summaryrefslogtreecommitdiffstats
path: root/remoting/tools/verify_resources.py
blob: 1f5d8d41f16dd3c060ea02870a6e567ff0881f8a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
#!/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.

"""Verifies that GRD resource files define all the strings used by a given
set of source files. For file formats where it is not possible to infer which
strings represent message identifiers, localized strings should be explicitly
annotated with the string "i18n-content", for example:

  LocalizeString(/*i18n-content*/"PRODUCT_NAME");

This script also recognises localized strings in HTML and manifest.json files:

  HTML:          i18n-content="PRODUCT_NAME"
              or i18n-value-name-1="BUTTON_NAME"
              or i18n-title="TOOLTIP_NAME"
  manifest.json: __MSG_PRODUCT_NAME__

Note that these forms must be exact; extra spaces are not permitted, though
either single or double quotes are recognized.

In addition, the script checks that all the messages are still in use; if
this is not the case then a warning is issued, but the script still succeeds.
"""

import json
import os
import optparse
import re
import sys
import xml.dom.minidom as minidom

WARNING_MESSAGE = """
To remove this warning, either remove the unused tags from
resource files, add the files that use the tags listed above to
remoting.gyp, or annotate existing uses of those tags with the
prefix /*i18n-content*/
"""

def LoadTagsFromGrd(filename):
  xml = minidom.parse(filename)
  tags = []
  msgs_and_structs = xml.getElementsByTagName("message")
  msgs_and_structs.extend(xml.getElementsByTagName("structure"))
  for res in msgs_and_structs:
    name = res.getAttribute("name")
    if not name or not name.startswith("IDS_"):
      raise Exception("Tag name doesn't start with IDS_: %s" % name)
    tags.append(name[4:])
  return tags

def ExtractTagFromLine(file_type, line):
  """Extract a tag from a line of HTML, C++, JS or JSON."""
  if file_type == "html":
    # HTML-style (tags)
    m = re.search('i18n-content=[\'"]([^\'"]*)[\'"]', line)
    if m: return m.group(1)
    # HTML-style (titles)
    m = re.search('i18n-title=[\'"]([^\'"]*)[\'"]', line)
    if m: return m.group(1)
    # HTML-style (substitutions)
    m = re.search('i18n-value-name-[1-9]=[\'"]([^\'"]*)[\'"]', line)
    if m: return m.group(1)
  elif file_type == 'js':
    # Javascript style
    m = re.search('/\*i18n-content\*/[\'"]([^\`"]*)[\'"]', line)
    if m: return m.group(1)
  elif file_type == 'cc' or file_type == 'mm':
    # C++ style
    m = re.search('IDS_([A-Z0-9_]*)', line)
    if m: return m.group(1)
    m = re.search('/\*i18n-content\*/["]([^\`"]*)["]', line)
    if m: return m.group(1)
  elif file_type == 'json':
    # Manifest style
    m = re.search('__MSG_(.*)__', line)
    if m: return m.group(1)
  elif file_type == 'jinja2':
    # Jinja2 template file
    m = re.search('\{\%\s+trans\s+\%\}([A-Z0-9_]+)\{\%\s+endtrans\s+\%\}', line)
    if m: return m.group(1)
  return None


def VerifyFile(filename, messages, used_tags):
  """
  Parse |filename|, looking for tags and report any that are not included in
  |messages|. Return True if all tags are present and correct, or False if
  any are missing. If no tags are found, print a warning message and return
  True.
  """

  base_name, extension = os.path.splitext(filename)
  extension = extension[1:]
  if extension not in ['js', 'cc', 'html', 'json', 'jinja2', 'mm']:
    raise Exception("Unknown file type: %s" % extension)

  result = True
  matches = False
  f = open(filename, 'r')
  lines = f.readlines()
  for i in xrange(0, len(lines)):
    tag = ExtractTagFromLine(extension, lines[i])
    if tag:
      tag = tag.upper()
      used_tags.add(tag)
      matches = True
      if not tag in messages:
        result = False
        print '%s/%s:%d: error: Undefined tag: %s' % \
            (os.getcwd(), filename, i + 1, tag)
  if not matches:
    print '%s/%s:0: warning: No tags found' % (os.getcwd(), filename)
  f.close()
  return result


def main():
  parser = optparse.OptionParser(
      usage='Usage: %prog [options...] [source_file...]')
  parser.add_option('-t', '--touch', dest='touch',
                    help='File to touch when finished.')
  parser.add_option('-r', '--grd', dest='grd', action='append',
                    help='grd file')

  options, args = parser.parse_args()
  if not options.touch:
    print '-t is not specified.'
    return 1
  if len(options.grd) == 0 or len(args) == 0:
    print 'At least one GRD file needs to be specified.'
    return 1

  resources = []
  for f in options.grd:
    resources.extend(LoadTagsFromGrd(f))

  used_tags = set([])
  exit_code = 0
  for f in args:
    if not VerifyFile(f, resources, used_tags):
      exit_code = 1

  warnings = False
  for tag in resources:
    if tag not in used_tags:
      print ('%s/%s:0: warning: %s is defined but not used') % \
          (os.getcwd(), sys.argv[2], tag)
      warnings = True
  if warnings:
    print WARNING_MESSAGE

  if exit_code == 0:
    f = open(options.touch, 'a')
    f.close()
    os.utime(options.touch, None)

  return exit_code


if __name__ == '__main__':
  sys.exit(main())