from .constants import tokenTypes, ReparseException, namespaces
-from .constants import htmlIntegrationPointElements, mathmlTextIntegrationPointElements
-from .constants import adjustForeignAttributes as adjustForeignAttributesMap
+from . import _utils
+from .constants import (
+    spaceCharacters, asciiUpper2Lower,
+    specialElements, headingElements, cdataElements, rcdataElements,
+    tokenTypes, tagTokenTypes,
+    namespaces,
+    htmlIntegrationPointElements, mathmlTextIntegrationPointElements,
+    adjustForeignAttributes as adjustForeignAttributesMap,
+    adjustMathMLAttributes, adjustSVGAttributes,
+    E,
+    _ReparseException
+)
 
 
-def parse(doc, treebuilder="etree", encoding=None,
-          namespaceHTMLElements=True):
-    """Parse a string or file-like object into a tree"""
+def parse(doc, treebuilder="etree", namespaceHTMLElements=True, **kwargs):
+    """Parse an HTML document as a string or file-like object into a tree
+
+    :arg doc: the document to parse as a string or file-like object
+
+    :arg treebuilder: the treebuilder to use when parsing
+
+    :arg namespaceHTMLElements: whether or not to namespace HTML elements
+
+    :returns: parsed tree
+
+    Example:
+
+    >>> from html5lib.html5parser import parse
+    >>> parse('<html><body><p>This is a doc</p></body></html>')
+    <Element u'{http://www.w3.org/1999/xhtml}html' at 0x7feac4909db0>
+
+    """
     tb = treebuilders.getTreeBuilder(treebuilder)
     p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
-    return p.parse(doc, encoding=encoding)
+    return p.parse(doc, **kwargs)
 
 
-def parseFragment(doc, container="div", treebuilder="etree", encoding=None,
-                  namespaceHTMLElements=True):
+def parseFragment(doc, container="div", treebuilder="etree", namespaceHTMLElements=True, **kwargs):
+    """Parse an HTML fragment as a string or file-like object into a tree
+
+    :arg doc: the fragment to parse as a string or file-like object
+
+    :arg container: the container context to parse the fragment in
+
+    :arg treebuilder: the treebuilder to use when parsing
+
+    :arg namespaceHTMLElements: whether or not to namespace HTML elements
+
+    :returns: parsed tree
+
+    Example:
+
+    >>> from html5lib.html5libparser import parseFragment
+    >>> parseFragment('<b>this is a fragment</b>')
+    <Element u'DOCUMENT_FRAGMENT' at 0x7feac484b090>
+
+    """
     tb = treebuilders.getTreeBuilder(treebuilder)
     p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
-    return p.parseFragment(doc, container=container, encoding=encoding)
+    return p.parseFragment(doc, container=container, **kwargs)
 
 
 def method_decorator_metaclass(function):
@@ -48,21 +85,30 @@ def method_decorator_metaclass(function):
 
 
 class HTMLParser(object):
-    """HTML parser. Generates a tree structure from a stream of (possibly
-        malformed) HTML"""
+    """HTML parser
 
-    def __init__(self, tree=None, tokenizer=tokenizer.HTMLTokenizer,
-                 strict=False, namespaceHTMLElements=True, debug=False):
+    Generates a tree structure from a stream of (possibly malformed) HTML.
+
+    """
+
+    def __init__(self, tree=None, strict=False, namespaceHTMLElements=True, debug=False):
         """
-        strict - raise an exception when a parse error is encountered
+        :arg tree: a treebuilder class controlling the type of tree that will be
+            returned. Built in treebuilders can be accessed through
+            html5lib.treebuilders.getTreeBuilder(treeType)
 
-        tree - a treebuilder class controlling the type of tree that will be
-        returned. Built in treebuilders can be accessed through
-        html5lib.treebuilders.getTreeBuilder(treeType)
+        :arg strict: raise an exception when a parse error is encountered
+
+        :arg namespaceHTMLElements: whether or not to namespace HTML elements
+
+        :arg debug: whether or not to enable debug mode which logs things
+
+        Example:
+
+        >>> from html5lib.html5parser import HTMLParser
+        >>> parser = HTMLParser()                     # generates parser with etree builder
+        >>> parser = HTMLParser('lxml', strict=True)  # generates parser with lxml builder which is strict
 
-        tokenizer - a class that provides a stream of tokens to the treebuilder.
-        This may be replaced for e.g. a sanitizer which converts some tags to
-        text
         """
 
         # Raise an exception on the first error encountered
@@ -71,29 +117,24 @@ class HTMLParser(object):
         if tree is None:
             tree = treebuilders.getTreeBuilder("etree")
         self.tree = tree(namespaceHTMLElements)
-        self.tokenizer_class = tokenizer
         self.errors = []
 
         self.phases = dict([(name, cls(self, self.tree)) for name, cls in
                             getPhases(debug).items()])
 
-    def _parse(self, stream, innerHTML=False, container="div",
-               encoding=None, parseMeta=True, useChardet=True, **kwargs):
+    def _parse(self, stream, innerHTML=False, container="div", scripting=False, **kwargs):
 
         self.innerHTMLMode = innerHTML
         self.container = container
-        self.tokenizer = self.tokenizer_class(stream, encoding=encoding,
-                                              parseMeta=parseMeta,
-                                              useChardet=useChardet,
-                                              parser=self, **kwargs)
+        self.scripting = scripting
+        self.tokenizer = _tokenizer.HTMLTokenizer(stream, parser=self, **kwargs)
         self.reset()
 
-        while True:
-            try:
-                self.mainLoop()
-                break
-            except ReparseException:
-                self.reset()
+        try:
+            self.mainLoop()
+        except _ReparseException:
+            self.reset()
+            self.mainLoop()
 
     def reset(self):
         self.tree.reset()
@@ -120,7 +161,7 @@ class HTMLParser(object):
             self.phase.insertHtmlElement()
             self.resetInsertionMode()
         else:
-            self.innerHTML = False
+            self.innerHTML = False  # pylint:disable=redefined-variable-type
             self.phase = self.phases["initial"]
 
         self.lastPhase = None
@@ -131,14 +172,13 @@ class HTMLParser(object):
 
     @property
     def documentEncoding(self):
-        """The name of the character encoding
-        that was used to decode the input stream,
-        or :obj:`None` if that is not determined yet.
+        """Name of the character encoding that was used to decode the input stream, or
+        :obj:`None` if that is not determined yet
 
         """
         if not hasattr(self, 'tokenizer'):
             return None
-        return self.tokenizer.stream.charEncoding[0]
+        return self.tokenizer.stream.charEncoding[0].name
 
     def isHTMLIntegrationPoint(self, element):
         if (element.name == "annotation-xml" and
@@ -163,8 +203,10 @@ class HTMLParser(object):
         ParseErrorToken = tokenTypes["ParseError"]
 
         for token in self.normalizedTokens():
+            prev_token = None
             new_token = token
             while new_token is not None:
+                prev_token = new_token
                 currentNode = self.tree.openElements[-1] if self.tree.openElements else None
                 currentNodeNamespace = currentNode.namespace if currentNode else None
                 currentNodeName = currentNode.name if currentNode else None
@@ -183,6 +225,7 @@ class HTMLParser(object):
                           type in (CharactersToken, SpaceCharactersToken))) or
                         (currentNodeNamespace == namespaces["mathml"] and
                          currentNodeName == "annotation-xml" and
+                         type == StartTagToken and
                          token["name"] == "svg") or
                         (self.isHTMLIntegrationPoint(currentNode) and
                          type in (StartTagToken, CharactersToken, SpaceCharactersToken))):
@@ -203,10 +246,10 @@ class HTMLParser(object):
                     elif type == DoctypeToken:
                         new_token = phase.processDoctype(new_token)
 
-            if (type == StartTagToken and token["selfClosing"]
-                    and not token["selfClosingAcknowledged"]):
+            if (type == StartTagToken and prev_token["selfClosing"] and
+                    not prev_token["selfClosingAcknowledged"]):
                 self.parseError("non-void-element-with-trailing-solidus",
-                                {"name": token["name"]})
+                                {"name": prev_token["name"]})
 
         # When the loop finishes it's EOF
         reprocess = True
@@ -221,139 +264,89 @@ class HTMLParser(object):
         for token in self.tokenizer:
             yield self.normalizeToken(token)
 
-    def parse(self, stream, encoding=None, parseMeta=True, useChardet=True):
+    def parse(self, stream, *args, **kwargs):
         """Parse a HTML document into a well-formed tree
 
-        stream - a filelike object or string containing the HTML to be parsed
+        :arg stream: a file-like object or string containing the HTML to be parsed
+
+            The optional encoding parameter must be a string that indicates
+            the encoding.  If specified, that encoding will be used,
+            regardless of any BOM or later declaration (such as in a meta
+            element).
+
+        :arg scripting: treat noscript elements as if JavaScript was turned on
+
+        :returns: parsed tree
+
+        Example:
+
+        >>> from html5lib.html5parser import HTMLParser
+        >>> parser = HTMLParser()
+        >>> parser.parse('<html><body><p>This is a doc</p></body></html>')
+        <Element u'{http://www.w3.org/1999/xhtml}html' at 0x7feac4909db0>
 
-        The optional encoding parameter must be a string that indicates
-        the encoding.  If specified, that encoding will be used,
-        regardless of any BOM or later declaration (such as in a meta
-        element)
         """
-        self._parse(stream, innerHTML=False, encoding=encoding,
-                    parseMeta=parseMeta, useChardet=useChardet)
+        self._parse(stream, False, None, *args, **kwargs)
         return self.tree.getDocument()
 
-    def parseFragment(self, stream, container="div", encoding=None,
-                      parseMeta=False, useChardet=True):
+    def parseFragment(self, stream, *args, **kwargs):
         """Parse a HTML fragment into a well-formed tree fragment
 
-        container - name of the element we're setting the innerHTML property
-        if set to None, default to 'div'
+        :arg container: name of the element we're setting the innerHTML
+            property if set to None, default to 'div'
 
-        stream - a filelike object or string containing the HTML to be parsed
+        :arg stream: a file-like object or string containing the HTML to be parsed
+
+            The optional encoding parameter must be a string that indicates
+            the encoding.  If specified, that encoding will be used,
+            regardless of any BOM or later declaration (such as in a meta
+            element)
+
+        :arg scripting: treat noscript elements as if JavaScript was turned on
+
+        :returns: parsed tree
+
+        Example:
+
+        >>> from html5lib.html5libparser import HTMLParser
+        >>> parser = HTMLParser()
+        >>> parser.parseFragment('<b>this is a fragment</b>')
+        <Element u'DOCUMENT_FRAGMENT' at 0x7feac484b090>
 
-        The optional encoding parameter must be a string that indicates
-        the encoding.  If specified, that encoding will be used,
-        regardless of any BOM or later declaration (such as in a meta
-        element)
         """
-        self._parse(stream, True, container=container, encoding=encoding)
+        self._parse(stream, True, *args, **kwargs)
         return self.tree.getFragment()
 
-    def parseError(self, errorcode="XXX-undefined-error", datavars={}):
+    def parseError(self, errorcode="XXX-undefined-error", datavars=None):
         # XXX The idea is to make errorcode mandatory.
+        if datavars is None:
+            datavars = {}
         self.errors.append((self.tokenizer.stream.position(), errorcode, datavars))
         if self.strict:
-            raise ParseError
+            raise ParseError(E[errorcode] % datavars)
 
     def normalizeToken(self, token):
-        """ HTML5 specific normalizations to the token stream """
-
+        # HTML5 specific normalizations to the token stream
         if token["type"] == tokenTypes["StartTag"]:
-            token["data"] = dict(token["data"][::-1])
+            raw = token["data"]
+            token["data"] = OrderedDict(raw)
+            if len(raw) > len(token["data"]):
+                # we had some duplicated attribute, fix so first wins
+                token["data"].update(raw[::-1])
 
         return token
 
     def adjustMathMLAttributes(self, token):
-        replacements = {"definitionurl": "definitionURL"}
-        for k, v in replacements.items():
-            if k in token["data"]:
-                token["data"][v] = token["data"][k]
-                del token["data"][k]
+        adjust_attributes(token, adjustMathMLAttributes)
 
     def adjustSVGAttributes(self, token):
-        replacements = {
-            "attributename": "attributeName",
-            "attributetype": "attributeType",
-            "basefrequency": "baseFrequency",
-            "baseprofile": "baseProfile",
-            "calcmode": "calcMode",
-            "clippathunits": "clipPathUnits",
-            "contentscripttype": "contentScriptType",
-            "contentstyletype": "contentStyleType",
-            "diffuseconstant": "diffuseConstant",
-            "edgemode": "edgeMode",
-            "externalresourcesrequired": "externalResourcesRequired",
-            "filterres": "filterRes",
-            "filterunits": "filterUnits",
-            "glyphref": "glyphRef",
-            "gradienttransform": "gradientTransform",
-            "gradientunits": "gradientUnits",
-            "kernelmatrix": "kernelMatrix",
-            "kernelunitlength": "kernelUnitLength",
-            "keypoints": "keyPoints",
-            "keysplines": "keySplines",
-            "keytimes": "keyTimes",
-            "lengthadjust": "lengthAdjust",
-            "limitingconeangle": "limitingConeAngle",
-            "markerheight": "markerHeight",
-            "markerunits": "markerUnits",
-            "markerwidth": "markerWidth",
-            "maskcontentunits": "maskContentUnits",
-            "maskunits": "maskUnits",
-            "numoctaves": "numOctaves",
-            "pathlength": "pathLength",
-            "patterncontentunits": "patternContentUnits",
-            "patterntransform": "patternTransform",
-            "patternunits": "patternUnits",
-            "pointsatx": "pointsAtX",
-            "pointsaty": "pointsAtY",
-            "pointsatz": "pointsAtZ",
-            "preservealpha": "preserveAlpha",
-            "preserveaspectratio": "preserveAspectRatio",
-            "primitiveunits": "primitiveUnits",
-            "refx": "refX",
-            "refy": "refY",
-            "repeatcount": "repeatCount",
-            "repeatdur": "repeatDur",
-            "requiredextensions": "requiredExtensions",
-            "requiredfeatures": "requiredFeatures",
-            "specularconstant": "specularConstant",
-            "specularexponent": "specularExponent",
-            "spreadmethod": "spreadMethod",
-            "startoffset": "startOffset",
-            "stddeviation": "stdDeviation",
-            "stitchtiles": "stitchTiles",
-            "surfacescale": "surfaceScale",
-            "systemlanguage": "systemLanguage",
-            "tablevalues": "tableValues",
-            "targetx": "targetX",
-            "targety": "targetY",
-            "textlength": "textLength",
-            "viewbox": "viewBox",
-            "viewtarget": "viewTarget",
-            "xchannelselector": "xChannelSelector",
-            "ychannelselector": "yChannelSelector",
-            "zoomandpan": "zoomAndPan"
-        }
-        for originalName in list(token["data"].keys()):
-            if originalName in replacements:
-                svgName = replacements[originalName]
-                token["data"][svgName] = token["data"][originalName]
-                del token["data"][originalName]
+        adjust_attributes(token, adjustSVGAttributes)
 
     def adjustForeignAttributes(self, token):
-        replacements = adjustForeignAttributesMap
-
-        for originalName in token["data"].keys():
-            if originalName in replacements:
-                foreignName = replacements[originalName]
-                token["data"][foreignName] = token["data"][originalName]
-                del token["data"][originalName]
+        adjust_attributes(token, adjustForeignAttributesMap)
 
     def reparseTokenNormal(self, token):
+        # pylint:disable=unused-argument
         self.parser.phase()
 
     def resetInsertionMode(self):
@@ -401,9 +394,7 @@ class HTMLParser(object):
         self.phase = new_phase
 
     def parseRCDataRawtext(self, token, contentType):
-        """Generic RCDATA/RAWTEXT Parsing algorithm
-        contentType - RCDATA or RAWTEXT
-        """
+        # Generic RCDATA/RAWTEXT Parsing algorithm
         assert contentType in ("RAWTEXT", "RCDATA")
 
         self.tree.insertElement(token)
@@ -418,11 +409,12 @@ class HTMLParser(object):
         self.phase = self.phases["text"]
 
 
+@_utils.memoize
 def getPhases(debug):
     def log(function):
         """Logger that records which phase processes each token"""
         type_names = dict((value, key) for key, value in
-                          constants.tokenTypes.items())
+                          tokenTypes.items())
 
         def wrapped(self, *args, **kwargs):
             if function.__name__.startswith("process") and len(args) > 0:
@@ -431,7 +423,7 @@ def getPhases(debug):
                     info = {"type": type_names[token['type']]}
                 except:
                     raise
-                if token['type'] in constants.tagTokenTypes:
+                if token['type'] in tagTokenTypes:
                     info["name"] = token['name']
 
                 self.parser.log.append((self.parser.tokenizer.state.__name__,
@@ -450,6 +442,7 @@ def getPhases(debug):
         else:
             return type
 
+    # pylint:disable=unused-argument
     class Phase(with_metaclass(getMetaclass(debug, log))):
         """Base class for helper object that implements each phase of processing
         """
@@ -516,77 +509,76 @@ def getPhases(debug):
             if publicId != "":
                 publicId = publicId.translate(asciiUpper2Lower)
 
-            if (not correct or token["name"] != "html"
-                or publicId.startswith(
-                    ("+//silmaril//dtd html pro v0r11 19970101//",
-                     "-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
-                     "-//as//dtd html 3.0 aswedit + extensions//",
-                     "-//ietf//dtd html 2.0 level 1//",
-                     "-//ietf//dtd html 2.0 level 2//",
-                     "-//ietf//dtd html 2.0 strict level 1//",
-                     "-//ietf//dtd html 2.0 strict level 2//",
-                     "-//ietf//dtd html 2.0 strict//",
-                     "-//ietf//dtd html 2.0//",
-                     "-//ietf//dtd html 2.1e//",
-                     "-//ietf//dtd html 3.0//",
-                     "-//ietf//dtd html 3.2 final//",
-                     "-//ietf//dtd html 3.2//",
-                     "-//ietf//dtd html 3//",
-                     "-//ietf//dtd html level 0//",
-                     "-//ietf//dtd html level 1//",
-                     "-//ietf//dtd html level 2//",
-                     "-//ietf//dtd html level 3//",
-                     "-//ietf//dtd html strict level 0//",
-                     "-//ietf//dtd html strict level 1//",
-                     "-//ietf//dtd html strict level 2//",
-                     "-//ietf//dtd html strict level 3//",
-                     "-//ietf//dtd html strict//",
-                     "-//ietf//dtd html//",
-                     "-//metrius//dtd metrius presentational//",
-                     "-//microsoft//dtd internet explorer 2.0 html strict//",
-                     "-//microsoft//dtd internet explorer 2.0 html//",
-                     "-//microsoft//dtd internet explorer 2.0 tables//",
-                     "-//microsoft//dtd internet explorer 3.0 html strict//",
-                     "-//microsoft//dtd internet explorer 3.0 html//",
-                     "-//microsoft//dtd internet explorer 3.0 tables//",
-                     "-//netscape comm. corp.//dtd html//",
-                     "-//netscape comm. corp.//dtd strict html//",
-                     "-//o'reilly and associates//dtd html 2.0//",
-                     "-//o'reilly and associates//dtd html extended 1.0//",
-                     "-//o'reilly and associates//dtd html extended relaxed 1.0//",
-                     "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
-                     "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
-                     "-//spyglass//dtd html 2.0 extended//",
-                     "-//sq//dtd html 2.0 hotmetal + extensions//",
-                     "-//sun microsystems corp.//dtd hotjava html//",
-                     "-//sun microsystems corp.//dtd hotjava strict html//",
-                     "-//w3c//dtd html 3 1995-03-24//",
-                     "-//w3c//dtd html 3.2 draft//",
-                     "-//w3c//dtd html 3.2 final//",
-                     "-//w3c//dtd html 3.2//",
-                     "-//w3c//dtd html 3.2s draft//",
-                     "-//w3c//dtd html 4.0 frameset//",
-                     "-//w3c//dtd html 4.0 transitional//",
-                     "-//w3c//dtd html experimental 19960712//",
-                     "-//w3c//dtd html experimental 970421//",
-                     "-//w3c//dtd w3 html//",
-                     "-//w3o//dtd w3 html 3.0//",
-                     "-//webtechs//dtd mozilla html 2.0//",
-                     "-//webtechs//dtd mozilla html//"))
-                or publicId in
-                    ("-//w3o//dtd w3 html strict 3.0//en//",
-                     "-/w3c/dtd html 4.0 transitional/en",
-                     "html")
-                or publicId.startswith(
-                    ("-//w3c//dtd html 4.01 frameset//",
-                     "-//w3c//dtd html 4.01 transitional//")) and
-                    systemId is None
-                    or systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"):
+            if (not correct or token["name"] != "html" or
+                    publicId.startswith(
+                        ("+//silmaril//dtd html pro v0r11 19970101//",
+                         "-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
+                         "-//as//dtd html 3.0 aswedit + extensions//",
+                         "-//ietf//dtd html 2.0 level 1//",
+                         "-//ietf//dtd html 2.0 level 2//",
+                         "-//ietf//dtd html 2.0 strict level 1//",
+                         "-//ietf//dtd html 2.0 strict level 2//",
+                         "-//ietf//dtd html 2.0 strict//",
+                         "-//ietf//dtd html 2.0//",
+                         "-//ietf//dtd html 2.1e//",
+                         "-//ietf//dtd html 3.0//",
+                         "-//ietf//dtd html 3.2 final//",
+                         "-//ietf//dtd html 3.2//",
+                         "-//ietf//dtd html 3//",
+                         "-//ietf//dtd html level 0//",
+                         "-//ietf//dtd html level 1//",
+                         "-//ietf//dtd html level 2//",
+                         "-//ietf//dtd html level 3//",
+                         "-//ietf//dtd html strict level 0//",
+                         "-//ietf//dtd html strict level 1//",
+                         "-//ietf//dtd html strict level 2//",
+                         "-//ietf//dtd html strict level 3//",
+                         "-//ietf//dtd html strict//",
+                         "-//ietf//dtd html//",
+                         "-//metrius//dtd metrius presentational//",
+                         "-//microsoft//dtd internet explorer 2.0 html strict//",
+                         "-//microsoft//dtd internet explorer 2.0 html//",
+                         "-//microsoft//dtd internet explorer 2.0 tables//",
+                         "-//microsoft//dtd internet explorer 3.0 html strict//",
+                         "-//microsoft//dtd internet explorer 3.0 html//",
+                         "-//microsoft//dtd internet explorer 3.0 tables//",
+                         "-//netscape comm. corp.//dtd html//",
+                         "-//netscape comm. corp.//dtd strict html//",
+                         "-//o'reilly and associates//dtd html 2.0//",
+                         "-//o'reilly and associates//dtd html extended 1.0//",
+                         "-//o'reilly and associates//dtd html extended relaxed 1.0//",
+                         "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
+                         "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
+                         "-//spyglass//dtd html 2.0 extended//",
+                         "-//sq//dtd html 2.0 hotmetal + extensions//",
+                         "-//sun microsystems corp.//dtd hotjava html//",
+                         "-//sun microsystems corp.//dtd hotjava strict html//",
+                         "-//w3c//dtd html 3 1995-03-24//",
+                         "-//w3c//dtd html 3.2 draft//",
+                         "-//w3c//dtd html 3.2 final//",
+                         "-//w3c//dtd html 3.2//",
+                         "-//w3c//dtd html 3.2s draft//",
+                         "-//w3c//dtd html 4.0 frameset//",
+                         "-//w3c//dtd html 4.0 transitional//",
+                         "-//w3c//dtd html experimental 19960712//",
+                         "-//w3c//dtd html experimental 970421//",
+                         "-//w3c//dtd w3 html//",
+                         "-//w3o//dtd w3 html 3.0//",
+                         "-//webtechs//dtd mozilla html 2.0//",
+                         "-//webtechs//dtd mozilla html//")) or
+                    publicId in ("-//w3o//dtd w3 html strict 3.0//en//",
+                                 "-/w3c/dtd html 4.0 transitional/en",
+                                 "html") or
+                    publicId.startswith(
+                        ("-//w3c//dtd html 4.01 frameset//",
+                         "-//w3c//dtd html 4.01 transitional//")) and
+                    systemId is None or
+                    systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"):
                 self.parser.compatMode = "quirks"
             elif (publicId.startswith(
                     ("-//w3c//dtd xhtml 1.0 frameset//",
-                     "-//w3c//dtd xhtml 1.0 transitional//"))
-                  or publicId.startswith(
+                     "-//w3c//dtd xhtml 1.0 transitional//")) or
+                  publicId.startswith(
                       ("-//w3c//dtd html 4.01 frameset//",
                        "-//w3c//dtd html 4.01 transitional//")) and
                   systemId is not None):
@@ -659,13 +651,13 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("head", self.startTagHead)
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 (("head", "body", "html", "br"), self.endTagImplyHead)
             ])
             self.endTagHandler.default = self.endTagOther
@@ -705,10 +697,11 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("title", self.startTagTitle),
-                (("noscript", "noframes", "style"), self.startTagNoScriptNoFramesStyle),
+                (("noframes", "style"), self.startTagNoFramesStyle),
+                ("noscript", self.startTagNoscript),
                 ("script", self.startTagScript),
                 (("base", "basefont", "bgsound", "command", "link"),
                  self.startTagBaseLinkCommand),
@@ -717,7 +710,7 @@ def getPhases(debug):
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self. endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("head", self.endTagHead),
                 (("br", "html", "body"), self.endTagHtmlBodyBr)
             ])
@@ -759,18 +752,25 @@ def getPhases(debug):
                     # the abstract Unicode string, and just use the
                     # ContentAttrParser on that, but using UTF-8 allows all chars
                     # to be encoded and as a ASCII-superset works.
-                    data = inputstream.EncodingBytes(attributes["content"].encode("utf-8"))
-                    parser = inputstream.ContentAttrParser(data)
+                    data = _inputstream.EncodingBytes(attributes["content"].encode("utf-8"))
+                    parser = _inputstream.ContentAttrParser(data)
                     codec = parser.parse()
                     self.parser.tokenizer.stream.changeEncoding(codec)
 
         def startTagTitle(self, token):
             self.parser.parseRCDataRawtext(token, "RCDATA")
 
-        def startTagNoScriptNoFramesStyle(self, token):
+        def startTagNoFramesStyle(self, token):
             # Need to decide whether to implement the scripting-disabled case
             self.parser.parseRCDataRawtext(token, "RAWTEXT")
 
+        def startTagNoscript(self, token):
+            if self.parser.scripting:
+                self.parser.parseRCDataRawtext(token, "RAWTEXT")
+            else:
+                self.tree.insertElement(token)
+                self.parser.phase = self.parser.phases["inHeadNoscript"]
+
         def startTagScript(self, token):
             self.tree.insertElement(token)
             self.parser.tokenizer.state = self.parser.tokenizer.scriptDataState
@@ -796,15 +796,75 @@ def getPhases(debug):
         def anythingElse(self):
             self.endTagHead(impliedTagToken("head"))
 
-    # XXX If we implement a parser for which scripting is disabled we need to
-    # implement this phase.
-    #
-    # class InHeadNoScriptPhase(Phase):
+    class InHeadNoscriptPhase(Phase):
+        def __init__(self, parser, tree):
+            Phase.__init__(self, parser, tree)
+
+            self.startTagHandler = _utils.MethodDispatcher([
+                ("html", self.startTagHtml),
+                (("basefont", "bgsound", "link", "meta", "noframes", "style"), self.startTagBaseLinkCommand),
+                (("head", "noscript"), self.startTagHeadNoscript),
+            ])
+            self.startTagHandler.default = self.startTagOther
+
+            self.endTagHandler = _utils.MethodDispatcher([
+                ("noscript", self.endTagNoscript),
+                ("br", self.endTagBr),
+            ])
+            self.endTagHandler.default = self.endTagOther
+
+        def processEOF(self):
+            self.parser.parseError("eof-in-head-noscript")
+            self.anythingElse()
+            return True
+
+        def processComment(self, token):
+            return self.parser.phases["inHead"].processComment(token)
+
+        def processCharacters(self, token):
+            self.parser.parseError("char-in-head-noscript")
+            self.anythingElse()
+            return token
+
+        def processSpaceCharacters(self, token):
+            return self.parser.phases["inHead"].processSpaceCharacters(token)
+
+        def startTagHtml(self, token):
+            return self.parser.phases["inBody"].processStartTag(token)
+
+        def startTagBaseLinkCommand(self, token):
+            return self.parser.phases["inHead"].processStartTag(token)
+
+        def startTagHeadNoscript(self, token):
+            self.parser.parseError("unexpected-start-tag", {"name": token["name"]})
+
+        def startTagOther(self, token):
+            self.parser.parseError("unexpected-inhead-noscript-tag", {"name": token["name"]})
+            self.anythingElse()
+            return token
+
+        def endTagNoscript(self, token):
+            node = self.parser.tree.openElements.pop()
+            assert node.name == "noscript", "Expected noscript got %s" % node.name
+            self.parser.phase = self.parser.phases["inHead"]
+
+        def endTagBr(self, token):
+            self.parser.parseError("unexpected-inhead-noscript-tag", {"name": token["name"]})
+            self.anythingElse()
+            return token
+
+        def endTagOther(self, token):
+            self.parser.parseError("unexpected-end-tag", {"name": token["name"]})
+
+        def anythingElse(self):
+            # Caller must raise parse error first!
+            self.endTagNoscript(impliedTagToken("noscript"))
+
     class AfterHeadPhase(Phase):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("body", self.startTagBody),
                 ("frameset", self.startTagFrameset),
@@ -814,8 +874,8 @@ def getPhases(debug):
                 ("head", self.startTagHead)
             ])
             self.startTagHandler.default = self.startTagOther
-            self.endTagHandler = utils.MethodDispatcher([(("body", "html", "br"),
-                                                          self.endTagHtmlBodyBr)])
+            self.endTagHandler = _utils.MethodDispatcher([(("body", "html", "br"),
+                                                           self.endTagHtmlBodyBr)])
             self.endTagHandler.default = self.endTagOther
 
         def processEOF(self):
@@ -873,18 +933,18 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            # Keep a ref to this for special handling of whitespace in <pre>
-            self.processSpaceCharactersNonPre = self.processSpaceCharacters
+            # Set this to the default handler
+            self.processSpaceCharacters = self.processSpaceCharactersNonPre
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 (("base", "basefont", "bgsound", "command", "link", "meta",
-                  "noframes", "script", "style", "title"),
+                  "script", "style", "title"),
                  self.startTagProcessInHead),
                 ("body", self.startTagBody),
                 ("frameset", self.startTagFrameset),
                 (("address", "article", "aside", "blockquote", "center", "details",
-                  "details", "dir", "div", "dl", "fieldset", "figcaption", "figure",
+                  "dir", "div", "dl", "fieldset", "figcaption", "figure",
                   "footer", "header", "hgroup", "main", "menu", "nav", "ol", "p",
                   "section", "summary", "ul"),
                  self.startTagCloseP),
@@ -910,7 +970,8 @@ def getPhases(debug):
                 ("isindex", self.startTagIsIndex),
                 ("textarea", self.startTagTextarea),
                 ("iframe", self.startTagIFrame),
-                (("noembed", "noframes", "noscript"), self.startTagRawtext),
+                ("noscript", self.startTagNoscript),
+                (("noembed", "noframes"), self.startTagRawtext),
                 ("select", self.startTagSelect),
                 (("rp", "rt"), self.startTagRpRt),
                 (("option", "optgroup"), self.startTagOpt),
@@ -922,7 +983,7 @@ def getPhases(debug):
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("body", self.endTagBody),
                 ("html", self.endTagHtml),
                 (("address", "article", "aside", "blockquote", "button", "center",
@@ -941,17 +1002,9 @@ def getPhases(debug):
             self.endTagHandler.default = self.endTagOther
 
         def isMatchingFormattingElement(self, node1, node2):
-            if node1.name != node2.name or node1.namespace != node2.namespace:
-                return False
-            elif len(node1.attributes) != len(node2.attributes):
-                return False
-            else:
-                attributes1 = sorted(node1.attributes.items())
-                attributes2 = sorted(node2.attributes.items())
-                for attr1, attr2 in zip(attributes1, attributes2):
-                    if attr1 != attr2:
-                        return False
-            return True
+            return (node1.name == node2.name and
+                    node1.namespace == node2.namespace and
+                    node1.attributes == node2.attributes)
 
         # helper
         def addFormattingElement(self, token):
@@ -987,8 +1040,8 @@ def getPhases(debug):
             data = token["data"]
             self.processSpaceCharacters = self.processSpaceCharactersNonPre
             if (data.startswith("\n") and
-                self.tree.openElements[-1].name in ("pre", "listing", "textarea")
-                    and not self.tree.openElements[-1].hasContent()):
+                self.tree.openElements[-1].name in ("pre", "listing", "textarea") and
+                    not self.tree.openElements[-1].hasContent()):
                 data = data[1:]
             if data:
                 self.tree.reconstructActiveFormattingElements()
@@ -1006,7 +1059,7 @@ def getPhases(debug):
                      for char in token["data"]])):
                 self.parser.framesetOK = False
 
-        def processSpaceCharacters(self, token):
+        def processSpaceCharactersNonPre(self, token):
             self.tree.reconstructActiveFormattingElements()
             self.tree.insertText(token["data"])
 
@@ -1015,8 +1068,8 @@ def getPhases(debug):
 
         def startTagBody(self, token):
             self.parser.parseError("unexpected-start-tag", {"name": "body"})
-            if (len(self.tree.openElements) == 1
-                    or self.tree.openElements[1].name != "body"):
+            if (len(self.tree.openElements) == 1 or
+                    self.tree.openElements[1].name != "body"):
                 assert self.parser.innerHTML
             else:
                 self.parser.framesetOK = False
@@ -1231,6 +1284,12 @@ def getPhases(debug):
             self.parser.framesetOK = False
             self.startTagRawtext(token)
 
+        def startTagNoscript(self, token):
+            if self.parser.scripting:
+                self.startTagRawtext(token)
+            else:
+                self.startTagOther(token)
+
         def startTagRawtext(self, token):
             """iframe, noembed noframes, noscript(if scripting enabled)"""
             self.parser.parseRCDataRawtext(token, "RAWTEXT")
@@ -1326,7 +1385,7 @@ def getPhases(debug):
                         # Not sure this is the correct name for the parse error
                         self.parser.parseError(
                             "expected-one-end-tag-but-got-another",
-                            {"expectedName": "body", "gotName": node.name})
+                            {"gotName": "body", "expectedName": node.name})
                         break
             self.parser.phase = self.parser.phases["afterBody"]
 
@@ -1594,9 +1653,9 @@ def getPhases(debug):
     class TextPhase(Phase):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
-            self.startTagHandler = utils.MethodDispatcher([])
+            self.startTagHandler = _utils.MethodDispatcher([])
             self.startTagHandler.default = self.startTagOther
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("script", self.endTagScript)])
             self.endTagHandler.default = self.endTagOther
 
@@ -1628,7 +1687,7 @@ def getPhases(debug):
         # http://www.whatwg.org/specs/web-apps/current-work/#in-table
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("caption", self.startTagCaption),
                 ("colgroup", self.startTagColgroup),
@@ -1642,7 +1701,7 @@ def getPhases(debug):
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("table", self.endTagTable),
                 (("body", "caption", "col", "colgroup", "html", "tbody", "td",
                   "tfoot", "th", "thead", "tr"), self.endTagIgnore)
@@ -1819,14 +1878,14 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 (("caption", "col", "colgroup", "tbody", "td", "tfoot", "th",
                   "thead", "tr"), self.startTagTableElement)
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("caption", self.endTagCaption),
                 ("table", self.endTagTable),
                 (("body", "col", "colgroup", "html", "tbody", "td", "tfoot", "th",
@@ -1891,13 +1950,13 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("col", self.startTagCol)
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("colgroup", self.endTagColgroup),
                 ("col", self.endTagCol)
             ])
@@ -1925,6 +1984,7 @@ def getPhases(debug):
         def startTagCol(self, token):
             self.tree.insertElement(token)
             self.tree.openElements.pop()
+            token["selfClosingAcknowledged"] = True
 
         def startTagOther(self, token):
             ignoreEndTag = self.ignoreEndTagColgroup()
@@ -1954,7 +2014,7 @@ def getPhases(debug):
         # http://www.whatwg.org/specs/web-apps/current-work/#in-table0
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("tr", self.startTagTr),
                 (("td", "th"), self.startTagTableCell),
@@ -1963,7 +2023,7 @@ def getPhases(debug):
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 (("tbody", "tfoot", "thead"), self.endTagTableRowGroup),
                 ("table", self.endTagTable),
                 (("body", "caption", "col", "colgroup", "html", "td", "th",
@@ -2052,7 +2112,7 @@ def getPhases(debug):
         # http://www.whatwg.org/specs/web-apps/current-work/#in-row
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 (("td", "th"), self.startTagTableCell),
                 (("caption", "col", "colgroup", "tbody", "tfoot", "thead",
@@ -2060,7 +2120,7 @@ def getPhases(debug):
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("tr", self.endTagTr),
                 ("table", self.endTagTable),
                 (("tbody", "tfoot", "thead"), self.endTagTableRowGroup),
@@ -2141,14 +2201,14 @@ def getPhases(debug):
         # http://www.whatwg.org/specs/web-apps/current-work/#in-cell
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 (("caption", "col", "colgroup", "tbody", "td", "tfoot", "th",
                   "thead", "tr"), self.startTagTableOther)
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 (("td", "th"), self.endTagTableCell),
                 (("body", "caption", "col", "colgroup", "html"), self.endTagIgnore),
                 (("table", "tbody", "tfoot", "thead", "tr"), self.endTagImply)
@@ -2217,7 +2277,7 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("option", self.startTagOption),
                 ("optgroup", self.startTagOptgroup),
@@ -2227,7 +2287,7 @@ def getPhases(debug):
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("option", self.endTagOption),
                 ("optgroup", self.endTagOptgroup),
                 ("select", self.endTagSelect)
@@ -2317,13 +2377,13 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 (("caption", "table", "tbody", "tfoot", "thead", "tr", "td", "th"),
                  self.startTagTable)
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 (("caption", "table", "tbody", "tfoot", "thead", "tr", "td", "th"),
                  self.endTagTable)
             ])
@@ -2444,7 +2504,7 @@ def getPhases(debug):
         def processEndTag(self, token):
             nodeIndex = len(self.tree.openElements) - 1
             node = self.tree.openElements[-1]
-            if node.name != token["name"]:
+            if node.name.translate(asciiUpper2Lower) != token["name"]:
                 self.parser.parseError("unexpected-end-tag", {"name": token["name"]})
 
             while True:
@@ -2471,12 +2531,12 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml)
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([("html", self.endTagHtml)])
+            self.endTagHandler = _utils.MethodDispatcher([("html", self.endTagHtml)])
             self.endTagHandler.default = self.endTagOther
 
         def processEOF(self):
@@ -2519,7 +2579,7 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("frameset", self.startTagFrameset),
                 ("frame", self.startTagFrame),
@@ -2527,7 +2587,7 @@ def getPhases(debug):
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("frameset", self.endTagFrameset)
             ])
             self.endTagHandler.default = self.endTagOther
@@ -2563,7 +2623,7 @@ def getPhases(debug):
                 self.tree.openElements.pop()
             if (not self.parser.innerHTML and
                     self.tree.openElements[-1].name != "frameset"):
-                # If we're not in innerHTML mode and the the current node is not a
+                # If we're not in innerHTML mode and the current node is not a
                 # "frameset" element (anymore) then switch.
                 self.parser.phase = self.parser.phases["afterFrameset"]
 
@@ -2576,13 +2636,13 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("noframes", self.startTagNoframes)
             ])
             self.startTagHandler.default = self.startTagOther
 
-            self.endTagHandler = utils.MethodDispatcher([
+            self.endTagHandler = _utils.MethodDispatcher([
                 ("html", self.endTagHtml)
             ])
             self.endTagHandler.default = self.endTagOther
@@ -2612,7 +2672,7 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml)
             ])
             self.startTagHandler.default = self.startTagOther
@@ -2650,7 +2710,7 @@ def getPhases(debug):
         def __init__(self, parser, tree):
             Phase.__init__(self, parser, tree)
 
-            self.startTagHandler = utils.MethodDispatcher([
+            self.startTagHandler = _utils.MethodDispatcher([
                 ("html", self.startTagHtml),
                 ("noframes", self.startTagNoFrames)
             ])
@@ -2681,13 +2741,14 @@ def getPhases(debug):
         def processEndTag(self, token):
             self.parser.parseError("expected-eof-but-got-end-tag",
                                    {"name": token["name"]})
+    # pylint:enable=unused-argument
 
     return {
         "initial": InitialPhase,
         "beforeHtml": BeforeHtmlPhase,
         "beforeHead": BeforeHeadPhase,
         "inHead": InHeadPhase,
-        # XXX "inHeadNoscript": InHeadNoScriptPhase,
+        "inHeadNoscript": InHeadNoscriptPhase,
         "afterHead": AfterHeadPhase,
         "inBody": InBodyPhase,
         "text": TextPhase,
@@ -2710,6 +2771,13 @@ def getPhases(debug):
     }
 
