Bug 1288567 - Extract function for creating context tars; r=dustin

Upcoming commits will refactor how context tarballs are created. In
preparation for this, we establish a standalone function for creating
context tarballs and refactor docker_image.py to use it.

MozReview-Commit-ID: KEW6ppO1vCl

--HG--
extra : rebase_source : b81decf9ca14ff0216514f47419e96eb57d6f851

taskcluster/taskgraph/task/docker_image.py

@@ -9,13 +9,13 @@ import json
 import os
 import re
 import urllib2
-import tarfile
 import time
 
 from . import base
 from taskgraph.util.docker import (
+    create_context_tar,
     docker_image,
-    generate_context_hash
+    generate_context_hash,
 )
 from taskgraph.util.templates import Templates
 
@@ -138,8 +138,7 @@ class DockerImageTask(base.Task):
         if not os.path.exists(os.path.dirname(destination)):
             os.makedirs(os.path.dirname(destination))
 
-        with tarfile.open(destination, 'w:gz') as tar:
-            tar.add(context_dir, arcname=image_name)
+        create_context_tar(context_dir, destination, image_name)
 
     @classmethod
     def from_json(cls, task_dict):

taskcluster/taskgraph/util/docker.py

@@ -6,6 +6,7 @@ from __future__ import absolute_import, print_function, unicode_literals
 
 import hashlib
 import os
+import tarfile
 
 GECKO = os.path.realpath(os.path.join(__file__, '..', '..', '..', '..'))
 DOCKER_ROOT = os.path.join(GECKO, 'testing', 'docker')
@@ -53,3 +54,25 @@ def generate_context_hash(image_path):
             context_hash.update(file_hash.hexdigest() + '\t' + relative_filename + '\n')
 
     return context_hash.hexdigest()
+
+
+def create_context_tar(context_dir, out_path, prefix):
+    """Create a context tarball.
+
+    A directory ``context_dir`` containing a Dockerfile will be assembled into
+    a gzipped tar file at ``out_path``. Files inside the archive will be
+    prefixed by directory ``prefix``.
+
+    Returns the SHA-256 hex digest of the created archive.
+    """
+    with tarfile.open(out_path, 'w:gz') as tar:
+        tar.add(context_dir, arcname=prefix)
+
+    h = hashlib.sha256()
+    with open(out_path, 'rb') as fh:
+        while True:
+            data = fh.read(32768)
+            if not data:
+                break
+            h.update(data)
+    return h.hexdigest()