tools: Check in tools for shrinking ICU size, change default to small-icu

* Change configure default to "small-icu" (Intl on, English only)
* add "--without-intl" and "vcbuild without-intl" options, equivalent
to --with-intl=none
* update BUILDING.md with above changes
* Checks in tools that generate the deps/icu-small source directory
from ICU source
* Tools and process for updating ICU documented in tools/icu/README.md

Fixes: https://github.com/nodejs/node/issues/3476
PR-URL: https://github.com/nodejs/node/pull/6088
Reviewed-By: James M Snell <jasnell@gmail.com>

BUILDING.md

@@ -117,29 +117,14 @@ $ make
 
 ### `Intl` (ECMA-402) support:
 
-[Intl](https://github.com/nodejs/node/wiki/Intl) support is not
-enabled by default.
+[Intl](https://github.com/nodejs/node/wiki/Intl) support is
+enabled by default, with English data only.
 
+#### Default: `small-icu` (English only) support
 
-#### "small" (English only) support
-
-This option will build with "small" (English only) support, but
-the full `Intl` (ECMA-402) APIs.  With `--download=all` it will
-download the ICU library as needed.
-
-##### Unix / OS X:
-
-```text
-$ ./configure --with-intl=small-icu --download=all
-```
-
-##### Windows:
-
-```text
-> vcbuild small-icu download-all
-```
-
-The `small-icu` mode builds with English-only data. You can add full
+By default, only English data is included, but
+the full `Intl` (ECMA-402) APIs.  It does not need to download
+any dependencies to function. You can add full
 data at runtime.
 
 *Note:* more docs are on
@@ -148,7 +133,8 @@ data at runtime.
 #### Build with full ICU support (all locales supported by ICU):
 
 With the `--download=all`, this may download ICU if you don't have an
-ICU in `deps/icu`.
+ICU in `deps/icu`. (The embedded `small-icu` included in the default
+Node.js source does not include all locales.)
 
 ##### Unix / OS X:
 
@@ -164,19 +150,19 @@ $ ./configure --with-intl=full-icu --download=all
 
 #### Building without Intl support
 
-The `Intl` object will not be available. This is the default at
-present, so this option is not normally needed.
+The `Intl` object will not be available, nor some other APIs such as
+`String.normalize`.
 
 ##### Unix / OS X:
 
 ```text
-$ ./configure --with-intl=none
+$ ./configure --without-intl
 ```
 
 ##### Windows:
 
 ```text
-> vcbuild intl-none
+> vcbuild without-intl
 ```
 
 #### Use existing installed ICU (Unix / OS X only):

configure

@@ -303,20 +303,28 @@ parser.add_option('--with-etw',
 intl_optgroup.add_option('--with-intl',
     action='store',
     dest='with_intl',
-    default='none',
+    default='small-icu',
     choices=valid_intl_modes,
     help='Intl mode (valid choices: {0}) [default: %default]'.format(
         ', '.join(valid_intl_modes)))
 
+intl_optgroup.add_option('--without-intl',
+    action='store_const',
+    dest='with_intl',
+    const='none',
+    help='Disable Intl, same as --with-intl=none')
+
 intl_optgroup.add_option('--with-icu-path',
     action='store',
     dest='with_icu_path',
     help='Path to icu.gyp (ICU i18n, Chromium version only.)')
 
+icu_default_locales='root,en'
+
 intl_optgroup.add_option('--with-icu-locales',
     action='store',
     dest='with_icu_locales',
-    default='root,en',
+    default=icu_default_locales,
     help='Comma-separated list of locales for "small-icu". "root" is assumed. '
         '[default: %default]')
 
@@ -880,7 +888,7 @@ do_not_edit = '# Do not edit. Generated by the configure script.\n'
 
 def glob_to_var(dir_base, dir_sub, patch_dir):
   list = []
-  dir_all = os.path.join(dir_base, dir_sub)
+  dir_all = '%s/%s' % (dir_base, dir_sub)
   files = os.walk(dir_all)
   for ent in files:
     (path, dirs, files) = ent
@@ -968,6 +976,7 @@ def configure_intl(o):
     locs = set(options.with_icu_locales.split(','))
     locs.add('root')  # must have root
     o['variables']['icu_locales'] = string.join(locs,',')
+    # We will check a bit later if we can use the canned deps/icu-small
   elif with_intl == 'full-icu':
     # full ICU
     o['variables']['v8_enable_i18n_support'] = 1
@@ -994,15 +1003,42 @@ def configure_intl(o):
   # this is just the 'deps' dir. Used for unpacking.
   icu_parent_path = os.path.join(root_dir, 'deps')
 