 
+def adjust_attributes(token, replacements):
+    needs_adjustment = viewkeys(token['data']) & viewkeys(replacements)
+    if needs_adjustment:
+        token['data'] = OrderedDict((replacements.get(k, k), v)
+                                    for k, v in token['data'].items())
+
+
 def impliedTagToken(name, type="EndTag", attributes=None,
                     selfClosing=False):
     if attributes is None:
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/serializer.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/serializer.py
new file mode 100644
index 000000000000..d6b7105d4809
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/serializer.py
@@ -0,0 +1,409 @@
+from __future__ import absolute_import, division, unicode_literals
+from six import text_type
+
+import re
+
+from codecs import register_error, xmlcharrefreplace_errors
+
+from .constants import voidElements, booleanAttributes, spaceCharacters
+from .constants import rcdataElements, entities, xmlEntities
+from . import treewalkers, _utils
+from xml.sax.saxutils import escape
+
+_quoteAttributeSpecChars = "".join(spaceCharacters) + "\"'=<>`"
+_quoteAttributeSpec = re.compile("[" + _quoteAttributeSpecChars + "]")
+_quoteAttributeLegacy = re.compile("[" + _quoteAttributeSpecChars +
+                                   "\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n"
+                                   "\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15"
+                                   "\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+                                   "\x20\x2f\x60\xa0\u1680\u180e\u180f\u2000"
+                                   "\u2001\u2002\u2003\u2004\u2005\u2006\u2007"
+                                   "\u2008\u2009\u200a\u2028\u2029\u202f\u205f"
+                                   "\u3000]")
+
+
+_encode_entity_map = {}
+_is_ucs4 = len("\U0010FFFF") == 1
+for k, v in list(entities.items()):
+    # skip multi-character entities
+    if ((_is_ucs4 and len(v) > 1) or
+            (not _is_ucs4 and len(v) > 2)):
+        continue
+    if v != "&":
+        if len(v) == 2:
+            v = _utils.surrogatePairToCodepoint(v)
+        else:
+            v = ord(v)
+        if v not in _encode_entity_map or k.islower():
+            # prefer &lt; over &LT; and similarly for &amp;, &gt;, etc.
+            _encode_entity_map[v] = k
+
+
+def htmlentityreplace_errors(exc):
+    if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
+        res = []
+        codepoints = []
+        skip = False
+        for i, c in enumerate(exc.object[exc.start:exc.end]):
+            if skip:
+                skip = False
+                continue
+            index = i + exc.start
+            if _utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
+                codepoint = _utils.surrogatePairToCodepoint(exc.object[index:index + 2])
+                skip = True
+            else:
+                codepoint = ord(c)
+            codepoints.append(codepoint)
+        for cp in codepoints:
+            e = _encode_entity_map.get(cp)
+            if e:
+                res.append("&")
+                res.append(e)
+                if not e.endswith(";"):
+                    res.append(";")
+            else:
+                res.append("&#x%s;" % (hex(cp)[2:]))
+        return ("".join(res), exc.end)
+    else:
+        return xmlcharrefreplace_errors(exc)
+
+
+register_error("htmlentityreplace", htmlentityreplace_errors)
+
+
+def serialize(input, tree="etree", encoding=None, **serializer_opts):
+    """Serializes the input token stream using the specified treewalker
+
+    :arg input: the token stream to serialize
+
+    :arg tree: the treewalker to use
+
+    :arg encoding: the encoding to use
+
+    :arg serializer_opts: any options to pass to the
+        :py:class:`html5lib.serializer.HTMLSerializer` that gets created
+
+    :returns: the tree serialized as a string
+
+    Example:
+
+    >>> from html5lib.html5parser import parse
+    >>> from html5lib.serializer import serialize
+    >>> token_stream = parse('<html><body><p>Hi!</p></body></html>')
+    >>> serialize(token_stream, omit_optional_tags=False)
+    '<html><head></head><body><p>Hi!</p></body></html>'
+
+    """
+    # XXX: Should we cache this?
+    walker = treewalkers.getTreeWalker(tree)
+    s = HTMLSerializer(**serializer_opts)
+    return s.render(walker(input), encoding)
+
+
+class HTMLSerializer(object):
+
+    # attribute quoting options
+    quote_attr_values = "legacy"  # be secure by default
+    quote_char = '"'
+    use_best_quote_char = True
+
+    # tag syntax options
+    omit_optional_tags = True
+    minimize_boolean_attributes = True
+    use_trailing_solidus = False
+    space_before_trailing_solidus = True
+
+    # escaping options
+    escape_lt_in_attrs = False
+    escape_rcdata = False
+    resolve_entities = True
+
+    # miscellaneous options
+    alphabetical_attributes = False
+    inject_meta_charset = True
+    strip_whitespace = False
+    sanitize = False
+
+    options = ("quote_attr_values", "quote_char", "use_best_quote_char",
+               "omit_optional_tags", "minimize_boolean_attributes",
+               "use_trailing_solidus", "space_before_trailing_solidus",
+               "escape_lt_in_attrs", "escape_rcdata", "resolve_entities",
+               "alphabetical_attributes", "inject_meta_charset",
+               "strip_whitespace", "sanitize")
+
+    def __init__(self, **kwargs):
+        """Initialize HTMLSerializer
+
+        :arg inject_meta_charset: Whether or not to inject the meta charset.
+
+            Defaults to ``True``.
+
+        :arg quote_attr_values: Whether to quote attribute values that don't
+            require quoting per legacy browser behavior (``"legacy"``), when
+            required by the standard (``"spec"``), or always (``"always"``).
+
+            Defaults to ``"legacy"``.
+
+        :arg quote_char: Use given quote character for attribute quoting.
+
+            Defaults to ``"`` which will use double quotes unless attribute
+            value contains a double quote, in which case single quotes are
+            used.
+
+        :arg escape_lt_in_attrs: Whether or not to escape ``<`` in attribute
+            values.
+
+            Defaults to ``False``.
+
+        :arg escape_rcdata: Whether to escape characters that need to be
+            escaped within normal elements within rcdata elements such as
+            style.
+
+            Defaults to ``False``.
+
+        :arg resolve_entities: Whether to resolve named character entities that
+            appear in the source tree. The XML predefined entities &lt; &gt;
+            &amp; &quot; &apos; are unaffected by this setting.
+
+            Defaults to ``True``.
+
+        :arg strip_whitespace: Whether to remove semantically meaningless
+            whitespace. (This compresses all whitespace to a single space
+            except within ``pre``.)
+
+            Defaults to ``False``.
+
+        :arg minimize_boolean_attributes: Shortens boolean attributes to give
+            just the attribute value, for example::
+
+              <input disabled="disabled">
+
+            becomes::
+
+              <input disabled>
+
+            Defaults to ``True``.
+
+        :arg use_trailing_solidus: Includes a close-tag slash at the end of the
+            start tag of void elements (empty elements whose end tag is
+            forbidden). E.g. ``<hr/>``.
+
+            Defaults to ``False``.
+
+        :arg space_before_trailing_solidus: Places a space immediately before
+            the closing slash in a tag using a trailing solidus. E.g.
+            ``<hr />``. Requires ``use_trailing_solidus=True``.
+
+            Defaults to ``True``.
+
+        :arg sanitize: Strip all unsafe or unknown constructs from output.
+            See :py:class:`html5lib.filters.sanitizer.Filter`.
+
+            Defaults to ``False``.
+
+        :arg omit_optional_tags: Omit start/end tags that are optional.
+
+            Defaults to ``True``.
+
+        :arg alphabetical_attributes: Reorder attributes to be in alphabetical order.
+
+            Defaults to ``False``.
+
+        """
+        unexpected_args = frozenset(kwargs) - frozenset(self.options)
+        if len(unexpected_args) > 0:
+            raise TypeError("__init__() got an unexpected keyword argument '%s'" % next(iter(unexpected_args)))
+        if 'quote_char' in kwargs:
+            self.use_best_quote_char = False
+        for attr in self.options:
+            setattr(self, attr, kwargs.get(attr, getattr(self, attr)))
+        self.errors = []
+        self.strict = False
+
+    def encode(self, string):
+        assert(isinstance(string, text_type))
+        if self.encoding:
+            return string.encode(self.encoding, "htmlentityreplace")
+        else:
+            return string
+
+    def encodeStrict(self, string):
+        assert(isinstance(string, text_type))
+        if self.encoding:
+            return string.encode(self.encoding, "strict")
+        else:
+            return string
+
+    def serialize(self, treewalker, encoding=None):
+        # pylint:disable=too-many-nested-blocks
+        self.encoding = encoding
+        in_cdata = False
+        self.errors = []
+
+        if encoding and self.inject_meta_charset:
+            from .filters.inject_meta_charset import Filter
+            treewalker = Filter(treewalker, encoding)
+        # Alphabetical attributes is here under the assumption that none of
+        # the later filters add or change order of attributes; it needs to be
+        # before the sanitizer so escaped elements come out correctly
+        if self.alphabetical_attributes:
+            from .filters.alphabeticalattributes import Filter
+            treewalker = Filter(treewalker)
+        # WhitespaceFilter should be used before OptionalTagFilter
+        # for maximum efficiently of this latter filter
+        if self.strip_whitespace:
+            from .filters.whitespace import Filter
+            treewalker = Filter(treewalker)
+        if self.sanitize:
+            from .filters.sanitizer import Filter
+            treewalker = Filter(treewalker)
+        if self.omit_optional_tags:
+            from .filters.optionaltags import Filter
+            treewalker = Filter(treewalker)
+
+        for token in treewalker:
+            type = token["type"]
+            if type == "Doctype":
+                doctype = "<!DOCTYPE %s" % token["name"]
+
+                if token["publicId"]:
+                    doctype += ' PUBLIC "%s"' % token["publicId"]
+                elif token["systemId"]:
+                    doctype += " SYSTEM"
+                if token["systemId"]:
+                    if token["systemId"].find('"') >= 0:
+                        if token["systemId"].find("'") >= 0:
+                            self.serializeError("System identifer contains both single and double quote characters")
+                        quote_char = "'"
+                    else:
+                        quote_char = '"'
+                    doctype += " %s%s%s" % (quote_char, token["systemId"], quote_char)
+
+                doctype += ">"
+                yield self.encodeStrict(doctype)
+
+            elif type in ("Characters", "SpaceCharacters"):
+                if type == "SpaceCharacters" or in_cdata:
+                    if in_cdata and token["data"].find("</") >= 0:
+                        self.serializeError("Unexpected </ in CDATA")
+                    yield self.encode(token["data"])
+                else:
+                    yield self.encode(escape(token["data"]))
+
+            elif type in ("StartTag", "EmptyTag"):
+                name = token["name"]
+                yield self.encodeStrict("<%s" % name)
+                if name in rcdataElements and not self.escape_rcdata:
+                    in_cdata = True
+                elif in_cdata:
+                    self.serializeError("Unexpected child element of a CDATA element")
+                for (_, attr_name), attr_value in token["data"].items():
+                    # TODO: Add namespace support here
+                    k = attr_name
+                    v = attr_value
+                    yield self.encodeStrict(' ')
+
+                    yield self.encodeStrict(k)
+                    if not self.minimize_boolean_attributes or \
+                        (k not in booleanAttributes.get(name, tuple()) and
+                         k not in booleanAttributes.get("", tuple())):
+                        yield self.encodeStrict("=")
+                        if self.quote_attr_values == "always" or len(v) == 0:
+                            quote_attr = True
+                        elif self.quote_attr_values == "spec":
+                            quote_attr = _quoteAttributeSpec.search(v) is not None
+                        elif self.quote_attr_values == "legacy":
+                            quote_attr = _quoteAttributeLegacy.search(v) is not None
+                        else:
+                            raise ValueError("quote_attr_values must be one of: "
+                                             "'always', 'spec', or 'legacy'")
+                        v = v.replace("&", "&amp;")
+                        if self.escape_lt_in_attrs:
+                            v = v.replace("<", "&lt;")
+                        if quote_attr:
+                            quote_char = self.quote_char
+                            if self.use_best_quote_char:
+                                if "'" in v and '"' not in v:
+                                    quote_char = '"'
+                                elif '"' in v and "'" not in v:
+                                    quote_char = "'"
+                            if quote_char == "'":
+                                v = v.replace("'", "&#39;")
+                            else:
+                                v = v.replace('"', "&quot;")
+                            yield self.encodeStrict(quote_char)
+                            yield self.encode(v)
+                            yield self.encodeStrict(quote_char)
+                        else:
+                            yield self.encode(v)
+                if name in voidElements and self.use_trailing_solidus:
+                    if self.space_before_trailing_solidus:
+                        yield self.encodeStrict(" /")
+                    else:
+                        yield self.encodeStrict("/")
+                yield self.encode(">")
+
+            elif type == "EndTag":
+                name = token["name"]
+                if name in rcdataElements:
+                    in_cdata = False
+                elif in_cdata:
+                    self.serializeError("Unexpected child element of a CDATA element")
+                yield self.encodeStrict("</%s>" % name)
+
+            elif type == "Comment":
+                data = token["data"]
+                if data.find("--") >= 0:
+                    self.serializeError("Comment contains --")
+                yield self.encodeStrict("<!--%s-->" % token["data"])
+
+            elif type == "Entity":
+                name = token["name"]
+                key = name + ";"
+                if key not in entities:
+                    self.serializeError("Entity %s not recognized" % name)
+                if self.resolve_entities and key not in xmlEntities:
+                    data = entities[key]
+                else:
+                    data = "&%s;" % name
+                yield self.encodeStrict(data)
+
+            else:
+                self.serializeError(token["data"])
+
+    def render(self, treewalker, encoding=None):
+        """Serializes the stream from the treewalker into a string
+
+        :arg treewalker: the treewalker to serialize
+
+        :arg encoding: the string encoding to use
+
+        :returns: the serialized tree
+
+        Example:
+
+        >>> from html5lib import parse, getTreeWalker
+        >>> from html5lib.serializer import HTMLSerializer
+        >>> token_stream = parse('<html><body>Hi!</body></html>')
+        >>> walker = getTreeWalker('etree')
+        >>> serializer = HTMLSerializer(omit_optional_tags=False)
+        >>> serializer.render(walker(token_stream))
+        '<html><head></head><body>Hi!</body></html>'
+
+        """
+        if encoding:
+            return b"".join(list(self.serialize(treewalker, encoding)))
+        else:
+            return "".join(list(self.serialize(treewalker)))
+
+    def serializeError(self, data="XXX ERROR MESSAGE NEEDED"):
+        # XXX The idea is to make data mandatory.
+        self.errors.append(data)
+        if self.strict:
+            raise SerializeError
+
+
+class SerializeError(Exception):
+    """Error in serialized tree"""
+    pass
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/__init__.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/__init__.py
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/html5lib/tests/__init__.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/__init__.py
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/conftest.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/conftest.py
new file mode 100644
index 000000000000..dad167c5832a
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/conftest.py
@@ -0,0 +1,108 @@
+from __future__ import print_function
+import os.path
+import sys
+
+import pkg_resources
+import pytest
+
+from .tree_construction import TreeConstructionFile
+from .tokenizer import TokenizerFile
+from .sanitizer import SanitizerFile
+
+_dir = os.path.abspath(os.path.dirname(__file__))
+_root = os.path.join(_dir, "..", "..")
+_testdata = os.path.join(_dir, "testdata")
+_tree_construction = os.path.join(_testdata, "tree-construction")
+_tokenizer = os.path.join(_testdata, "tokenizer")
+_sanitizer_testdata = os.path.join(_dir, "sanitizer-testdata")
+
+
+def fail_if_missing_pytest_expect():
+    """Throws an exception halting pytest if pytest-expect isn't working"""
+    try:
+        from pytest_expect import expect  # noqa
+    except ImportError:
+        header = '*' * 78
+        print(
+            '\n' +
+            header + '\n' +
+            'ERROR: Either pytest-expect or its dependency u-msgpack-python is not\n' +
+            'installed. Please install them both before running pytest.\n' +
+            header + '\n',
+            file=sys.stderr
+        )
+        raise
+
+
+fail_if_missing_pytest_expect()
+
+
+def pytest_configure(config):
+    msgs = []
+
+    if not os.path.exists(_testdata):
+        msg = "testdata not available! "
+        if os.path.exists(os.path.join(_root, ".git")):
+            msg += ("Please run git submodule update --init --recursive " +
+                    "and then run tests again.")
+        else:
+            msg += ("The testdata doesn't appear to be included with this package, " +
+                    "so finding the right version will be hard. :(")
+        msgs.append(msg)
+
+    if config.option.update_xfail:
+        # Check for optional requirements
+        req_file = os.path.join(_root, "requirements-optional.txt")
+        if os.path.exists(req_file):
+            with open(req_file, "r") as fp:
+                for line in fp:
+                    if (line.strip() and
+                        not (line.startswith("-r") or
+                             line.startswith("#"))):
+                        if ";" in line:
+                            spec, marker = line.strip().split(";", 1)
+                        else:
+                            spec, marker = line.strip(), None
+                        req = pkg_resources.Requirement.parse(spec)
+                        if marker and not pkg_resources.evaluate_marker(marker):
+                            msgs.append("%s not available in this environment" % spec)
+                        else:
+                            try:
+                                installed = pkg_resources.working_set.find(req)
+                            except pkg_resources.VersionConflict:
+                                msgs.append("Outdated version of %s installed, need %s" % (req.name, spec))
+                            else:
+                                if not installed:
+                                    msgs.append("Need %s" % spec)
+
+        # Check cElementTree
+        import xml.etree.ElementTree as ElementTree
+
+        try:
+            import xml.etree.cElementTree as cElementTree
+        except ImportError:
+            msgs.append("cElementTree unable to be imported")
+        else:
+            if cElementTree.Element is ElementTree.Element:
+                msgs.append("cElementTree is just an alias for ElementTree")
+
+    if msgs:
+        pytest.exit("\n".join(msgs))
+
+
+def pytest_collect_file(path, parent):
+    dir = os.path.abspath(path.dirname)
+    dir_and_parents = set()
+    while dir not in dir_and_parents:
+        dir_and_parents.add(dir)
+        dir = os.path.dirname(dir)
+
+    if _tree_construction in dir_and_parents:
+        if path.ext == ".dat":
+            return TreeConstructionFile(path, parent)
+    elif _tokenizer in dir_and_parents:
+        if path.ext == ".test":
+            return TokenizerFile(path, parent)
+    elif _sanitizer_testdata in dir_and_parents:
+        if path.ext == ".dat":
+            return SanitizerFile(path, parent)
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/sanitizer-testdata/tests1.dat b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/sanitizer-testdata/tests1.dat
new file mode 100644
index 000000000000..74e8833686cf
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/sanitizer-testdata/tests1.dat
@@ -0,0 +1,433 @@
+[
+  {
+    "name": "IE_Comments",
+    "input": "<!--[if gte IE 4]><script>alert('XSS');</script><![endif]-->",
+    "output": ""
+  },
+
+  {
+    "name": "IE_Comments_2",
+    "input": "<![if !IE 5]><script>alert('XSS');</script><![endif]>",
+    "output": "&lt;script&gt;alert('XSS');&lt;/script&gt;"
+  },
+
+  {
+    "name": "allow_colons_in_path_component",
+    "input": "<a href=\"./this:that\">foo</a>",
+    "output": "<a href='./this:that'>foo</a>"
+  },
+
+  {
+    "name": "background_attribute",
+    "input": "<div background=\"javascript:alert('XSS')\"></div>",
+    "output": "<div></div>"
+  },
+
+  {
+    "name": "bgsound",
+    "input": "<bgsound src=\"javascript:alert('XSS');\" />",
+    "output": "&lt;bgsound src=\"javascript:alert('XSS');\"&gt;&lt;/bgsound&gt;"
+  },
+
+  {
+    "name": "div_background_image_unicode_encoded",
+    "input": "<div style=\"background-image:\u00a5\u00a2\u006C\u0028'\u006a\u0061\u00a6\u0061\u00a3\u0063\u00a2\u0069\u00a0\u00a4\u003a\u0061\u006c\u0065\u00a2\u00a4\u0028.1027\u0058.1053\u0053\u0027\u0029'\u0029\">foo</div>",
+    "output": "<div style=''>foo</div>"
+  },
+
+  {
+    "name": "div_expression",
+    "input": "<div style=\"width: expression(alert('XSS'));\">foo</div>",
+    "output": "<div style=''>foo</div>"
+  },
+
+  {
+    "name": "double_open_angle_brackets",
+    "input": "<img src=http://ha.ckers.org/scriptlet.html <",
+    "output": ""
+  },
+
+  {
+    "name": "double_open_angle_brackets_2",
+    "input": "<script src=http://ha.ckers.org/scriptlet.html <",
+    "output": ""
+  },
+
+  {
+    "name": "grave_accents",
+    "input": "<img src=`javascript:alert('XSS')` />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "img_dynsrc_lowsrc",
+    "input": "<img dynsrc=\"javascript:alert('XSS')\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "img_vbscript",
+    "input": "<img src='vbscript:msgbox(\"XSS\")' />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "input_image",
+    "input": "<input type=\"image\" src=\"javascript:alert('XSS');\" />",
+    "output": "<input type='image'/>"
+  },
+
+  {
+    "name": "link_stylesheets",
+    "input": "<link rel=\"stylesheet\" href=\"javascript:alert('XSS');\" />",
+    "output": "&lt;link href=\"javascript:alert('XSS');\" rel=\"stylesheet\"&gt;"
+  },
+
+  {
+    "name": "link_stylesheets_2",
+    "input": "<link rel=\"stylesheet\" href=\"http://ha.ckers.org/xss.css\" />",
+    "output": "&lt;link href=\"http://ha.ckers.org/xss.css\" rel=\"stylesheet\"&gt;"
+  },
+
+  {
+    "name": "list_style_image",
+    "input": "<li style=\"list-style-image: url(javascript:alert('XSS'))\">foo</li>",
+    "output": "<li style=''>foo</li>"
+  },
+
+  {
+    "name": "no_closing_script_tags",
+    "input": "<script src=http://ha.ckers.org/xss.js?<b>",
+    "output": "&lt;script src=\"http://ha.ckers.org/xss.js?&amp;lt;b\"&gt;&lt;/script&gt;"
+  },
+
+  {
+    "name": "non_alpha_non_digit",
+    "input": "<script/XSS src=\"http://ha.ckers.org/xss.js\"></script>",
+    "output": "&lt;script src=\"http://ha.ckers.org/xss.js\" xss=\"\"&gt;&lt;/script&gt;"
+  },
+
+  {
+    "name": "non_alpha_non_digit_2",
+    "input": "<a onclick!\\#$%&()*~+-_.,:;?@[/|\\]^`=alert(\"XSS\")>foo</a>",
+    "output": "<a>foo</a>"
+  },
+
+  {
+    "name": "non_alpha_non_digit_3",
+    "input": "<img/src=\"http://ha.ckers.org/xss.js\"/>",
+    "output": "<img src='http://ha.ckers.org/xss.js'/>"
+  },
+
+  {
+    "name": "non_alpha_non_digit_II",
+    "input": "<a href!\\#$%&()*~+-_.,:;?@[/|]^`=alert('XSS')>foo</a>",
+    "output": "<a>foo</a>"
+  },
+
+  {
+    "name": "non_alpha_non_digit_III",
+    "input": "<a/href=\"javascript:alert('XSS');\">foo</a>",
+    "output": "<a>foo</a>"
+  },
+
+  {
+    "name": "platypus",
+    "input": "<a href=\"http://www.ragingplatypus.com/\" style=\"display:block; position:absolute; left:0; top:0; width:100%; height:100%; z-index:1; background-color:black; background-image:url(http://www.ragingplatypus.com/i/cam-full.jpg); background-x:center; background-y:center; background-repeat:repeat;\">never trust your upstream platypus</a>",
+    "output": "<a href='http://www.ragingplatypus.com/' style='display: block; width: 100%; height: 100%; background-color: black; background-x: center; background-y: center;'>never trust your upstream platypus</a>"
+  },
+
+  {
+    "name": "protocol_resolution_in_script_tag",
+    "input": "<script src=//ha.ckers.org/.j></script>",
+    "output": "&lt;script src=\"//ha.ckers.org/.j\"&gt;&lt;/script&gt;"
+  },
+
+  {
+    "name": "should_allow_anchors",
+    "input": "<a href='foo' onclick='bar'><script>baz</script></a>",
+    "output": "<a href='foo'>&lt;script&gt;baz&lt;/script&gt;</a>"
+  },
+
+  {
+    "name": "should_allow_image_alt_attribute",
+    "input": "<img alt='foo' onclick='bar' />",
+    "output": "<img alt='foo'/>"
+  },
+
+  {
+    "name": "should_allow_image_height_attribute",
+    "input": "<img height='foo' onclick='bar' />",
+    "output": "<img height='foo'/>"
+  },
+
+  {
+    "name": "should_allow_image_src_attribute",
+    "input": "<img src='foo' onclick='bar' />",
+    "output": "<img src='foo'/>"
+  },
+
+  {
+    "name": "should_allow_image_width_attribute",
+    "input": "<img width='foo' onclick='bar' />",
+    "output": "<img width='foo'/>"
+  },
+
+  {
+    "name": "should_handle_blank_text",
+    "input": "",
+    "output": ""
+  },
+
+  {
+    "name": "should_handle_malformed_image_tags",
+    "input": "<img \"\"\"><script>alert(\"XSS\")</script>\">",
+    "output": "<img/>&lt;script&gt;alert(\"XSS\")&lt;/script&gt;\"&gt;"
+  },
+
+  {
+    "name": "should_handle_non_html",
+    "input": "abc",
+    "output": "abc"
+  },
+
+  {
+    "name": "should_not_fall_for_ridiculous_hack",
+    "input": "<img\nsrc\n=\n\"\nj\na\nv\na\ns\nc\nr\ni\np\nt\n:\na\nl\ne\nr\nt\n(\n'\nX\nS\nS\n'\n)\n\"\n />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_0",
+    "input": "<img src=\"javascript:alert('XSS');\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_1",
+    "input": "<img src=javascript:alert('XSS') />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_10",
+    "input": "<img src=\"jav&#x0A;ascript:alert('XSS');\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_11",
+    "input": "<img src=\"jav&#x0D;ascript:alert('XSS');\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_12",
+    "input": "<img src=\" &#14;  javascript:alert('XSS');\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_13",
+    "input": "<img src=\"&#x20;javascript:alert('XSS');\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_14",
+    "input": "<img src=\"&#xA0;javascript:alert('XSS');\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_2",
+    "input": "<img src=\"JaVaScRiPt:alert('XSS')\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_3",
+    "input": "<img src='javascript:alert(&quot;XSS&quot;)' />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_4",
+    "input": "<img src='javascript:alert(String.fromCharCode(88,83,83))' />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_5",
+    "input": "<img src='&#106;&#97;&#118;&#97;&#115;&#99;&#114;&#105;&#112;&#116;&#58;&#97;&#108;&#101;&#114;&#116;&#40;&#39;&#88;&#83;&#83;&#39;&#41;' />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_6",
+    "input": "<img src='&#0000106;&#0000097;&#0000118;&#0000097;&#0000115;&#0000099;&#0000114;&#0000105;&#0000112;&#0000116;&#0000058;&#0000097;&#0000108;&#0000101;&#0000114;&#0000116;&#0000040;&#0000039;&#0000088;&#0000083;&#0000083;&#0000039;&#0000041' />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_7",
+    "input": "<img src='&#x6A;&#x61;&#x76;&#x61;&#x73;&#x63;&#x72;&#x69;&#x70;&#x74;&#x3A;&#x61;&#x6C;&#x65;&#x72;&#x74;&#x28;&#x27;&#x58;&#x53;&#x53;&#x27;&#x29' />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_8",
+    "input": "<img src=\"jav\tascript:alert('XSS');\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_not_fall_for_xss_image_hack_9",
+    "input": "<img src=\"jav&#x09;ascript:alert('XSS');\" />",
+    "output": "<img/>"
+  },
+
+  {
+    "name": "should_sanitize_half_open_scripts",
+    "input": "<img src=\"javascript:alert('XSS')\"",
+    "output": ""
+  },
+
+  {
+    "name": "should_sanitize_invalid_script_tag",
+    "input": "<script/XSS SRC=\"http://ha.ckers.org/xss.js\"></script>",
+    "output": "&lt;script src=\"http://ha.ckers.org/xss.js\" xss=\"\"&gt;&lt;/script&gt;"
+  },
+
+  {
+    "name": "should_sanitize_script_tag_with_multiple_open_brackets",
+    "input": "<<script>alert(\"XSS\");//<</script>",
+    "output": "&lt;&lt;script&gt;alert(\"XSS\");//&lt;&lt;/script&gt;"
+  },
+
+  {
+    "name": "should_sanitize_script_tag_with_multiple_open_brackets_2",
+    "input": "<iframe src=http://ha.ckers.org/scriptlet.html\n<",
+    "output": ""
+  },
+
+  {
+    "name": "should_sanitize_tag_broken_up_by_null",
+    "input": "<scr\u0000ipt>alert(\"XSS\")</scr\u0000ipt>",
+    "output": "&lt;scr\ufffdipt&gt;alert(\"XSS\")&lt;/scr\ufffdipt&gt;"
+  },
+
+  {
+    "name": "should_sanitize_unclosed_script",
+    "input": "<script src=http://ha.ckers.org/xss.js?<b>",
+    "output": "&lt;script src=\"http://ha.ckers.org/xss.js?&amp;lt;b\"&gt;&lt;/script&gt;"
+  },
+
+  {
+    "name": "should_strip_href_attribute_in_a_with_bad_protocols",
+    "input": "<a href=\"javascript:XSS\" title=\"1\">boo</a>",
+    "output": "<a title='1'>boo</a>"
+  },
+
+  {
+    "name": "should_strip_href_attribute_in_a_with_bad_protocols_and_whitespace",
+    "input": "<a href=\" javascript:XSS\" title=\"1\">boo</a>",
+    "output": "<a title='1'>boo</a>"
+  },
+
+  {
+    "name": "should_strip_src_attribute_in_img_with_bad_protocols",
+    "input": "<img src=\"javascript:XSS\" title=\"1\">boo</img>",
+    "output": "<img title='1'/>boo"
+  },
+
+  {
+    "name": "should_strip_src_attribute_in_img_with_bad_protocols_and_whitespace",
+    "input": "<img src=\" javascript:XSS\" title=\"1\">boo</img>",
+    "output": "<img title='1'/>boo"
+  },
+
+  {
+    "name": "xml_base",
+    "input": "<div xml:base=\"javascript:alert('XSS');//\">foo</div>",
+    "output": "<div>foo</div>"
+  },
+
+  {
+    "name": "xul",
+    "input": "<p style=\"-moz-binding:url('http://ha.ckers.org/xssmoz.xml#xss')\">fubar</p>",
+    "output": "<p style=''>fubar</p>"
+  },
+
+  {
+    "name": "quotes_in_attributes",
+    "input": "<img src='foo' title='\"foo\" bar' />",
+    "output": "<img src='foo' title='\"foo\" bar'/>"
+  },
+
+  {
+    "name": "uri_refs_in_svg_attributes",
+    "input": "<svg><rect fill='url(#foo)' />",
+    "output": "<svg><rect fill='url(#foo)'></rect></svg>"
+  },
+
+  {
+    "name": "absolute_uri_refs_in_svg_attributes",
+    "input": "<svg><rect fill='url(http://bad.com/) #fff' />",
+    "output": "<svg><rect fill='  #fff'></rect></svg>"
+  },
+
+  {
+    "name": "uri_ref_with_space_in svg_attribute",
+    "input": "<svg><rect fill='url(\n#foo)' />",
+    "output": "<svg><rect fill='url(\n#foo)'></rect></svg>"
+  },
+
+  {
+    "name": "absolute_uri_ref_with_space_in svg_attribute",
+    "input": "<svg><rect fill=\"url(\nhttp://bad.com/)\" />",
+    "output": "<svg><rect fill=' '></rect></svg>"
+  },
+
+  {
+    "name": "allow_html5_image_tag",
+    "input": "<image src='foo' />",
+    "output": "<img src='foo'/>"
+  },
+
+  {
+    "name": "style_attr_end_with_nothing",
+    "input": "<div style=\"color: blue\" />",
+    "output": "<div style='color: blue;'></div>"
+  },
+
+  {
+    "name": "style_attr_end_with_space",
+    "input": "<div style=\"color: blue \" />",
+    "output": "<div style='color: blue ;'></div>"
+  },
+
+  {
+    "name": "style_attr_end_with_semicolon",
+    "input": "<div style=\"color: blue;\" />",
+    "output": "<div style='color: blue;'></div>"
+  },
+
+  {
+    "name": "style_attr_end_with_semicolon_space",
+    "input": "<div style=\"color: blue; \" />",
+    "output": "<div style='color: blue;'></div>"
+  },
+  
+  {
+   "name": "attributes_with_embedded_quotes",
+   "input": "<img src=doesntexist.jpg\"'onerror=\"alert(1) />",
+   "output": "<img src='doesntexist.jpg\"&#39;onerror=\"alert(1)'/>"
+  },
+  
+  {
+   "name": "attributes_with_embedded_quotes_II",
+   "input": "<img src=notthere.jpg\"\"onerror=\"alert(2) />",
+   "output": "<img src='notthere.jpg\"\"onerror=\"alert(2)'/>"
+  }
+]
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/sanitizer.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/sanitizer.py
new file mode 100644
index 000000000000..93882ec477c7
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/sanitizer.py
@@ -0,0 +1,50 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import codecs
+import json
+
+import pytest
+
+from html5lib import parseFragment, serialize
+
+
+class SanitizerFile(pytest.File):
+    def collect(self):
+        with codecs.open(str(self.fspath), "r", encoding="utf-8") as fp:
+            tests = json.load(fp)
+        for i, test in enumerate(tests):
+            yield SanitizerTest(str(i), self, test=test)
+
+
+class SanitizerTest(pytest.Item):
+    def __init__(self, name, parent, test):
+        super(SanitizerTest, self).__init__(name, parent)
+        self.obj = lambda: 1  # this is to hack around skipif needing a function!
+        self.test = test
+
+    def runtest(self):
+        input = self.test["input"]
+        expected = self.test["output"]
+
+        parsed = parseFragment(input)
+        serialized = serialize(parsed,
+                               sanitize=True,
+                               omit_optional_tags=False,
+                               use_trailing_solidus=True,
+                               space_before_trailing_solidus=False,
+                               quote_attr_values="always",
+                               quote_char="'",
+                               alphabetical_attributes=True)
+        errorMsg = "\n".join(["\n\nInput:", input,
+                              "\nExpected:", expected,
+                              "\nReceived:", serialized])
+        assert expected == serialized, errorMsg
+
+    def repr_failure(self, excinfo):
+        traceback = excinfo.traceback
+        ntraceback = traceback.cut(path=__file__)
+        excinfo.traceback = ntraceback.filter()
+
+        return excinfo.getrepr(funcargs=True,
+                               showlocals=False,
+                               style="short", tbfilter=False)
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/core.test b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/core.test
new file mode 100644
index 000000000000..70828d0d25e6
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/core.test
@@ -0,0 +1,395 @@
+{
+    "tests": [
+        {
+            "expected": [
+                "<span title='test \"with\" &amp;quot;'>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "test \"with\" &quot;"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value escaping"
+        },
+        {
+            "expected": [
+                "<span title=foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value non-quoting"
+        },
+        {
+            "expected": [
+                "<span title=\"foo<bar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo<bar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value non-quoting (with <)"
+        },
+        {
+            "expected": [
+                "<span title=\"foo=bar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo=bar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with =)"
+        },
+        {
+            "expected": [
+                "<span title=\"foo>bar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo>bar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with >)"
+        },
+        {
+            "expected": [
+                "<span title='foo\"bar'>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo\"bar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with \")"
+        },
+        {
+            "expected": [
+                "<span title=\"foo'bar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo'bar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with ')"
+        },
+        {
+            "expected": [
+                "<span title=\"foo'bar&quot;baz\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo'bar\"baz"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with both \" and ')"
+        },
+        {
+            "expected": [
+                "<span title=\"foo bar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo bar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with space)"
+        },
+        {
+            "expected": [
+                "<span title=\"foo\tbar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo\tbar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with tab)"
+        },
+        {
+            "expected": [
+                "<span title=\"foo\nbar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo\nbar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with LF)"
+        },
+        {
+            "expected": [
+                "<span title=\"foo\rbar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo\rbar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with CR)"
+        },
+        {
+            "expected": [
+                "<span title=\"foo\u000bbar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo\u000bbar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value non-quoting (with linetab)"
+        },
+        {
+            "expected": [
+                "<span title=\"foo\fbar\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "foo\fbar"
+                        }
+                    ]
+                ]
+            ],
+            "description": "proper attribute value quoting (with form feed)"
+        },
+        {
+            "expected": [
+                "<img>"
+            ],
+            "input": [
+                [
+                    "EmptyTag",
+                    "img",
+                    {}
+                ]
+            ],
+            "description": "void element (as EmptyTag token)"
+        },
+        {
+            "expected": [
+                "<!DOCTYPE foo>"
+            ],
+            "input": [
+                [
+                    "Doctype",
+                    "foo"
+                ]
+            ],
+            "description": "doctype in error"
+        },
+        {
+            "expected": [
+                "a&lt;b&gt;c&amp;d"
+            ],
+            "input": [
+                [
+                    "Characters",
+                    "a<b>c&d"
+                ]
+            ],
+            "description": "character data",
+            "options": {
+                "encoding": "utf-8"
+            }
+        },
+        {
+            "expected": [
+                "<script>a<b>c&d"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "script",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "a<b>c&d"
+                ]
+            ],
+            "description": "rcdata"
+        },
+        {
+            "expected": [
+                "<!DOCTYPE HTML>"
+            ],
+            "input": [
+                [
+                    "Doctype",
+                    "HTML"
+                ]
+            ],
+            "description": "doctype"
+        },
+        {
+            "expected": [
+                "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">"
+            ],
+            "input": [
+                [
+                    "Doctype",
+                    "HTML",
+                    "-//W3C//DTD HTML 4.01//EN",
+                    "http://www.w3.org/TR/html4/strict.dtd"
+                ]
+            ],
+            "description": "HTML 4.01 DOCTYPE"
+        },
+        {
+            "expected": [
+                "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\">"
+            ],
+            "input": [
+                [
+                    "Doctype",
+                    "HTML",
+                    "-//W3C//DTD HTML 4.01//EN"
+                ]
+            ],
+            "description": "HTML 4.01 DOCTYPE without system identifer"
+        },
+        {
+            "expected": [
+                "<!DOCTYPE html SYSTEM \"http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd\">"
+            ],
+            "input": [
+                [
+                    "Doctype",
+                    "html",
+                    "",
+                    "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"
+                ]
+            ],
+            "description": "IBM DOCTYPE without public identifer"
+        }
+    ]
+}
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/injectmeta.test b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/injectmeta.test
new file mode 100644
index 000000000000..399590c3f357
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/injectmeta.test
@@ -0,0 +1,350 @@
+{
+    "tests": [
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "no encoding",
+            "options": {
+                "inject_meta_charset": true
+            }
+        },
+        {
+            "expected": [
+                "<meta charset=utf-8>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "empytag head",
+            "options": {
+                "encoding": "utf-8",
+                "inject_meta_charset": true
+            }
+        },
+        {
+            "expected": [
+                "<meta charset=utf-8><title>foo</title>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "title",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "title"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "head w/title",
+            "options": {
+                "encoding": "utf-8",
+                "inject_meta_charset": true
+            }
+        },
+        {
+            "expected": [
+                "<meta charset=utf-8>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "charset",
+                            "value": "ascii"
+                        }
+                    ]
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "head w/meta-charset",
+            "options": {
+                "encoding": "utf-8",
+                "inject_meta_charset": true
+            }
+        },
+        {
+            "expected": [
+                "<meta charset=utf-8><meta charset=utf-8>",
+                "<head><meta charset=utf-8><meta charset=ascii>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "charset",
+                            "value": "ascii"
+                        }
+                    ]
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "charset",
+                            "value": "ascii"
+                        }
+                    ]
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "head w/ two meta-charset",
+            "options": {
+                "encoding": "utf-8",
+                "inject_meta_charset": true
+            }
+        },
+        {
+            "expected": [
+                "<meta charset=utf-8><meta content=noindex name=robots>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "name",
+                            "value": "robots"
+                        },
+                        {
+                            "namespace": null,
+                            "name": "content",
+                            "value": "noindex"
+                        }
+                    ]
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "head w/robots",
+            "options": {
+                "encoding": "utf-8",
+                "inject_meta_charset": true
+            }
+        },
+        {
+            "expected": [
+                "<meta content=noindex name=robots><meta charset=utf-8>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "name",
+                            "value": "robots"
+                        },
+                        {
+                            "namespace": null,
+                            "name": "content",
+                            "value": "noindex"
+                        }
+                    ]
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "charset",
+                            "value": "ascii"
+                        }
+                    ]
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "head w/robots & charset",
+            "options": {
+                "encoding": "utf-8",
+                "inject_meta_charset": true
+            }
+        },
+        {
+            "expected": [
+                "<meta content=\"text/html; charset=utf-8\" http-equiv=content-type>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "http-equiv",
+                            "value": "content-type"
+                        },
+                        {
+                            "namespace": null,
+                            "name": "content",
+                            "value": "text/html; charset=ascii"
+                        }
+                    ]
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "head w/ charset in http-equiv content-type",
+            "options": {
+                "encoding": "utf-8",
+                "inject_meta_charset": true
+            }
+        },
+        {
+            "expected": [
+                "<meta content=noindex name=robots><meta content=\"text/html; charset=utf-8\" http-equiv=content-type>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "name",
+                            "value": "robots"
+                        },
+                        {
+                            "namespace": null,
+                            "name": "content",
+                            "value": "noindex"
+                        }
+                    ]
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "http-equiv",
+                            "value": "content-type"
+                        },
+                        {
+                            "namespace": null,
+                            "name": "content",
+                            "value": "text/html; charset=ascii"
+                        }
+                    ]
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "head w/robots & charset in http-equiv content-type",
+            "options": {
+                "encoding": "utf-8",
+                "inject_meta_charset": true
+            }
+        }
+    ]
+}
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/optionaltags.test b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/optionaltags.test
new file mode 100644
index 000000000000..e67725ca26ff
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/optionaltags.test
@@ -0,0 +1,3254 @@
+{
+    "tests": [
+        {
+            "expected": [
+                "<html lang=en>foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "lang",
+                            "value": "en"
+                        }
+                    ]
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "html start-tag followed by text, with attributes"
+        },
+        {
+            "expected": [
+                "<html><!--foo-->"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html",
+                    {}
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "html start-tag followed by comment"
+        },
+        {
+            "expected": [
+                "<html> foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html",
+                    {}
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "html start-tag followed by space character"
+        },
+        {
+            "expected": [
+                "foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "html start-tag followed by text"
+        },
+        {
+            "expected": [
+                "<foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "html start-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html",
+                    {}
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "html start-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html",
+                    {}
+                ]
+            ],
+            "description": "html start-tag at EOF (shouldn't ever happen?!)"
+        },
+        {
+            "expected": [
+                "</html><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "html end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</html> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "html end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "html end-tag followed by text"
+        },
+        {
+            "expected": [
+                "<foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "html end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "html end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "html"
+                ]
+            ],
+            "description": "html end-tag at EOF"
+        },
+        {
+            "expected": [
+                "<head><!--foo-->"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "head start-tag followed by comment"
+        },
+        {
+            "expected": [
+                "<head> foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "head start-tag followed by space character"
+        },
+        {
+            "expected": [
+                "<head>foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "head start-tag followed by text"
+        },
+        {
+            "expected": [
+                "<foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "head start-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<head></foo>",
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "head start-tag followed by end-tag (shouldn't ever happen?!)"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "empty head element"
+        },
+        {
+            "expected": [
+                "<meta>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "meta",
+                    {}
+                ]
+            ],
+            "description": "head start-tag followed by empty-tag"
+        },
+        {
+            "expected": [
+                "<head>",
+                ""
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head",
+                    {}
+                ]
+            ],
+            "description": "head start-tag at EOF (shouldn't ever happen?!)"
+        },
+        {
+            "expected": [
+                "</head><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "head end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</head> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "head end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "head end-tag followed by text"
+        },
+        {
+            "expected": [
+                "<foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "head end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "head end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "head"
+                ]
+            ],
+            "description": "head end-tag at EOF"
+        },
+        {
+            "expected": [
+                "<body><!--foo-->"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body",
+                    {}
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "body start-tag followed by comment"
+        },
+        {
+            "expected": [
+                "<body> foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body",
+                    {}
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "body start-tag followed by space character"
+        },
+        {
+            "expected": [
+                "foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "body start-tag followed by text"
+        },
+        {
+            "expected": [
+                "<foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "body start-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body",
+                    {}
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "body start-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body",
+                    {}
+                ]
+            ],
+            "description": "body start-tag at EOF (shouldn't ever happen?!)"
+        },
+        {
+            "expected": [
+                "</body><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "body end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</body> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "body end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "body end-tag followed by text"
+        },
+        {
+            "expected": [
+                "<foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "body end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "body end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "body"
+                ]
+            ],
+            "description": "body end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</li><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "li"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "li end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</li> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "li"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "li end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</li>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "li"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "li end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</li><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "li"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "li end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<li>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "li"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "li",
+                    {}
+                ]
+            ],
+            "description": "li end-tag followed by li start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "li"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "li end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "li"
+                ]
+            ],
+            "description": "li end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</dt><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "dt end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</dt> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "dt end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</dt>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "dt end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</dt><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "dt end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<dt>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt",
+                    {}
+                ]
+            ],
+            "description": "dt end-tag followed by dt start-tag"
+        },
+        {
+            "expected": [
+                "<dd>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd",
+                    {}
+                ]
+            ],
+            "description": "dt end-tag followed by dd start-tag"
+        },
+        {
+            "expected": [
+                "</dt></foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "dt end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                "</dt>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt"
+                ]
+            ],
+            "description": "dt end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</dd><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "dd end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</dd> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "dd end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</dd>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "dd end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</dd><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "dd end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<dd>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd",
+                    {}
+                ]
+            ],
+            "description": "dd end-tag followed by dd start-tag"
+        },
+        {
+            "expected": [
+                "<dt>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dt",
+                    {}
+                ]
+            ],
+            "description": "dd end-tag followed by dt start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "dd end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dd"
+                ]
+            ],
+            "description": "dd end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</p><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "p end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</p> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "p end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</p>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "p end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</p><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<address>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "address",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by address start-tag"
+        },
+        {
+            "expected": [
+                "<article>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "article",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by article start-tag"
+        },
+        {
+            "expected": [
+                "<aside>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "aside",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by aside start-tag"
+        },
+        {
+            "expected": [
+                "<blockquote>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "blockquote",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by blockquote start-tag"
+        },
+        {
+            "expected": [
+                "<datagrid>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "datagrid",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by datagrid start-tag"
+        },
+        {
+            "expected": [
+                "<dialog>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dialog",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by dialog start-tag"
+        },
+        {
+            "expected": [
+                "<dir>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dir",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by dir start-tag"
+        },
+        {
+            "expected": [
+                "<div>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by div start-tag"
+        },
+        {
+            "expected": [
+                "<dl>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "dl",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by dl start-tag"
+        },
+        {
+            "expected": [
+                "<fieldset>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "fieldset",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by fieldset start-tag"
+        },
+        {
+            "expected": [
+                "<footer>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "footer",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by footer start-tag"
+        },
+        {
+            "expected": [
+                "<form>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "form",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by form start-tag"
+        },
+        {
+            "expected": [
+                "<h1>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "h1",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by h1 start-tag"
+        },
+        {
+            "expected": [
+                "<h2>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "h2",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by h2 start-tag"
+        },
+        {
+            "expected": [
+                "<h3>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "h3",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by h3 start-tag"
+        },
+        {
+            "expected": [
+                "<h4>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "h4",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by h4 start-tag"
+        },
+        {
+            "expected": [
+                "<h5>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "h5",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by h5 start-tag"
+        },
+        {
+            "expected": [
+                "<h6>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "h6",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by h6 start-tag"
+        },
+        {
+            "expected": [
+                "<header>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "header",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by header start-tag"
+        },
+        {
+            "expected": [
+                "<hr>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "EmptyTag",
+                    "hr",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by hr empty-tag"
+        },
+        {
+            "expected": [
+                "<menu>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "menu",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by menu start-tag"
+        },
+        {
+            "expected": [
+                "<nav>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "nav",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by nav start-tag"
+        },
+        {
+            "expected": [
+                "<ol>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "ol",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by ol start-tag"
+        },
+        {
+            "expected": [
+                "<p>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by p start-tag"
+        },
+        {
+            "expected": [
+                "<pre>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "pre",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by pre start-tag"
+        },
+        {
+            "expected": [
+                "<section>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "section",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by section start-tag"
+        },
+        {
+            "expected": [
+                "<table>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "table",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by table start-tag"
+        },
+        {
+            "expected": [
+                "<ul>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "ul",
+                    {}
+                ]
+            ],
+            "description": "p end-tag followed by ul start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "p end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "p"
+                ]
+            ],
+            "description": "p end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</optgroup><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "optgroup end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</optgroup> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "optgroup end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</optgroup>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "optgroup end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</optgroup><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "optgroup end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<optgroup>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup",
+                    {}
+                ]
+            ],
+            "description": "optgroup end-tag followed by optgroup start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "optgroup end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup"
+                ]
+            ],
+            "description": "optgroup end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</option><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "option end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</option> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "option end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</option>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "option end-tag followed by text"
+        },
+        {
+            "expected": [
+                "<optgroup>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "optgroup",
+                    {}
+                ]
+            ],
+            "description": "option end-tag followed by optgroup start-tag"
+        },
+        {
+            "expected": [
+                "</option><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "option end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<option>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option",
+                    {}
+                ]
+            ],
+            "description": "option end-tag followed by option start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "option end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "option"
+                ]
+            ],
+            "description": "option end-tag at EOF"
+        },
+        {
+            "expected": [
+                "<colgroup><!--foo-->"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup",
+                    {}
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "colgroup start-tag followed by comment"
+        },
+        {
+            "expected": [
+                "<colgroup> foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup",
+                    {}
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "colgroup start-tag followed by space character"
+        },
+        {
+            "expected": [
+                "<colgroup>foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "colgroup start-tag followed by text"
+        },
+        {
+            "expected": [
+                "<colgroup><foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "colgroup start-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<table><col>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "table",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "col",
+                    {}
+                ]
+            ],
+            "description": "first colgroup in a table with a col child"
+        },
+        {
+            "expected": [
+                "</colgroup><col>",
+                "<colgroup><col>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup",
+                    {}
+                ],
+                [
+                    "EmptyTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "col",
+                    {}
+                ]
+            ],
+            "description": "colgroup with a col child, following another colgroup"
+        },
+        {
+            "expected": [
+                "<colgroup></foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup",
+                    {}
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "colgroup start-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                "<colgroup>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup",
+                    {}
+                ]
+            ],
+            "description": "colgroup start-tag at EOF"
+        },
+        {
+            "expected": [
+                "</colgroup><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "colgroup end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</colgroup> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "colgroup end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "colgroup end-tag followed by text"
+        },
+        {
+            "expected": [
+                "<foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "colgroup end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "colgroup end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "colgroup"
+                ]
+            ],
+            "description": "colgroup end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</thead><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "thead end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</thead> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "thead end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</thead>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "thead end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</thead><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "thead end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<tbody>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ]
+            ],
+            "description": "thead end-tag followed by tbody start-tag"
+        },
+        {
+            "expected": [
+                "<tfoot>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot",
+                    {}
+                ]
+            ],
+            "description": "thead end-tag followed by tfoot start-tag"
+        },
+        {
+            "expected": [
+                "</thead></foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "thead end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                "</thead>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ]
+            ],
+            "description": "thead end-tag at EOF"
+        },
+        {
+            "expected": [
+                "<tbody><!--foo-->"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "tbody start-tag followed by comment"
+        },
+        {
+            "expected": [
+                "<tbody> foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "tbody start-tag followed by space character"
+        },
+        {
+            "expected": [
+                "<tbody>foo"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "tbody start-tag followed by text"
+        },
+        {
+            "expected": [
+                "<tbody><foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "tbody start-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<table><tr>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "table",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr",
+                    {}
+                ]
+            ],
+            "description": "first tbody in a table with a tr child"
+        },
+        {
+            "expected": [
+                "<tbody><tr>",
+                "</tbody><tr>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr",
+                    {}
+                ]
+            ],
+            "description": "tbody with a tr child, following another tbody"
+        },
+        {
+            "expected": [
+                "<tbody><tr>",
+                "</thead><tr>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "thead"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr",
+                    {}
+                ]
+            ],
+            "description": "tbody with a tr child, following a thead"
+        },
+        {
+            "expected": [
+                "<tbody><tr>",
+                "</tfoot><tr>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr",
+                    {}
+                ]
+            ],
+            "description": "tbody with a tr child, following a tfoot"
+        },
+        {
+            "expected": [
+                "<tbody></foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "tbody start-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                "<tbody>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ]
+            ],
+            "description": "tbody start-tag at EOF"
+        },
+        {
+            "expected": [
+                "</tbody><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "tbody end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</tbody> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "tbody end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</tbody>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "tbody end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</tbody><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "tbody end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<tbody>",
+                "</tbody>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ]
+            ],
+            "description": "tbody end-tag followed by tbody start-tag"
+        },
+        {
+            "expected": [
+                "<tfoot>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot",
+                    {}
+                ]
+            ],
+            "description": "tbody end-tag followed by tfoot start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "tbody end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody"
+                ]
+            ],
+            "description": "tbody end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</tfoot><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "tfoot end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</tfoot> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "tfoot end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</tfoot>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "tfoot end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</tfoot><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "tfoot end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<tbody>",
+                "</tfoot>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tbody",
+                    {}
+                ]
+            ],
+            "description": "tfoot end-tag followed by tbody start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "tfoot end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tfoot"
+                ]
+            ],
+            "description": "tfoot end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</tr><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "tr end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</tr> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "tr end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</tr>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "tr end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</tr><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "tr end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<tr>",
+                "</tr>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr",
+                    {}
+                ]
+            ],
+            "description": "tr end-tag followed by tr start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "tr end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "tr"
+                ]
+            ],
+            "description": "tr end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</td><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "td end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</td> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "td end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</td>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "td end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</td><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "td end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<td>",
+                "</td>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td",
+                    {}
+                ]
+            ],
+            "description": "td end-tag followed by td start-tag"
+        },
+        {
+            "expected": [
+                "<th>",
+                "</td>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th",
+                    {}
+                ]
+            ],
+            "description": "td end-tag followed by th start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "td end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td"
+                ]
+            ],
+            "description": "td end-tag at EOF"
+        },
+        {
+            "expected": [
+                "</th><!--foo-->"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th"
+                ],
+                [
+                    "Comment",
+                    "foo"
+                ]
+            ],
+            "description": "th end-tag followed by comment"
+        },
+        {
+            "expected": [
+                "</th> foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th"
+                ],
+                [
+                    "Characters",
+                    " foo"
+                ]
+            ],
+            "description": "th end-tag followed by space character"
+        },
+        {
+            "expected": [
+                "</th>foo"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th"
+                ],
+                [
+                    "Characters",
+                    "foo"
+                ]
+            ],
+            "description": "th end-tag followed by text"
+        },
+        {
+            "expected": [
+                "</th><foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo",
+                    {}
+                ]
+            ],
+            "description": "th end-tag followed by start-tag"
+        },
+        {
+            "expected": [
+                "<th>",
+                "</th>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th",
+                    {}
+                ]
+            ],
+            "description": "th end-tag followed by th start-tag"
+        },
+        {
+            "expected": [
+                "<td>",
+                "</th>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "td",
+                    {}
+                ]
+            ],
+            "description": "th end-tag followed by td start-tag"
+        },
+        {
+            "expected": [
+                "</foo>"
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "foo"
+                ]
+            ],
+            "description": "th end-tag followed by end-tag"
+        },
+        {
+            "expected": [
+                ""
+            ],
+            "input": [
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "th"
+                ]
+            ],
+            "description": "th end-tag at EOF"
+        }
+    ]
+}
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/options.test b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/options.test
new file mode 100644
index 000000000000..a22eebfcf3bd
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/options.test
@@ -0,0 +1,334 @@
+{
+    "tests": [
+        {
+            "expected": [
+                "<span title='test &#39;with&#39; quote_char'>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "test 'with' quote_char"
+                        }
+                    ]
+                ]
+            ],
+            "description": "quote_char=\"'\"",
+            "options": {
+                "quote_char": "'"
+            }
+        },
+        {
+            "expected": [
+                "<button disabled>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "button",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "disabled",
+                            "value": "disabled"
+                        }
+                    ]
+                ]
+            ],
+            "description": "quote_attr_values='always'",
+            "options": {
+                "quote_attr_values": "always"
+            }
+        },
+        {
+            "expected": [
+                "<div itemscope>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "itemscope",
+                            "value": "itemscope"
+                        }
+                    ]
+                ]
+            ],
+            "description": "quote_attr_values='always' with itemscope",
+            "options": {
+                "quote_attr_values": "always"
+            }
+        },
+        {
+            "expected": [
+                "<div irrelevant>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "irrelevant",
+                            "value": "irrelevant"
+                        }
+                    ]
+                ]
+            ],
+            "description": "quote_attr_values='always' with irrelevant",
+            "options": {
+                "quote_attr_values": "always"
+            }
+        },
+        {
+            "expected": [
+                "<div class=\"foo\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "class",
+                            "value": "foo"
+                        }
+                    ]
+                ]
+            ],
+            "description": "non-minimized quote_attr_values='always'",
+            "options": {
+                "quote_attr_values": "always"
+            }
+        },
+        {
+            "expected": [
+                "<div class=foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "class",
+                            "value": "foo"
+                        }
+                    ]
+                ]
+            ],
+            "description": "non-minimized quote_attr_values='legacy'",
+            "options": {
+                "quote_attr_values": "legacy"
+            }
+        },
+        {
+            "expected": [
+                "<div class=foo>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "class",
+                            "value": "foo"
+                        }
+                    ]
+                ]
+            ],
+            "description": "non-minimized quote_attr_values='spec'",
+            "options": {
+                "quote_attr_values": "spec"
+            }
+        },
+        {
+            "expected": [
+                "<img />"
+            ],
+            "input": [
+                [
+                    "EmptyTag",
+                    "img",
+                    {}
+                ]
+            ],
+            "description": "use_trailing_solidus=true with void element",
+            "options": {
+                "use_trailing_solidus": true
+            }
+        },
+        {
+            "expected": [
+                "<div>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    {}
+                ]
+            ],
+            "description": "use_trailing_solidus=true with non-void element",
+            "options": {
+                "use_trailing_solidus": true
+            }
+        },
+        {
+            "expected": [
+                "<div itemscope=itemscope>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "itemscope",
+                            "value": "itemscope"
+                        }
+                    ]
+                ]
+            ],
+            "description": "minimize_boolean_attributes=false",
+            "options": {
+                "minimize_boolean_attributes": false
+            }
+        },
+        {
+            "expected": [
+                "<div irrelevant=irrelevant>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "irrelevant",
+                            "value": "irrelevant"
+                        }
+                    ]
+                ]
+            ],
+            "description": "minimize_boolean_attributes=false",
+            "options": {
+                "minimize_boolean_attributes": false
+            }
+        },
+        {
+            "expected": [
+                "<div itemscope=\"\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "itemscope",
+                            "value": ""
+                        }
+                    ]
+                ]
+            ],
+            "description": "minimize_boolean_attributes=false with empty value",
+            "options": {
+                "minimize_boolean_attributes": false
+            }
+        },
+        {
+            "expected": [
+                "<div irrelevant=\"\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "div",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "irrelevant",
+                            "value": ""
+                        }
+                    ]
+                ]
+            ],
+            "description": "minimize_boolean_attributes=false with empty value",
+            "options": {
+                "minimize_boolean_attributes": false
+            }
+        },
+        {
+            "expected": [
+                "<a title=\"a&lt;b>c&amp;d\">"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "a",
+                    [
+                        {
+                            "namespace": null,
+                            "name": "title",
+                            "value": "a<b>c&d"
+                        }
+                    ]
+                ]
+            ],
+            "description": "escape less than signs in attribute values",
+            "options": {
+                "escape_lt_in_attrs": true
+            }
+        },
+        {
+            "expected": [
+                "<script>a&lt;b&gt;c&amp;d"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "script",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "a<b>c&d"
+                ]
+            ],
+            "description": "rcdata",
+            "options": {
+                "escape_rcdata": true
+            }
+        }
+    ]
+}
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/whitespace.test b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/whitespace.test
new file mode 100644
index 000000000000..dac3a69e27f8
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/serializer-testdata/whitespace.test
@@ -0,0 +1,198 @@
+{
+    "tests": [
+        {
+            "expected": [
+                " foo"
+            ],
+            "input": [
+                [
+                    "Characters",
+                    "\t\r\n\f foo"
+                ]
+            ],
+            "description": "bare text with leading spaces",
+            "options": {
+                "strip_whitespace": true
+            }
+        },
+        {
+            "expected": [
+                "foo "
+            ],
+            "input": [
+                [
+                    "Characters",
+                    "foo \t\r\n\f"
+                ]
+            ],
+            "description": "bare text with trailing spaces",
+            "options": {
+                "strip_whitespace": true
+            }
+        },
+        {
+            "expected": [
+                "foo bar"
+            ],
+            "input": [
+                [
+                    "Characters",
+                    "foo \t\r\n\f bar"
+                ]
+            ],
+            "description": "bare text with inner spaces",
+            "options": {
+                "strip_whitespace": true
+            }
+        },
+        {
+            "expected": [
+                "<pre>\t\r\n\f foo \t\r\n\f bar \t\r\n\f</pre>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "pre",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "\t\r\n\f foo \t\r\n\f bar \t\r\n\f"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "pre"
+                ]
+            ],
+            "description": "text within <pre>",
+            "options": {
+                "strip_whitespace": true
+            }
+        },
+        {
+            "expected": [
+                "<pre>\t\r\n\f fo<span>o \t\r\n\f b</span>ar \t\r\n\f</pre>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "pre",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "\t\r\n\f fo"
+                ],
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "o \t\r\n\f b"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "span"
+                ],
+                [
+                    "Characters",
+                    "ar \t\r\n\f"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "pre"
+                ]
+            ],
+            "description": "text within <pre>, with inner markup",
+            "options": {
+                "strip_whitespace": true
+            }
+        },
+        {
+            "expected": [
+                "<textarea>\t\r\n\f foo \t\r\n\f bar \t\r\n\f</textarea>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "textarea",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "\t\r\n\f foo \t\r\n\f bar \t\r\n\f"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "textarea"
+                ]
+            ],
+            "description": "text within <textarea>",
+            "options": {
+                "strip_whitespace": true
+            }
+        },
+        {
+            "expected": [
+                "<script>\t\r\n\f foo \t\r\n\f bar \t\r\n\f</script>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "script",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "\t\r\n\f foo \t\r\n\f bar \t\r\n\f"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "script"
+                ]
+            ],
+            "description": "text within <script>",
+            "options": {
+                "strip_whitespace": true
+            }
+        },
+        {
+            "expected": [
+                "<style>\t\r\n\f foo \t\r\n\f bar \t\r\n\f</style>"
+            ],
+            "input": [
+                [
+                    "StartTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "style",
+                    {}
+                ],
+                [
+                    "Characters",
+                    "\t\r\n\f foo \t\r\n\f bar \t\r\n\f"
+                ],
+                [
+                    "EndTag",
+                    "http://www.w3.org/1999/xhtml",
+                    "style"
+                ]
+            ],
+            "description": "text within <style>",
+            "options": {
+                "strip_whitespace": true
+            }
+        }
+    ]
+}
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/support.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/support.py
similarity index 70%
rename from testing/web-platform/tests/tools/html5lib/html5lib/tests/support.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/support.py
index 41f2d2a072d7..dab65c1c9d19 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/support.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/support.py
@@ -1,5 +1,7 @@
 from __future__ import absolute_import, division, unicode_literals
 
