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
|
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# Copyright © 2018 Michal Čihař <michal@cihar.com>
#
# This file is part of Weblate translation-finder
# <https://github.com/WeblateOrg/translation-finder>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
#
#
# Helper script to generate Python code from language-data repository
# see https://github.com/WeblateOrg/language-data
import csv
from itertools import chain
import json
import re
from textwrap import TextWrapper
SPLIT_RE = re.compile(
r"(?:\&(?:nbsp|rsaquo|lt|gt|amp|ldquo|rdquo|times|quot);|"
+ r'[() ,.^`"\'\\/_<>!?;:|{}*^@%#&~=+\r\n✓—‑…\[\]0-9-])+'
)
HEADER = '''# -*- coding: utf-8 -*-
#
# Copyright © 2018 Michal Čihař <michal@cihar.com>
#
# This file is part of Weblate translation-finder
# <https://github.com/WeblateOrg/translation-finder>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
#
"""
Language data definitions.
This is an automatically generated file, see scripts/generate-language-data
Do not edit, please adjust language definitions in following repository:
https://github.com/WeblateOrg/language-data
"""
from __future__ import unicode_literals
'''
WRAPPER = TextWrapper(width=79, initial_indent=" " * 4, subsequent_indent=" " * 4)
# Read languages
with open("scripts/language-data/languages.csv", "r") as csvfile:
reader = csv.reader(csvfile, delimiter=";")
LANGUAGES = list(reader)
# Read aliases
with open("scripts/language-data/aliases.csv", "r") as csvfile:
reader = csv.reader(csvfile, delimiter=";")
ALIASES = [alias for alias in reader if alias[0] != "#"]
CODES = set([item[0].lower() for item in chain(ALIASES, LANGUAGES)])
# Write same check blacklist
with open("translation_finder/languages.py", "w") as output:
output.write(HEADER)
output.write("\n\n")
output.write("# Known language codes\n")
output.write("LANGUAGES = frozenset(\n (\n")
for word in sorted(CODES):
output.write(' "{}",\n'.format(word.replace('"', '\\"')))
output.write(" )\n)\n")
|