-  # The full path to the ICU source directory.
-  icu_full_path = os.path.join(icu_parent_path, 'icu')
+  # The full path to the ICU source directory. Should not include './'.
+  icu_full_path = 'deps/icu'
 
   # icu-tmp is used to download and unpack the ICU tarball.
   icu_tmp_path = os.path.join(icu_parent_path, 'icu-tmp')
 
+  # canned ICU. see tools/icu/README.md to update.
+  canned_icu_dir = 'deps/icu-small'
+
+  # We can use 'deps/icu-small' - pre-canned ICU *iff*
+  # - with_intl == small-icu (the default!)
+  # - with_icu_locales == 'root,en' (the default!)
+  # - deps/icu-small exists!
+  # - with_icu_source is unset (i.e. no other ICU was specified)
+  # (Note that this is the *DEFAULT CASE*.)
+  #
+  # This is *roughly* equivalent to
+  # $ configure --with-intl=small-icu --with-icu-source=deps/icu-small
+  # .. Except that we avoid copying icu-small over to deps/icu.
+  # In this default case, deps/icu is ignored, although make clean will
+  # still harmlessly remove deps/icu.
+
+  # are we using default locales?
+  using_default_locales = ( options.with_icu_locales == icu_default_locales )
+
+  # make sure the canned ICU really exists
+  canned_icu_available = os.path.isdir(canned_icu_dir)
+
+  if (o['variables']['icu_small'] == b(True)) and using_default_locales and (not with_icu_source) and canned_icu_available:
+    # OK- we can use the canned ICU.
+    icu_config['variables']['icu_small_canned'] = 1
+    icu_full_path = canned_icu_dir
+
   # --with-icu-source processing
-  # first, check that they didn't pass --with-icu-source=deps/icu
-  if with_icu_source and os.path.abspath(icu_full_path) == os.path.abspath(with_icu_source):
+  # now, check that they didn't pass --with-icu-source=deps/icu
+  elif with_icu_source and os.path.abspath(icu_full_path) == os.path.abspath(with_icu_source):
     print 'Ignoring redundant --with-icu-source=%s' % (with_icu_source)
     with_icu_source = None
   # if with_icu_source is still set, try to use it.
@@ -1043,7 +1079,7 @@ def configure_intl(o):
 
   # ICU mode. (icu-generic.gyp)
   o['variables']['icu_gyp_path'] = 'tools/icu/icu-generic.gyp'
-  # ICU source dir relative to root
+  # ICU source dir relative to tools/icu (for .gyp file)
   o['variables']['icu_path'] = icu_full_path
   if not os.path.isdir(icu_full_path):
     print '* ECMA-402 (Intl) support didn\'t find ICU in %s..' % (icu_full_path)
@@ -1083,14 +1119,14 @@ def configure_intl(o):
                                'source/data/in',
                                icu_data_file_l)
   # relative to dep..
-  icu_data_in = os.path.join('../../deps/icu/source/data/in', icu_data_file_l)
+  icu_data_in = os.path.join('..','..', icu_full_path, 'source/data/in', icu_data_file_l)
   if not os.path.isfile(icu_data_path) and icu_endianness != 'l':
     # use host endianness
     icu_data_path = os.path.join(icu_full_path,
                                  'source/data/in',
                                  icu_data_file)
     # relative to dep..
-    icu_data_in = os.path.join('icu/source/data/in',
+    icu_data_in = os.path.join('..', icu_full_path, 'source/data/in',
                                icu_data_file)
   # this is the input '.dat' file to use .. icudt*.dat
   # may be little-endian if from a icu-project.org tarball
@@ -1117,7 +1153,7 @@ def configure_intl(o):
   # with a list of the src files to use
   for i in icu_src:
     var  = 'icu_src_%s' % i
-    path = '../../deps/icu/source/%s' % icu_src[i]
+    path = '../../%s/source/%s' % (icu_full_path, icu_src[i])
     icu_config['variables'][var] = glob_to_var('tools/icu', path, 'patches/%s/source/%s' % (icu_ver_major, icu_src[i]) )
   # write updated icu_config.gypi with a bunch of paths
   write(icu_config_name, do_not_edit +

