Make building of resource zips and srcjars hermetic

build/android/gyp/util/build_utils.py

Index: build/android/gyp/util/build_utils.py
diff --git a/build/android/gyp/util/build_utils.py b/build/android/gyp/util/build_utils.py
index 65b1a643c26a2ca920ff176af40bfcad85057f3d..562632464e28eeed2eabb38e25df2438a9aceba0 100644
--- a/build/android/gyp/util/build_utils.py
+++ b/build/android/gyp/util/build_utils.py
@@ -25,6 +25,7 @@ COLORAMA_ROOT = os.path.join(CHROMIUM_SRC,
 # aapt should ignore OWNERS files in addition the default ignore pattern.
 AAPT_IGNORE_PATTERN = ('!OWNERS:!.svn:!.git:!.ds_store:!*.scc:.*:<dir>_*:' +
                        '!CVS:!thumbs.db:!picasa.ini:!*~:!*.d.stamp')
+HERMETIC_TIMESTAMP = (2001, 1, 1, 0, 0, 0)
 
 
 @contextlib.contextmanager
@@ -218,24 +219,42 @@ def ExtractAll(zip_path, path=None, no_clobber=True, pattern=None):
     z.extractall(path=path)
 
 
-def DoZip(inputs, output, base_dir):
+def DoZip(inputs, output, base_dir=None):
+  """Creates a zip file from a list of files.
+
+  Args:
+    inputs: A list of paths to zip, or a list of (zip_path, fs_path) tuples.
+    output: Destination .zip file.
+    base_dir: Prefix to strip from inputs.
+  """
+  input_tuples = []
+  for tup in inputs:
+    if isinstance(tup, basestring):
+      tup = (os.path.relpath(tup, base_dir), tup)
+    input_tuples.append(tup)
+
+  # Sort by zip path to ensure stable zip ordering.
+  input_tuples.sort(key=lambda tup: tup[0])
   with zipfile.ZipFile(output, 'w') as outfile:
-    for f in inputs:
-      CheckZipPath(os.path.relpath(f, base_dir))
-      outfile.write(f, os.path.relpath(f, base_dir))
+    for zip_path, fs_path in input_tuples:
+      CheckZipPath(zip_path)
+      zipinfo = zipfile.ZipInfo(filename=zip_path, date_time=HERMETIC_TIMESTAMP)

[jbudorick, 2015/09/01 18:11:33]

Maybe I'm not following ... if the inputs are the same, won't the timestamp be
the same? And if the timestamp changes, don't we want to update the zip?

[agrieve, 2015/09/01 19:06:16]

The most relevant example is in our process_resources.py step. The doesn't have
a good idea of when it needs to re-run, so it re-runs fairly aggressively,
(often) generating the same assets as before, but with new timestamps. Rules
that depend on process_resources use md5_check to see if the results have
changed, and if so re-run themselves. Without this change, the outputs looks
like they always change because md5_check is foiled by timestamps embedded in
the file.

+      with file(fs_path) as f:
+        contents = f.read()
+      outfile.writestr(zipinfo, contents)
 
 
 def ZipDir(output, base_dir):
-  with zipfile.ZipFile(output, 'w') as outfile:
-    for root, _, files in os.walk(base_dir):
-      for f in files:
-        path = os.path.join(root, f)
-        archive_path = os.path.relpath(path, base_dir)
-        CheckZipPath(archive_path)
-        outfile.write(path, archive_path)
+  """Creates a zip file from a directory."""
+  inputs = []
+  for root, _, files in os.walk(base_dir):
+    for f in files:
+      inputs.append(os.path.join(root, f))
+  DoZip(inputs, output, base_dir)
 
 
-def MergeZips(output, inputs, exclude_patterns=None):
+def MergeZips(output, inputs, exclude_patterns=None, path_transform=None):
+  path_transform = path_transform or (lambda p, z: p)
   added_names = set()
   def Allow(name):
     if exclude_patterns is not None:
@@ -248,9 +267,12 @@ def MergeZips(output, inputs, exclude_patterns=None):
     for in_file in inputs:
       with zipfile.ZipFile(in_file, 'r') as in_zip:
         for name in in_zip.namelist():
-          if name not in added_names and Allow(name):
-            out_zip.writestr(name, in_zip.read(name))
-            added_names.add(name)
+          dst_name = path_transform(name, in_file)
+          if dst_name not in added_names and Allow(name):
+            zipinfo = zipfile.ZipInfo(filename=dst_name,
+                                      date_time=HERMETIC_TIMESTAMP)
+            out_zip.writestr(zipinfo, in_zip.read(name))
+            added_names.add(dst_name)
 
 
 def PrintWarning(message):