+# pylint:disable=wrong-import-position
+
 import os
 import sys
 import codecs
@@ -13,44 +15,66 @@ sys.path.insert(0, os.path.abspath(os.path.join(base_path,
                                                 os.path.pardir,
                                                 os.path.pardir)))
 
-from html5lib import treebuilders
+from html5lib import treebuilders, treewalkers, treeadapters  # noqa
 del base_path
 
-# Build a dict of avaliable trees
-treeTypes = {"DOM": treebuilders.getTreeBuilder("dom")}
+# Build a dict of available trees
+treeTypes = {}
 
-# Try whatever etree implementations are avaliable from a list that are
-#"supposed" to work
-try:
-    import xml.etree.ElementTree as ElementTree
-    treeTypes['ElementTree'] = treebuilders.getTreeBuilder("etree", ElementTree, fullTree=True)
-except ImportError:
-    try:
-        import elementtree.ElementTree as ElementTree
-        treeTypes['ElementTree'] = treebuilders.getTreeBuilder("etree", ElementTree, fullTree=True)
-    except ImportError:
-        pass
+# DOM impls
+treeTypes["DOM"] = {
+    "builder": treebuilders.getTreeBuilder("dom"),
+    "walker": treewalkers.getTreeWalker("dom")
+}
+
+# ElementTree impls
+import xml.etree.ElementTree as ElementTree  # noqa
+treeTypes['ElementTree'] = {
+    "builder": treebuilders.getTreeBuilder("etree", ElementTree, fullTree=True),
+    "walker": treewalkers.getTreeWalker("etree", ElementTree)
+}
 
 try:
-    import xml.etree.cElementTree as cElementTree
-    treeTypes['cElementTree'] = treebuilders.getTreeBuilder("etree", cElementTree, fullTree=True)
+    import xml.etree.cElementTree as cElementTree  # noqa
 except ImportError:
-    try:
-        import cElementTree
-        treeTypes['cElementTree'] = treebuilders.getTreeBuilder("etree", cElementTree, fullTree=True)
-    except ImportError:
-        pass
-
-try:
-    import lxml.etree as lxml  # flake8: noqa
-except ImportError:
-    pass
+    treeTypes['cElementTree'] = None
 else:
-    treeTypes['lxml'] = treebuilders.getTreeBuilder("lxml")
+    # On Python 3.3 and above cElementTree is an alias, don't run them twice.
+    if cElementTree.Element is ElementTree.Element:
+        treeTypes['cElementTree'] = None
+    else:
+        treeTypes['cElementTree'] = {
+            "builder": treebuilders.getTreeBuilder("etree", cElementTree, fullTree=True),
+            "walker": treewalkers.getTreeWalker("etree", cElementTree)
+        }
+
+try:
+    import lxml.etree as lxml  # noqa
+except ImportError:
+    treeTypes['lxml'] = None
+else:
+    treeTypes['lxml'] = {
+        "builder": treebuilders.getTreeBuilder("lxml"),
+        "walker": treewalkers.getTreeWalker("lxml")
+    }
+
+# Genshi impls
+try:
+    import genshi  # noqa
+except ImportError:
+    treeTypes["genshi"] = None
+else:
+    treeTypes["genshi"] = {
+        "builder": treebuilders.getTreeBuilder("dom"),
+        "adapter": lambda tree: treeadapters.genshi.to_genshi(treewalkers.getTreeWalker("dom")(tree)),
+        "walker": treewalkers.getTreeWalker("genshi")
+    }
+
+# pylint:enable=wrong-import-position
 
 
-def get_data_files(subdirectory, files='*.dat'):
-    return glob.glob(os.path.join(test_dir, subdirectory, files))
+def get_data_files(subdirectory, files='*.dat', search_dir=test_dir):
+    return sorted(glob.glob(os.path.join(search_dir, subdirectory, files)))
 
 
 class DefaultDict(dict):
@@ -71,9 +95,6 @@ class TestData(object):
         self.encoding = encoding
         self.newTestHeading = newTestHeading
 
-    def __del__(self):
-        self.f.close()
-
     def __iter__(self):
         data = DefaultDict(None)
         key = None
@@ -128,7 +149,7 @@ convertExpected = convert(2)
 def errorMessage(input, expected, actual):
     msg = ("Input:\n%s\nExpected:\n%s\nRecieved\n%s\n" %
            (repr(input), repr(expected), repr(actual)))
-    if sys.version_info.major == 2:
+    if sys.version_info[0] == 2:
         msg = msg.encode("ascii", "backslashreplace")
     return msg
 
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_alphabeticalattributes.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_alphabeticalattributes.py
new file mode 100644
index 000000000000..7d5b8e0f6560
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_alphabeticalattributes.py
@@ -0,0 +1,78 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from collections import OrderedDict
+
+import pytest
+
+import html5lib
+from html5lib.filters.alphabeticalattributes import Filter
+from html5lib.serializer import HTMLSerializer
+
+
+@pytest.mark.parametrize('msg, attrs, expected_attrs', [
+    (
+        'no attrs',
+        {},
+        {}
+    ),
+    (
+        'one attr',
+        {(None, 'alt'): 'image'},
+        OrderedDict([((None, 'alt'), 'image')])
+    ),
+    (
+        'multiple attrs',
+        {
+            (None, 'src'): 'foo',
+            (None, 'alt'): 'image',
+            (None, 'style'): 'border: 1px solid black;'
+        },
+        OrderedDict([
+            ((None, 'alt'), 'image'),
+            ((None, 'src'), 'foo'),
+            ((None, 'style'), 'border: 1px solid black;')
+        ])
+    ),
+])
+def test_alphabetizing(msg, attrs, expected_attrs):
+    tokens = [{'type': 'StartTag', 'name': 'img', 'data': attrs}]
+    output_tokens = list(Filter(tokens))
+
+    attrs = output_tokens[0]['data']
+    assert attrs == expected_attrs
+
+
+def test_with_different_namespaces():
+    tokens = [{
+        'type': 'StartTag',
+        'name': 'pattern',
+        'data': {
+            (None, 'id'): 'patt1',
+            ('http://www.w3.org/1999/xlink', 'href'): '#patt2'
+        }
+    }]
+    output_tokens = list(Filter(tokens))
+
+    attrs = output_tokens[0]['data']
+    assert attrs == OrderedDict([
+        ((None, 'id'), 'patt1'),
+        (('http://www.w3.org/1999/xlink', 'href'), '#patt2')
+    ])
+
+
+def test_with_serializer():
+    """Verify filter works in the context of everything else"""
+    parser = html5lib.HTMLParser()
+    dom = parser.parseFragment('<svg><pattern xlink:href="#patt2" id="patt1"></svg>')
+    walker = html5lib.getTreeWalker('etree')
+    ser = HTMLSerializer(
+        alphabetical_attributes=True,
+        quote_attr_values='always'
+    )
+
+    # FIXME(willkg): The "xlink" namespace gets dropped by the serializer. When
+    # that gets fixed, we can fix this expected result.
+    assert (
+        ser.render(walker(dom)) ==
+        '<svg><pattern id="patt1" href="#patt2"></pattern></svg>'
+    )
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_encoding.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_encoding.py
new file mode 100644
index 000000000000..9a411c77d288
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_encoding.py
@@ -0,0 +1,116 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import os
+
+import pytest
+
+from .support import get_data_files, test_dir, errorMessage, TestData as _TestData
+from html5lib import HTMLParser, _inputstream
+
+
+def test_basic_prescan_length():
+    data = "<title>Caf\u00E9</title><!--a--><meta charset='utf-8'>".encode('utf-8')
+    pad = 1024 - len(data) + 1
+    data = data.replace(b"-a-", b"-" + (b"a" * pad) + b"-")
+    assert len(data) == 1024  # Sanity
+    stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False)
+    assert 'utf-8' == stream.charEncoding[0].name
+
+
+def test_parser_reparse():
+    data = "<title>Caf\u00E9</title><!--a--><meta charset='utf-8'>".encode('utf-8')
+    pad = 10240 - len(data) + 1
+    data = data.replace(b"-a-", b"-" + (b"a" * pad) + b"-")
+    assert len(data) == 10240  # Sanity
+    stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False)
+    assert 'windows-1252' == stream.charEncoding[0].name
+    p = HTMLParser(namespaceHTMLElements=False)
+    doc = p.parse(data, useChardet=False)
+    assert 'utf-8' == p.documentEncoding
+    assert doc.find(".//title").text == "Caf\u00E9"
+
+
+@pytest.mark.parametrize("expected,data,kwargs", [
+    ("utf-16le", b"\xFF\xFE", {"override_encoding": "iso-8859-2"}),
+    ("utf-16be", b"\xFE\xFF", {"override_encoding": "iso-8859-2"}),
+    ("utf-8", b"\xEF\xBB\xBF", {"override_encoding": "iso-8859-2"}),
+    ("iso-8859-2", b"", {"override_encoding": "iso-8859-2", "transport_encoding": "iso-8859-3"}),
+    ("iso-8859-2", b"<meta charset=iso-8859-3>", {"transport_encoding": "iso-8859-2"}),
+    ("iso-8859-2", b"<meta charset=iso-8859-2>", {"same_origin_parent_encoding": "iso-8859-3"}),
+    ("iso-8859-2", b"", {"same_origin_parent_encoding": "iso-8859-2", "likely_encoding": "iso-8859-3"}),
+    ("iso-8859-2", b"", {"same_origin_parent_encoding": "utf-16", "likely_encoding": "iso-8859-2"}),
+    ("iso-8859-2", b"", {"same_origin_parent_encoding": "utf-16be", "likely_encoding": "iso-8859-2"}),
+    ("iso-8859-2", b"", {"same_origin_parent_encoding": "utf-16le", "likely_encoding": "iso-8859-2"}),
+    ("iso-8859-2", b"", {"likely_encoding": "iso-8859-2", "default_encoding": "iso-8859-3"}),
+    ("iso-8859-2", b"", {"default_encoding": "iso-8859-2"}),
+    ("windows-1252", b"", {"default_encoding": "totally-bogus-string"}),
+    ("windows-1252", b"", {}),
+])
+def test_parser_args(expected, data, kwargs):
+    stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False, **kwargs)
+    assert expected == stream.charEncoding[0].name
+    p = HTMLParser()
+    p.parse(data, useChardet=False, **kwargs)
+    assert expected == p.documentEncoding
+
+
+@pytest.mark.parametrize("kwargs", [
+    {"override_encoding": "iso-8859-2"},
+    {"override_encoding": None},
+    {"transport_encoding": "iso-8859-2"},
+    {"transport_encoding": None},
+    {"same_origin_parent_encoding": "iso-8859-2"},
+    {"same_origin_parent_encoding": None},
+    {"likely_encoding": "iso-8859-2"},
+    {"likely_encoding": None},
+    {"default_encoding": "iso-8859-2"},
+    {"default_encoding": None},
+    {"foo_encoding": "iso-8859-2"},
+    {"foo_encoding": None},
+])
+def test_parser_args_raises(kwargs):
+    with pytest.raises(TypeError) as exc_info:
+        p = HTMLParser()
+        p.parse("", useChardet=False, **kwargs)
+    assert exc_info.value.args[0].startswith("Cannot set an encoding with a unicode input")
+
+
+def runParserEncodingTest(data, encoding):
+    p = HTMLParser()
+    assert p.documentEncoding is None
+    p.parse(data, useChardet=False)
+    encoding = encoding.lower().decode("ascii")
+
+    assert encoding == p.documentEncoding, errorMessage(data, encoding, p.documentEncoding)
+
+
+def runPreScanEncodingTest(data, encoding):
+    stream = _inputstream.HTMLBinaryInputStream(data, useChardet=False)
+    encoding = encoding.lower().decode("ascii")
+
+    # Very crude way to ignore irrelevant tests
+    if len(data) > stream.numBytesMeta:
+        return
+
+    assert encoding == stream.charEncoding[0].name, errorMessage(data, encoding, stream.charEncoding[0].name)
+
+
+def test_encoding():
+    for filename in get_data_files("encoding"):
+        tests = _TestData(filename, b"data", encoding=None)
+        for test in tests:
+            yield (runParserEncodingTest, test[b'data'], test[b'encoding'])
+            yield (runPreScanEncodingTest, test[b'data'], test[b'encoding'])
+
+
+# pylint:disable=wrong-import-position
+try:
+    import chardet  # noqa
+except ImportError:
+    print("chardet not found, skipping chardet tests")
+else:
+    def test_chardet():
+        with open(os.path.join(test_dir, "encoding", "chardet", "test_big5.txt"), "rb") as fp:
+            encoding = _inputstream.HTMLInputStream(fp.read()).charEncoding
+            assert encoding[0].name == "big5"
+# pylint:enable=wrong-import-position
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_meta.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_meta.py
new file mode 100644
index 000000000000..e42eafdba4a0
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_meta.py
@@ -0,0 +1,41 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import six
+from mock import Mock
+
+from . import support
+
+
+def _createReprMock(r):
+    """Creates a mock with a __repr__ returning r
+
+    Also provides __str__ mock with default mock behaviour"""
+    mock = Mock()
+    mock.__repr__ = Mock()
+    mock.__repr__.return_value = r
+    mock.__str__ = Mock(wraps=mock.__str__)
+    return mock
+
+
+def test_errorMessage():
+    # Create mock objects to take repr of
+    input = _createReprMock("1")
+    expected = _createReprMock("2")
+    actual = _createReprMock("3")
+
+    # Run the actual test
+    r = support.errorMessage(input, expected, actual)
+
+    # Assertions!
+    if six.PY2:
+        assert b"Input:\n1\nExpected:\n2\nRecieved\n3\n" == r
+    else:
+        assert six.PY3
+        assert "Input:\n1\nExpected:\n2\nRecieved\n3\n" == r
+
+    assert input.__repr__.call_count == 1
+    assert expected.__repr__.call_count == 1
+    assert actual.__repr__.call_count == 1
+    assert not input.__str__.called
+    assert not expected.__str__.called
+    assert not actual.__str__.called
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_optionaltags_filter.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_optionaltags_filter.py
new file mode 100644
index 000000000000..cd2821497fdf
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_optionaltags_filter.py
@@ -0,0 +1,7 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from html5lib.filters.optionaltags import Filter
+
+
+def test_empty():
+    assert list(Filter([])) == []
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_parser2.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_parser2.py
new file mode 100644
index 000000000000..bcc0bf48f082
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_parser2.py
@@ -0,0 +1,130 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from six import PY2, text_type, unichr
+
+import io
+
+from . import support  # noqa
+
+from html5lib.constants import namespaces, tokenTypes
+from html5lib import parse, parseFragment, HTMLParser
+
+
+# tests that aren't autogenerated from text files
+def test_assertDoctypeCloneable():
+    doc = parse('<!DOCTYPE HTML>', treebuilder="dom")
+    assert doc.cloneNode(True) is not None
+
+
+def test_line_counter():
+    # http://groups.google.com/group/html5lib-discuss/browse_frm/thread/f4f00e4a2f26d5c0
+    assert parse("<pre>\nx\n&gt;\n</pre>") is not None
+
+
+def test_namespace_html_elements_0_dom():
+    doc = parse("<html></html>",
+                treebuilder="dom",
+                namespaceHTMLElements=True)
+    assert doc.childNodes[0].namespaceURI == namespaces["html"]
+
+
+def test_namespace_html_elements_1_dom():
+    doc = parse("<html></html>",
+                treebuilder="dom",
+                namespaceHTMLElements=False)
+    assert doc.childNodes[0].namespaceURI is None
+
+
+def test_namespace_html_elements_0_etree():
+    doc = parse("<html></html>",
+                treebuilder="etree",
+                namespaceHTMLElements=True)
+    assert doc.tag == "{%s}html" % (namespaces["html"],)
+
+
+def test_namespace_html_elements_1_etree():
+    doc = parse("<html></html>",
+                treebuilder="etree",
+                namespaceHTMLElements=False)
+    assert doc.tag == "html"
+
+
+def test_unicode_file():
+    assert parse(io.StringIO("a")) is not None
+
+
+def test_maintain_attribute_order():
+    # This is here because we impl it in parser and not tokenizer
+    p = HTMLParser()
+    # generate loads to maximize the chance a hash-based mutation will occur
+    attrs = [(unichr(x), i) for i, x in enumerate(range(ord('a'), ord('z')))]
+    token = {'name': 'html',
+             'selfClosing': False,
+             'selfClosingAcknowledged': False,
+             'type': tokenTypes["StartTag"],
+             'data': attrs}
+    out = p.normalizeToken(token)
+    attr_order = list(out["data"].keys())
+    assert attr_order == [x for x, i in attrs]
+
+
+def test_duplicate_attribute():
+    # This is here because we impl it in parser and not tokenizer
+    doc = parse('<p class=a class=b>')
+    el = doc[1][0]
+    assert el.get("class") == "a"
+
+
+def test_maintain_duplicate_attribute_order():
+    # This is here because we impl it in parser and not tokenizer
+    p = HTMLParser()
+    attrs = [(unichr(x), i) for i, x in enumerate(range(ord('a'), ord('z')))]
+    token = {'name': 'html',
+             'selfClosing': False,
+             'selfClosingAcknowledged': False,
+             'type': tokenTypes["StartTag"],
+             'data': attrs + [('a', len(attrs))]}
+    out = p.normalizeToken(token)
+    attr_order = list(out["data"].keys())
+    assert attr_order == [x for x, i in attrs]
+
+
+def test_debug_log():
+    parser = HTMLParser(debug=True)
+    parser.parse("<!doctype html><title>a</title><p>b<script>c</script>d</p>e")
+
+    expected = [('dataState', 'InitialPhase', 'InitialPhase', 'processDoctype', {'type': 'Doctype'}),
+                ('dataState', 'BeforeHtmlPhase', 'BeforeHtmlPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
+                ('dataState', 'BeforeHeadPhase', 'BeforeHeadPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
+                ('dataState', 'InHeadPhase', 'InHeadPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
+                ('rcdataState', 'TextPhase', 'TextPhase', 'processCharacters', {'type': 'Characters'}),
+                ('dataState', 'TextPhase', 'TextPhase', 'processEndTag', {'name': 'title', 'type': 'EndTag'}),
+                ('dataState', 'InHeadPhase', 'InHeadPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
+                ('dataState', 'AfterHeadPhase', 'AfterHeadPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processStartTag', {'name': 'script', 'type': 'StartTag'}),
+                ('dataState', 'InBodyPhase', 'InHeadPhase', 'processStartTag', {'name': 'script', 'type': 'StartTag'}),
+                ('scriptDataState', 'TextPhase', 'TextPhase', 'processCharacters', {'type': 'Characters'}),
+                ('dataState', 'TextPhase', 'TextPhase', 'processEndTag', {'name': 'script', 'type': 'EndTag'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processEndTag', {'name': 'p', 'type': 'EndTag'}),
+                ('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'})]
+
+    if PY2:
+        for i, log in enumerate(expected):
+            log = [x.encode("ascii") if isinstance(x, text_type) else x for x in log]
+            expected[i] = tuple(log)
+
+    assert parser.log == expected
+
+
+def test_no_duplicate_clone():
+    frag = parseFragment("<b><em><foo><foob><fooc><aside></b></em>")
+    assert len(frag) == 2
+
+
+def test_self_closing_col():
+    parser = HTMLParser()
+    parser.parseFragment('<table><colgroup><col /></colgroup></table>')
+    assert not parser.errors
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_sanitizer.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_sanitizer.py
new file mode 100644
index 000000000000..45046d572297
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_sanitizer.py
@@ -0,0 +1,127 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from html5lib import constants, parseFragment, serialize
+from html5lib.filters import sanitizer
+
+
+def runSanitizerTest(_, expected, input):
+    parsed = parseFragment(expected)
+    expected = serialize(parsed,
+                         omit_optional_tags=False,
+                         use_trailing_solidus=True,
+                         space_before_trailing_solidus=False,
+                         quote_attr_values="always",
+                         quote_char='"',
+                         alphabetical_attributes=True)
+    assert expected == sanitize_html(input)
+
+
+def sanitize_html(stream):
+    parsed = parseFragment(stream)
+    serialized = serialize(parsed,
+                           sanitize=True,
+                           omit_optional_tags=False,
+                           use_trailing_solidus=True,
+                           space_before_trailing_solidus=False,
+                           quote_attr_values="always",
+                           quote_char='"',
+                           alphabetical_attributes=True)
+    return serialized
+
+
+def test_should_handle_astral_plane_characters():
+    sanitized = sanitize_html("<p>&#x1d4b5; &#x1d538;</p>")
+    expected = '<p>\U0001d4b5 \U0001d538</p>'
+    assert expected == sanitized
+
+
+def test_should_allow_relative_uris():
+    sanitized = sanitize_html('<p><a href="/example.com"></a></p>')
+    expected = '<p><a href="/example.com"></a></p>'
+    assert expected == sanitized
+
+
+def test_invalid_data_uri():
+    sanitized = sanitize_html('<audio controls="" src="data:foobar"></audio>')
+    expected = '<audio controls></audio>'
+    assert expected == sanitized
+
+
+def test_invalid_ipv6_url():
+    sanitized = sanitize_html('<a href="h://]">')
+    expected = "<a></a>"
+    assert expected == sanitized
+
+
+def test_data_uri_disallowed_type():
+    sanitized = sanitize_html('<audio controls="" src="data:text/html,<html>"></audio>')
+    expected = "<audio controls></audio>"
+    assert expected == sanitized
+
+
+def test_sanitizer():
+    for ns, tag_name in sanitizer.allowed_elements:
+        if ns != constants.namespaces["html"]:
+            continue
+        if tag_name in ['caption', 'col', 'colgroup', 'optgroup', 'option', 'table', 'tbody', 'td',
+                        'tfoot', 'th', 'thead', 'tr', 'select']:
+            continue  # TODO
+        if tag_name == 'image':
+            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
+                   "<img title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz",
+                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
+        elif tag_name == 'br':
+            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
+                   "<br title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz<br/>",
+                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
+        elif tag_name in constants.voidElements:
+            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
+                   "<%s title=\"1\"/>foo &lt;bad&gt;bar&lt;/bad&gt; baz" % tag_name,
+                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
+        else:
+            yield (runSanitizerTest, "test_should_allow_%s_tag" % tag_name,
+                   "<%s title=\"1\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</%s>" % (tag_name, tag_name),
+                   "<%s title='1'>foo <bad>bar</bad> baz</%s>" % (tag_name, tag_name))
+
+    for ns, attribute_name in sanitizer.allowed_attributes:
+        if ns is not None:
+            continue
+        if attribute_name != attribute_name.lower():
+            continue  # TODO
+        if attribute_name == 'style':
+            continue
+        attribute_value = 'foo'
+        if attribute_name in sanitizer.attr_val_is_uri:
+            attribute_value = '%s://sub.domain.tld/path/object.ext' % sanitizer.allowed_protocols[0]
+        yield (runSanitizerTest, "test_should_allow_%s_attribute" % attribute_name,
+               "<p %s=\"%s\">foo &lt;bad&gt;bar&lt;/bad&gt; baz</p>" % (attribute_name, attribute_value),
+               "<p %s='%s'>foo <bad>bar</bad> baz</p>" % (attribute_name, attribute_value))
+
+    for protocol in sanitizer.allowed_protocols:
+        rest_of_uri = '//sub.domain.tld/path/object.ext'
+        if protocol == 'data':
+            rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='
+        yield (runSanitizerTest, "test_should_allow_uppercase_%s_uris" % protocol,
+               "<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
+               """<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))
+
+    for protocol in sanitizer.allowed_protocols:
+        rest_of_uri = '//sub.domain.tld/path/object.ext'
+        if protocol == 'data':
+            rest_of_uri = 'image/png;base64,aGVsbG8gd29ybGQ='
+        protocol = protocol.upper()
+        yield (runSanitizerTest, "test_should_allow_uppercase_%s_uris" % protocol,
+               "<img src=\"%s:%s\">foo</a>" % (protocol, rest_of_uri),
+               """<img src="%s:%s">foo</a>""" % (protocol, rest_of_uri))
+
+
+def test_lowercase_color_codes_in_style():
+    sanitized = sanitize_html("<p style=\"border: 1px solid #a2a2a2;\"></p>")
+    expected = '<p style=\"border: 1px solid #a2a2a2;\"></p>'
+    assert expected == sanitized
+
+
+def test_uppercase_color_codes_in_style():
+    sanitized = sanitize_html("<p style=\"border: 1px solid #A2A2A2;\"></p>")
+    expected = '<p style=\"border: 1px solid #A2A2A2;\"></p>'
+    assert expected == sanitized
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_serializer.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_serializer.py
new file mode 100644
index 000000000000..9333286ef142
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_serializer.py
@@ -0,0 +1,225 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import os
+import json
+
+import pytest
+
+from .support import get_data_files
+
+from html5lib import constants
+from html5lib.filters.lint import Filter as Lint
+from html5lib.serializer import HTMLSerializer, serialize
+from html5lib.treewalkers.base import TreeWalker
+
+# pylint:disable=wrong-import-position
+optionals_loaded = []
+
+try:
+    from lxml import etree
+    optionals_loaded.append("lxml")
+except ImportError:
+    pass
+# pylint:enable=wrong-import-position
+
+default_namespace = constants.namespaces["html"]
+
+
+class JsonWalker(TreeWalker):
+    def __iter__(self):
+        for token in self.tree:
+            type = token[0]
+            if type == "StartTag":
+                if len(token) == 4:
+                    namespace, name, attrib = token[1:4]
+                else:
+                    namespace = default_namespace
+                    name, attrib = token[1:3]
+                yield self.startTag(namespace, name, self._convertAttrib(attrib))
+            elif type == "EndTag":
+                if len(token) == 3:
+                    namespace, name = token[1:3]
+                else:
+                    namespace = default_namespace
+                    name = token[1]
+                yield self.endTag(namespace, name)
+            elif type == "EmptyTag":
+                if len(token) == 4:
+                    namespace, name, attrib = token[1:]
+                else:
+                    namespace = default_namespace
+                    name, attrib = token[1:]
+                for token in self.emptyTag(namespace, name, self._convertAttrib(attrib)):
+                    yield token
+            elif type == "Comment":
+                yield self.comment(token[1])
+            elif type in ("Characters", "SpaceCharacters"):
+                for token in self.text(token[1]):
+                    yield token
+            elif type == "Doctype":
+                if len(token) == 4:
+                    yield self.doctype(token[1], token[2], token[3])
+                elif len(token) == 3:
+                    yield self.doctype(token[1], token[2])
+                else:
+                    yield self.doctype(token[1])
+            else:
+                raise ValueError("Unknown token type: " + type)
+
+    def _convertAttrib(self, attribs):
+        """html5lib tree-walkers use a dict of (namespace, name): value for
+        attributes, but JSON cannot represent this. Convert from the format
+        in the serializer tests (a list of dicts with "namespace", "name",
+        and "value" as keys) to html5lib's tree-walker format."""
+        attrs = {}
+        for attrib in attribs:
+            name = (attrib["namespace"], attrib["name"])
+            assert(name not in attrs)
+            attrs[name] = attrib["value"]
+        return attrs
+
+
+def serialize_html(input, options):
+    options = dict([(str(k), v) for k, v in options.items()])
+    encoding = options.get("encoding", None)
+    if "encoding" in options:
+        del options["encoding"]
+    stream = Lint(JsonWalker(input), False)
+    serializer = HTMLSerializer(alphabetical_attributes=True, **options)
+    return serializer.render(stream, encoding)
+
+
+def runSerializerTest(input, expected, options):
+    encoding = options.get("encoding", None)
+
+    if encoding:
+        expected = list(map(lambda x: x.encode(encoding), expected))
+
+    result = serialize_html(input, options)
+    if len(expected) == 1:
+        assert expected[0] == result, "Expected:\n%s\nActual:\n%s\nOptions:\n%s" % (expected[0], result, str(options))
+    elif result not in expected:
+        assert False, "Expected: %s, Received: %s" % (expected, result)
+
+
+def throwsWithLatin1(input):
+    with pytest.raises(UnicodeEncodeError):
+        serialize_html(input, {"encoding": "iso-8859-1"})
+
+
+def testDoctypeName():
+    throwsWithLatin1([["Doctype", "\u0101"]])
+
+
+def testDoctypePublicId():
+    throwsWithLatin1([["Doctype", "potato", "\u0101"]])
+
+
+def testDoctypeSystemId():
+    throwsWithLatin1([["Doctype", "potato", "potato", "\u0101"]])
+
+
+def testCdataCharacters():
+    runSerializerTest([["StartTag", "http://www.w3.org/1999/xhtml", "style", {}], ["Characters", "\u0101"]],
+                      ["<style>&amacr;"], {"encoding": "iso-8859-1"})
+
+
+def testCharacters():
+    runSerializerTest([["Characters", "\u0101"]],
+                      ["&amacr;"], {"encoding": "iso-8859-1"})
+
+
+def testStartTagName():
+    throwsWithLatin1([["StartTag", "http://www.w3.org/1999/xhtml", "\u0101", []]])
+
+
+def testAttributeName():
+    throwsWithLatin1([["StartTag", "http://www.w3.org/1999/xhtml", "span", [{"namespace": None, "name": "\u0101", "value": "potato"}]]])
+
+
+def testAttributeValue():
+    runSerializerTest([["StartTag", "http://www.w3.org/1999/xhtml", "span",
+                        [{"namespace": None, "name": "potato", "value": "\u0101"}]]],
+                      ["<span potato=&amacr;>"], {"encoding": "iso-8859-1"})
+
+
+def testEndTagName():
+    throwsWithLatin1([["EndTag", "http://www.w3.org/1999/xhtml", "\u0101"]])
+
+
+def testComment():
+    throwsWithLatin1([["Comment", "\u0101"]])
+
+
+def testThrowsUnknownOption():
+    with pytest.raises(TypeError):
+        HTMLSerializer(foobar=None)
+
+
+@pytest.mark.parametrize("c", list("\t\n\u000C\x20\r\"'=<>`"))
+def testSpecQuoteAttribute(c):
+    input_ = [["StartTag", "http://www.w3.org/1999/xhtml", "span",
+               [{"namespace": None, "name": "foo", "value": c}]]]
+    if c == '"':
+        output_ = ["<span foo='%s'>" % c]
+    else:
+        output_ = ['<span foo="%s">' % c]
+    options_ = {"quote_attr_values": "spec"}
+    runSerializerTest(input_, output_, options_)
+
+
+@pytest.mark.parametrize("c", list("\t\n\u000C\x20\r\"'=<>`"
+                                   "\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n"
+                                   "\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15"
+                                   "\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"
+                                   "\x20\x2f\x60\xa0\u1680\u180e\u180f\u2000"
+                                   "\u2001\u2002\u2003\u2004\u2005\u2006\u2007"
+                                   "\u2008\u2009\u200a\u2028\u2029\u202f\u205f"
+                                   "\u3000"))
+def testLegacyQuoteAttribute(c):
+    input_ = [["StartTag", "http://www.w3.org/1999/xhtml", "span",
+               [{"namespace": None, "name": "foo", "value": c}]]]
+    if c == '"':
+        output_ = ["<span foo='%s'>" % c]
+    else:
+        output_ = ['<span foo="%s">' % c]
+    options_ = {"quote_attr_values": "legacy"}
+    runSerializerTest(input_, output_, options_)
+
+
+@pytest.fixture
+def lxml_parser():
+    return etree.XMLParser(resolve_entities=False)
+
+
+@pytest.mark.skipif("lxml" not in optionals_loaded, reason="lxml not importable")
+def testEntityReplacement(lxml_parser):
+    doc = '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>'
+    tree = etree.fromstring(doc, parser=lxml_parser).getroottree()
+    result = serialize(tree, tree="lxml", omit_optional_tags=False)
+    assert result == '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>\u03B2</html>'
+
+
+@pytest.mark.skipif("lxml" not in optionals_loaded, reason="lxml not importable")
+def testEntityXML(lxml_parser):
+    doc = '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&gt;</html>'
+    tree = etree.fromstring(doc, parser=lxml_parser).getroottree()
+    result = serialize(tree, tree="lxml", omit_optional_tags=False)
+    assert result == '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&gt;</html>'
+
+
+@pytest.mark.skipif("lxml" not in optionals_loaded, reason="lxml not importable")
+def testEntityNoResolve(lxml_parser):
+    doc = '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>'
+    tree = etree.fromstring(doc, parser=lxml_parser).getroottree()
+    result = serialize(tree, tree="lxml", omit_optional_tags=False,
+                                  resolve_entities=False)
+    assert result == '<!DOCTYPE html SYSTEM "about:legacy-compat"><html>&beta;</html>'
+
+
+def test_serializer():
+    for filename in get_data_files('serializer-testdata', '*.test', os.path.dirname(__file__)):
+        with open(filename) as fp:
+            tests = json.load(fp)
+            for test in tests['tests']:
+                yield runSerializerTest, test["input"], test["expected"], test.get("options", {})
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_stream.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_stream.py
new file mode 100644
index 000000000000..27c39538c8b1
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_stream.py
@@ -0,0 +1,323 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from . import support  # noqa
+
+import codecs
+import sys
+from io import BytesIO, StringIO
+
+import pytest
+
+import six
+from six.moves import http_client, urllib
+
+from html5lib._inputstream import (BufferedStream, HTMLInputStream,
+                                   HTMLUnicodeInputStream, HTMLBinaryInputStream)
+from html5lib._utils import supports_lone_surrogates
+
+
+def test_basic():
+    s = b"abc"
+    fp = BufferedStream(BytesIO(s))
+    read = fp.read(10)
+    assert read == s
+
+
+def test_read_length():
+    fp = BufferedStream(BytesIO(b"abcdef"))
+    read1 = fp.read(1)
+    assert read1 == b"a"
+    read2 = fp.read(2)
+    assert read2 == b"bc"
+    read3 = fp.read(3)
+    assert read3 == b"def"
+    read4 = fp.read(4)
+    assert read4 == b""
+
+
+def test_tell():
+    fp = BufferedStream(BytesIO(b"abcdef"))
+    read1 = fp.read(1)
+    assert read1 == b"a"
+    assert fp.tell() == 1
+    read2 = fp.read(2)
+    assert read2 == b"bc"
+    assert fp.tell() == 3
+    read3 = fp.read(3)
+    assert read3 == b"def"
+    assert fp.tell() == 6
+    read4 = fp.read(4)
+    assert read4 == b""
+    assert fp.tell() == 6
+
+
+def test_seek():
+    fp = BufferedStream(BytesIO(b"abcdef"))
+    read1 = fp.read(1)
+    assert read1 == b"a"
+    fp.seek(0)
+    read2 = fp.read(1)
+    assert read2 == b"a"
+    read3 = fp.read(2)
+    assert read3 == b"bc"
+    fp.seek(2)
+    read4 = fp.read(2)
+    assert read4 == b"cd"
+    fp.seek(4)
+    read5 = fp.read(2)
+    assert read5 == b"ef"
+
+
+def test_seek_tell():
+    fp = BufferedStream(BytesIO(b"abcdef"))
+    read1 = fp.read(1)
+    assert read1 == b"a"
+    assert fp.tell() == 1
+    fp.seek(0)
+    read2 = fp.read(1)
+    assert read2 == b"a"
+    assert fp.tell() == 1
+    read3 = fp.read(2)
+    assert read3 == b"bc"
+    assert fp.tell() == 3
+    fp.seek(2)
+    read4 = fp.read(2)
+    assert read4 == b"cd"
+    assert fp.tell() == 4
+    fp.seek(4)
+    read5 = fp.read(2)
+    assert read5 == b"ef"
+    assert fp.tell() == 6
+
+
+class HTMLUnicodeInputStreamShortChunk(HTMLUnicodeInputStream):
+    _defaultChunkSize = 2
+
+
+class HTMLBinaryInputStreamShortChunk(HTMLBinaryInputStream):
+    _defaultChunkSize = 2
+
+
+def test_char_ascii():
+    stream = HTMLInputStream(b"'", override_encoding='ascii')
+    assert stream.charEncoding[0].name == 'windows-1252'
+    assert stream.char() == "'"
+
+
+def test_char_utf8():
+    stream = HTMLInputStream('\u2018'.encode('utf-8'), override_encoding='utf-8')
+    assert stream.charEncoding[0].name == 'utf-8'
+    assert stream.char() == '\u2018'
+
+
+def test_char_win1252():
+    stream = HTMLInputStream("\xa9\xf1\u2019".encode('windows-1252'))
+    assert stream.charEncoding[0].name == 'windows-1252'
+    assert stream.char() == "\xa9"
+    assert stream.char() == "\xf1"
+    assert stream.char() == "\u2019"
+
+
+def test_bom():
+    stream = HTMLInputStream(codecs.BOM_UTF8 + b"'")
+    assert stream.charEncoding[0].name == 'utf-8'
+    assert stream.char() == "'"
+
+
+def test_utf_16():
+    stream = HTMLInputStream((' ' * 1025).encode('utf-16'))
+    assert stream.charEncoding[0].name in ['utf-16le', 'utf-16be']
+    assert len(stream.charsUntil(' ', True)) == 1025
+
+
+def test_newlines():
+    stream = HTMLBinaryInputStreamShortChunk(codecs.BOM_UTF8 + b"a\nbb\r\nccc\rddddxe")
+    assert stream.position() == (1, 0)
+    assert stream.charsUntil('c') == "a\nbb\n"
+    assert stream.position() == (3, 0)
+    assert stream.charsUntil('x') == "ccc\ndddd"
+    assert stream.position() == (4, 4)
+    assert stream.charsUntil('e') == "x"
+    assert stream.position() == (4, 5)
+
+
+def test_newlines2():
+    size = HTMLUnicodeInputStream._defaultChunkSize
+    stream = HTMLInputStream("\r" * size + "\n")
+    assert stream.charsUntil('x') == "\n" * size
+
+
+def test_position():
+    stream = HTMLBinaryInputStreamShortChunk(codecs.BOM_UTF8 + b"a\nbb\nccc\nddde\nf\ngh")
+    assert stream.position() == (1, 0)
+    assert stream.charsUntil('c') == "a\nbb\n"
+    assert stream.position() == (3, 0)
+    stream.unget("\n")
+    assert stream.position() == (2, 2)
+    assert stream.charsUntil('c') == "\n"
+    assert stream.position() == (3, 0)
+    stream.unget("\n")
+    assert stream.position() == (2, 2)
+    assert stream.char() == "\n"
+    assert stream.position() == (3, 0)
+    assert stream.charsUntil('e') == "ccc\nddd"
+    assert stream.position() == (4, 3)
+    assert stream.charsUntil('h') == "e\nf\ng"
+    assert stream.position() == (6, 1)
+
+
+def test_position2():
+    stream = HTMLUnicodeInputStreamShortChunk("abc\nd")
+    assert stream.position() == (1, 0)
+    assert stream.char() == "a"
+    assert stream.position() == (1, 1)
+    assert stream.char() == "b"
+    assert stream.position() == (1, 2)
+    assert stream.char() == "c"
+    assert stream.position() == (1, 3)
+    assert stream.char() == "\n"
+    assert stream.position() == (2, 0)
+    assert stream.char() == "d"
+    assert stream.position() == (2, 1)
+
+
+def test_python_issue_20007():
+    """
+    Make sure we have a work-around for Python bug #20007
+    http://bugs.python.org/issue20007
+    """
+    class FakeSocket(object):
+        def makefile(self, _mode, _bufsize=None):
+            # pylint:disable=unused-argument
+            return BytesIO(b"HTTP/1.1 200 Ok\r\n\r\nText")
+
+    source = http_client.HTTPResponse(FakeSocket())
+    source.begin()
+    stream = HTMLInputStream(source)
+    assert stream.charsUntil(" ") == "Text"
+
+
+def test_python_issue_20007_b():
+    """
+    Make sure we have a work-around for Python bug #20007
+    http://bugs.python.org/issue20007
+    """
+    if six.PY2:
+        return
+
+    class FakeSocket(object):
+        def makefile(self, _mode, _bufsize=None):
+            # pylint:disable=unused-argument
+            return BytesIO(b"HTTP/1.1 200 Ok\r\n\r\nText")
+
+    source = http_client.HTTPResponse(FakeSocket())
+    source.begin()
+    wrapped = urllib.response.addinfourl(source, source.msg, "http://example.com")
+    stream = HTMLInputStream(wrapped)
+    assert stream.charsUntil(" ") == "Text"
+
+
+@pytest.mark.parametrize("inp,num",
+                         [("\u0000", 0),
+                          ("\u0001", 1),
+                          ("\u0008", 1),
+                          ("\u0009", 0),
+                          ("\u000A", 0),
+                          ("\u000B", 1),
+                          ("\u000C", 0),
+                          ("\u000D", 0),
+                          ("\u000E", 1),
+                          ("\u001F", 1),
+                          ("\u0020", 0),
+                          ("\u007E", 0),
+                          ("\u007F", 1),
+                          ("\u009F", 1),
+                          ("\u00A0", 0),
+                          ("\uFDCF", 0),
+                          ("\uFDD0", 1),
+                          ("\uFDEF", 1),
+                          ("\uFDF0", 0),
+                          ("\uFFFD", 0),
+                          ("\uFFFE", 1),
+                          ("\uFFFF", 1),
+                          ("\U0001FFFD", 0),
+                          ("\U0001FFFE", 1),
+                          ("\U0001FFFF", 1),
+                          ("\U0002FFFD", 0),
+                          ("\U0002FFFE", 1),
+                          ("\U0002FFFF", 1),
+                          ("\U0003FFFD", 0),
+                          ("\U0003FFFE", 1),
+                          ("\U0003FFFF", 1),
+                          ("\U0004FFFD", 0),
+                          ("\U0004FFFE", 1),
+                          ("\U0004FFFF", 1),
+                          ("\U0005FFFD", 0),
+                          ("\U0005FFFE", 1),
+                          ("\U0005FFFF", 1),
+                          ("\U0006FFFD", 0),
+                          ("\U0006FFFE", 1),
+                          ("\U0006FFFF", 1),
+                          ("\U0007FFFD", 0),
+                          ("\U0007FFFE", 1),
+                          ("\U0007FFFF", 1),
+                          ("\U0008FFFD", 0),
+                          ("\U0008FFFE", 1),
+                          ("\U0008FFFF", 1),
+                          ("\U0009FFFD", 0),
+                          ("\U0009FFFE", 1),
+                          ("\U0009FFFF", 1),
+                          ("\U000AFFFD", 0),
+                          ("\U000AFFFE", 1),
+                          ("\U000AFFFF", 1),
+                          ("\U000BFFFD", 0),
+                          ("\U000BFFFE", 1),
+                          ("\U000BFFFF", 1),
+                          ("\U000CFFFD", 0),
+                          ("\U000CFFFE", 1),
+                          ("\U000CFFFF", 1),
+                          ("\U000DFFFD", 0),
+                          ("\U000DFFFE", 1),
+                          ("\U000DFFFF", 1),
+                          ("\U000EFFFD", 0),
+                          ("\U000EFFFE", 1),
+                          ("\U000EFFFF", 1),
+                          ("\U000FFFFD", 0),
+                          ("\U000FFFFE", 1),
+                          ("\U000FFFFF", 1),
+                          ("\U0010FFFD", 0),
+                          ("\U0010FFFE", 1),
+                          ("\U0010FFFF", 1),
+                          ("\x01\x01\x01", 3),
+                          ("a\x01a\x01a\x01a", 3)])
+def test_invalid_codepoints(inp, num):
+    stream = HTMLUnicodeInputStream(StringIO(inp))
+    for _i in range(len(inp)):
+        stream.char()
+    assert len(stream.errors) == num
+
+
+@pytest.mark.skipif(not supports_lone_surrogates, reason="doesn't support lone surrogates")
+@pytest.mark.parametrize("inp,num",
+                         [("'\\uD7FF'", 0),
+                          ("'\\uD800'", 1),
+                          ("'\\uDBFF'", 1),
+                          ("'\\uDC00'", 1),
+                          ("'\\uDFFF'", 1),
+                          ("'\\uE000'", 0),
+                          ("'\\uD800\\uD800\\uD800'", 3),
+                          ("'a\\uD800a\\uD800a\\uD800a'", 3),
+                          ("'\\uDFFF\\uDBFF'", 2),
+                          pytest.mark.skipif(sys.maxunicode == 0xFFFF,
+                                             ("'\\uDBFF\\uDFFF'", 2),
+                                             reason="narrow Python")])
+def test_invalid_codepoints_surrogates(inp, num):
+    inp = eval(inp)  # pylint:disable=eval-used
+    fp = StringIO(inp)
+    if ord(max(fp.read())) > 0xFFFF:
+        pytest.skip("StringIO altered string")
+    fp.seek(0)
+    stream = HTMLUnicodeInputStream(fp)
+    for _i in range(len(inp)):
+        stream.char()
+    assert len(stream.errors) == num
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_treeadapters.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_treeadapters.py
similarity index 93%
rename from testing/web-platform/tests/tools/html5lib/html5lib/tests/test_treeadapters.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_treeadapters.py
index 5f38b6c33d25..95e56c00c9da 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_treeadapters.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_treeadapters.py
@@ -1,6 +1,6 @@
 from __future__ import absolute_import, division, unicode_literals
 