tools/icu/README.md

@@ -1,6 +1,84 @@
 Notes about the icu directory.
 ===
 
+How to upgrade ICU
+---
+
+- Make sure your node workspace is clean (clean `git status`) should be sufficient.
+- Configure Node with the specific [ICU version](http://icu-project.org/download) you want to upgrade to, for example:
+
+```
+./configure \
+    --with-intl=small-icu \
+    --with-icu-source=http://download.icu-project.org/files/icu4c/56.1/icu4c-56_1-src.zip
+make
+```
+
+(the equivalent `vcbuild.bat` commands should work also.)
+
+- (note- may need to make changes in `icu-generic.gyp` or `tools/icu/patches` for
+version specific stuff)
+
+- Verify the node build works
+
+```
+make test-ci
+```
+
+Also running
+```js
+ new Intl.DateTimeFormat('es',{month:'long'}).format(new Date(9E8));
+```
+
+…Should return `January` not `enero`.
+(TODO here: improve [testing](https://github.com/nodejs/Intl/issues/16))
+
+
+- Now, copy `deps/icu` over to `deps/icu-small`
+
+```
+python tools/icu/shrink-icu-src.py
+```
+
+- Now, do a clean rebuild of node to test:
+
+(TODO: fix this when these options become default)
+
+```
+./configure --with-intl=small-icu --with-icu-source=deps/icu-small
+make
+```
+
+- Test this newly default-generated Node.js
+```js
+process.versions.icu;
+new Intl.DateTimeFormat('es',{month:'long'}).format(new Date(9E8));
+```
+
+(should return your updated ICU version number, and also `January` again.)
+
+- You are ready to check in the updated `deps/small-icu`.
+This is a big commit, so make this a separate commit from other changes.
+
+- Now, fix the default URL for the `full-icu` build in `/configure`, in
+the `configure_intl()` function. It should match the ICU URL used in the
+first step.  When this is done, the following should build with full ICU.
+
+```
+# clean up
+rm -rf out deps/icu deps/icu4c*
+./configure --with-intl=full-icu --download=all
+make
+make test-ci
+```
+
+- commit the change to `configure`.
+
+-----
+
+Notes about these tools
+---
+
 The files in this directory were written for the node.js effort. It's
 the intent of their author (Steven R. Loomis / srl295) to merge them
 upstream into ICU, pending much discussion within the ICU-PMC.

