Patch path filtering script.

scripts/slave/patch_path_filter.py

+#!/usr/bin/python
+# Copyright 2013 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.
+
+"""Script that can be used to filter out files from a patch/diff.
+
+Just pipe the patch contents to stdin and the filtered output will be written
+to stdout.
+
+This script supports the following types of diff entries where each file entry
+starts with the following four lines:
+
+* Subversion patch:
+Index: path_and_filename
+===================================================================
+--- path_and_filename  (revision xxxx)
++++ path_and_filename  (working copy)
+
+
+* Git patch:
+diff --git path_and_filename path_and_filename
+index abcdef..123456 100644
+--- path_and_filename
++++ path_and_filename
+"""
+
+import optparse
+import re
+import sys
+
+
+class PatchEntry():
+  def __init__(self, file_path, contents):
+    self.file_path = file_path
+    self.contents = contents
+
+  def __str__(self):
+    return self.contents
+
+
+GIT_REGEX = ('^diff\s--git\s(.*?)\s(.*?)\n'
+             '^.*?\n'
+             '^-{3}\s(.*?)\n'
+             '^\+{3}\s(.*?)$')

[iannucci, 2013/10/29 17:15:02]

I would use a raw string here (i.e. r' stuff '). The only escape char which
works is r'\''

And although I think the -{3} is cute, '---' is probably better :)

Also, you'll want to make sure you test with weird patches, like moving/copying
files, mode changes (executable v. not), etc.

I think there is already some diff-parsing code in depot_tools that's used by
apply_issue.py. It may be worth investigating and sharing?

[kjellander_chromium, 2013/11/26 22:11:25]

This is remade in Patch set #3.
No longer needed since I use patch.py's parsing now.
I'm trusting patch.py is heavily tested already.
Patch Set #3 is now using depot tools patch.py and the only thing that is parsed
in here is the splitting of the patch set into patches.

+SVN_REGEX = ('^Index:\s(.*?)\n'
+             '^.*?\n'
+             '^-{3}\s.*?\n'
+             '^\+{3}\s.*?$')
+ITEM_PREFIX_TYPES = (GIT_REGEX, SVN_REGEX)
+
+def parse_entries(item_prefix_regex, patch_contents):
+  regex = re.compile(item_prefix_regex, re.MULTILINE | re.DOTALL)
+
+  # List to contain tuples of filename and start position in the patch.
+  file_and_start_index_list = []
+
+  start_index = 0
+  match_data = regex.search(patch_contents[start_index:])
+  while match_data:
+    file_and_start_index_list.append((match_data.group(1),
+                                      start_index + match_data.start()))
+    start_index += match_data.end()
+    match_data = regex.search(patch_contents[start_index:])
+
+  # Build a PatchEntry list from the list of filename and start indexes.
+  entries = []
+  i = iter(file_and_start_index_list)
+  previous_item = None
+  try:
+    while True:
+      item = i.next()
+      if previous_item:
+        entries.append(PatchEntry(previous_item[0],
+                                  patch_contents[previous_item[1]:item[1]]))
+      previous_item = item
+  except StopIteration:
+    if previous_item:
+      entries.append(PatchEntry(previous_item[0],
+                                patch_contents[previous_item[1]:]))
+  return entries
+
+def main():
+  parser = optparse.OptionParser()
+  parser.add_option('-f', '--path-filter',
+                    help=('The path filter (UNIX paths) that all file paths '
+                          'are required to have to pass this filter (no '
+                          'regexp).'))
+
+  options, args = parser.parse_args()
+  if args:
+    parser.error('Unused args: %s' % args)
+  if not options.path_filter:
+    parser.error('A path filter must be be specified.')
+
+  patch_contents = sys.stdin.read()
+
+  # Try with Git first, since it's the most likely used patch format.
+  patch_entries = parse_entries(GIT_REGEX, patch_contents)
+  if len(patch_entries) == 0:
+    patch_entries = parse_entries(SVN_REGEX, patch_contents)
+
+  # Only print the patch entries that passes our path filter.
+  for entry in patch_entries:
+    if entry.file_path.startswith(options.path_filter):
+      print entry
+
+if __name__ == '__main__':
+  sys.exit(main())