-from . import support  # flake8: noqa
+from . import support  # noqa
 
 import html5lib
 from html5lib.treeadapters import sax
@@ -25,7 +25,7 @@ def test_to_sax():
         ('endElementNS', ('http://www.w3.org/1999/xhtml', 'title'), 'title'),
         ('characters', '\n        '),
         ('endElementNS', ('http://www.w3.org/1999/xhtml', 'head'), 'head'),
-        ('startElementNS',  ('http://www.w3.org/1999/xhtml', 'body'), 'body', {}),
+        ('startElementNS', ('http://www.w3.org/1999/xhtml', 'body'), 'body', {}),
         ('startElementNS', ('http://www.w3.org/1999/xhtml', 'a'), 'a', {(None, 'href'): '/'}),
         ('startElementNS', ('http://www.w3.org/1999/xhtml', 'b'), 'b', {}),
         ('startElementNS', ('http://www.w3.org/1999/xhtml', 'p'), 'p', {}),
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_treewalkers.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_treewalkers.py
new file mode 100644
index 000000000000..67fc89e55f3b
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_treewalkers.py
@@ -0,0 +1,136 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import itertools
+
+import pytest
+
+try:
+    import lxml.etree
+except ImportError:
+    pass
+
+from .support import treeTypes
+
+from html5lib import html5parser, treewalkers
+from html5lib.filters.lint import Filter as Lint
+
+import re
+attrlist = re.compile(r"^(\s+)\w+=.*(\n\1\w+=.*)+", re.M)
+
+
+def sortattrs(x):
+    lines = x.group(0).split("\n")
+    lines.sort()
+    return "\n".join(lines)
+
+
+def test_all_tokens():
+    expected = [
+        {'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'html'},
+        {'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'head'},
+        {'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'head'},
+        {'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'body'},
+        {'data': 'a', 'type': 'Characters'},
+        {'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'div'},
+        {'data': 'b', 'type': 'Characters'},
+        {'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'div'},
+        {'data': 'c', 'type': 'Characters'},
+        {'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'body'},
+        {'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'html'}
+    ]
+    for _, treeCls in sorted(treeTypes.items()):
+        if treeCls is None:
+            continue
+        p = html5parser.HTMLParser(tree=treeCls["builder"])
+        document = p.parse("<html><head></head><body>a<div>b</div>c</body></html>")
+        document = treeCls.get("adapter", lambda x: x)(document)
+        output = Lint(treeCls["walker"](document))
+        for expectedToken, outputToken in zip(expected, output):
+            assert expectedToken == outputToken
+
+
+def set_attribute_on_first_child(docfrag, name, value, treeName):
+    """naively sets an attribute on the first child of the document
+    fragment passed in"""
+    setter = {'ElementTree': lambda d: d[0].set,
+              'DOM': lambda d: d.firstChild.setAttribute}
+    setter['cElementTree'] = setter['ElementTree']
+    try:
+        setter.get(treeName, setter['DOM'])(docfrag)(name, value)
+    except AttributeError:
+        setter['ElementTree'](docfrag)(name, value)
+
+
+def runTreewalkerEditTest(intext, expected, attrs_to_add, tree):
+    """tests what happens when we add attributes to the intext"""
+    treeName, treeClass = tree
+    if treeClass is None:
+        pytest.skip("Treebuilder not loaded")
+    parser = html5parser.HTMLParser(tree=treeClass["builder"])
+    document = parser.parseFragment(intext)
+    for nom, val in attrs_to_add:
+        set_attribute_on_first_child(document, nom, val, treeName)
+
+    document = treeClass.get("adapter", lambda x: x)(document)
+    output = treewalkers.pprint(treeClass["walker"](document))
+    output = attrlist.sub(sortattrs, output)
+    if output not in expected:
+        raise AssertionError("TreewalkerEditTest: %s\nExpected:\n%s\nReceived:\n%s" % (treeName, expected, output))
+
+
+def test_treewalker_six_mix():
+    """Str/Unicode mix. If str attrs added to tree"""
+
+    # On Python 2.x string literals are of type str. Unless, like this
+    # file, the programmer imports unicode_literals from __future__.
+    # In that case, string literals become objects of type unicode.
+
+    # This test simulates a Py2 user, modifying attributes on a document
+    # fragment but not using the u'' syntax nor importing unicode_literals
+    sm_tests = [
+        ('<a href="http://example.com">Example</a>',
+         [(str('class'), str('test123'))],
+         '<a>\n  class="test123"\n  href="http://example.com"\n  "Example"'),
+
+        ('<link href="http://example.com/cow">',
+         [(str('rel'), str('alternate'))],
+         '<link>\n  href="http://example.com/cow"\n  rel="alternate"\n  "Example"')
+    ]
+
+    for tree in sorted(treeTypes.items()):
+        for intext, attrs, expected in sm_tests:
+            yield runTreewalkerEditTest, intext, expected, attrs, tree
+
+
+@pytest.mark.parametrize("tree,char", itertools.product(sorted(treeTypes.items()), ["x", "\u1234"]))
+def test_fragment_single_char(tree, char):
+    expected = [
+        {'data': char, 'type': 'Characters'}
+    ]
+
+    treeName, treeClass = tree
+    if treeClass is None:
+        pytest.skip("Treebuilder not loaded")
+
+    parser = html5parser.HTMLParser(tree=treeClass["builder"])
+    document = parser.parseFragment(char)
+    document = treeClass.get("adapter", lambda x: x)(document)
+    output = Lint(treeClass["walker"](document))
+
+    assert list(output) == expected
+
+
+@pytest.mark.skipif(treeTypes["lxml"] is None, reason="lxml not importable")
+def test_lxml_xml():
+    expected = [
+        {'data': {}, 'name': 'div', 'namespace': None, 'type': 'StartTag'},
+        {'data': {}, 'name': 'div', 'namespace': None, 'type': 'StartTag'},
+        {'name': 'div', 'namespace': None, 'type': 'EndTag'},
+        {'name': 'div', 'namespace': None, 'type': 'EndTag'}
+    ]
+
+    lxmltree = lxml.etree.fromstring('<div><div></div></div>')
+    walker = treewalkers.getTreeWalker('lxml')
+    output = Lint(walker(lxmltree))
+
+    assert list(output) == expected
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_whitespace_filter.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_whitespace_filter.py
new file mode 100644
index 000000000000..e9da6140a934
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/test_whitespace_filter.py
@@ -0,0 +1,125 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from html5lib.filters.whitespace import Filter
+from html5lib.constants import spaceCharacters
+spaceCharacters = "".join(spaceCharacters)
+
+
+def runTest(input, expected):
+    output = list(Filter(input))
+    errorMsg = "\n".join(["\n\nInput:", str(input),
+                          "\nExpected:", str(expected),
+                          "\nReceived:", str(output)])
+    assert expected == output, errorMsg
+
+
+def runTestUnmodifiedOutput(input):
+    runTest(input, input)
+
+
+def testPhrasingElements():
+    runTestUnmodifiedOutput(
+        [{"type": "Characters", "data": "This is a "},
+         {"type": "StartTag", "name": "span", "data": []},
+         {"type": "Characters", "data": "phrase"},
+         {"type": "EndTag", "name": "span", "data": []},
+         {"type": "SpaceCharacters", "data": " "},
+         {"type": "Characters", "data": "with"},
+         {"type": "SpaceCharacters", "data": " "},
+         {"type": "StartTag", "name": "em", "data": []},
+         {"type": "Characters", "data": "emphasised text"},
+         {"type": "EndTag", "name": "em", "data": []},
+         {"type": "Characters", "data": " and an "},
+         {"type": "StartTag", "name": "img", "data": [["alt", "image"]]},
+         {"type": "Characters", "data": "."}])
+
+
+def testLeadingWhitespace():
+    runTest(
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "SpaceCharacters", "data": spaceCharacters},
+         {"type": "Characters", "data": "foo"},
+         {"type": "EndTag", "name": "p", "data": []}],
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "SpaceCharacters", "data": " "},
+         {"type": "Characters", "data": "foo"},
+         {"type": "EndTag", "name": "p", "data": []}])
+
+
+def testLeadingWhitespaceAsCharacters():
+    runTest(
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "Characters", "data": spaceCharacters + "foo"},
+         {"type": "EndTag", "name": "p", "data": []}],
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "Characters", "data": " foo"},
+         {"type": "EndTag", "name": "p", "data": []}])
+
+
+def testTrailingWhitespace():
+    runTest(
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "Characters", "data": "foo"},
+         {"type": "SpaceCharacters", "data": spaceCharacters},
+         {"type": "EndTag", "name": "p", "data": []}],
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "Characters", "data": "foo"},
+         {"type": "SpaceCharacters", "data": " "},
+         {"type": "EndTag", "name": "p", "data": []}])
+
+
+def testTrailingWhitespaceAsCharacters():
+    runTest(
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "Characters", "data": "foo" + spaceCharacters},
+         {"type": "EndTag", "name": "p", "data": []}],
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "Characters", "data": "foo "},
+         {"type": "EndTag", "name": "p", "data": []}])
+
+
+def testWhitespace():
+    runTest(
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "Characters", "data": "foo" + spaceCharacters + "bar"},
+         {"type": "EndTag", "name": "p", "data": []}],
+        [{"type": "StartTag", "name": "p", "data": []},
+         {"type": "Characters", "data": "foo bar"},
+         {"type": "EndTag", "name": "p", "data": []}])
+
+
+def testLeadingWhitespaceInPre():
+    runTestUnmodifiedOutput(
+        [{"type": "StartTag", "name": "pre", "data": []},
+         {"type": "SpaceCharacters", "data": spaceCharacters},
+         {"type": "Characters", "data": "foo"},
+         {"type": "EndTag", "name": "pre", "data": []}])
+
+
+def testLeadingWhitespaceAsCharactersInPre():
+    runTestUnmodifiedOutput(
+        [{"type": "StartTag", "name": "pre", "data": []},
+         {"type": "Characters", "data": spaceCharacters + "foo"},
+         {"type": "EndTag", "name": "pre", "data": []}])
+
+
+def testTrailingWhitespaceInPre():
+    runTestUnmodifiedOutput(
+        [{"type": "StartTag", "name": "pre", "data": []},
+         {"type": "Characters", "data": "foo"},
+         {"type": "SpaceCharacters", "data": spaceCharacters},
+         {"type": "EndTag", "name": "pre", "data": []}])
+
+
+def testTrailingWhitespaceAsCharactersInPre():
+    runTestUnmodifiedOutput(
+        [{"type": "StartTag", "name": "pre", "data": []},
+         {"type": "Characters", "data": "foo" + spaceCharacters},
+         {"type": "EndTag", "name": "pre", "data": []}])
+
+
+def testWhitespaceInPre():
+    runTestUnmodifiedOutput(
+        [{"type": "StartTag", "name": "pre", "data": []},
+         {"type": "Characters", "data": "foo" + spaceCharacters + "bar"},
+         {"type": "EndTag", "name": "pre", "data": []}])
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_tokenizer.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tokenizer.py
similarity index 52%
rename from testing/web-platform/tests/tools/html5lib/html5lib/tests/test_tokenizer.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tokenizer.py
index 90315ab35d24..1440a722cb8a 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/tests/test_tokenizer.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tokenizer.py
@@ -1,13 +1,15 @@
 from __future__ import absolute_import, division, unicode_literals
 
+import codecs
 import json
 import warnings
 import re
 
-from .support import get_data_files
+import pytest
+from six import unichr
 
-from html5lib.tokenizer import HTMLTokenizer
-from html5lib import constants
+from html5lib._tokenizer import HTMLTokenizer
+from html5lib import constants, _utils
 
 
 class TokenizerTestParser(object):
@@ -17,6 +19,7 @@ class TokenizerTestParser(object):
         self._lastStartTag = lastStartTag
 
     def parse(self, stream, encoding=None, innerHTML=False):
+        # pylint:disable=unused-argument
         tokenizer = self.tokenizer(stream, encoding)
         self.outputTokens = []
 
@@ -96,8 +99,8 @@ def tokensMatch(expectedTokens, receivedTokens, ignoreErrorOrder,
     """
     checkSelfClosing = False
     for token in expectedTokens:
-        if (token[0] == "StartTag" and len(token) == 4
-                or token[0] == "EndTag" and len(token) == 3):
+        if (token[0] == "StartTag" and len(token) == 4 or
+                token[0] == "EndTag" and len(token) == 3):
             checkSelfClosing = True
             break
 
@@ -107,6 +110,7 @@ def tokensMatch(expectedTokens, receivedTokens, ignoreErrorOrder,
                 token.pop()
 
     if not ignoreErrorOrder and not ignoreErrors:
+        expectedTokens = concatenateCharacterTokens(expectedTokens)
         return expectedTokens == receivedTokens
     else:
         # Sort the tokens into two groups; non-parse errors and parse errors
@@ -119,12 +123,42 @@ def tokensMatch(expectedTokens, receivedTokens, ignoreErrorOrder,
                 else:
                     if not ignoreErrors:
                         tokens[tokenType][1].append(token)
+            tokens[tokenType][0] = concatenateCharacterTokens(tokens[tokenType][0])
         return tokens["expected"] == tokens["received"]
 
 
+_surrogateRe = re.compile(r"\\u([0-9A-Fa-f]{4})(?:\\u([0-9A-Fa-f]{4}))?")
+
+
 def unescape(test):
     def decode(inp):
-        return inp.encode("utf-8").decode("unicode-escape")
+        """Decode \\uXXXX escapes
+
+        This decodes \\uXXXX escapes, possibly into non-BMP characters when
+        two surrogate character escapes are adjacent to each other.
+        """
+        # This cannot be implemented using the unicode_escape codec
+        # because that requires its input be ISO-8859-1, and we need
+        # arbitrary unicode as input.
+        def repl(m):
+            if m.group(2) is not None:
+                high = int(m.group(1), 16)
+                low = int(m.group(2), 16)
+                if 0xD800 <= high <= 0xDBFF and 0xDC00 <= low <= 0xDFFF:
+                    cp = ((high - 0xD800) << 10) + (low - 0xDC00) + 0x10000
+                    return unichr(cp)
+                else:
+                    return unichr(high) + unichr(low)
+            else:
+                return unichr(int(m.group(1), 16))
+        try:
+            return _surrogateRe.sub(repl, inp)
+        except ValueError:
+            # This occurs when unichr throws ValueError, which should
+            # only be for a lone-surrogate.
+            if _utils.supports_lone_surrogates:
+                raise
+            return None
 
     test["input"] = decode(test["input"])
     for token in test["output"]:
@@ -139,28 +173,6 @@ def unescape(test):
     return test
 
 
-def runTokenizerTest(test):
-    warnings.resetwarnings()
-    warnings.simplefilter("error")
-
-    expected = concatenateCharacterTokens(test['output'])
-    if 'lastStartTag' not in test:
-        test['lastStartTag'] = None
-    parser = TokenizerTestParser(test['initialState'],
-                                 test['lastStartTag'])
-    tokens = parser.parse(test['input'])
-    tokens = concatenateCharacterTokens(tokens)
-    received = normalizeTokens(tokens)
-    errorMsg = "\n".join(["\n\nInitial state:",
-                          test['initialState'],
-                          "\nInput:", test['input'],
-                          "\nExpected:", repr(expected),
-                          "\nreceived:", repr(tokens)])
-    errorMsg = errorMsg
-    ignoreErrorOrder = test.get('ignoreErrorOrder', False)
-    assert tokensMatch(expected, received, ignoreErrorOrder, True), errorMsg
-
-
 def _doCapitalize(match):
     return match.group(1).upper()
 
@@ -173,16 +185,68 @@ def capitalize(s):
     return s
 
 
-def testTokenizer():
-    for filename in get_data_files('tokenizer', '*.test'):
-        with open(filename) as fp:
+class TokenizerFile(pytest.File):
+    def collect(self):
+        with codecs.open(str(self.fspath), "r", encoding="utf-8") as fp:
             tests = json.load(fp)
-            if 'tests' in tests:
-                for index, test in enumerate(tests['tests']):
-                    if 'initialStates' not in test:
-                        test["initialStates"] = ["Data state"]
-                    if 'doubleEscaped' in test:
-                        test = unescape(test)
-                    for initialState in test["initialStates"]:
-                        test["initialState"] = capitalize(initialState)
-                        yield runTokenizerTest, test
+        if 'tests' in tests:
+            for i, test in enumerate(tests['tests']):
+                yield TokenizerTestCollector(str(i), self, testdata=test)
+
+
+class TokenizerTestCollector(pytest.Collector):
+    def __init__(self, name, parent=None, config=None, session=None, testdata=None):
+        super(TokenizerTestCollector, self).__init__(name, parent, config, session)
+        if 'initialStates' not in testdata:
+            testdata["initialStates"] = ["Data state"]
+        if 'doubleEscaped' in testdata:
+            testdata = unescape(testdata)
+        self.testdata = testdata
+
+    def collect(self):
+        for initialState in self.testdata["initialStates"]:
+            initialState = capitalize(initialState)
+            item = TokenizerTest(initialState,
+                                 self,
+                                 self.testdata,
+                                 initialState)
+            if self.testdata["input"] is None:
+                item.add_marker(pytest.mark.skipif(True, reason="Relies on lone surrogates"))
+            yield item
+
+
+class TokenizerTest(pytest.Item):
+    def __init__(self, name, parent, test, initialState):
+        super(TokenizerTest, self).__init__(name, parent)
+        self.obj = lambda: 1  # this is to hack around skipif needing a function!
+        self.test = test
+        self.initialState = initialState
+
+    def runtest(self):
+        warnings.resetwarnings()
+        warnings.simplefilter("error")
+
+        expected = self.test['output']
+        if 'lastStartTag' not in self.test:
+            self.test['lastStartTag'] = None
+        parser = TokenizerTestParser(self.initialState,
+                                     self.test['lastStartTag'])
+        tokens = parser.parse(self.test['input'])
+        received = normalizeTokens(tokens)
+        errorMsg = "\n".join(["\n\nInitial state:",
+                              self.initialState,
+                              "\nInput:", self.test['input'],
+                              "\nExpected:", repr(expected),
+                              "\nreceived:", repr(tokens)])
+        errorMsg = errorMsg
+        ignoreErrorOrder = self.test.get('ignoreErrorOrder', False)
+        assert tokensMatch(expected, received, ignoreErrorOrder, True), errorMsg
+
+    def repr_failure(self, excinfo):
+        traceback = excinfo.traceback
+        ntraceback = traceback.cut(path=__file__)
+        excinfo.traceback = ntraceback.filter()
+
+        return excinfo.getrepr(funcargs=True,
+                               showlocals=False,
+                               style="short", tbfilter=False)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/tokenizertotree.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tokenizertotree.py
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/html5lib/tests/tokenizertotree.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tokenizertotree.py
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tree_construction.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tree_construction.py
new file mode 100644
index 000000000000..c6e7ca09050d
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/tree_construction.py
@@ -0,0 +1,204 @@
+from __future__ import absolute_import, division, unicode_literals
+
+import itertools
+import re
+import warnings
+from difflib import unified_diff
+
+import pytest
+
+from .support import TestData, convert, convertExpected, treeTypes
+from html5lib import html5parser, constants, treewalkers
+from html5lib.filters.lint import Filter as Lint
+
+_attrlist_re = re.compile(r"^(\s+)\w+=.*(\n\1\w+=.*)+", re.M)
+
+
+def sortattrs(s):
+    def replace(m):
+        lines = m.group(0).split("\n")
+        lines.sort()
+        return "\n".join(lines)
+    return _attrlist_re.sub(replace, s)
+
+
+class TreeConstructionFile(pytest.File):
+    def collect(self):
+        tests = TestData(str(self.fspath), "data")
+        for i, test in enumerate(tests):
+            yield TreeConstructionTest(str(i), self, testdata=test)
+
+
+class TreeConstructionTest(pytest.Collector):
+    def __init__(self, name, parent=None, config=None, session=None, testdata=None):
+        super(TreeConstructionTest, self).__init__(name, parent, config, session)
+        self.testdata = testdata
+
+    def collect(self):
+        for treeName, treeAPIs in sorted(treeTypes.items()):
+            for x in itertools.chain(self._getParserTests(treeName, treeAPIs),
+                                     self._getTreeWalkerTests(treeName, treeAPIs)):
+                yield x
+
+    def _getParserTests(self, treeName, treeAPIs):
+        if treeAPIs is not None and "adapter" in treeAPIs:
+            return
+        for namespaceHTMLElements in (True, False):
+            if namespaceHTMLElements:
+                nodeid = "%s::parser::namespaced" % treeName
+            else:
+                nodeid = "%s::parser::void-namespace" % treeName
+            item = ParserTest(nodeid,
+                              self,
+                              self.testdata,
+                              treeAPIs["builder"] if treeAPIs is not None else None,
+                              namespaceHTMLElements)
+            item.add_marker(getattr(pytest.mark, treeName))
+            item.add_marker(pytest.mark.parser)
+            if namespaceHTMLElements:
+                item.add_marker(pytest.mark.namespaced)
+            if treeAPIs is None:
+                item.add_marker(pytest.mark.skipif(True, reason="Treebuilder not loaded"))
+            yield item
+
+    def _getTreeWalkerTests(self, treeName, treeAPIs):
+        nodeid = "%s::treewalker" % treeName
+        item = TreeWalkerTest(nodeid,
+                              self,
+                              self.testdata,
+                              treeAPIs)
+        item.add_marker(getattr(pytest.mark, treeName))
+        item.add_marker(pytest.mark.treewalker)
+        if treeAPIs is None:
+            item.add_marker(pytest.mark.skipif(True, reason="Treebuilder not loaded"))
+        yield item
+
+
+def convertTreeDump(data):
+    return "\n".join(convert(3)(data).split("\n")[1:])
+
+namespaceExpected = re.compile(r"^(\s*)<(\S+)>", re.M).sub
+
+
+class ParserTest(pytest.Item):
+    def __init__(self, name, parent, test, treeClass, namespaceHTMLElements):
+        super(ParserTest, self).__init__(name, parent)
+        self.obj = lambda: 1  # this is to hack around skipif needing a function!
+        self.test = test
+        self.treeClass = treeClass
+        self.namespaceHTMLElements = namespaceHTMLElements
+
+    def runtest(self):
+        p = html5parser.HTMLParser(tree=self.treeClass,
+                                   namespaceHTMLElements=self.namespaceHTMLElements)
+
+        input = self.test['data']
+        fragmentContainer = self.test['document-fragment']
+        expected = convertExpected(self.test['document'])
+        expectedErrors = self.test['errors'].split("\n") if self.test['errors'] else []
+
+        scripting = False
+        if 'script-on' in self.test:
+            scripting = True
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("error")
+            try:
+                if fragmentContainer:
+                    document = p.parseFragment(input, fragmentContainer, scripting=scripting)
+                else:
+                    document = p.parse(input, scripting=scripting)
+            except constants.DataLossWarning:
+                pytest.skip("data loss warning")
+
+        output = convertTreeDump(p.tree.testSerializer(document))
+
+        expected = expected
+        if self.namespaceHTMLElements:
+            expected = namespaceExpected(r"\1<html \2>", expected)
+
+        errorMsg = "\n".join(["\n\nInput:", input, "\nExpected:", expected,
+                              "\nReceived:", output])
+        assert expected == output, errorMsg
+
+        errStr = []
+        for (line, col), errorcode, datavars in p.errors:
+            assert isinstance(datavars, dict), "%s, %s" % (errorcode, repr(datavars))
+            errStr.append("Line: %i Col: %i %s" % (line, col,
+                                                   constants.E[errorcode] % datavars))
+
+        errorMsg2 = "\n".join(["\n\nInput:", input,
+                               "\nExpected errors (" + str(len(expectedErrors)) + "):\n" + "\n".join(expectedErrors),
+                               "\nActual errors (" + str(len(p.errors)) + "):\n" + "\n".join(errStr)])
+        if False:  # we're currently not testing parse errors
+            assert len(p.errors) == len(expectedErrors), errorMsg2
+
+    def repr_failure(self, excinfo):
+        traceback = excinfo.traceback
+        ntraceback = traceback.cut(path=__file__)
+        excinfo.traceback = ntraceback.filter()
+
+        return excinfo.getrepr(funcargs=True,
+                               showlocals=False,
+                               style="short", tbfilter=False)
+
+
+class TreeWalkerTest(pytest.Item):
+    def __init__(self, name, parent, test, treeAPIs):
+        super(TreeWalkerTest, self).__init__(name, parent)
+        self.obj = lambda: 1  # this is to hack around skipif needing a function!
+        self.test = test
+        self.treeAPIs = treeAPIs
+
+    def runtest(self):
+        p = html5parser.HTMLParser(tree=self.treeAPIs["builder"])
+
+        input = self.test['data']
+        fragmentContainer = self.test['document-fragment']
+        expected = convertExpected(self.test['document'])
+
+        scripting = False
+        if 'script-on' in self.test:
+            scripting = True
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("error")
+            try:
+                if fragmentContainer:
+                    document = p.parseFragment(input, fragmentContainer, scripting=scripting)
+                else:
+                    document = p.parse(input, scripting=scripting)
+            except constants.DataLossWarning:
+                pytest.skip("data loss warning")
+
+        poutput = convertTreeDump(p.tree.testSerializer(document))
+        namespace_expected = namespaceExpected(r"\1<html \2>", expected)
+        if poutput != namespace_expected:
+            pytest.skip("parser output incorrect")
+
+        document = self.treeAPIs.get("adapter", lambda x: x)(document)
+
+        try:
+            output = treewalkers.pprint(Lint(self.treeAPIs["walker"](document)))
+            output = sortattrs(output)
+            expected = sortattrs(expected)
+            diff = "".join(unified_diff([line + "\n" for line in expected.splitlines()],
+                                        [line + "\n" for line in output.splitlines()],
+                                        "Expected", "Received"))
+            assert expected == output, "\n".join([
+                "", "Input:", input,
+                    "", "Expected:", expected,
+                    "", "Received:", output,
+                    "", "Diff:", diff,
+            ])
+        except NotImplementedError:
+            pytest.skip("tree walker NotImplementedError")
+
+    def repr_failure(self, excinfo):
+        traceback = excinfo.traceback
+        ntraceback = traceback.cut(path=__file__)
+        excinfo.traceback = ntraceback.filter()
+
+        return excinfo.getrepr(funcargs=True,
+                               showlocals=False,
+                               style="short", tbfilter=False)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/us-ascii.html b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/us-ascii.html
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/html5lib/tests/us-ascii.html
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/us-ascii.html
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/tests/utf-8-bom.html b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/utf-8-bom.html
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/html5lib/tests/utf-8-bom.html
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/tests/utf-8-bom.html
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/__init__.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/__init__.py
new file mode 100644
index 000000000000..dfeb0ba5e1c3
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/__init__.py
@@ -0,0 +1,30 @@
+"""Tree adapters let you convert from one tree structure to another
+
+Example:
+
+.. code-block:: python
+
+   import html5lib
+   from html5lib.treeadapters import genshi
+
+   doc = '<html><body>Hi!</body></html>'
+   treebuilder = html5lib.getTreeBuilder('etree')
+   parser = html5lib.HTMLParser(tree=treebuilder)
+   tree = parser.parse(doc)
+   TreeWalker = html5lib.getTreeWalker('etree')
+
+   genshi_tree = genshi.to_genshi(TreeWalker(tree))
+
+"""
+from __future__ import absolute_import, division, unicode_literals
+
+from . import sax
+
+__all__ = ["sax"]
+
+try:
+    from . import genshi  # noqa
+except ImportError:
+    pass
+else:
+    __all__.append("genshi")
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/genshi.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/genshi.py
new file mode 100644
index 000000000000..61d5fb6ac42c
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/genshi.py
@@ -0,0 +1,54 @@
+from __future__ import absolute_import, division, unicode_literals
+
+from genshi.core import QName, Attrs
+from genshi.core import START, END, TEXT, COMMENT, DOCTYPE
+
+
+def to_genshi(walker):
+    """Convert a tree to a genshi tree
+
+    :arg walker: the treewalker to use to walk the tree to convert it
+
+    :returns: generator of genshi nodes
+
+    """
+    text = []
+    for token in walker:
+        type = token["type"]
+        if type in ("Characters", "SpaceCharacters"):
+            text.append(token["data"])
+        elif text:
+            yield TEXT, "".join(text), (None, -1, -1)
+            text = []
+
+        if type in ("StartTag", "EmptyTag"):
+            if token["namespace"]:
+                name = "{%s}%s" % (token["namespace"], token["name"])
+            else:
+                name = token["name"]
+            attrs = Attrs([(QName("{%s}%s" % attr if attr[0] is not None else attr[1]), value)
+                           for attr, value in token["data"].items()])
+            yield (START, (QName(name), attrs), (None, -1, -1))
+            if type == "EmptyTag":
+                type = "EndTag"
+
+        if type == "EndTag":
+            if token["namespace"]:
+                name = "{%s}%s" % (token["namespace"], token["name"])
+            else:
+                name = token["name"]
+
+            yield END, QName(name), (None, -1, -1)
+
+        elif type == "Comment":
+            yield COMMENT, token["data"], (None, -1, -1)
+
+        elif type == "Doctype":
+            yield DOCTYPE, (token["name"], token["publicId"],
+                            token["systemId"]), (None, -1, -1)
+
+        else:
+            pass  # FIXME: What to do?
+
+    if text:
+        yield TEXT, "".join(text), (None, -1, -1)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treeadapters/sax.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/sax.py
similarity index 89%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treeadapters/sax.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/sax.py
index ad47df95648c..f4ccea5a2565 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treeadapters/sax.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treeadapters/sax.py
@@ -11,7 +11,13 @@ for prefix, localName, namespace in adjustForeignAttributes.values():
 
