WebUI: Add GN rules for Vulcanize.

chrome/browser/resources/unpack_pak.py

Index: chrome/browser/resources/unpack_pak.py
diff --git a/chrome/browser/resources/unpack_pak.py b/chrome/browser/resources/unpack_pak.py
new file mode 100755
index 0000000000000000000000000000000000000000..904fb8010e6a29d2506004975da2dc7b01f02fc2
--- /dev/null
+++ b/chrome/browser/resources/unpack_pak.py
@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+# Copyright 2016 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+import os
+import re
+import sys
+
+_HERE_PATH = os.path.join(os.path.dirname(__file__))
+_SRC_PATH = os.path.normpath(os.path.join(_HERE_PATH, '..', '..', '..'))
+sys.path.append(os.path.join(_SRC_PATH, 'tools', 'grit'))
+from grit.format import data_pack
+
+def unpack(pak_path, out_path):
+  pak_dir = os.path.dirname(pak_path);
+  pak_id = os.path.splitext(os.path.basename(pak_path))[0]
+
+  data = data_pack.DataPack.ReadDataPack(pak_path)
+
+  # Associate numerical grit IDs to strings.
+  # For example 120045 -> 'IDR_SETTINGS_ABOUT_PAGE_HTML'
+  resource_ids = dict()
+  resources_path = os.path.join(pak_dir, 'grit', pak_id + '.h')
+  with open(resources_path) as resources_file:
+    for line in resources_file:
+      res = re.match('#define ([^ ]+) (\d+)', line)

[dschuyler, 2017/01/12 00:58:10]

This is cool as-is, but I wanted to offer a tip in the hope it's helpful. Regex
has special escapes for white-space and C-like keywords, e.g. [A-Za-z0-9_]. So,
this could be (if you prefer):

res = re.match('^\s*#define\s+(\w+)\s(\d+)', line)

That may be more robust. Though it may not matter if the file being scanned is
mechanically generated (which would be unlikely to have a variance in the
layout).

[dschuyler, 2017/01/12 01:10:55]

Whoops, the ^ is redundant with re.match().

(The ^ would help with re.search(), but re.match() already implies 'at start of
line').

+      if res:
+        resource_ids[int(res.group(2))] = res.group(1)
+
+  # Associate numerical string IDs to files.
+  resource_filenames = dict()
+  resources_map_path = os.path.join(pak_dir, 'grit', pak_id + '_map.cc')
+  with open(resources_map_path) as resources_map:
+    for line in resources_map:
+      res = re.match('  {"([^"]+)", ([^}]+)', line)
+      if res:
+        resource_filenames[res.group(2)] = res.group(1)
+
+  # Extract packed files, while preserving directory structure.
+  for (resource_id, text) in data.resources.iteritems():
+    #print '%s: %s' % (resource_id, text)
+
+    filename = resource_filenames[resource_ids[resource_id]]
+    dirname = os.path.join(out_path, os.path.dirname(filename))
+    if not os.path.exists(dirname):
+      os.makedirs(dirname)
+    with open(os.path.join(out_path, filename), 'w') as file:
+      file.write(text)
+
+if __name__ == '__main__':
+  pak_path = os.path.join(
+      _SRC_PATH,
+      'out/gchrome_gn/gen/chrome/browser/resources/settings/' +
+          'settings_resources.pak');
+  out_path = os.path.join(
+      _SRC_PATH,
+      'out/gchrome_gn/gen/chrome/browser/resources/settings/flattened');
+  unpack(pak_path, out_path)