File: phonetic_dictionaries.py

package info (click to toggle)
chromium 139.0.7258.127-1
  • links: PTS, VCS
  • area: main
  • in suites:
  • size: 6,122,068 kB
  • sloc: cpp: 35,100,771; ansic: 7,163,530; javascript: 4,103,002; python: 1,436,920; asm: 946,517; xml: 746,709; pascal: 187,653; perl: 88,691; sh: 88,436; objc: 79,953; sql: 51,488; cs: 44,583; fortran: 24,137; makefile: 22,147; tcl: 15,277; php: 13,980; yacc: 8,984; ruby: 7,485; awk: 3,720; lisp: 3,096; lex: 1,327; ada: 727; jsp: 228; sed: 36
file content (89 lines) | stat: -rwxr-xr-x 2,492 bytes parent folder | download | duplicates (6)
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
#!/usr/bin/env python

# Copyright 2020 The Chromium Authors
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
'''Generates phonetic_dictionaries.js'''

import gzip
import json
import optparse
import os
import sys


HEADER = '''export const PhoneticDictionaries = {};

PhoneticDictionaries.phoneticMap_ = {
'''

CONTENT_TEMPLATE = '''"%(locale)s": %(data)s,
'''

FOOTER = '''};
'''

def quit(message):
  '''Prints an error message and exit the program.'''
  sys.stderr.write(message + '\n')
  sys.exit(1)

def open_file(filename):
    if filename.endswith('.gz'):
        return gzip.open(filename)
    return open(filename)

def main():
    # Parse input.
    parser = optparse.OptionParser(description=__doc__)
    parser.add_option(
      '-o',
      '--output_file',
      action='store',
      metavar='SPEC',
      help=('Where to output the generated file.'))
    options, args = parser.parse_args()
    if options.output_file is None:
        quit('Output file not specified')
    if len(args) != 1:
        quit('Exactly one input directory must be specified')
    dir_name = args[0]
    out_file = options.output_file
    output = HEADER

    # Extract phonetic dictionaries from all compressed message files and write
    # them to a .js file.
    for locale in os.listdir(dir_name):
        locale_dir = os.path.join(dir_name, locale)

        if not os.path.isdir(locale_dir):
            continue

        files = os.listdir(locale_dir)
        if not len(files) == 1:
            continue

        file = files[0]
        file_path = os.path.join(locale_dir,file)
        with open_file(file_path) as in_file:
            contents = json.loads(in_file.read().strip())
            try:
                test = json.loads(contents['CHROMEVOX_PHONETIC_MAP']['message'])
                if sys.version_info >= (3,0):
                    data = contents['CHROMEVOX_PHONETIC_MAP']['message']
                else:
                    # Need to encode utf8 if running python 2.
                    data = (contents['CHROMEVOX_PHONETIC_MAP']['message']
                    .encode('utf-8'))
                locale = locale.replace('_', '-').lower()
                output += CONTENT_TEMPLATE % {'locale': locale, 'data': data}
            except ValueError as e:
                continue

    # Write to file.
    with open(out_file, 'w') as dest_file:
        dest_file.write(output + FOOTER)


if __name__ == '__main__':
    main()