tools/icu/icu-generic.gyp

@@ -8,8 +8,8 @@
 {
   'variables': {
     'icu_src_derb': [
-      '../../deps/icu/source/tools/genrb/derb.c',
-      '../../deps/icu/source/tools/genrb/derb.cpp'
+      '<(icu_path)/source/tools/genrb/derb.c',
+      '<(icu_path)/source/tools/genrb/derb.cpp'
     ],
   },
   'includes': [ '../../icu_config.gypi' ],
@@ -121,49 +121,82 @@
           'sources': [
             '<@(icu_src_i18n)'
           ],
+          ## if your compiler can dead-strip, these exclusions will
+          ## make ZERO difference to binary size.
+          ## Made ICU-specific for future-proofing.
           'conditions': [
             [ 'icu_ver_major == 55', { 'sources!': [
-              ## Strip out the following for ICU 55 only.
-              ## add more conditions in the future?
-              ## if your compiler can dead-strip, this will
-              ## make ZERO difference to binary size.
-              ## Made ICU-specific for future-proofing.
-
               # alphabetic index
-              '../../deps/icu/source/i18n/alphaindex.cpp',
+              '<(icu_path)/source/i18n/alphaindex.cpp',
               # BOCSU
               # misc
-              '../../deps/icu/source/i18n/regexcmp.cpp',
-              '../../deps/icu/source/i18n/regexcmp.h',
-              '../../deps/icu/source/i18n/regexcst.h',
-              '../../deps/icu/source/i18n/regeximp.cpp',
-              '../../deps/icu/source/i18n/regeximp.h',
-              '../../deps/icu/source/i18n/regexst.cpp',
-              '../../deps/icu/source/i18n/regexst.h',
-              '../../deps/icu/source/i18n/regextxt.cpp',
-              '../../deps/icu/source/i18n/regextxt.h',
-              '../../deps/icu/source/i18n/region.cpp',
-              '../../deps/icu/source/i18n/region_impl.h',
-              '../../deps/icu/source/i18n/reldatefmt.cpp',
-              '../../deps/icu/source/i18n/reldatefmt.h'
-              '../../deps/icu/source/i18n/scientificformathelper.cpp',
-              '../../deps/icu/source/i18n/tmunit.cpp',
-              '../../deps/icu/source/i18n/tmutamt.cpp',
-              '../../deps/icu/source/i18n/tmutfmt.cpp',
-              '../../deps/icu/source/i18n/uregex.cpp',
-              '../../deps/icu/source/i18n/uregexc.cpp',
-              '../../deps/icu/source/i18n/uregion.cpp',
-              '../../deps/icu/source/i18n/uspoof.cpp',
-              '../../deps/icu/source/i18n/uspoof_build.cpp',
-              '../../deps/icu/source/i18n/uspoof_conf.cpp',
-              '../../deps/icu/source/i18n/uspoof_conf.h',
-              '../../deps/icu/source/i18n/uspoof_impl.cpp',
-              '../../deps/icu/source/i18n/uspoof_impl.h',
-              '../../deps/icu/source/i18n/uspoof_wsconf.cpp',
-              '../../deps/icu/source/i18n/uspoof_wsconf.h',
-            ]}]],
+              '<(icu_path)/source/i18n/regexcmp.cpp',
+              '<(icu_path)/source/i18n/regexcmp.h',
+              '<(icu_path)/source/i18n/regexcst.h',
+              '<(icu_path)/source/i18n/regeximp.cpp',
+              '<(icu_path)/source/i18n/regeximp.h',
+              '<(icu_path)/source/i18n/regexst.cpp',
+              '<(icu_path)/source/i18n/regexst.h',
+              '<(icu_path)/source/i18n/regextxt.cpp',
+              '<(icu_path)/source/i18n/regextxt.h',
+              '<(icu_path)/source/i18n/region.cpp',
+              '<(icu_path)/source/i18n/region_impl.h',
+              '<(icu_path)/source/i18n/reldatefmt.cpp',
+              '<(icu_path)/source/i18n/reldatefmt.h'
+              '<(icu_path)/source/i18n/scientificformathelper.cpp',
+              '<(icu_path)/source/i18n/tmunit.cpp',
+              '<(icu_path)/source/i18n/tmutamt.cpp',
+              '<(icu_path)/source/i18n/tmutfmt.cpp',
+              '<(icu_path)/source/i18n/uregex.cpp',
+              '<(icu_path)/source/i18n/uregexc.cpp',
+              '<(icu_path)/source/i18n/uregion.cpp',
+              '<(icu_path)/source/i18n/uspoof.cpp',
+              '<(icu_path)/source/i18n/uspoof_build.cpp',
+              '<(icu_path)/source/i18n/uspoof_conf.cpp',
+              '<(icu_path)/source/i18n/uspoof_conf.h',
