Speed-up whitelist check in data_pack.py

grit/format/data_pack.py

 #!/usr/bin/env python
 # Copyright (c) 2012 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.
 
 """Support for formatting a data pack file used for platform agnostic resource
 files.
 """
 
 import collections
@@ skipping 109 matching lines @@
                       all resources.
 
   Raises:
       KeyError: if there are duplicate keys or resource encoding is
       inconsistent.
   """
   input_data_packs = [ReadDataPack(filename) for filename in input_files]
   whitelist = None
   if whitelist_file:
     whitelist = util.ReadFile(whitelist_file, util.RAW_TEXT).strip().split('\n')
-    whitelist = map(int, whitelist)
+    whitelist = set(map(int, whitelist))
   resources, encoding = RePackFromDataPackStrings(input_data_packs, whitelist)
   WriteDataPack(resources, output_file, encoding)
 
 
 def RePackFromDataPackStrings(inputs, whitelist):
   """Returns a data pack string that combines the resources from inputs.
 
   Args:
       inputs: a list of data pack strings that need to be combined.
       whitelist: a list of resource IDs that should be kep in the output string
@@ skipping 58 matching lines @@
     # Just write a simple file.
     data = {1: '', 4: 'this is id 4', 6: 'this is id 6', 10: ''}
     WriteDataPack(data, 'datapack1.pak', UTF8)
     data2 = {1000: 'test', 5: 'five'}
     WriteDataPack(data2, 'datapack2.pak', UTF8)
     print 'wrote datapack1 and datapack2 to current directory.'
 
 
 if __name__ == '__main__':
   main()