 
 def to_sax(walker, handler):
-    """Call SAX-like content handler based on treewalker walker"""
+    """Call SAX-like content handler based on treewalker walker
+
+    :arg walker: the treewalker to use to walk the tree to convert it
+
+    :arg handler: SAX handler to use
+
+    """
     handler.startDocument()
     for prefix, namespace in prefix_mapping.items():
         handler.startPrefixMapping(prefix, namespace)
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/__init__.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/__init__.py
new file mode 100644
index 000000000000..d44447eaf5a3
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/__init__.py
@@ -0,0 +1,88 @@
+"""A collection of modules for building different kinds of trees from HTML
+documents.
+
+To create a treebuilder for a new type of tree, you need to do
+implement several things:
+
+1. A set of classes for various types of elements: Document, Doctype, Comment,
+   Element. These must implement the interface of ``base.treebuilders.Node``
+   (although comment nodes have a different signature for their constructor,
+   see ``treebuilders.etree.Comment``) Textual content may also be implemented
+   as another node type, or not, as your tree implementation requires.
+
+2. A treebuilder object (called ``TreeBuilder`` by convention) that inherits
+   from ``treebuilders.base.TreeBuilder``. This has 4 required attributes:
+
+   * ``documentClass`` - the class to use for the bottommost node of a document
+   * ``elementClass`` - the class to use for HTML Elements
+   * ``commentClass`` - the class to use for comments
+   * ``doctypeClass`` - the class to use for doctypes
+
+   It also has one required method:
+
+   * ``getDocument`` - Returns the root node of the complete document tree
+
+3. If you wish to run the unit tests, you must also create a ``testSerializer``
+   method on your treebuilder which accepts a node and returns a string
+   containing Node and its children serialized according to the format used in
+   the unittests
+
+"""
+
+from __future__ import absolute_import, division, unicode_literals
+
+from .._utils import default_etree
+
+treeBuilderCache = {}
+
+
+def getTreeBuilder(treeType, implementation=None, **kwargs):
+    """Get a TreeBuilder class for various types of trees with built-in support
+
+    :arg treeType: the name of the tree type required (case-insensitive). Supported
+        values are:
+
+        * "dom" - A generic builder for DOM implementations, defaulting to a
+          xml.dom.minidom based implementation.
+        * "etree" - A generic builder for tree implementations exposing an
+          ElementTree-like interface, defaulting to xml.etree.cElementTree if
+          available and xml.etree.ElementTree if not.
+        * "lxml" - A etree-based builder for lxml.etree, handling limitations
+          of lxml's implementation.
+
+    :arg implementation: (Currently applies to the "etree" and "dom" tree
+        types). A module implementing the tree type e.g. xml.etree.ElementTree
+        or xml.etree.cElementTree.
+
+    :arg kwargs: Any additional options to pass to the TreeBuilder when
+        creating it.
+
+    Example:
+
+    >>> from html5lib.treebuilders import getTreeBuilder
+    >>> builder = getTreeBuilder('etree')
+
+    """
+
+    treeType = treeType.lower()
+    if treeType not in treeBuilderCache:
+        if treeType == "dom":
+            from . import dom
+            # Come up with a sane default (pref. from the stdlib)
+            if implementation is None:
+                from xml.dom import minidom
+                implementation = minidom
+            # NEVER cache here, caching is done in the dom submodule
+            return dom.getDomModule(implementation, **kwargs).TreeBuilder
+        elif treeType == "lxml":
+            from . import etree_lxml
+            treeBuilderCache[treeType] = etree_lxml.TreeBuilder
+        elif treeType == "etree":
+            from . import etree
+            if implementation is None:
+                implementation = default_etree
+            # NEVER cache here, caching is done in the etree submodule
+            return etree.getETreeModule(implementation, **kwargs).TreeBuilder
+        else:
+            raise ValueError("""Unrecognised treebuilder "%s" """ % treeType)
+    return treeBuilderCache.get(treeType)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/_base.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/base.py
similarity index 86%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/_base.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/base.py
index 8b97cc11a21a..05d97eccc898 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/_base.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/base.py
@@ -21,22 +21,25 @@ listElementsMap = {
 
 
 class Node(object):
+    """Represents an item in the tree"""
     def __init__(self, name):
-        """Node representing an item in the tree.
-        name - The tag name associated with the node
-        parent - The parent of the current node (or None for the document node)
-        value - The value of the current node (applies to text nodes and
-        comments
-        attributes - a dict holding name, value pairs for attributes of the node
-        childNodes - a list of child nodes of the current node. This must
-        include all elements but not necessarily other node types
-        _flags - A list of miscellaneous flags that can be set on the node
+        """Creates a Node
+
+        :arg name: The tag name associated with the node
+
         """
+        # The tag name assocaited with the node
         self.name = name
+        # The parent of the current node (or None for the document node)
         self.parent = None
+        # The value of the current node (applies to text nodes and comments)
         self.value = None
+        # A dict holding name -> value pairs for attributes of the node
         self.attributes = {}
+        # A list of child nodes of the current node. This must include all
+        # elements but not necessarily other node types.
         self.childNodes = []
+        # A list of miscellaneous flags that can be set on the node.
         self._flags = []
 
     def __str__(self):
@@ -53,23 +56,41 @@ class Node(object):
 
     def appendChild(self, node):
         """Insert node as a child of the current node
+
+        :arg node: the node to insert
+
         """
         raise NotImplementedError
 
     def insertText(self, data, insertBefore=None):
         """Insert data as text in the current node, positioned before the
         start of node insertBefore or to the end of the node's text.
+
+        :arg data: the data to insert
+
+        :arg insertBefore: True if you want to insert the text before the node
+            and False if you want to insert it after the node
+
         """
         raise NotImplementedError
 
     def insertBefore(self, node, refNode):
         """Insert node as a child of the current node, before refNode in the
         list of child nodes. Raises ValueError if refNode is not a child of
-        the current node"""
+        the current node
+
+        :arg node: the node to insert
+
+        :arg refNode: the child node to insert the node before
+
+        """
         raise NotImplementedError
 
     def removeChild(self, node):
         """Remove node from the children of the current node
+
+        :arg node: the child node to remove
+
         """
         raise NotImplementedError
 
@@ -77,6 +98,9 @@ class Node(object):
         """Move all the children of the current node to newParent.
         This is needed so that trees that don't store text as nodes move the
         text in the correct way
+
+        :arg newParent: the node to move all this node's children to
+
         """
         # XXX - should this method be made more general?
         for child in self.childNodes:
@@ -121,11 +145,14 @@ class ActiveFormattingElements(list):
 
 class TreeBuilder(object):
     """Base treebuilder implementation
-    documentClass - the class to use for the bottommost node of a document
-    elementClass - the class to use for HTML Elements
-    commentClass - the class to use for comments
-    doctypeClass - the class to use for doctypes
+
+    * documentClass - the class to use for the bottommost node of a document
+    * elementClass - the class to use for HTML Elements
+    * commentClass - the class to use for comments
+    * doctypeClass - the class to use for doctypes
+
     """
+    # pylint:disable=not-callable
 
     # Document class
     documentClass = None
@@ -143,6 +170,11 @@ class TreeBuilder(object):
     fragmentClass = None
 
     def __init__(self, namespaceHTMLElements):
+        """Create a TreeBuilder
+
+        :arg namespaceHTMLElements: whether or not to namespace HTML elements
+
+        """
         if namespaceHTMLElements:
             self.defaultNamespace = "http://www.w3.org/1999/xhtml"
         else:
@@ -166,12 +198,17 @@ class TreeBuilder(object):
         # If we pass a node in we match that. if we pass a string
         # match any node with that name
         exactNode = hasattr(target, "nameTuple")
+        if not exactNode:
+            if isinstance(target, text_type):
+                target = (namespaces["html"], target)
+            assert isinstance(target, tuple)
 
         listElements, invert = listElementsMap[variant]
 
         for node in reversed(self.openElements):
-            if (node.name == target and not exactNode or
-                    node == target and exactNode):
+            if exactNode and node == target:
+                return True
+            elif not exactNode and node.nameTuple == target:
                 return True
             elif (invert ^ (node.nameTuple in listElements)):
                 return False
@@ -353,19 +390,19 @@ class TreeBuilder(object):
     def generateImpliedEndTags(self, exclude=None):
         name = self.openElements[-1].name
         # XXX td, th and tr are not actually needed
-        if (name in frozenset(("dd", "dt", "li", "option", "optgroup", "p", "rp", "rt"))
-                and name != exclude):
+        if (name in frozenset(("dd", "dt", "li", "option", "optgroup", "p", "rp", "rt")) and
+                name != exclude):
             self.openElements.pop()
             # XXX This is not entirely what the specification says. We should
             # investigate it more closely.
             self.generateImpliedEndTags(exclude)
 
     def getDocument(self):
-        "Return the final tree"
+        """Return the final tree"""
         return self.document
 
     def getFragment(self):
-        "Return the final fragment"
+        """Return the final fragment"""
         # assert self.innerHTML
         fragment = self.fragmentClass()
         self.openElements[0].reparentChildren(fragment)
@@ -373,5 +410,8 @@ class TreeBuilder(object):
 
     def testSerializer(self, node):
         """Serialize the subtree of node in the format required by unit tests
-        node - the node from which to start serializing"""
+
+        :arg node: the node from which to start serializing
+
+        """
         raise NotImplementedError
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/dom.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/dom.py
similarity index 85%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/dom.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/dom.py
index 234233b79323..dcfac220bfaf 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/dom.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/dom.py
@@ -1,54 +1,62 @@
 from __future__ import absolute_import, division, unicode_literals
 
 
+from collections import MutableMapping
 from xml.dom import minidom, Node
 import weakref
 
-from . import _base
+from . import base
 from .. import constants
 from ..constants import namespaces
-from ..utils import moduleFactoryFactory
+from .._utils import moduleFactoryFactory
 
 
 def getDomBuilder(DomImplementation):
     Dom = DomImplementation
 
-    class AttrList(object):
+    class AttrList(MutableMapping):
         def __init__(self, element):
             self.element = element
 
         def __iter__(self):
-            return list(self.element.attributes.items()).__iter__()
+            return iter(self.element.attributes.keys())
 
         def __setitem__(self, name, value):
-            self.element.setAttribute(name, value)
-
-        def __len__(self):
-            return len(list(self.element.attributes.items()))
-
-        def items(self):
-            return [(item[0], item[1]) for item in
-                    list(self.element.attributes.items())]
-
-        def keys(self):
-            return list(self.element.attributes.keys())
-
-        def __getitem__(self, name):
-            return self.element.getAttribute(name)
-
-        def __contains__(self, name):
             if isinstance(name, tuple):
                 raise NotImplementedError
             else:
-                return self.element.hasAttribute(name)
+                attr = self.element.ownerDocument.createAttribute(name)
+                attr.value = value
+                self.element.attributes[name] = attr
 
-    class NodeBuilder(_base.Node):
+        def __len__(self):
+            return len(self.element.attributes)
+
+        def items(self):
+            return list(self.element.attributes.items())
+
+        def values(self):
+            return list(self.element.attributes.values())
+
+        def __getitem__(self, name):
+            if isinstance(name, tuple):
+                raise NotImplementedError
+            else:
+                return self.element.attributes[name].value
+
+        def __delitem__(self, name):
+            if isinstance(name, tuple):
+                raise NotImplementedError
+            else:
+                del self.element.attributes[name]
+
+    class NodeBuilder(base.Node):
         def __init__(self, element):
-            _base.Node.__init__(self, element.nodeName)
+            base.Node.__init__(self, element.nodeName)
             self.element = element
 
-        namespace = property(lambda self: hasattr(self.element, "namespaceURI")
-                             and self.element.namespaceURI or None)
+        namespace = property(lambda self: hasattr(self.element, "namespaceURI") and
+                             self.element.namespaceURI or None)
 
         def appendChild(self, node):
             node.parent = self
@@ -109,7 +117,7 @@ def getDomBuilder(DomImplementation):
 
         nameTuple = property(getNameTuple)
 
-    class TreeBuilder(_base.TreeBuilder):
+    class TreeBuilder(base.TreeBuilder):  # pylint:disable=unused-variable
         def documentClass(self):
             self.dom = Dom.getDOMImplementation().createDocument(None, None, None)
             return weakref.proxy(self)
@@ -149,15 +157,16 @@ def getDomBuilder(DomImplementation):
             return self.dom
 
         def getFragment(self):
-            return _base.TreeBuilder.getFragment(self).element
+            return base.TreeBuilder.getFragment(self).element
 
         def insertText(self, data, parent=None):
             data = data
             if parent != self:
-                _base.TreeBuilder.insertText(self, data, parent)
+                base.TreeBuilder.insertText(self, data, parent)
             else:
                 # HACK: allow text nodes as children of the document node
                 if hasattr(self.dom, '_child_node_types'):
+                    # pylint:disable=protected-access
                     if Node.TEXT_NODE not in self.dom._child_node_types:
                         self.dom._child_node_types = list(self.dom._child_node_types)
                         self.dom._child_node_types.append(Node.TEXT_NODE)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/etree.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/etree.py
similarity index 96%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/etree.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/etree.py
index 2c8ed19f8fe8..cb1d4aef5036 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/etree.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/etree.py
@@ -1,13 +1,15 @@
 from __future__ import absolute_import, division, unicode_literals
+# pylint:disable=protected-access
+
 from six import text_type
 
 import re
 
-from . import _base
-from .. import ihatexml
+from . import base
+from .. import _ihatexml
 from .. import constants
 from ..constants import namespaces
-from ..utils import moduleFactoryFactory
+from .._utils import moduleFactoryFactory
 
 tag_regexp = re.compile("{([^}]*)}(.*)")
 
@@ -16,7 +18,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False):
     ElementTree = ElementTreeImplementation
     ElementTreeCommentType = ElementTree.Comment("asd").tag
 
-    class Element(_base.Node):
+    class Element(base.Node):
         def __init__(self, name, namespace=None):
             self._name = name
             self._namespace = namespace
@@ -98,6 +100,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False):
             node.parent = self
 
         def removeChild(self, node):
+            self._childNodes.remove(node)
             self._element.remove(node._element)
             node.parent = None
 
@@ -139,7 +142,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False):
                 if self._element.text is not None:
                     newParent._element.text += self._element.text
             self._element.text = ""
-            _base.Node.reparentChildren(self, newParent)
+            base.Node.reparentChildren(self, newParent)
 
     class Comment(Element):
         def __init__(self, data):
@@ -253,10 +256,10 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False):
 
         return "\n".join(rv)
 
-    def tostring(element):
+    def tostring(element):  # pylint:disable=unused-variable
         """Serialize an element and its child nodes to a string"""
         rv = []
-        filter = ihatexml.InfosetFilter()
+        filter = _ihatexml.InfosetFilter()
 
         def serializeElement(element):
             if isinstance(element, ElementTree.ElementTree):
@@ -307,7 +310,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False):
 
         return "".join(rv)
 
-    class TreeBuilder(_base.TreeBuilder):
+    class TreeBuilder(base.TreeBuilder):  # pylint:disable=unused-variable
         documentClass = Document
         doctypeClass = DocumentType
         elementClass = Element
@@ -329,7 +332,7 @@ def getETreeBuilder(ElementTreeImplementation, fullTree=False):
                     return self.document._element.find("html")
 
         def getFragment(self):
-            return _base.TreeBuilder.getFragment(self)._element
+            return base.TreeBuilder.getFragment(self)._element
 
     return locals()
 
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/etree_lxml.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/etree_lxml.py
similarity index 93%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/etree_lxml.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/etree_lxml.py
index 35d08efaa614..ca12a99cccf9 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treebuilders/etree_lxml.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treebuilders/etree_lxml.py
@@ -10,16 +10,17 @@ When any of these things occur, we emit a DataLossWarning
 """
 
 from __future__ import absolute_import, division, unicode_literals
+# pylint:disable=protected-access
 
 import warnings
 import re
 import sys
 
-from . import _base
+from . import base
 from ..constants import DataLossWarning
 from .. import constants
 from . import etree as etree_builders
-from .. import ihatexml
+from .. import _ihatexml
 
 import lxml.etree as etree
 
@@ -53,8 +54,7 @@ class Document(object):
 
 def testSerializer(element):
     rv = []
-    finalText = None
-    infosetFilter = ihatexml.InfosetFilter()
+    infosetFilter = _ihatexml.InfosetFilter(preventDoubleDashComments=True)
 
     def serializeElement(element, indent=0):
         if not hasattr(element, "tag"):
@@ -79,7 +79,7 @@ def testSerializer(element):
                     next_element = next_element.getnext()
             elif isinstance(element, str) or isinstance(element, bytes):
                 # Text in a fragment
-                assert isinstance(element, str) or sys.version_info.major == 2
+                assert isinstance(element, str) or sys.version_info[0] == 2
                 rv.append("|%s\"%s\"" % (' ' * indent, element))
             else:
                 # Fragment case
@@ -128,16 +128,12 @@ def testSerializer(element):
                 rv.append("|%s\"%s\"" % (' ' * (indent - 2), element.tail))
     serializeElement(element, 0)
 
-    if finalText is not None:
-        rv.append("|%s\"%s\"" % (' ' * 2, finalText))
-
     return "\n".join(rv)
 
 
 def tostring(element):
     """Serialize an element and its child nodes to a string"""
     rv = []
-    finalText = None
 
     def serializeElement(element):
         if not hasattr(element, "tag"):
@@ -173,13 +169,10 @@ def tostring(element):
 
     serializeElement(element)
 
-    if finalText is not None:
-        rv.append("%s\"" % (' ' * 2, finalText))
-
     return "".join(rv)
 
 
-class TreeBuilder(_base.TreeBuilder):
+class TreeBuilder(base.TreeBuilder):
     documentClass = Document
     doctypeClass = DocumentType
     elementClass = None
@@ -189,13 +182,15 @@ class TreeBuilder(_base.TreeBuilder):
 
     def __init__(self, namespaceHTMLElements, fullTree=False):
         builder = etree_builders.getETreeModule(etree, fullTree=fullTree)
-        infosetFilter = self.infosetFilter = ihatexml.InfosetFilter()
+        infosetFilter = self.infosetFilter = _ihatexml.InfosetFilter(preventDoubleDashComments=True)
         self.namespaceHTMLElements = namespaceHTMLElements
 
         class Attributes(dict):
-            def __init__(self, element, value={}):
+            def __init__(self, element, value=None):
+                if value is None:
+                    value = {}
                 self._element = element
-                dict.__init__(self, value)
+                dict.__init__(self, value)  # pylint:disable=non-parent-init-called
                 for key, value in self.items():
                     if isinstance(key, tuple):
                         name = "{%s}%s" % (key[2], infosetFilter.coerceAttribute(key[1]))
@@ -257,12 +252,12 @@ class TreeBuilder(_base.TreeBuilder):
             data = property(_getData, _setData)
 
         self.elementClass = Element
-        self.commentClass = builder.Comment
+        self.commentClass = Comment
         # self.fragmentClass = builder.DocumentFragment
-        _base.TreeBuilder.__init__(self, namespaceHTMLElements)
+        base.TreeBuilder.__init__(self, namespaceHTMLElements)
 
     def reset(self):
-        _base.TreeBuilder.reset(self)
+        base.TreeBuilder.reset(self)
         self.insertComment = self.insertCommentInitial
         self.initial_comments = []
         self.doctype = None
@@ -303,19 +298,20 @@ class TreeBuilder(_base.TreeBuilder):
             self.doctype = doctype
 
     def insertCommentInitial(self, data, parent=None):
+        assert parent is None or parent is self.document
+        assert self.document._elementTree is None
         self.initial_comments.append(data)
 
     def insertCommentMain(self, data, parent=None):
         if (parent == self.document and
                 self.document._elementTree.getroot()[-1].tag == comment_type):
-                warnings.warn("lxml cannot represent adjacent comments beyond the root elements", DataLossWarning)
+            warnings.warn("lxml cannot represent adjacent comments beyond the root elements", DataLossWarning)
         super(TreeBuilder, self).insertComment(data, parent)
 
     def insertRoot(self, token):
-        """Create the document root"""
         # Because of the way libxml2 works, it doesn't seem to be possible to
         # alter information like the doctype after the tree has been parsed.
-        # Therefore we need to use the built-in parser to create our iniial
+        # Therefore we need to use the built-in parser to create our initial
         # tree, after which we can add elements like normal
         docStr = ""
         if self.doctype:
@@ -344,7 +340,8 @@ class TreeBuilder(_base.TreeBuilder):
 
         # Append the initial comments:
         for comment_token in self.initial_comments:
-            root.addprevious(etree.Comment(comment_token["data"]))
+            comment = self.commentClass(comment_token["data"])
+            root.addprevious(comment._element)
 
         # Create the root document and add the ElementTree to it
         self.document = self.documentClass()
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/__init__.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/__init__.py
new file mode 100644
index 000000000000..9bec2076f3f6
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/__init__.py
@@ -0,0 +1,154 @@
+"""A collection of modules for iterating through different kinds of
+tree, generating tokens identical to those produced by the tokenizer
+module.
+
+To create a tree walker for a new type of tree, you need to do
+implement a tree walker object (called TreeWalker by convention) that
+implements a 'serialize' method taking a tree as sole argument and
+returning an iterator generating tokens.
+"""
+
+from __future__ import absolute_import, division, unicode_literals
+
+from .. import constants
+from .._utils import default_etree
+
+__all__ = ["getTreeWalker", "pprint"]
+
+treeWalkerCache = {}
+
+
+def getTreeWalker(treeType, implementation=None, **kwargs):
+    """Get a TreeWalker class for various types of tree with built-in support
+
+    :arg str treeType: the name of the tree type required (case-insensitive).
+        Supported values are:
+
+        * "dom": The xml.dom.minidom DOM implementation
+        * "etree": A generic walker for tree implementations exposing an
+          elementtree-like interface (known to work with ElementTree,
+          cElementTree and lxml.etree).
+        * "lxml": Optimized walker for lxml.etree
+        * "genshi": a Genshi stream
+
+    :arg implementation: A module implementing the tree type e.g.
+        xml.etree.ElementTree or cElementTree (Currently applies to the "etree"
+        tree type only).
+
+    :arg kwargs: keyword arguments passed to the etree walker--for other
+        walkers, this has no effect
+
+    :returns: a TreeWalker class
+
+    """
+
+    treeType = treeType.lower()
+    if treeType not in treeWalkerCache:
+        if treeType == "dom":
+            from . import dom
+            treeWalkerCache[treeType] = dom.TreeWalker
+        elif treeType == "genshi":
+            from . import genshi
+            treeWalkerCache[treeType] = genshi.TreeWalker
+        elif treeType == "lxml":
+            from . import etree_lxml
+            treeWalkerCache[treeType] = etree_lxml.TreeWalker
+        elif treeType == "etree":
+            from . import etree
+            if implementation is None:
+                implementation = default_etree
+            # XXX: NEVER cache here, caching is done in the etree submodule
+            return etree.getETreeModule(implementation, **kwargs).TreeWalker
+    return treeWalkerCache.get(treeType)
+
+
+def concatenateCharacterTokens(tokens):
+    pendingCharacters = []
+    for token in tokens:
+        type = token["type"]
+        if type in ("Characters", "SpaceCharacters"):
+            pendingCharacters.append(token["data"])
+        else:
+            if pendingCharacters:
+                yield {"type": "Characters", "data": "".join(pendingCharacters)}
+                pendingCharacters = []
+            yield token
+    if pendingCharacters:
+        yield {"type": "Characters", "data": "".join(pendingCharacters)}
+
+
+def pprint(walker):
+    """Pretty printer for tree walkers
+
+    Takes a TreeWalker instance and pretty prints the output of walking the tree.
+
+    :arg walker: a TreeWalker instance
+
+    """
+    output = []
+    indent = 0
+    for token in concatenateCharacterTokens(walker):
+        type = token["type"]
+        if type in ("StartTag", "EmptyTag"):
+            # tag name
+            if token["namespace"] and token["namespace"] != constants.namespaces["html"]:
+                if token["namespace"] in constants.prefixes:
+                    ns = constants.prefixes[token["namespace"]]
+                else:
+                    ns = token["namespace"]
+                name = "%s %s" % (ns, token["name"])
+            else:
+                name = token["name"]
+            output.append("%s<%s>" % (" " * indent, name))
+            indent += 2
+            # attributes (sorted for consistent ordering)
+            attrs = token["data"]
+            for (namespace, localname), value in sorted(attrs.items()):
+                if namespace:
+                    if namespace in constants.prefixes:
+                        ns = constants.prefixes[namespace]
+                    else:
+                        ns = namespace
+                    name = "%s %s" % (ns, localname)
+                else:
+                    name = localname
+                output.append("%s%s=\"%s\"" % (" " * indent, name, value))
+            # self-closing
+            if type == "EmptyTag":
+                indent -= 2
+
+        elif type == "EndTag":
+            indent -= 2
+
+        elif type == "Comment":
+            output.append("%s<!-- %s -->" % (" " * indent, token["data"]))
+
+        elif type == "Doctype":
+            if token["name"]:
+                if token["publicId"]:
+                    output.append("""%s<!DOCTYPE %s "%s" "%s">""" %
+                                  (" " * indent,
+                                   token["name"],
+                                   token["publicId"],
+                                   token["systemId"] if token["systemId"] else ""))
+                elif token["systemId"]:
+                    output.append("""%s<!DOCTYPE %s "" "%s">""" %
+                                  (" " * indent,
+                                   token["name"],
+                                   token["systemId"]))
+                else:
+                    output.append("%s<!DOCTYPE %s>" % (" " * indent,
+                                                       token["name"]))
+            else:
+                output.append("%s<!DOCTYPE >" % (" " * indent,))
+
+        elif type == "Characters":
+            output.append("%s\"%s\"" % (" " * indent, token["data"]))
+
+        elif type == "SpaceCharacters":
+            assert False, "concatenateCharacterTokens should have got rid of all Space tokens"
+
+        else:
+            raise ValueError("Unknown token type, %s" % type)
+
+    return "\n".join(output)
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/_base.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/base.py
similarity index 52%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/_base.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/base.py
index 34252e50c0e8..80c474c4e939 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/_base.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/base.py
@@ -1,10 +1,10 @@
 from __future__ import absolute_import, division, unicode_literals
-from six import text_type, string_types
-
-import gettext
-_ = gettext.gettext
 
 from xml.dom import Node
+from ..constants import namespaces, voidElements, spaceCharacters
+
+__all__ = ["DOCUMENT", "DOCTYPE", "TEXT", "ELEMENT", "COMMENT", "ENTITY", "UNKNOWN",
+           "TreeWalker", "NonRecursiveTreeWalker"]
 
 DOCUMENT = Node.DOCUMENT_NODE
 DOCTYPE = Node.DOCUMENT_TYPE_NODE
@@ -14,80 +14,115 @@ COMMENT = Node.COMMENT_NODE
 ENTITY = Node.ENTITY_NODE
 UNKNOWN = "<#UNKNOWN#>"
 
-from ..constants import voidElements, spaceCharacters
 spaceCharacters = "".join(spaceCharacters)
 
 
-def to_text(s, blank_if_none=True):
-    """Wrapper around six.text_type to convert None to empty string"""
-    if s is None:
-        if blank_if_none:
-            return ""
-        else:
-            return None
-    elif isinstance(s, text_type):
-        return s
-    else:
-        return text_type(s)
-
-
-def is_text_or_none(string):
-    """Wrapper around isinstance(string_types) or is None"""
-    return string is None or isinstance(string, string_types)
-
-
 class TreeWalker(object):
+    """Walks a tree yielding tokens
+
+    Tokens are dicts that all have a ``type`` field specifying the type of the
+    token.
+
+    """
     def __init__(self, tree):
+        """Creates a TreeWalker
+
+        :arg tree: the tree to walk
+
+        """
         self.tree = tree
 
     def __iter__(self):
         raise NotImplementedError
 
     def error(self, msg):
+        """Generates an error token with the given message
+
+        :arg msg: the error message
+
+        :returns: SerializeError token
+
+        """
         return {"type": "SerializeError", "data": msg}
 
     def emptyTag(self, namespace, name, attrs, hasChildren=False):
-        assert namespace is None or isinstance(namespace, string_types), type(namespace)
-        assert isinstance(name, string_types), type(name)
-        assert all((namespace is None or isinstance(namespace, string_types)) and
-                   isinstance(name, string_types) and
-                   isinstance(value, string_types)
-                   for (namespace, name), value in attrs.items())
+        """Generates an EmptyTag token
 
-        yield {"type": "EmptyTag", "name": to_text(name, False),
-               "namespace": to_text(namespace),
+        :arg namespace: the namespace of the token--can be ``None``
+
+        :arg name: the name of the element
+
+        :arg attrs: the attributes of the element as a dict
+
+        :arg hasChildren: whether or not to yield a SerializationError because
+            this tag shouldn't have children
+
+        :returns: EmptyTag token
+
+        """
+        yield {"type": "EmptyTag", "name": name,
+               "namespace": namespace,
                "data": attrs}
         if hasChildren:
-            yield self.error(_("Void element has children"))
+            yield self.error("Void element has children")
 
     def startTag(self, namespace, name, attrs):
-        assert namespace is None or isinstance(namespace, string_types), type(namespace)
-        assert isinstance(name, string_types), type(name)
-        assert all((namespace is None or isinstance(namespace, string_types)) and
-                   isinstance(name, string_types) and
-                   isinstance(value, string_types)
-                   for (namespace, name), value in attrs.items())
+        """Generates a StartTag token
 
+        :arg namespace: the namespace of the token--can be ``None``
+
+        :arg name: the name of the element
+
+        :arg attrs: the attributes of the element as a dict
+
+        :returns: StartTag token
+
+        """
         return {"type": "StartTag",
-                "name": text_type(name),
-                "namespace": to_text(namespace),
-                "data": dict(((to_text(namespace, False), to_text(name)),
-                              to_text(value, False))
-                             for (namespace, name), value in attrs.items())}
+                "name": name,
+                "namespace": namespace,
+                "data": attrs}
 
     def endTag(self, namespace, name):
-        assert namespace is None or isinstance(namespace, string_types), type(namespace)
-        assert isinstance(name, string_types), type(namespace)
+        """Generates an EndTag token
 
+        :arg namespace: the namespace of the token--can be ``None``
+
+        :arg name: the name of the element
+
+        :returns: EndTag token
+
+        """
         return {"type": "EndTag",
-                "name": to_text(name, False),
-                "namespace": to_text(namespace),
-                "data": {}}
+                "name": name,
+                "namespace": namespace}
 
     def text(self, data):
-        assert isinstance(data, string_types), type(data)
+        """Generates SpaceCharacters and Characters tokens
 
-        data = to_text(data)
+        Depending on what's in the data, this generates one or more
+        ``SpaceCharacters`` and ``Characters`` tokens.
+
+        For example:
+
+            >>> from html5lib.treewalkers.base import TreeWalker
+            >>> # Give it an empty tree just so it instantiates
+            >>> walker = TreeWalker([])
+            >>> list(walker.text(''))
+            []
+            >>> list(walker.text('  '))
+            [{u'data': '  ', u'type': u'SpaceCharacters'}]
+            >>> list(walker.text(' abc '))  # doctest: +NORMALIZE_WHITESPACE
+            [{u'data': ' ', u'type': u'SpaceCharacters'},
+            {u'data': u'abc', u'type': u'Characters'},
+            {u'data': u' ', u'type': u'SpaceCharacters'}]
+
+        :arg data: the text data
+
+        :returns: one or more ``SpaceCharacters`` and ``Characters`` tokens
+
+        """
+        data = data
         middle = data.lstrip(spaceCharacters)
         left = data[:len(data) - len(middle)]
         if left:
@@ -101,28 +136,45 @@ class TreeWalker(object):
             yield {"type": "SpaceCharacters", "data": right}
 
     def comment(self, data):
-        assert isinstance(data, string_types), type(data)
+        """Generates a Comment token
 
-        return {"type": "Comment", "data": text_type(data)}
+        :arg data: the comment
 
-    def doctype(self, name, publicId=None, systemId=None, correct=True):
-        assert is_text_or_none(name), type(name)
-        assert is_text_or_none(publicId), type(publicId)
-        assert is_text_or_none(systemId), type(systemId)
+        :returns: Comment token
 
+        """
+        return {"type": "Comment", "data": data}
+
+    def doctype(self, name, publicId=None, systemId=None):
+        """Generates a Doctype token
+
+        :arg name:
+
+        :arg publicId:
+
+        :arg systemId:
+
+        :returns: the Doctype token
+
+        """
         return {"type": "Doctype",
-                "name": to_text(name),
-                "publicId": to_text(publicId),
-                "systemId": to_text(systemId),
-                "correct": to_text(correct)}
+                "name": name,
+                "publicId": publicId,
+                "systemId": systemId}
 
     def entity(self, name):
-        assert isinstance(name, string_types), type(name)
+        """Generates an Entity token
 
-        return {"type": "Entity", "name": text_type(name)}
+        :arg name: the entity name
+
+        :returns: an Entity token
+
+        """
+        return {"type": "Entity", "name": name}
 
     def unknown(self, nodeType):
-        return self.error(_("Unknown node type: ") + nodeType)
+        """Handles unknown node types"""
+        return self.error("Unknown node type: " + nodeType)
 
 
 class NonRecursiveTreeWalker(TreeWalker):
@@ -154,7 +206,7 @@ class NonRecursiveTreeWalker(TreeWalker):
 
             elif type == ELEMENT:
                 namespace, name, attributes, hasChildren = details
-                if name in voidElements:
+                if (not namespace or namespace == namespaces["html"]) and name in voidElements:
                     for token in self.emptyTag(namespace, name, attributes,
                                                hasChildren):
                         yield token
@@ -187,7 +239,7 @@ class NonRecursiveTreeWalker(TreeWalker):
                     type, details = details[0], details[1:]
                     if type == ELEMENT:
                         namespace, name, attributes, hasChildren = details
-                        if name not in voidElements:
+                        if (namespace and namespace != namespaces["html"]) or name not in voidElements:
                             yield self.endTag(namespace, name)
                     if self.tree is currentNode:
                         currentNode = None
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/dom.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/dom.py
similarity index 70%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/dom.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/dom.py
index a01287a94481..b0c89b001fd3 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/dom.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/dom.py
@@ -2,19 +2,16 @@ from __future__ import absolute_import, division, unicode_literals
 
 from xml.dom import Node
 
-import gettext
-_ = gettext.gettext
-
-from . import _base
+from . import base
 
 
-class TreeWalker(_base.NonRecursiveTreeWalker):
+class TreeWalker(base.NonRecursiveTreeWalker):
     def getNodeDetails(self, node):
         if node.nodeType == Node.DOCUMENT_TYPE_NODE:
-            return _base.DOCTYPE, node.name, node.publicId, node.systemId
+            return base.DOCTYPE, node.name, node.publicId, node.systemId
 
         elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
-            return _base.TEXT, node.nodeValue
+            return base.TEXT, node.nodeValue
 
         elif node.nodeType == Node.ELEMENT_NODE:
             attrs = {}
@@ -24,17 +21,17 @@ class TreeWalker(_base.NonRecursiveTreeWalker):
                     attrs[(attr.namespaceURI, attr.localName)] = attr.value
                 else:
                     attrs[(None, attr.name)] = attr.value
-            return (_base.ELEMENT, node.namespaceURI, node.nodeName,
+            return (base.ELEMENT, node.namespaceURI, node.nodeName,
                     attrs, node.hasChildNodes())
 
         elif node.nodeType == Node.COMMENT_NODE:
-            return _base.COMMENT, node.nodeValue
+            return base.COMMENT, node.nodeValue
 
         elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
-            return (_base.DOCUMENT,)
+            return (base.DOCUMENT,)
 
         else:
-            return _base.UNKNOWN, node.nodeType
+            return base.UNKNOWN, node.nodeType
 
     def getFirstChild(self, node):
         return node.firstChild
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/etree.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/etree.py
similarity index 84%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/etree.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/etree.py
index fd8a9cc9b52c..d15a7eebfe8c 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/etree.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/etree.py
@@ -1,21 +1,12 @@
 from __future__ import absolute_import, division, unicode_literals
 
-try:
-    from collections import OrderedDict
-except ImportError:
-    try:
-        from ordereddict import OrderedDict
-    except ImportError:
-        OrderedDict = dict
-import gettext
-_ = gettext.gettext
-
+from collections import OrderedDict
 import re
 
-from six import text_type
+from six import string_types
 
-from . import _base
-from ..utils import moduleFactoryFactory
+from . import base
+from .._utils import moduleFactoryFactory
 
 tag_regexp = re.compile("{([^}]*)}(.*)")
 
@@ -24,7 +15,7 @@ def getETreeBuilder(ElementTreeImplementation):
     ElementTree = ElementTreeImplementation
     ElementTreeCommentType = ElementTree.Comment("asd").tag
 
-    class TreeWalker(_base.NonRecursiveTreeWalker):
+    class TreeWalker(base.NonRecursiveTreeWalker):  # pylint:disable=unused-variable
         """Given the particular ElementTree representation, this implementation,
         to avoid using recursion, returns "nodes" as tuples with the following
         content:
@@ -40,9 +31,9 @@ def getETreeBuilder(ElementTreeImplementation):
         """
         def getNodeDetails(self, node):
             if isinstance(node, tuple):  # It might be the root Element
-                elt, key, parents, flag = node
+                elt, _, _, flag = node
                 if flag in ("text", "tail"):
-                    return _base.TEXT, getattr(elt, flag)
+                    return base.TEXT, getattr(elt, flag)
                 else:
                     node = elt
 
@@ -50,17 +41,17 @@ def getETreeBuilder(ElementTreeImplementation):
                 node = node.getroot()
 
             if node.tag in ("DOCUMENT_ROOT", "DOCUMENT_FRAGMENT"):
-                return (_base.DOCUMENT,)
+                return (base.DOCUMENT,)
 
             elif node.tag == "<!DOCTYPE>":
-                return (_base.DOCTYPE, node.text,
+                return (base.DOCTYPE, node.text,
                         node.get("publicId"), node.get("systemId"))
 
             elif node.tag == ElementTreeCommentType:
-                return _base.COMMENT, node.text
+                return base.COMMENT, node.text
 
             else:
-                assert type(node.tag) == text_type, type(node.tag)
+                assert isinstance(node.tag, string_types), type(node.tag)
                 # This is assumed to be an ordinary element
                 match = tag_regexp.match(node.tag)
                 if match:
@@ -75,7 +66,7 @@ def getETreeBuilder(ElementTreeImplementation):
                         attrs[(match.group(1), match.group(2))] = value
                     else:
                         attrs[(None, name)] = value
-                return (_base.ELEMENT, namespace, tag,
+                return (base.ELEMENT, namespace, tag,
                         attrs, len(node) or node.text)
 
         def getFirstChild(self, node):
@@ -131,6 +122,7 @@ def getETreeBuilder(ElementTreeImplementation):
                 if not parents:
                     return parent
                 else:
+                    assert list(parents[-1]).count(parent) == 1
                     return parent, list(parents[-1]).index(parent), parents, None
 
     return locals()
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/lxmletree.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/etree_lxml.py
similarity index 72%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/lxmletree.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/etree_lxml.py
index bc934ac05a9a..fb2363112b1e 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/lxmletree.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/etree_lxml.py
@@ -4,12 +4,9 @@ from six import text_type
 from lxml import etree
 from ..treebuilders.etree import tag_regexp
 
-from gettext import gettext
-_ = gettext
+from . import base
 
-from . import _base
-
-from .. import ihatexml
+from .. import _ihatexml
 
 
 def ensure_str(s):
@@ -18,20 +15,27 @@ def ensure_str(s):
     elif isinstance(s, text_type):
         return s
     else:
-        return s.decode("utf-8", "strict")
+        return s.decode("ascii", "strict")
 
 
 class Root(object):
     def __init__(self, et):
         self.elementtree = et
         self.children = []
-        if et.docinfo.internalDTD:
-            self.children.append(Doctype(self,
-                                         ensure_str(et.docinfo.root_name),
-                                         ensure_str(et.docinfo.public_id),
-                                         ensure_str(et.docinfo.system_url)))
-        root = et.getroot()
-        node = root
+
+        try:
+            if et.docinfo.internalDTD:
+                self.children.append(Doctype(self,
+                                             ensure_str(et.docinfo.root_name),
+                                             ensure_str(et.docinfo.public_id),
+                                             ensure_str(et.docinfo.system_url)))
+        except AttributeError:
+            pass
+
+        try:
+            node = et.getroot()
+        except AttributeError:
+            node = et
 
         while node.getprevious() is not None:
             node = node.getprevious()
@@ -118,35 +122,38 @@ class FragmentWrapper(object):
         return len(self.obj)
 