+              '<(icu_path)/source/i18n/uspoof_impl.cpp',
+              '<(icu_path)/source/i18n/uspoof_impl.h',
+              '<(icu_path)/source/i18n/uspoof_wsconf.cpp',
+              '<(icu_path)/source/i18n/uspoof_wsconf.h',
+            ]}],
+            [ 'icu_ver_major == 57', { 'sources!': [
+
+              # alphabetic index
+              '<(icu_path)/source/i18n/alphaindex.cpp',
+              # BOCSU
+              # misc
+              '<(icu_path)/source/i18n/regexcmp.cpp',
+              '<(icu_path)/source/i18n/regexcmp.h',
+              '<(icu_path)/source/i18n/regexcst.h',
+              '<(icu_path)/source/i18n/regeximp.cpp',
+              '<(icu_path)/source/i18n/regeximp.h',
+              '<(icu_path)/source/i18n/regexst.cpp',
+              '<(icu_path)/source/i18n/regexst.h',
+              '<(icu_path)/source/i18n/regextxt.cpp',
+              '<(icu_path)/source/i18n/regextxt.h',
+              '<(icu_path)/source/i18n/region.cpp',
+              '<(icu_path)/source/i18n/region_impl.h',
+              '<(icu_path)/source/i18n/reldatefmt.cpp',
+              '<(icu_path)/source/i18n/reldatefmt.h'
+              '<(icu_path)/source/i18n/scientificformathelper.cpp',
+              '<(icu_path)/source/i18n/tmunit.cpp',
+              '<(icu_path)/source/i18n/tmutamt.cpp',
+              '<(icu_path)/source/i18n/tmutfmt.cpp',
+              '<(icu_path)/source/i18n/uregex.cpp',
+              '<(icu_path)/source/i18n/uregexc.cpp',
+              '<(icu_path)/source/i18n/uregion.cpp',
+              '<(icu_path)/source/i18n/uspoof.cpp',
+              '<(icu_path)/source/i18n/uspoof_build.cpp',
+              '<(icu_path)/source/i18n/uspoof_conf.cpp',
+              '<(icu_path)/source/i18n/uspoof_conf.h',
+              '<(icu_path)/source/i18n/uspoof_impl.cpp',
+              '<(icu_path)/source/i18n/uspoof_impl.h',
+              '<(icu_path)/source/i18n/uspoof_wsconf.cpp',
+              '<(icu_path)/source/i18n/uspoof_wsconf.h',
+            ]}],
+            ],
           'include_dirs': [
-            '../../deps/icu/source/i18n',
+            '<(icu_path)/source/i18n',
           ],
           'defines': [
             'U_I18N_IMPLEMENTATION=1',
@@ -171,7 +204,7 @@
           'dependencies': [ 'icuucx', 'icu_implementation', 'icu_uconfig', 'icu_uconfig_target' ],
           'direct_dependent_settings': {
             'include_dirs': [
-              '../../deps/icu/source/i18n',
+              '<(icu_path)/source/i18n',
             ],
           },
           'export_dependent_settings': [ 'icuucx', 'icu_uconfig_target' ],
@@ -253,7 +286,7 @@
               'sources': [ '<(SHARED_INTERMEDIATE_DIR)/icudt<(icu_ver_major)_dat.c' ],
               'dependencies': [ 'genccode#host', 'icupkg#host', 'icu_implementation#host', 'icu_uconfig' ],
               'include_dirs': [
-                '../../deps/icu/source/common',
+                '<(icu_path)/source/common',
               ],
               'actions': [
                 {
@@ -333,7 +366,7 @@
               'sources': [ '<(SHARED_INTERMEDIATE_DIR)/icusmdt<(icu_ver_major)_dat.c' ],
               # for umachine.h
               'include_dirs': [
-                '../../deps/icu/source/common',
+                '<(icu_path)/source/common',
               ],
             }]], # end icu_small == true
         }]], # end OS != win
@@ -349,7 +382,7 @@
         '<@(icu_src_stubdata)'
       ],
       'include_dirs': [
-        '../../deps/icu/source/common',
+        '<(icu_path)/source/common',
       ],
     },
     # this target is for v8 consumption.
@@ -379,34 +412,51 @@
       'sources': [
         '<@(icu_src_common)',
       ],
-      'conditions': [
-        [ 'icu_ver_major == 55', { 'sources!': [
-          ## Strip out the following for ICU 55 only.
-          ## add more conditions in the future?
           ## if your compiler can dead-strip, this will
           ## make ZERO difference to binary size.
           ## Made ICU-specific for future-proofing.
+      'conditions': [
+        [ 'icu_ver_major == 55', { 'sources!': [
 
