Add source generation to GSUtils.download_file.

py/utils/gs_utils.py

 #!/usr/bin/python
 
 # pylint: disable=C0301
 """
 Copyright 2014 Google Inc.
 
 Use of this source code is governed by a BSD-style license that can be
 found in the LICENSE file.
 
 Utilities for accessing Google Cloud Storage, using the boto library (wrapper
@@ skipping 393 matching lines @@
         q.task_done()
     for _ in range(num_threads):
       t = threading.Thread(target=worker)
       t.daemon = True
       t.start()
 
     # Block until all files have been uploaded and all workers have exited.
     q.join()
 
   def download_file(self, source_bucket, source_path, dest_path,
-                    create_subdirs_if_needed=False):
+                    create_subdirs_if_needed=False, source_generation=None):
     """Downloads a single file from Google Cloud Storage to local disk.
 
     Args:
       source_bucket: GS bucket to download the file from
       source_path: full path (Posix-style) within that bucket
       dest_path: full path (local-OS-style) on local disk to copy the file to
       create_subdirs_if_needed: boolean; whether to create subdirectories as
           needed to create dest_path
+      source_generation: the generation version of the source
     """
     b = self._connect_to_bucket(bucket=source_bucket)
     key = Key(b)
     key.name = source_path
+    if source_generation:
+      key.generation = source_generation
     if create_subdirs_if_needed:
       _makedirs_if_needed(os.path.dirname(dest_path))
     with open(dest_path, 'w') as f:
       try:
         key.get_contents_to_file(fp=f)
       except BotoServerError, e:
         e.body = (repr(e.body) +
                   ' while downloading gs://%s/%s to local_path=%s' % (
                       b.name, source_path, dest_path))
         raise
@@ skipping 264 matching lines @@
 
 def _get_local_md5(path):
   """Returns the MD5 hash of a file on local disk."""
   hasher = hashlib.md5()
   with open(path, 'rb') as f:
     while True:
       data = f.read(64*1024)
       if not data:
         return hasher.hexdigest()
       hasher.update(data)