 
-class TreeWalker(_base.NonRecursiveTreeWalker):
+class TreeWalker(base.NonRecursiveTreeWalker):
     def __init__(self, tree):
-        if hasattr(tree, "getroot"):
-            tree = Root(tree)
-        elif isinstance(tree, list):
+        # pylint:disable=redefined-variable-type
+        if isinstance(tree, list):
+            self.fragmentChildren = set(tree)
             tree = FragmentRoot(tree)
-        _base.NonRecursiveTreeWalker.__init__(self, tree)
-        self.filter = ihatexml.InfosetFilter()
+        else:
+            self.fragmentChildren = set()
+            tree = Root(tree)
+        base.NonRecursiveTreeWalker.__init__(self, tree)
+        self.filter = _ihatexml.InfosetFilter()
 
     def getNodeDetails(self, node):
         if isinstance(node, tuple):  # Text node
             node, key = node
-            assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
-            return _base.TEXT, ensure_str(getattr(node, key))
+            assert key in ("text", "tail"), "Text nodes are text or tail, found %s" % key
+            return base.TEXT, ensure_str(getattr(node, key))
 
         elif isinstance(node, Root):
-            return (_base.DOCUMENT,)
+            return (base.DOCUMENT,)
 
         elif isinstance(node, Doctype):
-            return _base.DOCTYPE, node.name, node.public_id, node.system_id
+            return base.DOCTYPE, node.name, node.public_id, node.system_id
 
         elif isinstance(node, FragmentWrapper) and not hasattr(node, "tag"):
-            return _base.TEXT, node.obj
+            return base.TEXT, ensure_str(node.obj)
 
         elif node.tag == etree.Comment:
-            return _base.COMMENT, ensure_str(node.text)
+            return base.COMMENT, ensure_str(node.text)
 
         elif node.tag == etree.Entity:
-            return _base.ENTITY, ensure_str(node.text)[1:-1]  # strip &;
+            return base.ENTITY, ensure_str(node.text)[1:-1]  # strip &;
 
         else:
             # This is assumed to be an ordinary element
@@ -165,11 +172,11 @@ class TreeWalker(_base.NonRecursiveTreeWalker):
                     attrs[(match.group(1), match.group(2))] = value
                 else:
                     attrs[(None, name)] = value
-            return (_base.ELEMENT, namespace, self.filter.fromXmlName(tag),
+            return (base.ELEMENT, namespace, self.filter.fromXmlName(tag),
                     attrs, len(node) > 0 or node.text)
 
     def getFirstChild(self, node):
-        assert not isinstance(node, tuple), _("Text nodes have no children")
+        assert not isinstance(node, tuple), "Text nodes have no children"
 
         assert len(node) or node.text, "Node has no children"
         if node.text:
@@ -180,7 +187,7 @@ class TreeWalker(_base.NonRecursiveTreeWalker):
     def getNextSibling(self, node):
         if isinstance(node, tuple):  # Text node
             node, key = node
-            assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
+            assert key in ("text", "tail"), "Text nodes are text or tail, found %s" % key
             if key == "text":
                 # XXX: we cannot use a "bool(node) and node[0] or None" construct here
                 # because node[0] might evaluate to False if it has no child element
@@ -196,9 +203,11 @@ class TreeWalker(_base.NonRecursiveTreeWalker):
     def getParentNode(self, node):
         if isinstance(node, tuple):  # Text node
             node, key = node
-            assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
+            assert key in ("text", "tail"), "Text nodes are text or tail, found %s" % key
             if key == "text":
                 return node
             # else: fallback to "normal" processing
+        elif node in self.fragmentChildren:
+            return None
 
         return node.getparent()
diff --git a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/genshistream.py b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/genshi.py
similarity index 90%
rename from testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/genshistream.py
rename to testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/genshi.py
index f559c45d0445..7483be27d4d2 100644
--- a/testing/web-platform/tests/tools/html5lib/html5lib/treewalkers/genshistream.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/html5lib/treewalkers/genshi.py
@@ -4,12 +4,12 @@ from genshi.core import QName
 from genshi.core import START, END, XML_NAMESPACE, DOCTYPE, TEXT
 from genshi.core import START_NS, END_NS, START_CDATA, END_CDATA, PI, COMMENT
 
-from . import _base
+from . import base
 
 from ..constants import voidElements, namespaces
 
 
-class TreeWalker(_base.TreeWalker):
+class TreeWalker(base.TreeWalker):
     def __iter__(self):
         # Buffer the events so we can pass in the following one
         previous = None
@@ -25,7 +25,7 @@ class TreeWalker(_base.TreeWalker):
                 yield token
 
     def tokens(self, event, next):
-        kind, data, pos = event
+        kind, data, _ = event
         if kind == START:
             tag, attribs = data
             name = tag.localname
@@ -39,8 +39,8 @@ class TreeWalker(_base.TreeWalker):
 
             if namespace == namespaces["html"] and name in voidElements:
                 for token in self.emptyTag(namespace, name, converted_attribs,
-                                           not next or next[0] != END
-                                           or next[1] != tag):
+                                           not next or next[0] != END or
+                                           next[1] != tag):
                     yield token
             else:
                 yield self.startTag(namespace, name, converted_attribs)
@@ -48,7 +48,7 @@ class TreeWalker(_base.TreeWalker):
         elif kind == END:
             name = data.localname
             namespace = data.namespace
-            if name not in voidElements:
+            if namespace != namespaces["html"] or name not in voidElements:
                 yield self.endTag(namespace, name)
 
         elif kind == COMMENT:
diff --git a/testing/web-platform/tests/tools/html5lib/parse.py b/testing/web-platform/tests/tools/third_party/html5lib/parse.py
similarity index 78%
rename from testing/web-platform/tests/tools/html5lib/parse.py
rename to testing/web-platform/tests/tools/third_party/html5lib/parse.py
index 9cbf3b8d1cc5..3e65c330d921 100755
--- a/testing/web-platform/tests/tools/html5lib/parse.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/parse.py
@@ -5,18 +5,18 @@ Parse a document to a tree, with optional profiling
 """
 
 import sys
-import os
 import traceback
 from optparse import OptionParser
 
-from html5lib import html5parser, sanitizer
-from html5lib.tokenizer import HTMLTokenizer
+from html5lib import html5parser
 from html5lib import treebuilders, serializer, treewalkers
 from html5lib import constants
+from html5lib import _utils
+
 
 def parse():
     optParser = getOptParser()
-    opts,args = optParser.parse_args()
+    opts, args = optParser.parse_args()
     encoding = "utf8"
 
     try:
@@ -24,7 +24,10 @@ def parse():
         # Try opening from the internet
         if f.startswith('http://'):
             try:
-                import urllib.request, urllib.parse, urllib.error, cgi
+                import urllib.request
+                import urllib.parse
+                import urllib.error
+                import cgi
                 f = urllib.request.urlopen(f)
                 contentType = f.headers.get('content-type')
                 if contentType:
@@ -40,7 +43,7 @@ def parse():
             try:
                 # Try opening from file system
                 f = open(f, "rb")
-            except IOError as e:                
+            except IOError as e:
                 sys.stderr.write("Unable to open file: %s\n" % e)
                 sys.exit(1)
     except IndexError:
@@ -49,12 +52,7 @@ def parse():
 
     treebuilder = treebuilders.getTreeBuilder(opts.treebuilder)
 
-    if opts.sanitize:
-        tokenizer = sanitizer.HTMLSanitizer
-    else:
-        tokenizer = HTMLTokenizer
-
-    p = html5parser.HTMLParser(tree=treebuilder, tokenizer=tokenizer, debug=opts.log)
+    p = html5parser.HTMLParser(tree=treebuilder, debug=opts.log)
 
     if opts.fragment:
         parseMethod = p.parseFragment
@@ -64,11 +62,12 @@ def parse():
     if opts.profile:
         import cProfile
         import pstats
-        cProfile.runctx("run(parseMethod, f, encoding)", None,
+        cProfile.runctx("run(parseMethod, f, encoding, scripting)", None,
                         {"run": run,
                          "parseMethod": parseMethod,
                          "f": f,
-                         "encoding": encoding},
+                         "encoding": encoding,
+                         "scripting": opts.scripting},
                         "stats.prof")
         # XXX - We should use a temp file here
         stats = pstats.Stats('stats.prof')
@@ -78,27 +77,29 @@ def parse():
     elif opts.time:
         import time
         t0 = time.time()
-        document = run(parseMethod, f, encoding)
+        document = run(parseMethod, f, encoding, opts.scripting)
         t1 = time.time()
         if document:
             printOutput(p, document, opts)
             t2 = time.time()
-            sys.stderr.write("\n\nRun took: %fs (plus %fs to print the output)"%(t1-t0, t2-t1))
+            sys.stderr.write("\n\nRun took: %fs (plus %fs to print the output)" % (t1 - t0, t2 - t1))
         else:
-            sys.stderr.write("\n\nRun took: %fs"%(t1-t0))
+            sys.stderr.write("\n\nRun took: %fs" % (t1 - t0))
     else:
-        document = run(parseMethod, f, encoding)
+        document = run(parseMethod, f, encoding, opts.scripting)
         if document:
             printOutput(p, document, opts)
 
-def run(parseMethod, f, encoding):
+
+def run(parseMethod, f, encoding, scripting):
     try:
-        document = parseMethod(f, encoding=encoding)
+        document = parseMethod(f, override_encoding=encoding, scripting=scripting)
     except:
         document = None
         traceback.print_exc()
     return document
 
+
 def printOutput(parser, document, opts):
     if opts.encoding:
         print("Encoding:", parser.tokenizer.stream.charEncoding)
@@ -108,24 +109,32 @@ def printOutput(parser, document, opts):
 
     if document is not None:
         if opts.xml:
-            sys.stdout.write(document.toxml("utf-8"))
+            tb = opts.treebuilder.lower()
+            if tb == "dom":
+                document.writexml(sys.stdout, encoding="utf-8")
+            elif tb == "lxml":
+                import lxml.etree
+                sys.stdout.write(lxml.etree.tostring(document, encoding="unicode"))
+            elif tb == "etree":
+                sys.stdout.write(_utils.default_etree.tostring(document, encoding="unicode"))
         elif opts.tree:
-            if not hasattr(document,'__getitem__'):
+            if not hasattr(document, '__getitem__'):
                 document = [document]
             for fragment in document:
                 print(parser.tree.testSerializer(fragment))
-        elif opts.hilite:
-            sys.stdout.write(document.hilite("utf-8"))
         elif opts.html:
             kwargs = {}
             for opt in serializer.HTMLSerializer.options:
                 try:
-                    kwargs[opt] = getattr(opts,opt)
+                    kwargs[opt] = getattr(opts, opt)
                 except:
                     pass
             if not kwargs['quote_char']:
                 del kwargs['quote_char']
 
+            if opts.sanitize:
+                kwargs["sanitize"] = True
+
             tokens = treewalkers.getTreeWalker(opts.treebuilder)(document)
             if sys.version_info[0] >= 3:
                 encoding = None
@@ -133,12 +142,14 @@ def printOutput(parser, document, opts):
                 encoding = "utf-8"
             for text in serializer.HTMLSerializer(**kwargs).serialize(tokens, encoding=encoding):
                 sys.stdout.write(text)
-            if not text.endswith('\n'): sys.stdout.write('\n')
+            if not text.endswith('\n'):
+                sys.stdout.write('\n')
     if opts.error:
-        errList=[]
+        errList = []
         for pos, errorcode, datavars in parser.errors:
-            errList.append("Line %i Col %i"%pos + " " + constants.E.get(errorcode, 'Unknown error "%s"' % errorcode) % datavars)
-        sys.stdout.write("\nParse errors:\n" + "\n".join(errList)+"\n")
+            errList.append("Line %i Col %i" % pos + " " + constants.E.get(errorcode, 'Unknown error "%s"' % errorcode) % datavars)
+        sys.stdout.write("\nParse errors:\n" + "\n".join(errList) + "\n")
+
 
 def getOptParser():
     parser = OptionParser(usage=__doc__)
@@ -152,7 +163,7 @@ def getOptParser():
                       help="Time the run using time.time (may not be accurate on all platforms, especially for short runs)")
 
     parser.add_option("-b", "--treebuilder", action="store", type="string",
-                      dest="treebuilder", default="simpleTree")
+                      dest="treebuilder", default="etree")
 
     parser.add_option("-e", "--error", action="store_true", default=False,
                       dest="error", help="Print a list of parse errors")
@@ -160,6 +171,9 @@ def getOptParser():
     parser.add_option("-f", "--fragment", action="store_true", default=False,
                       dest="fragment", help="Parse as a fragment")
 
+    parser.add_option("-s", "--scripting", action="store_true", default=False,
+                      dest="scripting", help="Handle noscript tags as if scripting was enabled")
+
     parser.add_option("", "--tree", action="store_true", default=False,
                       dest="tree", help="Output as debug tree")
 
@@ -169,9 +183,6 @@ def getOptParser():
     parser.add_option("", "--no-html", action="store_false", default=True,
                       dest="html", help="Don't output html")
 
-    parser.add_option("", "--hilite", action="store_true", default=False,
-                      dest="hilite", help="Output as formatted highlighted code.")
-
     parser.add_option("-c", "--encoding", action="store_true", default=False,
                       dest="encoding", help="Print character encoding used")
 
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/pytest.ini b/testing/web-platform/tests/tools/third_party/html5lib/pytest.ini
new file mode 100644
index 000000000000..8824977a8f40
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/pytest.ini
@@ -0,0 +1,17 @@
+[pytest]
+# Output fails, errors, xpass, and warnings; ignore doctest; make warnings errors
+addopts = -rfEXw -p no:doctest --strict
+
+# Make xpass results be considered fail
+xfail_strict = true
+
+# Document our markers
+markers =
+    DOM: mark a test as a DOM tree test
+    ElementTree: mark a test as a ElementTree tree test
+    cElementTree: mark a test as a cElementTree tree test
+    lxml: mark a test as a lxml tree test
+    genshi: mark a test as a genshi tree test
+    parser: mark a test as a parser test
+    namespaced: mark a test as a namespaced parser test
+    treewalker: mark a test as a treewalker test
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/requirements-install.sh b/testing/web-platform/tests/tools/third_party/html5lib/requirements-install.sh
new file mode 100755
index 000000000000..b7a8d96dd6c2
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/requirements-install.sh
@@ -0,0 +1,15 @@
+#!/bin/bash -ex
+
+if [[ $SIX_VERSION ]]; then
+  pip install six==$SIX_VERSION
+fi
+
+pip install -r requirements-test.txt
+
+if [[ $USE_OPTIONAL == "true" ]]; then
+  pip install -r requirements-optional.txt
+fi
+
+if [[ $CI == "true" ]]; then
+  pip install codecov
+fi
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/requirements-optional.txt b/testing/web-platform/tests/tools/third_party/html5lib/requirements-optional.txt
new file mode 100644
index 000000000000..c00fd242f6f4
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/requirements-optional.txt
@@ -0,0 +1,17 @@
+-r requirements.txt
+
+# We support a Genshi treewalker that can be used to serialize Genshi
+# streams.
+genshi
+
+# chardet can be used as a fallback in case we are unable to determine
+# the encoding of a document.
+chardet>=2.2
+
+# lxml is supported with its own treebuilder ("lxml") and otherwise
+# uses the standard ElementTree support
+lxml ; platform_python_implementation == 'CPython'
+
+# DATrie can be used in place of our Python trie implementation for
+# slightly better parsing performance.
+datrie ; platform_python_implementation == 'CPython'
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/requirements-test.txt b/testing/web-platform/tests/tools/third_party/html5lib/requirements-test.txt
new file mode 100644
index 000000000000..4e223a3fde1e
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/requirements-test.txt
@@ -0,0 +1,10 @@
+-r requirements.txt
+
+tox
+
+flake8<3.0
+
+pytest==3.2.5
+coverage
+pytest-expect>=1.1,<2.0
+mock
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/requirements.txt b/testing/web-platform/tests/tools/third_party/html5lib/requirements.txt
new file mode 100644
index 000000000000..ae7ec3d08b90
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/requirements.txt
@@ -0,0 +1,2 @@
+six>=1.9
+webencodings
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/setup.cfg b/testing/web-platform/tests/tools/third_party/html5lib/setup.cfg
new file mode 100644
index 000000000000..d309fdaa3f42
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/setup.cfg
@@ -0,0 +1,14 @@
+[bdist_wheel]
+universal = 1
+
+[pep8]
+ignore = N
+max-line-length = 139
+exclude = .git,__pycache__,.tox,doc
+
+[flake8]
+ignore = N
+max-line-length = 139
+
+[metadata]
+license_file = LICENSE
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/setup.py b/testing/web-platform/tests/tools/third_party/html5lib/setup.py
new file mode 100644
index 000000000000..3e413f2a933a
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/setup.py
@@ -0,0 +1,125 @@
+from __future__ import print_function
+
+import ast
+import codecs
+import sys
+
+from os.path import join, dirname
+from setuptools import setup, find_packages, __version__ as setuptools_version
+from pkg_resources import parse_version
+
+import pkg_resources
+
+try:
+    import _markerlib.markers
+except ImportError:
+    _markerlib = None
+
+
+# _markerlib.default_environment() obtains its data from _VARS
+# and wraps it in another dict, but _markerlib_evaluate writes
+# to the dict while it is iterating the keys, causing an error
+# on Python 3 only.
+# Replace _markerlib.default_environment to return a custom dict
+# that has all the necessary markers, and ignores any writes.
+
+class Python3MarkerDict(dict):
+
+    def __setitem__(self, key, value):
+        pass
+
+    def pop(self, i=-1):
+        return self[i]
+
+
+if _markerlib and sys.version_info[0] == 3:
+    env = _markerlib.markers._VARS
+    for key in list(env.keys()):
+        new_key = key.replace('.', '_')
+        if new_key != key:
+            env[new_key] = env[key]
+
+    _markerlib.markers._VARS = Python3MarkerDict(env)
+
+    def default_environment():
+        return _markerlib.markers._VARS
+
+    _markerlib.default_environment = default_environment
+
+# Avoid the very buggy pkg_resources.parser, which doesnt consistently
+# recognise the markers needed by this setup.py
+# Change this to setuptools 20.10.0 to support all markers.
+if pkg_resources:
+    if parse_version(setuptools_version) < parse_version('18.5'):
+        MarkerEvaluation = pkg_resources.MarkerEvaluation
+
+        del pkg_resources.parser
+        pkg_resources.evaluate_marker = MarkerEvaluation._markerlib_evaluate
+        MarkerEvaluation.evaluate_marker = MarkerEvaluation._markerlib_evaluate
+
+classifiers = [
+    'Development Status :: 5 - Production/Stable',
+    'Intended Audience :: Developers',
+    'License :: OSI Approved :: MIT License',
+    'Operating System :: OS Independent',
+    'Programming Language :: Python',
+    'Programming Language :: Python :: 2',
+    'Programming Language :: Python :: 2.7',
+    'Programming Language :: Python :: 3',
+    'Programming Language :: Python :: 3.3',
+    'Programming Language :: Python :: 3.4',
+    'Programming Language :: Python :: 3.5',
+    'Programming Language :: Python :: 3.6',
+    'Topic :: Software Development :: Libraries :: Python Modules',
+    'Topic :: Text Processing :: Markup :: HTML'
+]
+
+here = dirname(__file__)
+with codecs.open(join(here, 'README.rst'), 'r', 'utf8') as readme_file:
+    with codecs.open(join(here, 'CHANGES.rst'), 'r', 'utf8') as changes_file:
+        long_description = readme_file.read() + '\n' + changes_file.read()
+
+version = None
+with open(join(here, "html5lib", "__init__.py"), "rb") as init_file:
+    t = ast.parse(init_file.read(), filename="__init__.py", mode="exec")
+    assert isinstance(t, ast.Module)
+    assignments = filter(lambda x: isinstance(x, ast.Assign), t.body)
+    for a in assignments:
+        if (len(a.targets) == 1 and
+                isinstance(a.targets[0], ast.Name) and
+                a.targets[0].id == "__version__" and
+                isinstance(a.value, ast.Str)):
+            version = a.value.s
+
+setup(name='html5lib',
+      version=version,
+      url='https://github.com/html5lib/html5lib-python',
+      license="MIT License",
+      description='HTML parser based on the WHATWG HTML specification',
+      long_description=long_description,
+      classifiers=classifiers,
+      maintainer='James Graham',
+      maintainer_email='james@hoppipolla.co.uk',
+      packages=find_packages(exclude=["*.tests", "*.tests.*", "tests.*", "tests"]),
+      install_requires=[
+          'six>=1.9',
+          'webencodings',
+      ],
+      extras_require={
+          # A conditional extra will only install these items when the extra is
+          # requested and the condition matches.
+          "datrie:platform_python_implementation == 'CPython'": ["datrie"],
+          "lxml:platform_python_implementation == 'CPython'": ["lxml"],
+
+          # Standard extras, will be installed when the extra is requested.
+          "genshi": ["genshi"],
+          "chardet": ["chardet>=2.2"],
+
+          # The all extra combines a standard extra which will be used anytime
+          # the all extra is requested, and it extends it with a conditional
+          # extra that will be installed whenever the condition matches and the
+          # all extra is requested.
+          "all": ["genshi", "chardet>=2.2"],
+          "all:platform_python_implementation == 'CPython'": ["datrie", "lxml"],
+      },
+      )
diff --git a/testing/web-platform/tests/tools/third_party/html5lib/tox.ini b/testing/web-platform/tests/tools/third_party/html5lib/tox.ini
new file mode 100644
index 000000000000..e07ef670cef9
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/html5lib/tox.ini
@@ -0,0 +1,23 @@
+[tox]
+envlist = {py27,py33,py34,py35,py36,pypy}-{base,six19,optional}
+
+[testenv]
+deps =
+  optional: -r{toxinidir}/requirements-optional.txt
+  -r{toxinidir}/requirements-test.txt
+  doc: Sphinx
+
+passenv =
+  PYTEST_COMMAND
+  COVERAGE_RUN_OPTIONS
+commands =
+  six19: pip install six==1.9
+  {env:PYTEST_COMMAND:{envbindir}/py.test} {posargs}
+  flake8 {toxinidir}
+
+[testenv:doc]
+changedir = doc
+commands = sphinx-build -b html . _build
+
+[flake8]
+exclude = ./.tox
diff --git a/testing/web-platform/tests/tools/html5lib/utils/entities.py b/testing/web-platform/tests/tools/third_party/html5lib/utils/entities.py
similarity index 67%
rename from testing/web-platform/tests/tools/html5lib/utils/entities.py
rename to testing/web-platform/tests/tools/third_party/html5lib/utils/entities.py
index 116a27cbc9b9..6dccf5f0bfd0 100644
--- a/testing/web-platform/tests/tools/html5lib/utils/entities.py
+++ b/testing/web-platform/tests/tools/third_party/html5lib/utils/entities.py
@@ -2,50 +2,59 @@ import json
 
 import html5lib
 
+
 def parse(path="html5ents.xml"):
     return html5lib.parse(open(path), treebuilder="lxml")
 
+
 def entity_table(tree):
     return dict((entity_name("".join(tr[0].xpath(".//text()"))),
                  entity_characters(tr[1].text))
                 for tr in tree.xpath("//h:tbody/h:tr",
-                                     namespaces={"h":"http://www.w3.org/1999/xhtml"}))
+                                     namespaces={"h": "http://www.w3.org/1999/xhtml"}))
+
 
 def entity_name(inp):
     return inp.strip()
 
+
 def entity_characters(inp):
     return "".join(codepoint_to_character(item)
-                    for item in inp.split()
-                    if item)
+                   for item in inp.split()
+                   if item)
+
 
 def codepoint_to_character(inp):
-    return ("\U000"+inp[2:]).decode("unicode-escape")
+    return ("\\U000" + inp[2:]).decode("unicode-escape")
+
 
 def make_tests_json(entities):
     test_list = make_test_list(entities)
     tests_json = {"tests":
-                      [make_test(*item) for item in test_list]
+                  [make_test(*item) for item in test_list]
                   }
     return tests_json
 
+
 def make_test(name, characters, good):
     return {
-        "description":test_description(name, good),
-        "input":"&%s"%name,
-        "output":test_expected(name, characters, good)
-        }
+        "description": test_description(name, good),
+        "input": "&%s" % name,
+        "output": test_expected(name, characters, good)
+    }
+
 
 def test_description(name, good):
     with_semicolon = name.endswith(";")
-    semicolon_text = {True:"with a semi-colon",
-                      False:"without a semi-colon"}[with_semicolon]
+    semicolon_text = {True: "with a semi-colon",
+                      False: "without a semi-colon"}[with_semicolon]
     if good:
-        text = "Named entity: %s %s"%(name, semicolon_text)
+        text = "Named entity: %s %s" % (name, semicolon_text)
     else:
-        text = "Bad named entity: %s %s"%(name, semicolon_text)
+        text = "Bad named entity: %s %s" % (name, semicolon_text)
     return text
 
+
 def test_expected(name, characters, good):
     rv = []
     if not good or not name.endswith(";"):
@@ -53,6 +62,7 @@ def test_expected(name, characters, good):
     rv.append(["Character", characters])
     return rv
 
+
 def make_test_list(entities):
     tests = []
     for entity_name, characters in entities.items():
@@ -61,20 +71,23 @@ def make_test_list(entities):
         tests.append((entity_name, characters, True))
     return sorted(tests)
 
+
 def subentity_exists(entity_name, entities):
     for i in range(1, len(entity_name)):
         if entity_name[:-i] in entities:
             return True
     return False
 
+
 def make_entities_code(entities):
-    entities_text = "\n".join("    \"%s\": u\"%s\","%(
-            name, entities[name].encode(
-                "unicode-escape").replace("\"", "\\\""))
-                              for name in sorted(entities.keys()))
+    entities_text = "\n".join("    \"%s\": u\"%s\"," % (
+        name, entities[name].encode(
+            "unicode-escape").replace("\"", "\\\""))
+        for name in sorted(entities.keys()))
     return """entities = {
 %s
-}"""%entities_text
+}""" % entities_text
+
 
 def main():
     entities = entity_table(parse())
@@ -85,4 +98,3 @@ def main():
 
 if __name__ == "__main__":
     main()
-
diff --git a/testing/web-platform/tests/tools/six/CHANGES b/testing/web-platform/tests/tools/third_party/six/CHANGES
similarity index 82%
rename from testing/web-platform/tests/tools/six/CHANGES
rename to testing/web-platform/tests/tools/third_party/six/CHANGES
index 25930bd9aa1a..b399882561ec 100644
--- a/testing/web-platform/tests/tools/six/CHANGES
+++ b/testing/web-platform/tests/tools/third_party/six/CHANGES
@@ -3,8 +3,52 @@ Changelog for six
 
 This file lists the changes in each six version.
 
-Development version
--------------------
+1.11.0
+------
+
+- Pull request #178: `with_metaclass` now properly proxies `__prepare__` to the
+  underlying metaclass.
+
+- Pull request #191: Allow `with_metaclass` to work with metaclasses implemented
+  in C.
+
+- Pull request #203: Add parse_http_list and parse_keqv_list to moved
+  urllib.request.
+
+- Pull request #172 and issue #171: Add unquote_to_bytes to moved urllib.parse.
+
+- Pull request #167: Add `six.moves.getoutput`.
+
+- Pull request #80: Add `six.moves.urllib_parse.splitvalue`.
+
+- Pull request #75: Add `six.moves.email_mime_image`.
+
+- Pull request #72: Avoid creating reference cycles through tracebacks in
+  `reraise`.
+
+1.10.0
+------
+
+- Issue #122: Improve the performance of `six.int2byte` on Python 3.
+
+- Pull request #55 and issue #99: Don't add the `winreg` module to `six.moves`
+  on non-Windows platforms.
+
+- Pull request #60 and issue #108: Add `six.moves.getcwd` and
+  `six.moves.getcwdu`.
+
+- Pull request #64: Add `create_unbound_method` to create unbound methods.
+
+1.9.0
+-----
+
+- Issue #106: Support the `flush` parameter to `six.print_`.
+
+- Pull request #48 and issue #15: Add the `python_2_unicode_compatible`
+  decorator.
+
+- Pull request #57 and issue #50: Add several compatibility methods for unittest
+  assertions that were renamed between Python 2 and 3.
 
 - Issue #105 and pull request #58: Ensure `six.wraps` respects the *updated* and
   *assigned* arguments.
@@ -18,6 +62,9 @@ Development version
 - Pull request #51: Add `six.view(keys|values|itmes)`, which provide dictionary
   views on Python 2.7+.
 
+- Issue #112: `six.moves.reload_module` now uses the importlib module on
+  Python 3.4+.
+
 1.8.0
 -----
 
diff --git a/testing/web-platform/tests/tools/six/LICENSE b/testing/web-platform/tests/tools/third_party/six/LICENSE
similarity index 96%
rename from testing/web-platform/tests/tools/six/LICENSE
rename to testing/web-platform/tests/tools/third_party/six/LICENSE
index d76e024263ce..f3068bfd9e0c 100644
--- a/testing/web-platform/tests/tools/six/LICENSE
+++ b/testing/web-platform/tests/tools/third_party/six/LICENSE
@@ -1,4 +1,4 @@
-Copyright (c) 2010-2014 Benjamin Peterson
+Copyright (c) 2010-2017 Benjamin Peterson
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of
 this software and associated documentation files (the "Software"), to deal in
diff --git a/testing/web-platform/tests/tools/six/MANIFEST.in b/testing/web-platform/tests/tools/third_party/six/MANIFEST.in
similarity index 100%
rename from testing/web-platform/tests/tools/six/MANIFEST.in
rename to testing/web-platform/tests/tools/third_party/six/MANIFEST.in
diff --git a/testing/web-platform/tests/tools/third_party/six/PKG-INFO b/testing/web-platform/tests/tools/third_party/six/PKG-INFO
new file mode 100644
index 000000000000..cd5ff4bb8e4f
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/six/PKG-INFO
@@ -0,0 +1,41 @@
+Metadata-Version: 1.1
+Name: six
+Version: 1.11.0
+Summary: Python 2 and 3 compatibility utilities
+Home-page: http://pypi.python.org/pypi/six/
+Author: Benjamin Peterson
+Author-email: benjamin@python.org
+License: MIT
+Description: .. image:: http://img.shields.io/pypi/v/six.svg
+           :target: https://pypi.python.org/pypi/six
+        
+        .. image:: https://travis-ci.org/benjaminp/six.svg?branch=master
+            :target: https://travis-ci.org/benjaminp/six
+        
+        .. image:: http://img.shields.io/badge/license-MIT-green.svg
+           :target: https://github.com/benjaminp/six/blob/master/LICENSE
+        
+        Six is a Python 2 and 3 compatibility library.  It provides utility functions
+        for smoothing over the differences between the Python versions with the goal of
+        writing Python code that is compatible on both Python versions.  See the
+        documentation for more information on what is provided.
+        
+        Six supports every Python version since 2.6.  It is contained in only one Python
+        file, so it can be easily copied into your project. (The copyright and license
+        notice must be retained.)
+        
+        Online documentation is at http://six.rtfd.org.
+        
+        Bugs can be reported to https://github.com/benjaminp/six.  The code can also
+        be found there.
+        
+        For questions about six or porting in general, email the python-porting mailing
+        list: https://mail.python.org/mailman/listinfo/python-porting
+        
+Platform: UNKNOWN
+Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 3
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Utilities
diff --git a/testing/web-platform/tests/tools/third_party/six/README.rst b/testing/web-platform/tests/tools/third_party/six/README.rst
new file mode 100644
index 000000000000..c17d8d732af8
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/six/README.rst
@@ -0,0 +1,25 @@
+.. image:: http://img.shields.io/pypi/v/six.svg
+   :target: https://pypi.python.org/pypi/six
+
+.. image:: https://travis-ci.org/benjaminp/six.svg?branch=master
+    :target: https://travis-ci.org/benjaminp/six
+
+.. image:: http://img.shields.io/badge/license-MIT-green.svg
+   :target: https://github.com/benjaminp/six/blob/master/LICENSE
+
+Six is a Python 2 and 3 compatibility library.  It provides utility functions
+for smoothing over the differences between the Python versions with the goal of
+writing Python code that is compatible on both Python versions.  See the
+documentation for more information on what is provided.
+
+Six supports every Python version since 2.6.  It is contained in only one Python
+file, so it can be easily copied into your project. (The copyright and license
+notice must be retained.)
+
+Online documentation is at http://six.rtfd.org.
+
+Bugs can be reported to https://github.com/benjaminp/six.  The code can also
+be found there.
+
+For questions about six or porting in general, email the python-porting mailing
+list: https://mail.python.org/mailman/listinfo/python-porting
diff --git a/testing/web-platform/tests/tools/six/documentation/Makefile b/testing/web-platform/tests/tools/third_party/six/documentation/Makefile
similarity index 100%
rename from testing/web-platform/tests/tools/six/documentation/Makefile
rename to testing/web-platform/tests/tools/third_party/six/documentation/Makefile
diff --git a/testing/web-platform/tests/tools/six/documentation/conf.py b/testing/web-platform/tests/tools/third_party/six/documentation/conf.py
similarity index 99%
rename from testing/web-platform/tests/tools/six/documentation/conf.py
rename to testing/web-platform/tests/tools/third_party/six/documentation/conf.py
index 7e54287a69e0..ad925c1c1d1e 100644
--- a/testing/web-platform/tests/tools/six/documentation/conf.py
+++ b/testing/web-platform/tests/tools/third_party/six/documentation/conf.py
@@ -33,7 +33,7 @@ master_doc = "index"
 
 # General information about the project.
 project = u"six"
-copyright = u"2010-2014, Benjamin Peterson"
+copyright = u"2010-2017, Benjamin Peterson"
 
 sys.path.append(os.path.abspath(os.path.join(".", "..")))
 from six import __version__ as six_version
diff --git a/testing/web-platform/tests/tools/six/documentation/index.rst b/testing/web-platform/tests/tools/third_party/six/documentation/index.rst
similarity index 73%
rename from testing/web-platform/tests/tools/six/documentation/index.rst
rename to testing/web-platform/tests/tools/third_party/six/documentation/index.rst
index 9827e6695b59..dd0dc6e3bde8 100644
--- a/testing/web-platform/tests/tools/six/documentation/index.rst
+++ b/testing/web-platform/tests/tools/third_party/six/documentation/index.rst
@@ -13,12 +13,12 @@ Python 3.  It is intended to support codebases that work on both Python 2 and 3
 without modification.  six consists of only one Python file, so it is painless
 to copy into a project.
 
-Six can be downloaded on `PyPi <http://pypi.python.org/pypi/six/>`_.  Its bug
-tracker and code hosting is on `BitBucket <http://bitbucket.org/gutworth/six>`_.
+Six can be downloaded on `PyPi <https://pypi.python.org/pypi/six/>`_.  Its bug
+tracker and code hosting is on `GitHub <https://github.com/benjaminp/six>`_.
 
 The name, "six", comes from the fact that 2*3 equals 6.  Why not addition?
 Multiplication is more powerful, and, anyway, "five" has already been snatched
-away by the Zope Five project.
+away by the (admittedly now moribund) Zope Five project.
 
 
 Indices and tables
@@ -164,7 +164,9 @@ functions and methods is the stdlib :mod:`py3:inspect` module.
 
    Get the next item of iterator *it*.  :exc:`py3:StopIteration` is raised if
    the iterator is exhausted.  This is a replacement for calling ``it.next()``
-   in Python 2 and ``next(it)`` in Python 3.
+   in Python 2 and ``next(it)`` in Python 3.  Python 2.6 and above have a
+   builtin ``next`` function, so six's version is only necessary for Python 2.5
+   compatibility.
 
 
 .. function:: callable(obj)
@@ -232,6 +234,13 @@ functions and methods is the stdlib :mod:`py3:inspect` module.
    requires the *obj*'s class to be passed.
 
 
+.. function:: create_unbound_method(func, cls)
+
+   Return an unbound method object wrapping *func*.  In Python 2, this will
+   return a :func:`py2:types.MethodType` object.  In Python 3, unbound methods
+   do not exist and this wrapper will simply return *func*.
+
+
 .. class:: Iterator
 
    A class for making portable iterators. The intention is that it be subclassed
@@ -243,7 +252,7 @@ functions and methods is the stdlib :mod:`py3:inspect` module.
    aliased to :class:`py3:object`.)
 
 
-.. function:: wraps(wrapped, assigned=functools.WRAPPER_ASSIGNMENTS, updated=functools.WRAPPER_UPDATES)
+.. decorator:: wraps(wrapped, assigned=functools.WRAPPER_ASSIGNMENTS, updated=functools.WRAPPER_UPDATES)
 
    This is exactly the :func:`py3:functools.wraps` decorator, but it sets the
    ``__wrapped__`` attribute on what it decorates as :func:`py3:functools.wraps`
@@ -270,10 +279,11 @@ Python 2 and 3.
       :func:`exec` with them should be avoided.
 
 
-.. function:: print_(*args, *, file=sys.stdout, end="\\n", sep=" ")
+.. function:: print_(*args, *, file=sys.stdout, end="\\n", sep=" ", flush=False)
 
    Print *args* into *file*.  Each argument will be separated with *sep* and
-   *end* will be written to the file after the last argument is printed.
+   *end* will be written to the file after the last argument is printed.  If
+   *flush* is true, ``file.flush()`` will be called after all data is written.
 
    .. note::
 
@@ -320,7 +330,7 @@ Python 2 and 3.
    decorator.
 
 
-.. function:: add_metaclass(metaclass)
+.. decorator:: add_metaclass(metaclass)
 
    Class decorator that replaces a normally-constructed class with a
    metaclass-constructed one.  Example usage: ::
@@ -337,7 +347,7 @@ Python 2 and 3.
    on Python 3 or ::
 
        class MyClass(object):
-           __metaclass__ = MyMeta
+           __metaclass__ = Meta
 
    on Python 2.
 
@@ -353,7 +363,7 @@ Binary and text data
 >>>>>>>>>>>>>>>>>>>>
 
 Python 3 enforces the distinction between byte strings and text strings far more
-rigoriously than Python 2 does; binary data cannot be automatically coerced to
+rigorously than Python 2 does; binary data cannot be automatically coerced to
 or from text data.  six provides several functions to assist in classifying
 string data in all Python versions.
 
@@ -368,7 +378,7 @@ string data in all Python versions.
    .. note::
 
       Since all Python versions 2.6 and after support the ``b`` prefix,
-      :func:`b`, code without 2.5 support doesn't need :func:`b`.
+      code without 2.5 support doesn't need :func:`b`.
 
 
 .. function:: u(text)
@@ -382,7 +392,7 @@ string data in all Python versions.
    .. note::
 
       In Python 3.3, the ``u`` prefix has been reintroduced. Code that only
-      supports Python 3 versions greater than 3.3 thus does not need
+      supports Python 3 versions of 3.3 and higher thus does not need
       :func:`u`.
 
    .. note::
@@ -425,7 +435,7 @@ string data in all Python versions.
 
 .. data:: StringIO
 
-   This is an fake file object for textual data.  It's an alias for
+   This is a fake file object for textual data.  It's an alias for
    :class:`py2:StringIO.StringIO` in Python 2 and :class:`py3:io.StringIO` in
    Python 3.
 
@@ -437,6 +447,48 @@ string data in all Python versions.
    :class:`py3:io.BytesIO`.
 