           # bidi- not needed (yet!)
-          '../../deps/icu/source/common/ubidi.c',
-          '../../deps/icu/source/common/ubidiimp.h',
-          '../../deps/icu/source/common/ubidiln.c',
-          '../../deps/icu/source/common/ubidiwrt.c',
-          #'../../deps/icu/source/common/ubidi_props.c',
-          #'../../deps/icu/source/common/ubidi_props.h',
-          #'../../deps/icu/source/common/ubidi_props_data.h',
+          '<(icu_path)/source/common/ubidi.c',
+          '<(icu_path)/source/common/ubidiimp.h',
+          '<(icu_path)/source/common/ubidiln.c',
+          '<(icu_path)/source/common/ubidiwrt.c',
+          #'<(icu_path)/source/common/ubidi_props.c',
+          #'<(icu_path)/source/common/ubidi_props.h',
+          #'<(icu_path)/source/common/ubidi_props_data.h',
           # and the callers
-          '../../deps/icu/source/common/ushape.cpp',
-          '../../deps/icu/source/common/usprep.cpp',
-          '../../deps/icu/source/common/uts46.cpp',
-          '../../deps/icu/source/common/uidna.cpp',
+          '<(icu_path)/source/common/ushape.cpp',
+          '<(icu_path)/source/common/usprep.cpp',
+          '<(icu_path)/source/common/uts46.cpp',
+          '<(icu_path)/source/common/uidna.cpp',
+        ]}],
+        [ 'icu_ver_major == 57', { 'sources!': [
+          # work around http://bugs.icu-project.org/trac/ticket/12451
+          # (benign afterwards)
+          '<(icu_path)/source/common/cstr.cpp',
+
+          # bidi- not needed (yet!)
+          '<(icu_path)/source/common/ubidi.c',
+          '<(icu_path)/source/common/ubidiimp.h',
+          '<(icu_path)/source/common/ubidiln.c',
+          '<(icu_path)/source/common/ubidiwrt.c',
+          #'<(icu_path)/source/common/ubidi_props.c',
+          #'<(icu_path)/source/common/ubidi_props.h',
+          #'<(icu_path)/source/common/ubidi_props_data.h',
+          # and the callers
+          '<(icu_path)/source/common/ushape.cpp',
+          '<(icu_path)/source/common/usprep.cpp',
+          '<(icu_path)/source/common/uts46.cpp',
+          '<(icu_path)/source/common/uidna.cpp',
         ]}],
         [ 'OS == "solaris"', { 'defines': [
           '_XOPEN_SOURCE_EXTENDED=0',
         ]}],
       ],
       'include_dirs': [
-        '../../deps/icu/source/common',
+        '<(icu_path)/source/common',
       ],
       'defines': [
         'U_COMMON_IMPLEMENTATION=1',
@@ -415,7 +465,7 @@
       'export_dependent_settings': [ 'icu_uconfig', 'icu_uconfig_target' ],
       'direct_dependent_settings': {
         'include_dirs': [
-          '../../deps/icu/source/common',
+          '<(icu_path)/source/common',
         ],
         'conditions': [
           [ 'OS=="win"', {
@@ -426,7 +476,7 @@
         ],
       },
     },
-    # tools library
+    # tools library. This builds all of ICU together.
     {
       'target_name': 'icutools',
       'type': '<(library)',
@@ -440,16 +490,16 @@
         '<@(icu_src_stubdata)',
       ],
       'sources!': [
-        '../../deps/icu/source/tools/toolutil/udbgutil.cpp',
-        '../../deps/icu/source/tools/toolutil/udbgutil.h',
-        '../../deps/icu/source/tools/toolutil/dbgutil.cpp',
-        '../../deps/icu/source/tools/toolutil/dbgutil.h',
+        '<(icu_path)/source/tools/toolutil/udbgutil.cpp',
+        '<(icu_path)/source/tools/toolutil/udbgutil.h',
+        '<(icu_path)/source/tools/toolutil/dbgutil.cpp',
+        '<(icu_path)/source/tools/toolutil/dbgutil.h',
       ],
       'include_dirs': [
-        '../../deps/icu/source/common',
-        '../../deps/icu/source/i18n',
-        '../../deps/icu/source/io',
-        '../../deps/icu/source/tools/toolutil',
+        '<(icu_path)/source/common',
+        '<(icu_path)/source/i18n',
+        '<(icu_path)/source/io',
+        '<(icu_path)/source/tools/toolutil',
       ],
       'defines': [
         'U_COMMON_IMPLEMENTATION=1',
@@ -466,10 +516,10 @@
       ],
       'direct_dependent_settings': {
         'include_dirs': [
-          '../../deps/icu/source/common',
-          '../../deps/icu/source/i18n',
-          '../../deps/icu/source/io',
-          '../../deps/icu/source/tools/toolutil',
+          '<(icu_path)/source/common',
+          '<(icu_path)/source/i18n',
+          '<(icu_path)/source/io',
+          '<(icu_path)/source/tools/toolutil',
         ],
         'conditions': [
           [ 'OS=="win"', {

