Add deduplication logic to .pak files

tools/grit/pak_util.py

 #!/usr/bin/env python
 # Copyright 2017 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.
 
 """A tool for interacting with .pak files.
 
 For details on the pak file format, see:
 https://dev.chromium.org/developers/design-documents/linuxresourcesandlocalizedstrings
 """
@@ skipping 15 matching lines @@
   pak = data_pack.ReadDataPack(args.pak_file)
 
   for resource_id, payload in pak.resources.iteritems():
     path = os.path.join(args.output_dir, str(resource_id))
     with open(path, 'w') as f:
       f.write(payload)
 
 
 def _PrintMain(args):
   pak = data_pack.ReadDataPack(args.pak_file)
+  id_map = {id(v): k for k, v in sorted(pak.resources.items(), reverse=True)}
   encoding = 'binary'
   if pak.encoding == 1:
     encoding = 'utf-8'
   elif pak.encoding == 2:
     encoding = 'utf-16'
   else:
     encoding = '?' + str(pak.encoding)
   print 'Encoding:', encoding
 
   try_decode = encoding.startswith('utf')
   # Print IDs in ascending order, since that's the order in which they appear in
   # the file (order is lost by Python dict).
   for resource_id in sorted(pak.resources):
     data = pak.resources[resource_id]
     desc = '<binary>'
     if try_decode:
       try:
         desc = unicode(data, encoding)
         if len(desc) > 60:
           desc = desc[:60] + u'...'
         desc = desc.replace('\n', '\\n')
       except UnicodeDecodeError:
         pass
     sha1 = hashlib.sha1(data).hexdigest()[:10]
-    line = u'Entry(id={}, len={}, sha1={}): {}'.format(
-        resource_id, len(data), sha1, desc)
+    canonical_id = id_map[id(data)]
+    if resource_id == canonical_id:
+      line = u'Entry(id={}, len={}, sha1={}): {}'.format(
+          resource_id, len(data), sha1, desc)
+    else:
+      line = u'Entry(id={}, alias_of={}): {}'.format(
+          resource_id, canonical_id, desc)
     print line.encode('utf-8')
 
 
 def _ListMain(args):
   resources, _ = data_pack.ReadDataPack(args.pak_file)
   for resource_id in sorted(resources.keys()):
     args.output.write('%d\n' % resource_id)
 
 
 def main():
@@ skipping 37 matching lines @@
   elif len(sys.argv) == 2 and sys.argv[1] in actions:
     parser.parse_args(sys.argv[1:] + ['-h'])
     sys.exit(1)
 
   args = parser.parse_args()
   args.func(args)
 
 
 if __name__ == '__main__':
   main()