 
+.. decorator:: python_2_unicode_compatible
+
+   A class decorator that takes a class defining a ``__str__`` method.  On
+   Python 3, the decorator does nothing.  On Python 2, it aliases the
+   ``__str__`` method to ``__unicode__`` and creates a new ``__str__`` method
+   that returns the result of ``__unicode__()`` encoded with UTF-8.
+
+
+unittest assertions
+>>>>>>>>>>>>>>>>>>>
+
+Six contains compatibility shims for unittest assertions that have been renamed.
+The parameters are the same as their aliases, but you must pass the test method
+as the first argument. For example::
+
+    import six
+    import unittest
+
+    class TestAssertCountEqual(unittest.TestCase):
+        def test(self):
+            six.assertCountEqual(self, (1, 2), [2, 1])
+
+Note these functions are only available on Python 2.7 or later.
+
+.. function:: assertCountEqual()
+
+   Alias for :meth:`~py3:unittest.TestCase.assertCountEqual` on Python 3 and
+   :meth:`~py2:unittest.TestCase.assertItemsEqual` on Python 2.
+
+
+.. function:: assertRaisesRegex()
+
+   Alias for :meth:`~py3:unittest.TestCase.assertRaisesRegex` on Python 3 and
+   :meth:`~py2:unittest.TestCase.assertRaisesRegexp` on Python 2.
+
+
+.. function:: assertRegex()
+
+   Alias for :meth:`~py3:unittest.TestCase.assertRegex` on Python 3 and
+   :meth:`~py2:unittest.TestCase.assertRegexpMatches` on Python 2.
+
+
 Renamed modules and attributes compatibility
 >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
 
@@ -480,14 +532,14 @@ functionality; its structure mimics the structure of the Python 3
 
      from six.moves.cPickle import loads
 
-   work, six places special proxy objects in in :data:`py3:sys.modules`. These
+   work, six places special proxy objects in :data:`py3:sys.modules`. These
    proxies lazily load the underlying module when an attribute is fetched. This
    will fail if the underlying module is not available in the Python
    interpreter. For example, ``sys.modules["six.moves.winreg"].LoadKey`` would
    fail on any non-Windows platform. Unfortunately, some applications try to
    load attributes on every module in :data:`py3:sys.modules`. six mitigates
    this problem for some applications by pretending attributes on unimportable
-   modules don't exist. This hack doesn't work in every case, though. If you are
+   modules do not exist. This hack does not work in every case, though. If you are
    encountering problems with the lazy modules and don't use any from imports
    directly from ``six.moves`` modules, you can workaround the issue by removing
    the six proxy modules::
@@ -498,133 +550,143 @@ functionality; its structure mimics the structure of the Python 3
 
 Supported renames:
 
-+------------------------------+-------------------------------------+-------------------------------------+
-| Name                         | Python 2 name                       | Python 3 name                       |
-+==============================+=====================================+=====================================+
-| ``builtins``                 | :mod:`py2:__builtin__`              | :mod:`py3:builtins`                 |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``configparser``             | :mod:`py2:ConfigParser`             | :mod:`py3:configparser`             |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``copyreg``                  | :mod:`py2:copy_reg`                 | :mod:`py3:copyreg`                  |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``cPickle``                  | :mod:`py2:cPickle`                  | :mod:`py3:pickle`                   |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``cStringIO``                | :func:`py2:cStringIO.StringIO`      | :class:`py3:io.StringIO`            |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``dbm_gnu``                  | :func:`py2:gdbm`                    | :class:`py3:dbm.gnu`                |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``_dummy_thread``            | :mod:`py2:dummy_thread`             | :mod:`py3:_dummy_thread`            |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``email_mime_multipart``     | :mod:`py2:email.MIMEMultipart`      | :mod:`py3:email.mime.multipart`     |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``email_mime_nonmultipart``  | :mod:`py2:email.MIMENonMultipart`   | :mod:`py3:email.mime.nonmultipart`  |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``email_mime_text``          | :mod:`py2:email.MIMEText`           | :mod:`py3:email.mime.text`          |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``email_mime_base``          | :mod:`py2:email.MIMEBase`           | :mod:`py3:email.mime.base`          |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``filter``                   | :func:`py2:itertools.ifilter`       | :func:`py3:filter`                  |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``filterfalse``              | :func:`py2:itertools.ifilterfalse`  | :func:`py3:itertools.filterfalse`   |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``http_cookiejar``           | :mod:`py2:cookielib`                | :mod:`py3:http.cookiejar`           |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``http_cookies``             | :mod:`py2:Cookie`                   | :mod:`py3:http.cookies`             |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``html_entities``            | :mod:`py2:htmlentitydefs`           | :mod:`py3:html.entities`            |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``html_parser``              | :mod:`py2:HTMLParser`               | :mod:`py3:html.parser`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``http_client``              | :mod:`py2:httplib`                  | :mod:`py3:http.client`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``BaseHTTPServer``           | :mod:`py2:BaseHTTPServer`           | :mod:`py3:http.server`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``CGIHTTPServer``            | :mod:`py2:CGIHTTPServer`            | :mod:`py3:http.server`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``SimpleHTTPServer``         | :mod:`py2:SimpleHTTPServer`         | :mod:`py3:http.server`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``input``                    | :func:`py2:raw_input`               | :func:`py3:input`                   |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``intern``                   | :func:`py2:intern`                  | :func:`py3:sys.intern`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``map``                      | :func:`py2:itertools.imap`          | :func:`py3:map`                     |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``queue``                    | :mod:`py2:Queue`                    | :mod:`py3:queue`                    |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``range``                    | :func:`py2:xrange`                  | :func:`py3:range`                   |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``reduce``                   | :func:`py2:reduce`                  | :func:`py3:functools.reduce`        |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``reload_module``            | :func:`py2:reload`                  | :func:`py3:imp.reload`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``reprlib``                  | :mod:`py2:repr`                     | :mod:`py3:reprlib`                  |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``shlex_quote``              | :mod:`py2:pipes.quote`              | :mod:`py3:shlex.quote`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``socketserver``             | :mod:`py2:SocketServer`             | :mod:`py3:socketserver`             |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``_thread``                  | :mod:`py2:thread`                   | :mod:`py3:_thread`                  |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter``                  | :mod:`py2:Tkinter`                  | :mod:`py3:tkinter`                  |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_dialog``           | :mod:`py2:Dialog`                   | :mod:`py3:tkinter.dialog`           |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_filedialog``       | :mod:`py2:FileDialog`               | :mod:`py3:tkinter.FileDialog`       |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_scrolledtext``     | :mod:`py2:ScrolledText`             | :mod:`py3:tkinter.scrolledtext`     |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_simpledialog``     | :mod:`py2:SimpleDialog`             | :mod:`py3:tkinter.simpledialog`     |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_ttk``              | :mod:`py2:ttk`                      | :mod:`py3:tkinter.ttk`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_tix``              | :mod:`py2:Tix`                      | :mod:`py3:tkinter.tix`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_constants``        | :mod:`py2:Tkconstants`              | :mod:`py3:tkinter.constants`        |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_dnd``              | :mod:`py2:Tkdnd`                    | :mod:`py3:tkinter.dnd`              |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_colorchooser``     | :mod:`py2:tkColorChooser`           | :mod:`py3:tkinter.colorchooser`     |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_commondialog``     | :mod:`py2:tkCommonDialog`           | :mod:`py3:tkinter.commondialog`     |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_tkfiledialog``     | :mod:`py2:tkFileDialog`             | :mod:`py3:tkinter.filedialog`       |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_font``             | :mod:`py2:tkFont`                   | :mod:`py3:tkinter.font`             |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_messagebox``       | :mod:`py2:tkMessageBox`             | :mod:`py3:tkinter.messagebox`       |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``tkinter_tksimpledialog``   | :mod:`py2:tkSimpleDialog`           | :mod:`py3:tkinter.simpledialog`     |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``urllib.parse``             | See :mod:`six.moves.urllib.parse`   | :mod:`py3:urllib.parse`             |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``urllib.error``             | See :mod:`six.moves.urllib.error`   | :mod:`py3:urllib.error`             |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``urllib.request``           | See :mod:`six.moves.urllib.request` | :mod:`py3:urllib.request`           |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``urllib.response``          | See :mod:`six.moves.urllib.response`| :mod:`py3:urllib.response`          |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``urllib.robotparser``       | :mod:`py2:robotparser`              | :mod:`py3:urllib.robotparser`       |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``urllib_robotparser``       | :mod:`py2:robotparser`              | :mod:`py3:urllib.robotparser`       |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``UserDict``                 | :class:`py2:UserDict.UserDict`      | :class:`py3:collections.UserDict`   |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``UserList``                 | :class:`py2:UserList.UserList`      | :class:`py3:collections.UserList`   |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``UserString``               | :class:`py2:UserString.UserString`  | :class:`py3:collections.UserString` |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``winreg``                   | :mod:`py2:_winreg`                  | :mod:`py3:winreg`                   |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``xmlrpc_client``            | :mod:`py2:xmlrpclib`                | :mod:`py3:xmlrpc.client`            |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``xmlrpc_server``            | :mod:`py2:SimpleXMLRPCServer`       | :mod:`py3:xmlrpc.server`            |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``xrange``                   | :func:`py2:xrange`                  | :func:`py3:range`                   |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``zip``                      | :func:`py2:itertools.izip`          | :func:`py3:zip`                     |
-+------------------------------+-------------------------------------+-------------------------------------+
-| ``zip_longest``              | :func:`py2:itertools.izip_longest`  | :func:`py3:itertools.zip_longest`   |
-+------------------------------+-------------------------------------+-------------------------------------+
++------------------------------+-------------------------------------+---------------------------------------+
+| Name                         | Python 2 name                       | Python 3 name                         |
++==============================+=====================================+=======================================+
+| ``builtins``                 | :mod:`py2:__builtin__`              | :mod:`py3:builtins`                   |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``configparser``             | :mod:`py2:ConfigParser`             | :mod:`py3:configparser`               |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``copyreg``                  | :mod:`py2:copy_reg`                 | :mod:`py3:copyreg`                    |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``cPickle``                  | :mod:`py2:cPickle`                  | :mod:`py3:pickle`                     |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``cStringIO``                | :func:`py2:cStringIO.StringIO`      | :class:`py3:io.StringIO`              |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``dbm_gnu``                  | :func:`py2:gdbm`                    | :class:`py3:dbm.gnu`                  |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``_dummy_thread``            | :mod:`py2:dummy_thread`             | :mod:`py3:_dummy_thread`              |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``email_mime_base``          | :mod:`py2:email.MIMEBase`           | :mod:`py3:email.mime.base`            |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``email_mime_image``         | :mod:`py2:email.MIMEImage`          | :mod:`py3:email.mime.image`           |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``email_mime_multipart``     | :mod:`py2:email.MIMEMultipart`      | :mod:`py3:email.mime.multipart`       |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``email_mime_nonmultipart``  | :mod:`py2:email.MIMENonMultipart`   | :mod:`py3:email.mime.nonmultipart`    |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``email_mime_text``          | :mod:`py2:email.MIMEText`           | :mod:`py3:email.mime.text`            |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``filter``                   | :func:`py2:itertools.ifilter`       | :func:`py3:filter`                    |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``filterfalse``              | :func:`py2:itertools.ifilterfalse`  | :func:`py3:itertools.filterfalse`     |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``getcwd``                   | :func:`py2:os.getcwdu`              | :func:`py3:os.getcwd`                 |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``getcwdb``                  | :func:`py2:os.getcwd`               | :func:`py3:os.getcwdb`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``getoutput``                | :func:`py2:commands.getoutput`      | :func:`py3:subprocess.getoutput`      |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``http_cookiejar``           | :mod:`py2:cookielib`                | :mod:`py3:http.cookiejar`             |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``http_cookies``             | :mod:`py2:Cookie`                   | :mod:`py3:http.cookies`               |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``html_entities``            | :mod:`py2:htmlentitydefs`           | :mod:`py3:html.entities`              |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``html_parser``              | :mod:`py2:HTMLParser`               | :mod:`py3:html.parser`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``http_client``              | :mod:`py2:httplib`                  | :mod:`py3:http.client`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``BaseHTTPServer``           | :mod:`py2:BaseHTTPServer`           | :mod:`py3:http.server`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``CGIHTTPServer``            | :mod:`py2:CGIHTTPServer`            | :mod:`py3:http.server`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``SimpleHTTPServer``         | :mod:`py2:SimpleHTTPServer`         | :mod:`py3:http.server`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``input``                    | :func:`py2:raw_input`               | :func:`py3:input`                     |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``intern``                   | :func:`py2:intern`                  | :func:`py3:sys.intern`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``map``                      | :func:`py2:itertools.imap`          | :func:`py3:map`                       |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``queue``                    | :mod:`py2:Queue`                    | :mod:`py3:queue`                      |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``range``                    | :func:`py2:xrange`                  | :func:`py3:range`                     |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``reduce``                   | :func:`py2:reduce`                  | :func:`py3:functools.reduce`          |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``reload_module``            | :func:`py2:reload`                  | :func:`py3:imp.reload`,               |
+|                              |                                     | :func:`py3:importlib.reload`          |
+|                              |                                     | on Python 3.4+                        |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``reprlib``                  | :mod:`py2:repr`                     | :mod:`py3:reprlib`                    |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``shlex_quote``              | :mod:`py2:pipes.quote`              | :mod:`py3:shlex.quote`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``socketserver``             | :mod:`py2:SocketServer`             | :mod:`py3:socketserver`               |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``_thread``                  | :mod:`py2:thread`                   | :mod:`py3:_thread`                    |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter``                  | :mod:`py2:Tkinter`                  | :mod:`py3:tkinter`                    |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_dialog``           | :mod:`py2:Dialog`                   | :mod:`py3:tkinter.dialog`             |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_filedialog``       | :mod:`py2:FileDialog`               | :mod:`py3:tkinter.FileDialog`         |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_scrolledtext``     | :mod:`py2:ScrolledText`             | :mod:`py3:tkinter.scrolledtext`       |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_simpledialog``     | :mod:`py2:SimpleDialog`             | :mod:`py3:tkinter.simpledialog`       |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_ttk``              | :mod:`py2:ttk`                      | :mod:`py3:tkinter.ttk`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_tix``              | :mod:`py2:Tix`                      | :mod:`py3:tkinter.tix`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_constants``        | :mod:`py2:Tkconstants`              | :mod:`py3:tkinter.constants`          |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_dnd``              | :mod:`py2:Tkdnd`                    | :mod:`py3:tkinter.dnd`                |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_colorchooser``     | :mod:`py2:tkColorChooser`           | :mod:`py3:tkinter.colorchooser`       |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_commondialog``     | :mod:`py2:tkCommonDialog`           | :mod:`py3:tkinter.commondialog`       |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_tkfiledialog``     | :mod:`py2:tkFileDialog`             | :mod:`py3:tkinter.filedialog`         |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_font``             | :mod:`py2:tkFont`                   | :mod:`py3:tkinter.font`               |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_messagebox``       | :mod:`py2:tkMessageBox`             | :mod:`py3:tkinter.messagebox`         |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``tkinter_tksimpledialog``   | :mod:`py2:tkSimpleDialog`           | :mod:`py3:tkinter.simpledialog`       |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``urllib.parse``             | See :mod:`six.moves.urllib.parse`   | :mod:`py3:urllib.parse`               |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``urllib.error``             | See :mod:`six.moves.urllib.error`   | :mod:`py3:urllib.error`               |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``urllib.request``           | See :mod:`six.moves.urllib.request` | :mod:`py3:urllib.request`             |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``urllib.response``          | See :mod:`six.moves.urllib.response`| :mod:`py3:urllib.response`            |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``urllib.robotparser``       | :mod:`py2:robotparser`              | :mod:`py3:urllib.robotparser`         |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``urllib_robotparser``       | :mod:`py2:robotparser`              | :mod:`py3:urllib.robotparser`         |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``UserDict``                 | :class:`py2:UserDict.UserDict`      | :class:`py3:collections.UserDict`     |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``UserList``                 | :class:`py2:UserList.UserList`      | :class:`py3:collections.UserList`     |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``UserString``               | :class:`py2:UserString.UserString`  | :class:`py3:collections.UserString`   |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``winreg``                   | :mod:`py2:_winreg`                  | :mod:`py3:winreg`                     |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``xmlrpc_client``            | :mod:`py2:xmlrpclib`                | :mod:`py3:xmlrpc.client`              |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``xmlrpc_server``            | :mod:`py2:SimpleXMLRPCServer`       | :mod:`py3:xmlrpc.server`              |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``xrange``                   | :func:`py2:xrange`                  | :func:`py3:range`                     |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``zip``                      | :func:`py2:itertools.izip`          | :func:`py3:zip`                       |
++------------------------------+-------------------------------------+---------------------------------------+
+| ``zip_longest``              | :func:`py2:itertools.izip_longest`  | :func:`py3:itertools.zip_longest`     |
++------------------------------+-------------------------------------+---------------------------------------+
 
 urllib parse
 <<<<<<<<<<<<
@@ -659,7 +721,8 @@ and :mod:`py2:urllib`:
 * :func:`py2:urllib.quote_plus`
 * :func:`py2:urllib.splittag`
 * :func:`py2:urllib.splituser`
-* :func:`py2:urllib.unquote`
+* :func:`py2:urllib.splitvalue`
+* :func:`py2:urllib.unquote` (also exposed as :func:`py3:urllib.parse.unquote_to_bytes`)
 * :func:`py2:urllib.unquote_plus`
 * :func:`py2:urllib.urlencode`
 
@@ -706,6 +769,8 @@ and :mod:`py2:urllib2`:
 * :func:`py2:urllib2.urlopen`
 * :func:`py2:urllib2.install_opener`
 * :func:`py2:urllib2.build_opener`
+* :func:`py2:urllib2.parse_http_list`
+* :func:`py2:urllib2.parse_keqv_list`
 * :class:`py2:urllib2.Request`
 * :class:`py2:urllib2.OpenerDirector`
 * :class:`py2:urllib2.HTTPDefaultErrorHandler`
diff --git a/testing/web-platform/tests/tools/third_party/six/setup.cfg b/testing/web-platform/tests/tools/third_party/six/setup.cfg
new file mode 100644
index 000000000000..e12068c573c6
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/six/setup.cfg
@@ -0,0 +1,21 @@
+[bdist_wheel]
+universal = 1
+
+[flake8]
+max-line-length = 100
+ignore = F821
+
+[tool:pytest]
+minversion = 2.2.0
+pep8ignore = 
+	documentation/*.py ALL
+	test_six.py ALL
+flakes-ignore = 
+	documentation/*.py ALL
+	test_six.py ALL
+	six.py UndefinedName
+
+[egg_info]
+tag_build = 
+tag_date = 0
+
diff --git a/testing/web-platform/tests/tools/third_party/six/setup.py b/testing/web-platform/tests/tools/third_party/six/setup.py
new file mode 100644
index 000000000000..ca44e100e427
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/six/setup.py
@@ -0,0 +1,56 @@
+# Copyright (c) 2010-2017 Benjamin Peterson
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+from __future__ import with_statement
+
+# Six is a dependency of setuptools, so using setuptools creates a
+# circular dependency when building a Python stack from source. We
+# therefore allow falling back to distutils to install six.
+try:
+    from setuptools import setup
+except ImportError:
+    from distutils.core import setup
+
+import six
+
+six_classifiers = [
+    "Programming Language :: Python :: 2",
+    "Programming Language :: Python :: 3",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Topic :: Software Development :: Libraries",
+    "Topic :: Utilities",
+]
+
+with open("README.rst", "r") as fp:
+    six_long_description = fp.read()
+
+setup(name="six",
+      version=six.__version__,
+      author="Benjamin Peterson",
+      author_email="benjamin@python.org",
+      url="http://pypi.python.org/pypi/six/",
+      tests_require=["pytest"],
+      py_modules=["six"],
+      description="Python 2 and 3 compatibility utilities",
+      long_description=six_long_description,
+      license="MIT",
+      classifiers=six_classifiers
+      )
diff --git a/testing/web-platform/tests/tools/third_party/six/six.egg-info/PKG-INFO b/testing/web-platform/tests/tools/third_party/six/six.egg-info/PKG-INFO
new file mode 100644
index 000000000000..cd5ff4bb8e4f
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/six/six.egg-info/PKG-INFO
@@ -0,0 +1,41 @@
+Metadata-Version: 1.1
+Name: six
+Version: 1.11.0
+Summary: Python 2 and 3 compatibility utilities
+Home-page: http://pypi.python.org/pypi/six/
+Author: Benjamin Peterson
+Author-email: benjamin@python.org
+License: MIT
+Description: .. image:: http://img.shields.io/pypi/v/six.svg
+           :target: https://pypi.python.org/pypi/six
+        
+        .. image:: https://travis-ci.org/benjaminp/six.svg?branch=master
+            :target: https://travis-ci.org/benjaminp/six
+        
+        .. image:: http://img.shields.io/badge/license-MIT-green.svg
+           :target: https://github.com/benjaminp/six/blob/master/LICENSE
+        
+        Six is a Python 2 and 3 compatibility library.  It provides utility functions
+        for smoothing over the differences between the Python versions with the goal of
+        writing Python code that is compatible on both Python versions.  See the
+        documentation for more information on what is provided.
+        
+        Six supports every Python version since 2.6.  It is contained in only one Python
+        file, so it can be easily copied into your project. (The copyright and license
+        notice must be retained.)
+        
+        Online documentation is at http://six.rtfd.org.
+        
+        Bugs can be reported to https://github.com/benjaminp/six.  The code can also
+        be found there.
+        
+        For questions about six or porting in general, email the python-porting mailing
+        list: https://mail.python.org/mailman/listinfo/python-porting
+        
+Platform: UNKNOWN
+Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 3
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Utilities
diff --git a/testing/web-platform/tests/tools/third_party/six/six.egg-info/SOURCES.txt b/testing/web-platform/tests/tools/third_party/six/six.egg-info/SOURCES.txt
new file mode 100644
index 000000000000..9a7f3dec6df3
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/six/six.egg-info/SOURCES.txt
@@ -0,0 +1,15 @@
+CHANGES
+LICENSE
+MANIFEST.in
+README.rst
+setup.cfg
+setup.py
+six.py
+test_six.py
+documentation/Makefile
+documentation/conf.py
+documentation/index.rst
+six.egg-info/PKG-INFO
+six.egg-info/SOURCES.txt
+six.egg-info/dependency_links.txt
+six.egg-info/top_level.txt
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/third_party/six/six.egg-info/dependency_links.txt b/testing/web-platform/tests/tools/third_party/six/six.egg-info/dependency_links.txt
new file mode 100644
index 000000000000..8b137891791f
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/six/six.egg-info/dependency_links.txt
@@ -0,0 +1 @@
+
diff --git a/testing/web-platform/tests/tools/html5lib/requirements.txt b/testing/web-platform/tests/tools/third_party/six/six.egg-info/top_level.txt
similarity index 100%
rename from testing/web-platform/tests/tools/html5lib/requirements.txt
rename to testing/web-platform/tests/tools/third_party/six/six.egg-info/top_level.txt
diff --git a/testing/web-platform/tests/tools/six/six.py b/testing/web-platform/tests/tools/third_party/six/six.py
similarity index 87%
rename from testing/web-platform/tests/tools/six/six.py
rename to testing/web-platform/tests/tools/third_party/six/six.py
index 686c20a15a6b..6bf4fd381046 100644
--- a/testing/web-platform/tests/tools/six/six.py
+++ b/testing/web-platform/tests/tools/third_party/six/six.py
@@ -1,6 +1,4 @@
-"""Utilities for writing code that runs on Python 2 and 3"""
-
-# Copyright (c) 2010-2014 Benjamin Peterson
+# Copyright (c) 2010-2017 Benjamin Peterson
 #
 # Permission is hereby granted, free of charge, to any person obtaining a copy
 # of this software and associated documentation files (the "Software"), to deal
@@ -20,6 +18,8 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 
+"""Utilities for writing code that runs on Python 2 and 3"""
+
 from __future__ import absolute_import
 
 import functools
@@ -29,12 +29,13 @@ import sys
 import types
 
 __author__ = "Benjamin Peterson <benjamin@python.org>"
-__version__ = "1.8.0"
+__version__ = "1.11.0"
 
 
 # Useful for very coarse version differentiation.
 PY2 = sys.version_info[0] == 2
 PY3 = sys.version_info[0] == 3
+PY34 = sys.version_info[0:2] >= (3, 4)
 
 if PY3:
     string_types = str,
@@ -57,6 +58,7 @@ else:
     else:
         # It's possible to have sizeof(long) != sizeof(Py_ssize_t).
         class X(object):
+
             def __len__(self):
                 return 1 << 31
         try:
@@ -88,7 +90,7 @@ class _LazyDescr(object):
 
     def __get__(self, obj, tp):
         result = self._resolve()
-        setattr(obj, self.name, result) # Invokes __set__.
+        setattr(obj, self.name, result)  # Invokes __set__.
         try:
             # This is a bit ugly, but it avoids running this again by
             # removing this descriptor.
@@ -160,12 +162,14 @@ class MovedAttribute(_LazyDescr):
 
 
 class _SixMetaPathImporter(object):
+
     """
     A meta path importer to import six.moves and its submodules.
 
     This class implements a PEP302 finder and loader. It should be compatible
     with Python 2.5 and all existing versions of Python3
     """
+
     def __init__(self, six_module_name):
         self.name = six_module_name
         self.known_modules = {}
@@ -223,6 +227,7 @@ _importer = _SixMetaPathImporter(__name__)
 
 
 class _MovedItems(_LazyModule):
+
     """Lazy loading of moved objects"""
     __path__ = []  # mark as package
 
@@ -234,8 +239,11 @@ _moved_attributes = [
     MovedAttribute("input", "__builtin__", "builtins", "raw_input", "input"),
     MovedAttribute("intern", "__builtin__", "sys"),
     MovedAttribute("map", "itertools", "builtins", "imap", "map"),
+    MovedAttribute("getcwd", "os", "os", "getcwdu", "getcwd"),
+    MovedAttribute("getcwdb", "os", "os", "getcwd", "getcwdb"),
+    MovedAttribute("getoutput", "commands", "subprocess"),
     MovedAttribute("range", "__builtin__", "builtins", "xrange", "range"),
-    MovedAttribute("reload_module", "__builtin__", "imp", "reload"),
+    MovedAttribute("reload_module", "__builtin__", "importlib" if PY34 else "imp", "reload"),
     MovedAttribute("reduce", "__builtin__", "functools"),
     MovedAttribute("shlex_quote", "pipes", "shlex", "quote"),
     MovedAttribute("StringIO", "StringIO", "io"),
@@ -245,7 +253,6 @@ _moved_attributes = [
     MovedAttribute("xrange", "__builtin__", "builtins", "xrange", "range"),
     MovedAttribute("zip", "itertools", "builtins", "izip", "zip"),
     MovedAttribute("zip_longest", "itertools", "itertools", "izip_longest", "zip_longest"),
-
     MovedModule("builtins", "__builtin__"),
     MovedModule("configparser", "ConfigParser"),
     MovedModule("copyreg", "copy_reg"),
@@ -256,10 +263,11 @@ _moved_attributes = [
     MovedModule("html_entities", "htmlentitydefs", "html.entities"),
     MovedModule("html_parser", "HTMLParser", "html.parser"),
     MovedModule("http_client", "httplib", "http.client"),
+    MovedModule("email_mime_base", "email.MIMEBase", "email.mime.base"),
+    MovedModule("email_mime_image", "email.MIMEImage", "email.mime.image"),
     MovedModule("email_mime_multipart", "email.MIMEMultipart", "email.mime.multipart"),
     MovedModule("email_mime_nonmultipart", "email.MIMENonMultipart", "email.mime.nonmultipart"),
     MovedModule("email_mime_text", "email.MIMEText", "email.mime.text"),
-    MovedModule("email_mime_base", "email.MIMEBase", "email.mime.base"),
     MovedModule("BaseHTTPServer", "BaseHTTPServer", "http.server"),
     MovedModule("CGIHTTPServer", "CGIHTTPServer", "http.server"),
     MovedModule("SimpleHTTPServer", "SimpleHTTPServer", "http.server"),
@@ -292,8 +300,13 @@ _moved_attributes = [
     MovedModule("urllib_robotparser", "robotparser", "urllib.robotparser"),
     MovedModule("xmlrpc_client", "xmlrpclib", "xmlrpc.client"),
     MovedModule("xmlrpc_server", "SimpleXMLRPCServer", "xmlrpc.server"),
-    MovedModule("winreg", "_winreg"),
 ]
+# Add windows specific modules.
+if sys.platform == "win32":
+    _moved_attributes += [
+        MovedModule("winreg", "_winreg"),
+    ]
+
 for attr in _moved_attributes:
     setattr(_MovedItems, attr.name, attr)
     if isinstance(attr, MovedModule):
@@ -307,6 +320,7 @@ _importer._add_module(moves, "moves")
 
 
 class Module_six_moves_urllib_parse(_LazyModule):
+
     """Lazy loading of moved objects in six.moves.urllib_parse"""
 
 
@@ -325,10 +339,12 @@ _urllib_parse_moved_attributes = [
     MovedAttribute("quote_plus", "urllib", "urllib.parse"),
     MovedAttribute("unquote", "urllib", "urllib.parse"),
     MovedAttribute("unquote_plus", "urllib", "urllib.parse"),
+    MovedAttribute("unquote_to_bytes", "urllib", "urllib.parse", "unquote", "unquote_to_bytes"),
     MovedAttribute("urlencode", "urllib", "urllib.parse"),
     MovedAttribute("splitquery", "urllib", "urllib.parse"),
     MovedAttribute("splittag", "urllib", "urllib.parse"),
     MovedAttribute("splituser", "urllib", "urllib.parse"),
+    MovedAttribute("splitvalue", "urllib", "urllib.parse"),
     MovedAttribute("uses_fragment", "urlparse", "urllib.parse"),
     MovedAttribute("uses_netloc", "urlparse", "urllib.parse"),
     MovedAttribute("uses_params", "urlparse", "urllib.parse"),
@@ -346,6 +362,7 @@ _importer._add_module(Module_six_moves_urllib_parse(__name__ + ".moves.urllib_pa
 
 
 class Module_six_moves_urllib_error(_LazyModule):
+
     """Lazy loading of moved objects in six.moves.urllib_error"""
 
 
@@ -365,6 +382,7 @@ _importer._add_module(Module_six_moves_urllib_error(__name__ + ".moves.urllib.er
 
 
 class Module_six_moves_urllib_request(_LazyModule):
+
     """Lazy loading of moved objects in six.moves.urllib_request"""
 
 
@@ -402,6 +420,8 @@ _urllib_request_moved_attributes = [
     MovedAttribute("URLopener", "urllib", "urllib.request"),
     MovedAttribute("FancyURLopener", "urllib", "urllib.request"),
     MovedAttribute("proxy_bypass", "urllib", "urllib.request"),
+    MovedAttribute("parse_http_list", "urllib2", "urllib.request"),
+    MovedAttribute("parse_keqv_list", "urllib2", "urllib.request"),
 ]
 for attr in _urllib_request_moved_attributes:
     setattr(Module_six_moves_urllib_request, attr.name, attr)
@@ -414,6 +434,7 @@ _importer._add_module(Module_six_moves_urllib_request(__name__ + ".moves.urllib.
 
 
 class Module_six_moves_urllib_response(_LazyModule):
+
     """Lazy loading of moved objects in six.moves.urllib_response"""
 
 
@@ -434,6 +455,7 @@ _importer._add_module(Module_six_moves_urllib_response(__name__ + ".moves.urllib
 
 
 class Module_six_moves_urllib_robotparser(_LazyModule):
+
     """Lazy loading of moved objects in six.moves.urllib_robotparser"""
 
 
@@ -451,6 +473,7 @@ _importer._add_module(Module_six_moves_urllib_robotparser(__name__ + ".moves.url
 
 
 class Module_six_moves_urllib(types.ModuleType):
+
     """Create a six.moves.urllib namespace that resembles the Python 3 namespace"""
     __path__ = []  # mark as package
     parse = _importer._get_module("moves.urllib_parse")
@@ -521,6 +544,9 @@ if PY3:
 
     create_bound_method = types.MethodType
 
+    def create_unbound_method(func, cls):
+        return func
+
     Iterator = object
 else:
     def get_unbound_function(unbound):
@@ -529,6 +555,9 @@ else:
     def create_bound_method(func, obj):
         return types.MethodType(func, obj, obj.__class__)
 
+    def create_unbound_method(func, cls):
+        return types.MethodType(func, None, cls)
+
     class Iterator(object):
 
         def next(self):
@@ -567,16 +596,16 @@ if PY3:
     viewitems = operator.methodcaller("items")
 else:
     def iterkeys(d, **kw):
-        return iter(d.iterkeys(**kw))
+        return d.iterkeys(**kw)
 
     def itervalues(d, **kw):
-        return iter(d.itervalues(**kw))
+        return d.itervalues(**kw)
 
     def iteritems(d, **kw):
-        return iter(d.iteritems(**kw))
+        return d.iteritems(**kw)
 
     def iterlists(d, **kw):
-        return iter(d.iterlists(**kw))
+        return d.iterlists(**kw)
 
     viewkeys = operator.methodcaller("viewkeys")
 
@@ -595,50 +624,76 @@ _add_doc(iterlists,
 if PY3:
     def b(s):
         return s.encode("latin-1")
+
     def u(s):
         return s
     unichr = chr
-    if sys.version_info[1] <= 1:
-        def int2byte(i):
-            return bytes((i,))
-    else:
-        # This is about 2x faster than the implementation above on 3.2+
-        int2byte = operator.methodcaller("to_bytes", 1, "big")
+    import struct
+    int2byte = struct.Struct(">B").pack
+    del struct
     byte2int = operator.itemgetter(0)
     indexbytes = operator.getitem
     iterbytes = iter
     import io
     StringIO = io.StringIO
     BytesIO = io.BytesIO
+    _assertCountEqual = "assertCountEqual"
+    if sys.version_info[1] <= 1:
+        _assertRaisesRegex = "assertRaisesRegexp"
+        _assertRegex = "assertRegexpMatches"
+    else:
+        _assertRaisesRegex = "assertRaisesRegex"
+        _assertRegex = "assertRegex"
 else:
     def b(s):
         return s
     # Workaround for standalone backslash
+
     def u(s):
         return unicode(s.replace(r'\\', r'\\\\'), "unicode_escape")
     unichr = unichr
     int2byte = chr
+
     def byte2int(bs):
         return ord(bs[0])
+
     def indexbytes(buf, i):
         return ord(buf[i])
     iterbytes = functools.partial(itertools.imap, ord)
     import StringIO
     StringIO = BytesIO = StringIO.StringIO
+    _assertCountEqual = "assertItemsEqual"
+    _assertRaisesRegex = "assertRaisesRegexp"
+    _assertRegex = "assertRegexpMatches"
 _add_doc(b, """Byte literal""")
 _add_doc(u, """Text literal""")
 
 
+def assertCountEqual(self, *args, **kwargs):
+    return getattr(self, _assertCountEqual)(*args, **kwargs)
+
+
+def assertRaisesRegex(self, *args, **kwargs):
+    return getattr(self, _assertRaisesRegex)(*args, **kwargs)
+
+
+def assertRegex(self, *args, **kwargs):
+    return getattr(self, _assertRegex)(*args, **kwargs)
+
+
 if PY3:
     exec_ = getattr(moves.builtins, "exec")
 
-
     def reraise(tp, value, tb=None):
-        if value is None:
-            value = tp()
-        if value.__traceback__ is not tb:
-            raise value.with_traceback(tb)
-        raise value
+        try:
+            if value is None:
+                value = tp()
+            if value.__traceback__ is not tb:
+                raise value.with_traceback(tb)
+            raise value
+        finally:
+            value = None
+            tb = None
 
 else:
     def exec_(_code_, _globs_=None, _locs_=None):
@@ -653,15 +708,29 @@ else:
             _locs_ = _globs_
         exec("""exec _code_ in _globs_, _locs_""")
 
-
     exec_("""def reraise(tp, value, tb=None):
-    raise tp, value, tb
+    try:
+        raise tp, value, tb
+    finally:
+        tb = None
 """)
 
 
-if sys.version_info > (3, 2):
+if sys.version_info[:2] == (3, 2):
     exec_("""def raise_from(value, from_value):
-    raise value from from_value
+    try:
+        if from_value is None:
+            raise value
+        raise value from from_value
+    finally:
+        value = None
+""")
+elif sys.version_info[:2] > (3, 2):
+    exec_("""def raise_from(value, from_value):
+    try:
+        raise value from from_value
+    finally:
+        value = None
 """)
 else:
     def raise_from(value, from_value):
@@ -675,13 +744,14 @@ if print_ is None:
         fp = kwargs.pop("file", sys.stdout)
         if fp is None:
             return
+
         def write(data):
             if not isinstance(data, basestring):
                 data = str(data)
             # If the file has an encoding, encode unicode with it.
             if (isinstance(fp, file) and
-                isinstance(data, unicode) and
-                fp.encoding is not None):
+                    isinstance(data, unicode) and
+                    fp.encoding is not None):
                 errors = getattr(fp, "errors", None)
                 if errors is None:
                     errors = "strict"
@@ -722,6 +792,15 @@ if print_ is None:
                 write(sep)
             write(arg)
         write(end)
+if sys.version_info[:2] < (3, 3):
+    _print = print_
+
+    def print_(*args, **kwargs):
+        fp = kwargs.get("file", sys.stdout)
+        flush = kwargs.pop("flush", False)
+        _print(*args, **kwargs)
+        if flush and fp is not None:
+            fp.flush()
 
 _add_doc(reraise, """Reraise an exception.""")
 
@@ -736,14 +815,20 @@ if sys.version_info[0:2] < (3, 4):
 else:
     wraps = functools.wraps
 
+
 def with_metaclass(meta, *bases):
     """Create a base class with a metaclass."""
     # This requires a bit of explanation: the basic idea is to make a dummy
     # metaclass for one level of class instantiation that replaces itself with
     # the actual metaclass.
-    class metaclass(meta):
+    class metaclass(type):
+
         def __new__(cls, name, this_bases, d):
             return meta(name, bases, d)
+
+        @classmethod
+        def __prepare__(cls, name, this_bases):
+            return meta.__prepare__(name, bases)
     return type.__new__(metaclass, 'temporary_class', (), {})
 
 
@@ -762,6 +847,25 @@ def add_metaclass(metaclass):
         return metaclass(cls.__name__, cls.__bases__, orig_vars)
     return wrapper
 
+
+def python_2_unicode_compatible(klass):
+    """
+    A decorator that defines __unicode__ and __str__ methods under Python 2.
+    Under Python 3 it does nothing.
+
+    To support Python 2 and 3 with a single code base, define a __str__ method
+    returning text and apply this decorator to the class.
+    """
+    if PY2:
+        if '__str__' not in klass.__dict__:
+            raise ValueError("@python_2_unicode_compatible cannot be applied "
+                             "to %s because it doesn't define __str__()." %
+                             klass.__name__)
+        klass.__unicode__ = klass.__str__
+        klass.__str__ = lambda self: self.__unicode__().encode('utf-8')
+    return klass
+
+
 # Complete the moves implementation.
 # This code is at the end of this module to speed up module loading.
 # Turn this module into a package.
@@ -779,7 +883,7 @@ if sys.meta_path:
         # the six meta path importer, since the other six instance will have
         # inserted an importer with different class.
         if (type(importer).__name__ == "_SixMetaPathImporter" and
-            importer.name == __name__):
+                importer.name == __name__):
             del sys.meta_path[i]
             break
     del i, importer
diff --git a/testing/web-platform/tests/tools/six/test_six.py b/testing/web-platform/tests/tools/third_party/six/test_six.py
similarity index 82%
rename from testing/web-platform/tests/tools/six/test_six.py
rename to testing/web-platform/tests/tools/third_party/six/test_six.py
index d5555e8ac3c2..43e7426dea12 100644
--- a/testing/web-platform/tests/tools/six/test_six.py
+++ b/testing/web-platform/tests/tools/third_party/six/test_six.py
@@ -1,6 +1,27 @@
+# Copyright (c) 2010-2017 Benjamin Peterson
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
 import operator
 import sys
 import types
+import unittest
 
 import py
 
@@ -211,6 +232,12 @@ def test_map():
     assert six.advance_iterator(map(lambda x: x + 1, range(2))) == 1
 
 
+def test_getoutput():
+    from six.moves import getoutput
+    output = getoutput('echo "foo"')
+    assert output == 'foo'
+
+
 def test_zip():
     from six.moves import zip
     assert six.advance_iterator(zip(range(2), range(2))) == (0, 0)
@@ -389,7 +416,7 @@ def test_dictionary_iterators(monkeypatch):
         monkeypatch.undo()
 
 
-@py.test.mark.skipif(sys.version_info[:2] < (2, 7),
+@py.test.mark.skipif("sys.version_info[:2] < (2, 7)",
                 reason="view methods on dictionaries only available on 2.7+")
 def test_dictionary_views():
     def stock_method_name(viewwhat):
@@ -455,6 +482,20 @@ def test_create_bound_method():
     assert b() is x
 
 
+def test_create_unbound_method():
+    class X(object):
+        pass
+
+    def f(self):
+        return self
+    u = six.create_unbound_method(f, X)
+    py.test.raises(TypeError, u)
+    if six.PY2:
+        assert isinstance(u, types.MethodType)
+    x = X()
+    assert f(x) is x
+
+
 if six.PY3:
 
     def test_b():
@@ -496,7 +537,7 @@ def test_unichr():
 
 def test_int2byte():
     assert six.int2byte(3) == six.b("\x03")
-    py.test.raises((OverflowError, ValueError), six.int2byte, 256)
+    py.test.raises(Exception, six.int2byte, 256)
 
 
 def test_byte2int():
@@ -635,6 +676,17 @@ def test_print_():
     out = six.StringIO()
     six.print_(None, file=out)
     assert out.getvalue() == "None\n"
+    class FlushableStringIO(six.StringIO):
+        def __init__(self):
+            six.StringIO.__init__(self)
+            self.flushed = False
+        def flush(self):
+            self.flushed = True
+    out = FlushableStringIO()
+    six.print_("Hello", file=out)
+    assert not out.flushed
+    six.print_("Hello", file=out, flush=True)
+    assert out.flushed
 