tools/icu/shrink-icu-src.py

@@ -0,0 +1,126 @@
+#!/usr/bin/env python
+import optparse
+import os
+import pprint
+import re
+import shlex
+import subprocess
+import sys
+import shutil
+import string
+
+parser = optparse.OptionParser()
+
+parser.add_option('--icu-small',
+    action='store',
+    dest='icusmall',
+    default='deps/icu-small',
+    help='path to target ICU directory to shrink. Will be deleted.')
+
+parser.add_option('--icu-src',
+    action='store',
+    dest='icusrc',
+    default='deps/icu',
+    help='path to source ICU directory.')
+
+parser.add_option('--icutmp',
+    action='store',
+    dest='icutmp',
+    default='out/Release/gen/icutmp',
+    help='path to icutmp dir.')
+
+
+(options, args) = parser.parse_args()
+
+if os.path.isdir(options.icusmall):
+    print 'Deleting existing icusmall %s' % (options.icusmall)
+    shutil.rmtree(options.icusmall)
+
+if not os.path.isdir(options.icusrc):
+    print 'Missing source ICU dir --icusrc=%' % (options.icusrc)
+    sys.exit(1)
+
+
+
+ignore_regex = re.compile('^.*\.(vcxproj|filters|nrm|icu|dat|xml|txt|ac|guess|m4|in|sub|py|mak)$')
+
+def icu_ignore(dir, files):
+    subdir = dir[len(options.icusrc)+1::]
+    ign = []
+    if len(subdir) == 0:
+        # remove all files at root level
+        ign = ign + files
+        # except...
+        ign.remove('source')
+        ign.remove('license.html')
+        ign.remove('LICENSE')
+    elif subdir == 'source':
+        ign = ign + ['layout','samples','test','extra','config','layoutex','allinone']
+        ign = ign + ['runConfigureICU','install-sh','mkinstalldirs','configure']
+    elif subdir == 'source/tools':
+        ign = ign + ['tzcode','ctestfw','gensprep','gennorm2','gendict','icuswap',
+        'genbrk','gencfu','gencolusb','genren','memcheck','makeconv','gencnval','icuinfo','gentest']
+    elif subdir == 'source/data':
+        ign = ign + ['unidata','curr','zone','unit','lang','region','misc','sprep']
+    # else:
+        # print '!%s! [%s]' % (subdir, files)
+    ign = ign + ['.DS_Store', 'Makefile', 'Makefile.in']
+
+    for file in files:
+        if ignore_regex.match(file):
+            ign = ign + [file]
+
+    # print '>%s< [%s]' % (subdir, ign)
+    return ign
+
+# copied from configure
+def icu_info(icu_full_path):
+    uvernum_h = os.path.join(icu_full_path, 'source/common/unicode/uvernum.h')
+    if not os.path.isfile(uvernum_h):
+        print ' Error: could not load %s - is ICU installed?' % uvernum_h
+        sys.exit(1)
+    icu_ver_major = None
+    matchVerExp = r'^\s*#define\s+U_ICU_VERSION_SHORT\s+"([^"]*)".*'
+    match_version = re.compile(matchVerExp)
+    for line in open(uvernum_h).readlines():
+        m = match_version.match(line)
+        if m:
+            icu_ver_major = m.group(1)
+    if not icu_ver_major:
+        print ' Could not read U_ICU_VERSION_SHORT version from %s' % uvernum_h
+        sys.exit(1)
+    icu_endianness = sys.byteorder[0];  # TODO(srl295): EBCDIC should be 'e'
+    return (icu_ver_major, icu_endianness)
+
+(icu_ver_major, icu_endianness) = icu_info(options.icusrc)
+print "icudt%s%s" % (icu_ver_major, icu_endianness)
+
+src_datafile = os.path.join(options.icutmp, "icusmdt%s.dat" % (icu_ver_major))
+dst_datafile = os.path.join(options.icusmall, "source","data","in", "icudt%s%s.dat" % (icu_ver_major, icu_endianness))
+
+if not os.path.isfile(src_datafile):
+    print "Could not find source datafile %s - did you build small-icu node?" % src_datafile
+    sys.exit(1)
+else:
+    print "will use small datafile %s" % (src_datafile)
+print '%s --> %s' % (options.icusrc, options.icusmall)
+shutil.copytree(options.icusrc, options.icusmall, ignore=icu_ignore)
+print '%s --> %s' % (src_datafile, dst_datafile)
+
+# OK, now copy the data file
+shutil.copy(src_datafile, dst_datafile)
+
+# Now, print a short notice
+readme_name = os.path.join(options.icusmall, "README-SMALL-ICU.txt" )
+
+fi = open(readme_name, 'wb')
+print >>fi, "Small ICU sources - auto generated by shrink-icu-src.py"
+print >>fi, ""
+print >>fi, "This directory contains the ICU subset used by --with-intl=small-icu (the default)"
+print >>fi, "It is a strict subset of ICU %s source files with the following exception(s):" % (icu_ver_major)
+print >>fi, "* %s : Reduced-size data file" % (dst_datafile)
+print >>fi, ""
+print >>fi, ""
+print >>fi, "To rebuild this directory, see ../../tools/icu/README.md"
+print >>fi, ""
+fi.close()

