tools/sort_sources.py

   1 #!/usr/bin/env python
   2 # Copyright 2015 The Chromium Authors. All rights reserved.
   3 # Use of this source code is governed by a BSD-style license that can be
   4 # found in the LICENSE file.
   5
   6 """Given a GYP/GN filename, sort C-ish source files in that file.
   7
   8 Shows a diff and prompts for confirmation before doing the deed.
   9 Works great with tools/git/for-all-touched-files.py.
  10
  11 Limitations:
  12
  13 1) Comments used as section headers
  14
  15 If a comment (1+ lines starting with #) appears in a source list without a
  16 preceding blank line, the tool assumes that the comment is about the next
  17 line. For example, given the following source list,
  18
  19   sources = [
  20     "b.cc",
  21     # Comment.
  22     "a.cc",
  23     "c.cc",
  24   ]
  25
  26 the tool will produce the following output:
  27
  28   sources = [
  29     # Comment.
  30     "a.cc",
  31     "b.cc",
  32     "c.cc",
  33   ]
  34
  35 This is not correct if the comment is for starting a new section like:
  36
  37   sources = [
  38     "b.cc",
  39     # These are for Linux.
  40     "a.cc",
  41     "c.cc",
  42   ]
  43
  44 The tool cannot disambiguate the two types of comments. The problem can be
  45 worked around by inserting a blank line before the comment because the tool
  46 interprets a blank line as the end of a source list.
  47
  48 2) Sources commented out
  49
  50 Sometimes sources are commented out with their positions kept in the
  51 alphabetical order, but what if the list is not sorted correctly? For
  52 example, given the following source list,
  53
  54   sources = [
  55     "a.cc",
  56     # "b.cc",
  57     "d.cc",
  58     "c.cc",
  59   ]
  60
  61 the tool will produce the following output:
  62
  63   sources = [
  64     "a.cc",
  65     "c.cc",
  66     # "b.cc",
  67     "d.cc",
  68   ]
  69
  70 This is because the tool assumes that the comment (# "b.cc",) is about the
  71 next line ("d.cc",). This kind of errors should be fixed manually, or the
  72 commented-out code should be deleted.
  73
  74 3) " and ' are used both used in the same source list (GYP only problem)
  75
  76 If both " and ' are used in the same source list, sources quoted with " will
  77 appear first in the output. The problem is rare enough so the tool does not
  78 attempt to normalize them. Hence this kind of errors should be fixed
  79 manually.
  80
  81 4) Spaces and tabs used in the same source list
  82
  83 Similarly, if spaces and tabs are both used in the same source list, sources
  84 indented with tabs will appear first in the output. This kind of errors
  85 should be fixed manually.
  86
  87 """
  88
  89 import difflib
  90 import optparse
  91 import re
  92 import sys
  93
  94 from yes_no import YesNo
  95
  96 SUFFIXES = ['c', 'cc', 'cpp', 'h', 'mm', 'rc', 'rc.version', 'ico', 'def',
  97             'release']
  98 SOURCE_PATTERN = re.compile(r'^\s+[\'"].*\.(%s)[\'"],$' %
  99                             '|'.join([re.escape(x) for x in SUFFIXES]))
 100 COMMENT_PATTERN = re.compile(r'^\s+#')
 101
 102
 103 def SortSources(original_lines):
 104   """Sort source file names in |original_lines|.
 105
 106   Args:
 107     original_lines: Lines of the original content as a list of strings.
 108
 109   Returns:
 110     Lines of the sorted content as a list of strings.
 111
 112   The algorithm is fairly naive. The code tries to find a list of C-ish
 113   source file names by a simple regex, then sort them. The code does not try
 114   to understand the syntax of the build files. See the file comment above for
 115   details.
 116   """
 117
 118   output_lines = []
 119   comments = []
 120   sources = []
 121   for line in original_lines:
 122     if re.search(COMMENT_PATTERN, line):
 123       comments.append(line)
 124     elif re.search(SOURCE_PATTERN, line):
 125       # Associate the line with the preceding comments.
 126       sources.append([line, comments])
 127       comments = []
 128     else:
 129       # |sources| should be flushed first, to handle comments at the end of a
 130       # source list correctly.
 131       if sources:
 132         for source_line, source_comments in sorted(sources):
 133           output_lines.extend(source_comments)
 134           output_lines.append(source_line)
 135         sources = []
 136       if comments:
 137         output_lines.extend(comments)
 138         comments = []
 139       output_lines.append(line)
 140   return output_lines
 141
 142
 143 def ProcessFile(filename, should_confirm):
 144   """Process the input file and rewrite if needed.
 145
 146   Args:
 147     filename: Path to the input file.
 148     should_confirm: If true, diff and confirmation prompt are shown.
 149   """
 150
 151   original_lines = []
 152   with open(filename, 'r') as input_file:
 153     for line in input_file:
 154       original_lines.append(line)
 155
 156   new_lines = SortSources(original_lines)
 157   if original_lines == new_lines:
 158     print '%s: no change' % filename
 159     return
 160
 161   if should_confirm:
 162     diff = difflib.unified_diff(original_lines, new_lines)
 163     sys.stdout.writelines(diff)
 164     if not YesNo('Use new file (y/N)'):
 165       return
 166
 167   with open(filename, 'w') as output_file:
 168     output_file.writelines(new_lines)
 169
 170
 171 def main():
 172   parser = optparse.OptionParser(usage='%prog filename1 filename2 ...')
 173   parser.add_option('-f', '--force', action='store_false', default=True,
 174                     dest='should_confirm',
 175                     help='Turn off confirmation prompt.')
 176   opts, filenames = parser.parse_args()
 177
 178   if len(filenames) < 1:
 179     parser.print_help()
 180     return 1
 181
 182   for filename in filenames:
 183     ProcessFile(filename, opts.should_confirm)
 184
 185
 186 if __name__ == '__main__':
 187   sys.exit(main())