 
 @py.test.mark.skipif("sys.version_info[:2] >= (2, 6)")
@@ -682,6 +734,42 @@ def test_with_metaclass():
     assert issubclass(X, Base)
     assert issubclass(X, Base2)
     assert X.__mro__ == (X, Base, Base2, object)
+    class X(six.with_metaclass(Meta)):
+        pass
+    class MetaSub(Meta):
+        pass
+    class Y(six.with_metaclass(MetaSub, X)):
+        pass
+    assert type(Y) is MetaSub
+    assert Y.__mro__ == (Y, X, object)
+
+
+@py.test.mark.skipif("sys.version_info[:2] < (3, 0)")
+def test_with_metaclass_prepare():
+    """Test that with_metaclass causes Meta.__prepare__ to be called with the correct arguments."""
+
+    class MyDict(dict):
+        pass
+
+    class Meta(type):
+
+        @classmethod
+        def __prepare__(cls, name, bases):
+            namespace = MyDict(super().__prepare__(name, bases), cls=cls, bases=bases)
+            namespace['namespace'] = namespace
+            return namespace
+
+    class Base(object):
+        pass
+
+    bases = (Base,)
+
+    class X(six.with_metaclass(Meta, *bases)):
+        pass
+
+    assert getattr(X, 'cls', type) is Meta
+    assert getattr(X, 'bases', ()) == bases
+    assert isinstance(getattr(X, 'namespace', {}), MyDict)
 
 
 def test_wraps():
@@ -785,3 +873,62 @@ def test_add_metaclass():
         __slots__ = "__weakref__",
     MySlotsWeakref = six.add_metaclass(Meta)(MySlotsWeakref)
     assert type(MySlotsWeakref) is Meta
+
+
+@py.test.mark.skipif("sys.version_info[:2] < (2, 7) or sys.version_info[:2] in ((3, 0), (3, 1))")
+def test_assertCountEqual():
+    class TestAssertCountEqual(unittest.TestCase):
+        def test(self):
+            with self.assertRaises(AssertionError):
+                six.assertCountEqual(self, (1, 2), [3, 4, 5])
+
+            six.assertCountEqual(self, (1, 2), [2, 1])
+
+    TestAssertCountEqual('test').test()
+
+
+@py.test.mark.skipif("sys.version_info[:2] < (2, 7)")
+def test_assertRegex():
+    class TestAssertRegex(unittest.TestCase):
+        def test(self):
+            with self.assertRaises(AssertionError):
+                six.assertRegex(self, 'test', r'^a')
+
+            six.assertRegex(self, 'test', r'^t')
+
+    TestAssertRegex('test').test()
+
+
+@py.test.mark.skipif("sys.version_info[:2] < (2, 7)")
+def test_assertRaisesRegex():
+    class TestAssertRaisesRegex(unittest.TestCase):
+        def test(self):
+            with six.assertRaisesRegex(self, AssertionError, '^Foo'):
+                raise AssertionError('Foo')
+
+            with self.assertRaises(AssertionError):
+                with six.assertRaisesRegex(self, AssertionError, r'^Foo'):
+                    raise AssertionError('Bar')
+
+    TestAssertRaisesRegex('test').test()
+
+
+def test_python_2_unicode_compatible():
+    @six.python_2_unicode_compatible
+    class MyTest(object):
+        def __str__(self):
+            return six.u('hello')
+
+        def __bytes__(self):
+            return six.b('hello')
+
+    my_test = MyTest()
+
+    if six.PY2:
+        assert str(my_test) == six.b("hello")
+        assert unicode(my_test) == six.u("hello")
+    elif six.PY3:
+        assert bytes(my_test) == six.b("hello")
+        assert str(my_test) == six.u("hello")
+
+    assert getattr(six.moves.builtins, 'bytes', str)(my_test) == six.b("hello")
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/PKG-INFO b/testing/web-platform/tests/tools/third_party/webencodings/PKG-INFO
new file mode 100644
index 000000000000..2a827bbad923
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/PKG-INFO
@@ -0,0 +1,50 @@
+Metadata-Version: 1.1
+Name: webencodings
+Version: 0.5.1
+Summary: Character encoding aliases for legacy web content
+Home-page: https://github.com/SimonSapin/python-webencodings
+Author: Geoffrey Sneddon
+Author-email: me@gsnedders.com
+License: BSD
+Description: python-webencodings
+        ===================
+        
+        This is a Python implementation of the `WHATWG Encoding standard
+        <http://encoding.spec.whatwg.org/>`_.
+        
+        * Latest documentation: http://packages.python.org/webencodings/
+        * Source code and issue tracker:
+          https://github.com/gsnedders/python-webencodings
+        * PyPI releases: http://pypi.python.org/pypi/webencodings
+        * License: BSD
+        * Python 2.6+ and 3.3+
+        
+        In order to be compatible with legacy web content
+        when interpreting something like ``Content-Type: text/html; charset=latin1``,
+        tools need to use a particular set of aliases for encoding labels
+        as well as some overriding rules.
+        For example, ``US-ASCII`` and ``iso-8859-1`` on the web are actually
+        aliases for ``windows-1252``, and an UTF-8 or UTF-16 BOM takes precedence
+        over any other encoding declaration.
+        The Encoding standard defines all such details so that implementations do
+        not have to reverse-engineer each other.
+        
+        This module has encoding labels and BOM detection,
+        but the actual implementation for encoders and decoders is Python’s.
+        
+Platform: UNKNOWN
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 2.6
+Classifier: Programming Language :: Python :: 2.7
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Internet :: WWW/HTTP
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/README.rst b/testing/web-platform/tests/tools/third_party/webencodings/README.rst
new file mode 100644
index 000000000000..c7e0f0cc3ef7
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/README.rst
@@ -0,0 +1,25 @@
+python-webencodings
+===================
+
+This is a Python implementation of the `WHATWG Encoding standard
+<http://encoding.spec.whatwg.org/>`_.
+
+* Latest documentation: http://packages.python.org/webencodings/
+* Source code and issue tracker:
+  https://github.com/gsnedders/python-webencodings
+* PyPI releases: http://pypi.python.org/pypi/webencodings
+* License: BSD
+* Python 2.6+ and 3.3+
+
+In order to be compatible with legacy web content
+when interpreting something like ``Content-Type: text/html; charset=latin1``,
+tools need to use a particular set of aliases for encoding labels
+as well as some overriding rules.
+For example, ``US-ASCII`` and ``iso-8859-1`` on the web are actually
+aliases for ``windows-1252``, and an UTF-8 or UTF-16 BOM takes precedence
+over any other encoding declaration.
+The Encoding standard defines all such details so that implementations do
+not have to reverse-engineer each other.
+
+This module has encoding labels and BOM detection,
+but the actual implementation for encoders and decoders is Python’s.
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/setup.cfg b/testing/web-platform/tests/tools/third_party/webencodings/setup.cfg
new file mode 100644
index 000000000000..460b0b405759
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/setup.cfg
@@ -0,0 +1,14 @@
+[bdist_wheel]
+universal = 1
+
+[build_sphinx]
+source-dir = docs
+build-dir = docs/_build
+
+[upload_sphinx]
+upload-dir = docs/_build/html
+
+[egg_info]
+tag_build = 
+tag_date = 0
+
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/setup.py b/testing/web-platform/tests/tools/third_party/webencodings/setup.py
new file mode 100644
index 000000000000..cf341cfd4752
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/setup.py
@@ -0,0 +1,47 @@
+from setuptools import setup, find_packages
+import io
+from os import path
+import re
+
+
+VERSION = re.search("VERSION = '([^']+)'", io.open(
+    path.join(path.dirname(__file__), 'webencodings', '__init__.py'),
+    encoding='utf-8'
+).read().strip()).group(1)
+
+LONG_DESCRIPTION = io.open(
+    path.join(path.dirname(__file__), 'README.rst'),
+    encoding='utf-8'
+).read()
+
+
+setup(
+    name='webencodings',
+    version=VERSION,
+    url='https://github.com/SimonSapin/python-webencodings',
+    license='BSD',
+    author='Simon Sapin',
+    author_email='simon.sapin@exyr.org',
+    maintainer='Geoffrey Sneddon',
+    maintainer_email='me@gsnedders.com',
+    description='Character encoding aliases for legacy web content',
+    long_description=LONG_DESCRIPTION,
+    classifiers=[
+        'Development Status :: 4 - Beta',
+        'Intended Audience :: Developers',
+        'License :: OSI Approved :: BSD License',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 2',
+        'Programming Language :: Python :: 2.6',
+        'Programming Language :: Python :: 2.7',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.3',
+        'Programming Language :: Python :: 3.4',
+        'Programming Language :: Python :: 3.5',
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: Implementation :: CPython',
+        'Programming Language :: Python :: Implementation :: PyPy',
+        'Topic :: Internet :: WWW/HTTP',
+    ],
+    packages=find_packages(),
+)
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/PKG-INFO b/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/PKG-INFO
new file mode 100644
index 000000000000..2a827bbad923
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/PKG-INFO
@@ -0,0 +1,50 @@
+Metadata-Version: 1.1
+Name: webencodings
+Version: 0.5.1
+Summary: Character encoding aliases for legacy web content
+Home-page: https://github.com/SimonSapin/python-webencodings
+Author: Geoffrey Sneddon
+Author-email: me@gsnedders.com
+License: BSD
+Description: python-webencodings
+        ===================
+        
+        This is a Python implementation of the `WHATWG Encoding standard
+        <http://encoding.spec.whatwg.org/>`_.
+        
+        * Latest documentation: http://packages.python.org/webencodings/
+        * Source code and issue tracker:
+          https://github.com/gsnedders/python-webencodings
+        * PyPI releases: http://pypi.python.org/pypi/webencodings
+        * License: BSD
+        * Python 2.6+ and 3.3+
+        
+        In order to be compatible with legacy web content
+        when interpreting something like ``Content-Type: text/html; charset=latin1``,
+        tools need to use a particular set of aliases for encoding labels
+        as well as some overriding rules.
+        For example, ``US-ASCII`` and ``iso-8859-1`` on the web are actually
+        aliases for ``windows-1252``, and an UTF-8 or UTF-16 BOM takes precedence
+        over any other encoding declaration.
+        The Encoding standard defines all such details so that implementations do
+        not have to reverse-engineer each other.
+        
+        This module has encoding labels and BOM detection,
+        but the actual implementation for encoders and decoders is Python’s.
+        
+Platform: UNKNOWN
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 2
+Classifier: Programming Language :: Python :: 2.6
+Classifier: Programming Language :: Python :: 2.7
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Classifier: Topic :: Internet :: WWW/HTTP
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/SOURCES.txt b/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/SOURCES.txt
new file mode 100644
index 000000000000..785d33ef4e9c
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/SOURCES.txt
@@ -0,0 +1,12 @@
+README.rst
+setup.cfg
+setup.py
+webencodings/__init__.py
+webencodings/labels.py
+webencodings/mklabels.py
+webencodings/tests.py
+webencodings/x_user_defined.py
+webencodings.egg-info/PKG-INFO
+webencodings.egg-info/SOURCES.txt
+webencodings.egg-info/dependency_links.txt
+webencodings.egg-info/top_level.txt
\ No newline at end of file
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/dependency_links.txt b/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/dependency_links.txt
new file mode 100644
index 000000000000..8b137891791f
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/dependency_links.txt
@@ -0,0 +1 @@
+
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/top_level.txt b/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/top_level.txt
new file mode 100644
index 000000000000..be8fcb779f88
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings.egg-info/top_level.txt
@@ -0,0 +1 @@
+webencodings
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings/__init__.py b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/__init__.py
new file mode 100644
index 000000000000..d21d697c887b
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/__init__.py
@@ -0,0 +1,342 @@
+# coding: utf-8
+"""
+
+    webencodings
+    ~~~~~~~~~~~~
+
+    This is a Python implementation of the `WHATWG Encoding standard
+    <http://encoding.spec.whatwg.org/>`. See README for details.
+
+    :copyright: Copyright 2012 by Simon Sapin
+    :license: BSD, see LICENSE for details.
+
+"""
+
+from __future__ import unicode_literals
+
+import codecs
+
+from .labels import LABELS
+
+
+VERSION = '0.5.1'
+
+
+# Some names in Encoding are not valid Python aliases. Remap these.
+PYTHON_NAMES = {
+    'iso-8859-8-i': 'iso-8859-8',
+    'x-mac-cyrillic': 'mac-cyrillic',
+    'macintosh': 'mac-roman',
+    'windows-874': 'cp874'}
+
+CACHE = {}
+
+
+def ascii_lower(string):
+    r"""Transform (only) ASCII letters to lower case: A-Z is mapped to a-z.
+
+    :param string: An Unicode string.
+    :returns: A new Unicode string.
+
+    This is used for `ASCII case-insensitive
+    <http://encoding.spec.whatwg.org/#ascii-case-insensitive>`_
+    matching of encoding labels.
+    The same matching is also used, among other things,
+    for `CSS keywords <http://dev.w3.org/csswg/css-values/#keywords>`_.
+
+    This is different from the :meth:`~py:str.lower` method of Unicode strings
+    which also affect non-ASCII characters,
+    sometimes mapping them into the ASCII range:
+
+        >>> keyword = u'Bac\N{KELVIN SIGN}ground'
+        >>> assert keyword.lower() == u'background'
+        >>> assert ascii_lower(keyword) != keyword.lower()
+        >>> assert ascii_lower(keyword) == u'bac\N{KELVIN SIGN}ground'
+
+    """
+    # This turns out to be faster than unicode.translate()
+    return string.encode('utf8').lower().decode('utf8')
+
+
+def lookup(label):
+    """
+    Look for an encoding by its label.
+    This is the spec’s `get an encoding
+    <http://encoding.spec.whatwg.org/#concept-encoding-get>`_ algorithm.
+    Supported labels are listed there.
+
+    :param label: A string.
+    :returns:
+        An :class:`Encoding` object, or :obj:`None` for an unknown label.
+
+    """
+    # Only strip ASCII whitespace: U+0009, U+000A, U+000C, U+000D, and U+0020.
+    label = ascii_lower(label.strip('\t\n\f\r '))
+    name = LABELS.get(label)
+    if name is None:
+        return None
+    encoding = CACHE.get(name)
+    if encoding is None:
+        if name == 'x-user-defined':
+            from .x_user_defined import codec_info
+        else:
+            python_name = PYTHON_NAMES.get(name, name)
+            # Any python_name value that gets to here should be valid.
+            codec_info = codecs.lookup(python_name)
+        encoding = Encoding(name, codec_info)
+        CACHE[name] = encoding
+    return encoding
+
+
+def _get_encoding(encoding_or_label):
+    """
+    Accept either an encoding object or label.
+
+    :param encoding: An :class:`Encoding` object or a label string.
+    :returns: An :class:`Encoding` object.
+    :raises: :exc:`~exceptions.LookupError` for an unknown label.
+
+    """
+    if hasattr(encoding_or_label, 'codec_info'):
+        return encoding_or_label
+
+    encoding = lookup(encoding_or_label)
+    if encoding is None:
+        raise LookupError('Unknown encoding label: %r' % encoding_or_label)
+    return encoding
+
+
+class Encoding(object):
+    """Reresents a character encoding such as UTF-8,
+    that can be used for decoding or encoding.
+
+    .. attribute:: name
+
+        Canonical name of the encoding
+
+    .. attribute:: codec_info
+
+        The actual implementation of the encoding,
+        a stdlib :class:`~codecs.CodecInfo` object.
+        See :func:`codecs.register`.
+
+    """
+    def __init__(self, name, codec_info):
+        self.name = name
+        self.codec_info = codec_info
+
+    def __repr__(self):
+        return '<Encoding %s>' % self.name
+
+
+#: The UTF-8 encoding. Should be used for new content and formats.
+UTF8 = lookup('utf-8')
+
+_UTF16LE = lookup('utf-16le')
+_UTF16BE = lookup('utf-16be')
+
+
+def decode(input, fallback_encoding, errors='replace'):
+    """
+    Decode a single string.
+
+    :param input: A byte string
+    :param fallback_encoding:
+        An :class:`Encoding` object or a label string.
+        The encoding to use if :obj:`input` does note have a BOM.
+    :param errors: Type of error handling. See :func:`codecs.register`.
+    :raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
+    :return:
+        A ``(output, encoding)`` tuple of an Unicode string
+        and an :obj:`Encoding`.
+
+    """
+    # Fail early if `encoding` is an invalid label.
+    fallback_encoding = _get_encoding(fallback_encoding)
+    bom_encoding, input = _detect_bom(input)
+    encoding = bom_encoding or fallback_encoding
+    return encoding.codec_info.decode(input, errors)[0], encoding
+
+
+def _detect_bom(input):
+    """Return (bom_encoding, input), with any BOM removed from the input."""
+    if input.startswith(b'\xFF\xFE'):
+        return _UTF16LE, input[2:]
+    if input.startswith(b'\xFE\xFF'):
+        return _UTF16BE, input[2:]
+    if input.startswith(b'\xEF\xBB\xBF'):
+        return UTF8, input[3:]
+    return None, input
+
+
+def encode(input, encoding=UTF8, errors='strict'):
+    """
+    Encode a single string.
+
+    :param input: An Unicode string.
+    :param encoding: An :class:`Encoding` object or a label string.
+    :param errors: Type of error handling. See :func:`codecs.register`.
+    :raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
+    :return: A byte string.
+
+    """
+    return _get_encoding(encoding).codec_info.encode(input, errors)[0]
+
+
+def iter_decode(input, fallback_encoding, errors='replace'):
+    """
+    "Pull"-based decoder.
+
+    :param input:
+        An iterable of byte strings.
+
+        The input is first consumed just enough to determine the encoding
+        based on the precense of a BOM,
+        then consumed on demand when the return value is.
+    :param fallback_encoding:
+        An :class:`Encoding` object or a label string.
+        The encoding to use if :obj:`input` does note have a BOM.
+    :param errors: Type of error handling. See :func:`codecs.register`.
+    :raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
+    :returns:
+        An ``(output, encoding)`` tuple.
+        :obj:`output` is an iterable of Unicode strings,
+        :obj:`encoding` is the :obj:`Encoding` that is being used.
+
+    """
+
+    decoder = IncrementalDecoder(fallback_encoding, errors)
+    generator = _iter_decode_generator(input, decoder)
+    encoding = next(generator)
+    return generator, encoding
+
+
+def _iter_decode_generator(input, decoder):
+    """Return a generator that first yields the :obj:`Encoding`,
+    then yields output chukns as Unicode strings.
+
+    """
+    decode = decoder.decode
+    input = iter(input)
+    for chunck in input:
+        output = decode(chunck)
+        if output:
+            assert decoder.encoding is not None
+            yield decoder.encoding
+            yield output
+            break
+    else:
+        # Input exhausted without determining the encoding
+        output = decode(b'', final=True)
+        assert decoder.encoding is not None
+        yield decoder.encoding
+        if output:
+            yield output
+        return
+
+    for chunck in input:
+        output = decode(chunck)
+        if output:
+            yield output
+    output = decode(b'', final=True)
+    if output:
+        yield output
+
+
+def iter_encode(input, encoding=UTF8, errors='strict'):
+    """
+    “Pull”-based encoder.
+
+    :param input: An iterable of Unicode strings.
+    :param encoding: An :class:`Encoding` object or a label string.
+    :param errors: Type of error handling. See :func:`codecs.register`.
+    :raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
+    :returns: An iterable of byte strings.
+
+    """
+    # Fail early if `encoding` is an invalid label.
+    encode = IncrementalEncoder(encoding, errors).encode
+    return _iter_encode_generator(input, encode)
+
+
+def _iter_encode_generator(input, encode):
+    for chunck in input:
+        output = encode(chunck)
+        if output:
+            yield output
+    output = encode('', final=True)
+    if output:
+        yield output
+
+
+class IncrementalDecoder(object):
+    """
+    “Push”-based decoder.
+
+    :param fallback_encoding:
+        An :class:`Encoding` object or a label string.
+        The encoding to use if :obj:`input` does note have a BOM.
+    :param errors: Type of error handling. See :func:`codecs.register`.
+    :raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
+
+    """
+    def __init__(self, fallback_encoding, errors='replace'):
+        # Fail early if `encoding` is an invalid label.
+        self._fallback_encoding = _get_encoding(fallback_encoding)
+        self._errors = errors
+        self._buffer = b''
+        self._decoder = None
+        #: The actual :class:`Encoding` that is being used,
+        #: or :obj:`None` if that is not determined yet.
+        #: (Ie. if there is not enough input yet to determine
+        #: if there is a BOM.)
+        self.encoding = None  # Not known yet.
+
+    def decode(self, input, final=False):
+        """Decode one chunk of the input.
+
+        :param input: A byte string.
+        :param final:
+            Indicate that no more input is available.
+            Must be :obj:`True` if this is the last call.
+        :returns: An Unicode string.
+
+        """
+        decoder = self._decoder
+        if decoder is not None:
+            return decoder(input, final)
+
+        input = self._buffer + input
+        encoding, input = _detect_bom(input)
+        if encoding is None:
+            if len(input) < 3 and not final:  # Not enough data yet.
+                self._buffer = input
+                return ''
+            else:  # No BOM
+                encoding = self._fallback_encoding
+        decoder = encoding.codec_info.incrementaldecoder(self._errors).decode
+        self._decoder = decoder
+        self.encoding = encoding
+        return decoder(input, final)
+
+
+class IncrementalEncoder(object):
+    """
+    “Push”-based encoder.
+
+    :param encoding: An :class:`Encoding` object or a label string.
+    :param errors: Type of error handling. See :func:`codecs.register`.
+    :raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
+
+    .. method:: encode(input, final=False)
+
+        :param input: An Unicode string.
+        :param final:
+            Indicate that no more input is available.
+            Must be :obj:`True` if this is the last call.
+        :returns: A byte string.
+
+    """
+    def __init__(self, encoding=UTF8, errors='strict'):
+        encoding = _get_encoding(encoding)
+        self.encode = encoding.codec_info.incrementalencoder(errors).encode
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings/labels.py b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/labels.py
new file mode 100644
index 000000000000..29cbf91ef79b
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/labels.py
@@ -0,0 +1,231 @@
+"""
+
+    webencodings.labels
+    ~~~~~~~~~~~~~~~~~~~
+
+    Map encoding labels to their name.
+
+    :copyright: Copyright 2012 by Simon Sapin
+    :license: BSD, see LICENSE for details.
+
+"""
+
+# XXX Do not edit!
+# This file is automatically generated by mklabels.py
+
+LABELS = {
+    'unicode-1-1-utf-8':   'utf-8',
+    'utf-8':               'utf-8',
+    'utf8':                'utf-8',
+    '866':                 'ibm866',
+    'cp866':               'ibm866',
+    'csibm866':            'ibm866',
+    'ibm866':              'ibm866',
+    'csisolatin2':         'iso-8859-2',
+    'iso-8859-2':          'iso-8859-2',
+    'iso-ir-101':          'iso-8859-2',
+    'iso8859-2':           'iso-8859-2',
+    'iso88592':            'iso-8859-2',
+    'iso_8859-2':          'iso-8859-2',
+    'iso_8859-2:1987':     'iso-8859-2',
+    'l2':                  'iso-8859-2',
+    'latin2':              'iso-8859-2',
+    'csisolatin3':         'iso-8859-3',
+    'iso-8859-3':          'iso-8859-3',
+    'iso-ir-109':          'iso-8859-3',
+    'iso8859-3':           'iso-8859-3',
+    'iso88593':            'iso-8859-3',
+    'iso_8859-3':          'iso-8859-3',
+    'iso_8859-3:1988':     'iso-8859-3',
+    'l3':                  'iso-8859-3',
+    'latin3':              'iso-8859-3',
+    'csisolatin4':         'iso-8859-4',
+    'iso-8859-4':          'iso-8859-4',
+    'iso-ir-110':          'iso-8859-4',
+    'iso8859-4':           'iso-8859-4',
+    'iso88594':            'iso-8859-4',
+    'iso_8859-4':          'iso-8859-4',
+    'iso_8859-4:1988':     'iso-8859-4',
+    'l4':                  'iso-8859-4',
+    'latin4':              'iso-8859-4',
+    'csisolatincyrillic':  'iso-8859-5',
+    'cyrillic':            'iso-8859-5',
+    'iso-8859-5':          'iso-8859-5',
+    'iso-ir-144':          'iso-8859-5',
+    'iso8859-5':           'iso-8859-5',
+    'iso88595':            'iso-8859-5',
+    'iso_8859-5':          'iso-8859-5',
+    'iso_8859-5:1988':     'iso-8859-5',
+    'arabic':              'iso-8859-6',
+    'asmo-708':            'iso-8859-6',
+    'csiso88596e':         'iso-8859-6',
+    'csiso88596i':         'iso-8859-6',
+    'csisolatinarabic':    'iso-8859-6',
+    'ecma-114':            'iso-8859-6',
+    'iso-8859-6':          'iso-8859-6',
+    'iso-8859-6-e':        'iso-8859-6',
+    'iso-8859-6-i':        'iso-8859-6',
+    'iso-ir-127':          'iso-8859-6',
+    'iso8859-6':           'iso-8859-6',
+    'iso88596':            'iso-8859-6',
+    'iso_8859-6':          'iso-8859-6',
+    'iso_8859-6:1987':     'iso-8859-6',
+    'csisolatingreek':     'iso-8859-7',
+    'ecma-118':            'iso-8859-7',
+    'elot_928':            'iso-8859-7',
+    'greek':               'iso-8859-7',
+    'greek8':              'iso-8859-7',
+    'iso-8859-7':          'iso-8859-7',
+    'iso-ir-126':          'iso-8859-7',
+    'iso8859-7':           'iso-8859-7',
+    'iso88597':            'iso-8859-7',
+    'iso_8859-7':          'iso-8859-7',
+    'iso_8859-7:1987':     'iso-8859-7',
+    'sun_eu_greek':        'iso-8859-7',
+    'csiso88598e':         'iso-8859-8',
+    'csisolatinhebrew':    'iso-8859-8',
+    'hebrew':              'iso-8859-8',
+    'iso-8859-8':          'iso-8859-8',
+    'iso-8859-8-e':        'iso-8859-8',
+    'iso-ir-138':          'iso-8859-8',
+    'iso8859-8':           'iso-8859-8',
+    'iso88598':            'iso-8859-8',
+    'iso_8859-8':          'iso-8859-8',
+    'iso_8859-8:1988':     'iso-8859-8',
+    'visual':              'iso-8859-8',
+    'csiso88598i':         'iso-8859-8-i',
+    'iso-8859-8-i':        'iso-8859-8-i',
+    'logical':             'iso-8859-8-i',
+    'csisolatin6':         'iso-8859-10',
+    'iso-8859-10':         'iso-8859-10',
+    'iso-ir-157':          'iso-8859-10',
+    'iso8859-10':          'iso-8859-10',
+    'iso885910':           'iso-8859-10',
+    'l6':                  'iso-8859-10',
+    'latin6':              'iso-8859-10',
+    'iso-8859-13':         'iso-8859-13',
+    'iso8859-13':          'iso-8859-13',
+    'iso885913':           'iso-8859-13',
+    'iso-8859-14':         'iso-8859-14',
+    'iso8859-14':          'iso-8859-14',
+    'iso885914':           'iso-8859-14',
+    'csisolatin9':         'iso-8859-15',
+    'iso-8859-15':         'iso-8859-15',
+    'iso8859-15':          'iso-8859-15',
+    'iso885915':           'iso-8859-15',
+    'iso_8859-15':         'iso-8859-15',
+    'l9':                  'iso-8859-15',
+    'iso-8859-16':         'iso-8859-16',
+    'cskoi8r':             'koi8-r',
+    'koi':                 'koi8-r',
+    'koi8':                'koi8-r',
+    'koi8-r':              'koi8-r',
+    'koi8_r':              'koi8-r',
+    'koi8-u':              'koi8-u',
+    'csmacintosh':         'macintosh',
+    'mac':                 'macintosh',
+    'macintosh':           'macintosh',
+    'x-mac-roman':         'macintosh',
+    'dos-874':             'windows-874',
+    'iso-8859-11':         'windows-874',
+    'iso8859-11':          'windows-874',
+    'iso885911':           'windows-874',
+    'tis-620':             'windows-874',
+    'windows-874':         'windows-874',
+    'cp1250':              'windows-1250',
+    'windows-1250':        'windows-1250',
+    'x-cp1250':            'windows-1250',
+    'cp1251':              'windows-1251',
+    'windows-1251':        'windows-1251',
+    'x-cp1251':            'windows-1251',
+    'ansi_x3.4-1968':      'windows-1252',
+    'ascii':               'windows-1252',
+    'cp1252':              'windows-1252',
+    'cp819':               'windows-1252',
+    'csisolatin1':         'windows-1252',
+    'ibm819':              'windows-1252',
+    'iso-8859-1':          'windows-1252',
+    'iso-ir-100':          'windows-1252',
+    'iso8859-1':           'windows-1252',
+    'iso88591':            'windows-1252',
+    'iso_8859-1':          'windows-1252',
+    'iso_8859-1:1987':     'windows-1252',
+    'l1':                  'windows-1252',
+    'latin1':              'windows-1252',
+    'us-ascii':            'windows-1252',
+    'windows-1252':        'windows-1252',
+    'x-cp1252':            'windows-1252',
+    'cp1253':              'windows-1253',
+    'windows-1253':        'windows-1253',
+    'x-cp1253':            'windows-1253',
+    'cp1254':              'windows-1254',
+    'csisolatin5':         'windows-1254',
+    'iso-8859-9':          'windows-1254',
+    'iso-ir-148':          'windows-1254',
+    'iso8859-9':           'windows-1254',
+    'iso88599':            'windows-1254',
+    'iso_8859-9':          'windows-1254',
+    'iso_8859-9:1989':     'windows-1254',
+    'l5':                  'windows-1254',
+    'latin5':              'windows-1254',
+    'windows-1254':        'windows-1254',
+    'x-cp1254':            'windows-1254',
+    'cp1255':              'windows-1255',
+    'windows-1255':        'windows-1255',
+    'x-cp1255':            'windows-1255',
+    'cp1256':              'windows-1256',
+    'windows-1256':        'windows-1256',
+    'x-cp1256':            'windows-1256',
+    'cp1257':              'windows-1257',
+    'windows-1257':        'windows-1257',
+    'x-cp1257':            'windows-1257',
+    'cp1258':              'windows-1258',
+    'windows-1258':        'windows-1258',
+    'x-cp1258':            'windows-1258',
+    'x-mac-cyrillic':      'x-mac-cyrillic',
+    'x-mac-ukrainian':     'x-mac-cyrillic',
+    'chinese':             'gbk',
+    'csgb2312':            'gbk',
+    'csiso58gb231280':     'gbk',
+    'gb2312':              'gbk',
+    'gb_2312':             'gbk',
+    'gb_2312-80':          'gbk',
+    'gbk':                 'gbk',
+    'iso-ir-58':           'gbk',
+    'x-gbk':               'gbk',
+    'gb18030':             'gb18030',
+    'hz-gb-2312':          'hz-gb-2312',
+    'big5':                'big5',
+    'big5-hkscs':          'big5',
+    'cn-big5':             'big5',
+    'csbig5':              'big5',
+    'x-x-big5':            'big5',
+    'cseucpkdfmtjapanese': 'euc-jp',
+    'euc-jp':              'euc-jp',
+    'x-euc-jp':            'euc-jp',
+    'csiso2022jp':         'iso-2022-jp',
+    'iso-2022-jp':         'iso-2022-jp',
+    'csshiftjis':          'shift_jis',
+    'ms_kanji':            'shift_jis',
+    'shift-jis':           'shift_jis',
+    'shift_jis':           'shift_jis',
+    'sjis':                'shift_jis',
+    'windows-31j':         'shift_jis',
+    'x-sjis':              'shift_jis',
+    'cseuckr':             'euc-kr',
+    'csksc56011987':       'euc-kr',
+    'euc-kr':              'euc-kr',
+    'iso-ir-149':          'euc-kr',
+    'korean':              'euc-kr',
+    'ks_c_5601-1987':      'euc-kr',
+    'ks_c_5601-1989':      'euc-kr',
+    'ksc5601':             'euc-kr',
+    'ksc_5601':            'euc-kr',
+    'windows-949':         'euc-kr',
+    'csiso2022kr':         'iso-2022-kr',
+    'iso-2022-kr':         'iso-2022-kr',
+    'utf-16be':            'utf-16be',
+    'utf-16':              'utf-16le',
+    'utf-16le':            'utf-16le',
+    'x-user-defined':      'x-user-defined',
+}
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings/mklabels.py b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/mklabels.py
new file mode 100644
index 000000000000..295dc928ba71
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/mklabels.py
@@ -0,0 +1,59 @@
+"""
+
+    webencodings.mklabels
+    ~~~~~~~~~~~~~~~~~~~~~
+
+    Regenarate the webencodings.labels module.
+
+    :copyright: Copyright 2012 by Simon Sapin
+    :license: BSD, see LICENSE for details.
+
+"""
+
+import json
+try:
+    from urllib import urlopen
+except ImportError:
+    from urllib.request import urlopen
+
+
+def assert_lower(string):
+    assert string == string.lower()
+    return string
+
+
+def generate(url):
+    parts = ['''\
+"""
+
+    webencodings.labels
+    ~~~~~~~~~~~~~~~~~~~
+
+    Map encoding labels to their name.
+
+    :copyright: Copyright 2012 by Simon Sapin
+    :license: BSD, see LICENSE for details.
+
+"""
+
+# XXX Do not edit!
+# This file is automatically generated by mklabels.py
+
+LABELS = {
+''']
+    labels = [
+        (repr(assert_lower(label)).lstrip('u'),
+         repr(encoding['name']).lstrip('u'))
+        for category in json.loads(urlopen(url).read().decode('ascii'))
+        for encoding in category['encodings']
+        for label in encoding['labels']]
+    max_len = max(len(label) for label, name in labels)
+    parts.extend(
+        '    %s:%s %s,\n' % (label, ' ' * (max_len - len(label)), name)
+        for label, name in labels)
+    parts.append('}')
+    return ''.join(parts)
+
+
+if __name__ == '__main__':
+    print(generate('http://encoding.spec.whatwg.org/encodings.json'))
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings/tests.py b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/tests.py
new file mode 100644
index 000000000000..e12c10d03302
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/tests.py
@@ -0,0 +1,153 @@
+# coding: utf-8
+"""
+
+    webencodings.tests
+    ~~~~~~~~~~~~~~~~~~
+
+    A basic test suite for Encoding.
+
+    :copyright: Copyright 2012 by Simon Sapin
+    :license: BSD, see LICENSE for details.
+
+"""
+
+from __future__ import unicode_literals
+
+from . import (lookup, LABELS, decode, encode, iter_decode, iter_encode,
+               IncrementalDecoder, IncrementalEncoder, UTF8)
+
+
+def assert_raises(exception, function, *args, **kwargs):
+    try:
+        function(*args, **kwargs)
+    except exception:
+        return
+    else:  # pragma: no cover
+        raise AssertionError('Did not raise %s.' % exception)
+
+
+def test_labels():
+    assert lookup('utf-8').name == 'utf-8'
+    assert lookup('Utf-8').name == 'utf-8'
+    assert lookup('UTF-8').name == 'utf-8'
+    assert lookup('utf8').name == 'utf-8'
+    assert lookup('utf8').name == 'utf-8'
+    assert lookup('utf8 ').name == 'utf-8'
+    assert lookup(' \r\nutf8\t').name == 'utf-8'
+    assert lookup('u8') is None  # Python label.
+    assert lookup('utf-8 ') is None  # Non-ASCII white space.
+
+    assert lookup('US-ASCII').name == 'windows-1252'
+    assert lookup('iso-8859-1').name == 'windows-1252'
+    assert lookup('latin1').name == 'windows-1252'
+    assert lookup('LATIN1').name == 'windows-1252'
+    assert lookup('latin-1') is None
+    assert lookup('LATİN1') is None  # ASCII-only case insensitivity.
+
+
+def test_all_labels():
+    for label in LABELS:
+        assert decode(b'', label) == ('', lookup(label))
+        assert encode('', label) == b''
+        for repeat in [0, 1, 12]:
+            output, _ = iter_decode([b''] * repeat, label)
+            assert list(output) == []
+            assert list(iter_encode([''] * repeat, label)) == []
+        decoder = IncrementalDecoder(label)
+        assert decoder.decode(b'') == ''
+        assert decoder.decode(b'', final=True) == ''
+        encoder = IncrementalEncoder(label)
+        assert encoder.encode('') == b''
+        assert encoder.encode('', final=True) == b''
+    # All encoding names are valid labels too:
+    for name in set(LABELS.values()):
+        assert lookup(name).name == name
+
+
+def test_invalid_label():
+    assert_raises(LookupError, decode, b'\xEF\xBB\xBF\xc3\xa9', 'invalid')
+    assert_raises(LookupError, encode, 'é', 'invalid')
+    assert_raises(LookupError, iter_decode, [], 'invalid')
+    assert_raises(LookupError, iter_encode, [], 'invalid')
+    assert_raises(LookupError, IncrementalDecoder, 'invalid')
+    assert_raises(LookupError, IncrementalEncoder, 'invalid')
+
+
+def test_decode():
+    assert decode(b'\x80', 'latin1') == ('€', lookup('latin1'))
+    assert decode(b'\x80', lookup('latin1')) == ('€', lookup('latin1'))
+    assert decode(b'\xc3\xa9', 'utf8') == ('é', lookup('utf8'))
+    assert decode(b'\xc3\xa9', UTF8) == ('é', lookup('utf8'))
+    assert decode(b'\xc3\xa9', 'ascii') == ('é', lookup('ascii'))
+    assert decode(b'\xEF\xBB\xBF\xc3\xa9', 'ascii') == ('é', lookup('utf8'))  # UTF-8 with BOM
+
+    assert decode(b'\xFE\xFF\x00\xe9', 'ascii') == ('é', lookup('utf-16be'))  # UTF-16-BE with BOM
+    assert decode(b'\xFF\xFE\xe9\x00', 'ascii') == ('é', lookup('utf-16le'))  # UTF-16-LE with BOM
+    assert decode(b'\xFE\xFF\xe9\x00', 'ascii') == ('\ue900', lookup('utf-16be'))
+    assert decode(b'\xFF\xFE\x00\xe9', 'ascii') == ('\ue900', lookup('utf-16le'))
+
+    assert decode(b'\x00\xe9', 'UTF-16BE') == ('é', lookup('utf-16be'))
+    assert decode(b'\xe9\x00', 'UTF-16LE') == ('é', lookup('utf-16le'))
+    assert decode(b'\xe9\x00', 'UTF-16') == ('é', lookup('utf-16le'))
+
+    assert decode(b'\xe9\x00', 'UTF-16BE') == ('\ue900', lookup('utf-16be'))
+    assert decode(b'\x00\xe9', 'UTF-16LE') == ('\ue900', lookup('utf-16le'))
+    assert decode(b'\x00\xe9', 'UTF-16') == ('\ue900', lookup('utf-16le'))
+
+
+def test_encode():
+    assert encode('é', 'latin1') == b'\xe9'
+    assert encode('é', 'utf8') == b'\xc3\xa9'
+    assert encode('é', 'utf8') == b'\xc3\xa9'
+    assert encode('é', 'utf-16') == b'\xe9\x00'
+    assert encode('é', 'utf-16le') == b'\xe9\x00'
+    assert encode('é', 'utf-16be') == b'\x00\xe9'
+
+
+def test_iter_decode():
+    def iter_decode_to_string(input, fallback_encoding):
+        output, _encoding = iter_decode(input, fallback_encoding)
+        return ''.join(output)
+    assert iter_decode_to_string([], 'latin1') == ''
+    assert iter_decode_to_string([b''], 'latin1') == ''
+    assert iter_decode_to_string([b'\xe9'], 'latin1') == 'é'
+    assert iter_decode_to_string([b'hello'], 'latin1') == 'hello'
+    assert iter_decode_to_string([b'he', b'llo'], 'latin1') == 'hello'
+    assert iter_decode_to_string([b'hell', b'o'], 'latin1') == 'hello'
+    assert iter_decode_to_string([b'\xc3\xa9'], 'latin1') == 'é'
+    assert iter_decode_to_string([b'\xEF\xBB\xBF\xc3\xa9'], 'latin1') == 'é'
+    assert iter_decode_to_string([
+        b'\xEF\xBB\xBF', b'\xc3', b'\xa9'], 'latin1') == 'é'
+    assert iter_decode_to_string([
+        b'\xEF\xBB\xBF', b'a', b'\xc3'], 'latin1') == 'a\uFFFD'
+    assert iter_decode_to_string([
+        b'', b'\xEF', b'', b'', b'\xBB\xBF\xc3', b'\xa9'], 'latin1') == 'é'
+    assert iter_decode_to_string([b'\xEF\xBB\xBF'], 'latin1') == ''
+    assert iter_decode_to_string([b'\xEF\xBB'], 'latin1') == 'ï»'
+    assert iter_decode_to_string([b'\xFE\xFF\x00\xe9'], 'latin1') == 'é'
+    assert iter_decode_to_string([b'\xFF\xFE\xe9\x00'], 'latin1') == 'é'
+    assert iter_decode_to_string([
+        b'', b'\xFF', b'', b'', b'\xFE\xe9', b'\x00'], 'latin1') == 'é'
+    assert iter_decode_to_string([
+        b'', b'h\xe9', b'llo'], 'x-user-defined') == 'h\uF7E9llo'
+
+
+def test_iter_encode():
+    assert b''.join(iter_encode([], 'latin1')) == b''
+    assert b''.join(iter_encode([''], 'latin1')) == b''
+    assert b''.join(iter_encode(['é'], 'latin1')) == b'\xe9'
+    assert b''.join(iter_encode(['', 'é', '', ''], 'latin1')) == b'\xe9'
+    assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16')) == b'\xe9\x00'
+    assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16le')) == b'\xe9\x00'
+    assert b''.join(iter_encode(['', 'é', '', ''], 'utf-16be')) == b'\x00\xe9'
+    assert b''.join(iter_encode([
+        '', 'h\uF7E9', '', 'llo'], 'x-user-defined')) == b'h\xe9llo'
+
+
+def test_x_user_defined():
+    encoded = b'2,\x0c\x0b\x1aO\xd9#\xcb\x0f\xc9\xbbt\xcf\xa8\xca'
+    decoded = '2,\x0c\x0b\x1aO\uf7d9#\uf7cb\x0f\uf7c9\uf7bbt\uf7cf\uf7a8\uf7ca'
+    encoded = b'aa'
+    decoded = 'aa'
+    assert decode(encoded, 'x-user-defined') == (decoded, lookup('x-user-defined'))
+    assert encode(decoded, 'x-user-defined') == encoded
diff --git a/testing/web-platform/tests/tools/third_party/webencodings/webencodings/x_user_defined.py b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/x_user_defined.py
new file mode 100644
index 000000000000..d16e326024c0
--- /dev/null
+++ b/testing/web-platform/tests/tools/third_party/webencodings/webencodings/x_user_defined.py
@@ -0,0 +1,325 @@
+# coding: utf-8
+"""
+
+    webencodings.x_user_defined
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    An implementation of the x-user-defined encoding.
+
+    :copyright: Copyright 2012 by Simon Sapin
+    :license: BSD, see LICENSE for details.
+
+"""
+
+from __future__ import unicode_literals
+
+import codecs
+
+
+### Codec APIs
+
+class Codec(codecs.Codec):
+
+    def encode(self, input, errors='strict'):
+        return codecs.charmap_encode(input, errors, encoding_table)
+
+    def decode(self, input, errors='strict'):
+        return codecs.charmap_decode(input, errors, decoding_table)
+
+
+class IncrementalEncoder(codecs.IncrementalEncoder):
+    def encode(self, input, final=False):
+        return codecs.charmap_encode(input, self.errors, encoding_table)[0]
+
+
+class IncrementalDecoder(codecs.IncrementalDecoder):
+    def decode(self, input, final=False):
+        return codecs.charmap_decode(input, self.errors, decoding_table)[0]
+
+
+class StreamWriter(Codec, codecs.StreamWriter):
+    pass
+
+
+class StreamReader(Codec, codecs.StreamReader):
+    pass
+
+
+### encodings module API
+
+codec_info = codecs.CodecInfo(
+    name='x-user-defined',
+    encode=Codec().encode,
+    decode=Codec().decode,
+    incrementalencoder=IncrementalEncoder,
+    incrementaldecoder=IncrementalDecoder,
+    streamreader=StreamReader,
+    streamwriter=StreamWriter,
+)
+
+
+### Decoding Table
+
+# Python 3:
+# for c in range(256): print('    %r' % chr(c if c < 128 else c + 0xF700))
+decoding_table = (
+    '\x00'
+    '\x01'
+    '\x02'
+    '\x03'
+    '\x04'
+    '\x05'
+    '\x06'
+    '\x07'
+    '\x08'
+    '\t'
+    '\n'
+    '\x0b'
+    '\x0c'
+    '\r'
+    '\x0e'
+    '\x0f'
+    '\x10'
+    '\x11'
+    '\x12'
+    '\x13'
+    '\x14'
+    '\x15'
+    '\x16'
+    '\x17'
+    '\x18'
+    '\x19'
+    '\x1a'
+    '\x1b'
+    '\x1c'
+    '\x1d'
+    '\x1e'
+    '\x1f'
+    ' '
+    '!'
+    '"'
+    '#'
+    '$'
+    '%'
+    '&'
+    "'"
+    '('
+    ')'
+    '*'
+    '+'
+    ','
+    '-'
+    '.'
+    '/'
+    '0'
+    '1'
+    '2'
+    '3'
+    '4'
+    '5'
+    '6'
+    '7'
+    '8'
+    '9'
+    ':'
+    ';'
+    '<'
+    '='
+    '>'
+    '?'
+    '@'
+    'A'
+    'B'
+    'C'
+    'D'
+    'E'
+    'F'
+    'G'
+    'H'
+    'I'
+    'J'
+    'K'
+    'L'
+    'M'
+    'N'
+    'O'
+    'P'
+    'Q'
+    'R'
+    'S'
+    'T'
+    'U'
+    'V'
+    'W'
+    'X'
+    'Y'
+    'Z'
+    '['
+    '\\'
+    ']'
+    '^'
+    '_'
+    '`'
+    'a'
+    'b'
+    'c'
+    'd'
+    'e'
+    'f'
+    'g'
+    'h'
+    'i'
+    'j'
+    'k'
+    'l'
+    'm'
+    'n'
+    'o'
+    'p'
+    'q'
+    'r'
+    's'
+    't'
+    'u'
+    'v'
+    'w'
+    'x'
+    'y'
+    'z'
+    '{'
+    '|'
+    '}'
+    '~'
+    '\x7f'
+    '\uf780'
+    '\uf781'
+    '\uf782'
+    '\uf783'
+    '\uf784'
+    '\uf785'
+    '\uf786'
+    '\uf787'
+    '\uf788'
+    '\uf789'
+    '\uf78a'
+    '\uf78b'
+    '\uf78c'
+    '\uf78d'
+    '\uf78e'
+    '\uf78f'
+    '\uf790'
+    '\uf791'
+    '\uf792'
+    '\uf793'
+    '\uf794'
+    '\uf795'
+    '\uf796'
+    '\uf797'
+    '\uf798'
+    '\uf799'
+    '\uf79a'
+    '\uf79b'
+    '\uf79c'
+    '\uf79d'
+    '\uf79e'
+    '\uf79f'
+    '\uf7a0'
+    '\uf7a1'
+    '\uf7a2'
+    '\uf7a3'
+    '\uf7a4'
+    '\uf7a5'
+    '\uf7a6'
+    '\uf7a7'
+    '\uf7a8'
+    '\uf7a9'
+    '\uf7aa'
+    '\uf7ab'
+    '\uf7ac'
+    '\uf7ad'
+    '\uf7ae'
+    '\uf7af'
+    '\uf7b0'
+    '\uf7b1'
+    '\uf7b2'
+    '\uf7b3'
+    '\uf7b4'
+    '\uf7b5'
+    '\uf7b6'
+    '\uf7b7'
+    '\uf7b8'
+    '\uf7b9'
+    '\uf7ba'
+    '\uf7bb'
+    '\uf7bc'
+    '\uf7bd'
+    '\uf7be'
+    '\uf7bf'
+    '\uf7c0'
+    '\uf7c1'
+    '\uf7c2'
+    '\uf7c3'
+    '\uf7c4'
+    '\uf7c5'
+    '\uf7c6'
+    '\uf7c7'
+    '\uf7c8'
+    '\uf7c9'
+    '\uf7ca'
+    '\uf7cb'
+    '\uf7cc'
+    '\uf7cd'
+    '\uf7ce'
+    '\uf7cf'
+    '\uf7d0'
+    '\uf7d1'
+    '\uf7d2'
+    '\uf7d3'
+    '\uf7d4'
+    '\uf7d5'
+    '\uf7d6'
+    '\uf7d7'
+    '\uf7d8'
+    '\uf7d9'
+    '\uf7da'
+    '\uf7db'
+    '\uf7dc'
+    '\uf7dd'
+    '\uf7de'
+    '\uf7df'
+    '\uf7e0'
+    '\uf7e1'
+    '\uf7e2'
+    '\uf7e3'
+    '\uf7e4'
+    '\uf7e5'
+    '\uf7e6'
+    '\uf7e7'
+    '\uf7e8'
+    '\uf7e9'
+    '\uf7ea'
+    '\uf7eb'
+    '\uf7ec'
+    '\uf7ed'
+    '\uf7ee'
+    '\uf7ef'
+    '\uf7f0'
+    '\uf7f1'
+    '\uf7f2'
+    '\uf7f3'
+    '\uf7f4'
+    '\uf7f5'
+    '\uf7f6'
+    '\uf7f7'
+    '\uf7f8'
+    '\uf7f9'
+    '\uf7fa'
+    '\uf7fb'
+    '\uf7fc'
+    '\uf7fd'
+    '\uf7fe'
+    '\uf7ff'
+)
+
+### Encoding table
+encoding_table = codecs.charmap_build(decoding_table)