vcbuild.bat

@@ -73,6 +73,7 @@ if /i "%1"=="upload"        set upload=1&goto arg-ok
 if /i "%1"=="small-icu"     set i18n_arg=%1&goto arg-ok
 if /i "%1"=="full-icu"      set i18n_arg=%1&goto arg-ok
 if /i "%1"=="intl-none"     set i18n_arg=%1&goto arg-ok
+if /i "%1"=="without-intl"     set i18n_arg=%1&goto arg-ok
 if /i "%1"=="download-all"  set download_arg="--download=all"&goto arg-ok
 if /i "%1"=="ignore-flaky"  set test_args=%test_args% --flaky-tests=dontcare&goto arg-ok
 if /i "%1"=="enable-vtune"  set enable_vtune_arg=1&goto arg-ok
@@ -108,6 +109,7 @@ if defined enable_vtune_arg set configure_flags=%configure_flags% --enable-vtune
 if "%i18n_arg%"=="full-icu" set configure_flags=%configure_flags% --with-intl=full-icu
 if "%i18n_arg%"=="small-icu" set configure_flags=%configure_flags% --with-intl=small-icu
 if "%i18n_arg%"=="intl-none" set configure_flags=%configure_flags% --with-intl=none
+if "%i18n_arg%"=="without-intl" set configure_flags=%configure_flags% --without-intl
 
 if defined config_flags set configure_flags=%configure_flags% %config_flags%
 
@@ -309,7 +311,7 @@ echo Failed to create vc project files.
 goto exit
 
 :help
-echo vcbuild.bat [debug/release] [msi] [test-all/test-uv/test-internet/test-pummel/test-simple/test-message] [clean] [noprojgen] [small-icu/full-icu/intl-none] [nobuild] [nosign] [x86/x64] [vc2013/vc2015] [download-all] [enable-vtune]
+echo vcbuild.bat [debug/release] [msi] [test-all/test-uv/test-internet/test-pummel/test-simple/test-message] [clean] [noprojgen] [small-icu/full-icu/without-intl] [nobuild] [nosign] [x86/x64] [vc2013/vc2015] [download-all] [enable-vtune]
 echo Examples:
 echo   vcbuild.bat                : builds release build
 echo   vcbuild.bat debug          : builds debug build