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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
|
#!/usr/bin/env python
# encoding: utf-8
from collections import defaultdict, namedtuple
import itertools
import os
import re
from confgettext import head
Token = namedtuple('Token', ['type', 'data'])
def _escape_pot_string(string):
return string.replace('\\', '\\\\').replace('"', '\\"')
def _format_msgid(tag, string, output):
# there was a bug in this code that would never output single line
# msg_ids. I decided not to fix it, since that wuold change a ton
# of pot files and maybe msg_ids.
# if not string.count('\n'): <== this was s.count
# s += 'msgid "%s"\n' % string
# else:
string = _escape_pot_string(string)
output.append('%s ""' % tag)
lines = string.split('\n')
for line in lines[:-1]:
output.append('"%s\\n"' % line)
output.append('"%s"' % lines[-1])
return output
class ParsingNode(list):
def __init__(self, parent=None):
self.parent = parent
self.type = 'NODE'
def __str__(self):
return 'N%s' % list.__str__(self)
class LuaParser(object):
def __init__(self):
self.scanner = re.Scanner([
(r"\-\-( TRANSLATORS)?", self._Tcomment),
(r"\(", self._Tleft),
(r"\)", self._Tright),
(r"\.\.", self._Tconcat),
(r"(?<!\\)[\"']", self._Ttoggle_string),
(r"\[\[", self._Topen_multiline_string),
(r"\]\]", self._Tclose_multiline_string),
(r"\b_\b", self._Ttranslate_next_string),
(r"[^\d\W]\w*", self._Tidentifier),
(r"\n", self._Tnewline),
(r"[ \t]+", self._Twhitespace),
(r".", self._Tidentifier),
], re.MULTILINE | re.DOTALL)
self.in_string = False
self.current_line = 1
self.current_string = ''
self.result = ParsingNode()
self.in_comment = False
self.translator_comment = ''
self.current = self.result
def parse(self, content):
self.scanner.scan(content)
def _recurse_lists(original_list, func):
def _internal(l):
new_l = ParsingNode()
for entry in l:
if isinstance(entry, list):
entry = _recurse_lists(entry, func)
new_l.append(entry)
return func(new_l)
return _internal(original_list)
def _combine_concatenated_strings(l):
for i in range(len(l)):
if i > 0 and l[i].type == '..':
if l[i - 1].type != 'STRING' or l[i + 1].type != 'STRING':
continue
# Do not concatenate translated and untranslated string.
if i - 2 >= 0 and l[i - 2].type == '_':
continue
first_string, line = l[i - 1].data
second_string, unused = l[i + 1].data
l[i - 1:i +
2] = [Token('STRING', (first_string + second_string, line))]
return _combine_concatenated_strings(l)
return l
translatable_items = []
translator_comment_lines = []
def _find_translatable_strings(l):
for i in range(len(l)):
if isinstance(l[i], list):
_find_translatable_strings(l[i])
continue
append_data = None
if l[i].type == 'TRANSLATOR_COMMENT':
translator_comment_lines.append(l[i].data[0])
if l[i].type == '_':
if l[i + 1].type == 'NODE':
msgid, line = l[i + 1][0].data
else:
msgid, line = l[i + 1].data
append_data = {
'type': 'gettext',
'msgid': msgid,
'line': line,
}
if l[i].type == 'pgettext':
assert l[i + 1].type == 'NODE'
assert len(l[i + 1]) == 3
line = l[i + 1][0].data[1]
msgctxt = l[i + 1][0].data[0]
msgid = l[i + 1][2].data[0]
append_data = {
'type': 'pgettext',
'msgid': msgid,
'msgctxt': msgctxt,
'line': line,
}
if l[i].type == 'ngettext':
assert l[i + 1].type == 'NODE'
assert len(l[i + 1]) >= 4
msgid, line = l[i + 1][0].data
msgid_plural = l[i + 1][2].data[0]
append_data = {
'type': 'ngettext',
'msgid': msgid,
'msgid_plural': msgid_plural,
'line': line,
}
if append_data:
comment = '\n'.join(translator_comment_lines).strip()
# Empty the list, but keep the reference the same, so that
# all recursed methods still use the same object.
while translator_comment_lines:
translator_comment_lines.pop()
if comment:
append_data['translator_comment'] = comment
translatable_items.append(append_data)
return l
def _remove_empties(l):
rv = ParsingNode()
for a in l:
if isinstance(a, list) and not a:
continue
rv.append(a)
return rv
self.result = _recurse_lists(self.result, _remove_empties)
self.result = _recurse_lists(
self.result, _combine_concatenated_strings)
_find_translatable_strings(self.result)
return translatable_items
def _skip_token(self, scanner, token):
if self.in_string:
self.current_string += token
elif self.translator_comment:
self.translator_comment += token
def _string_done(self):
text = eval('str(""" %s """)' % self.current_string)[1:-1]
self.current.append(Token('STRING', (text, self.string_started)))
self.current_string = ''
del self.string_started
self.in_string = None
def _Tleft(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif self.in_string:
self._skip_token(scanner, token)
else:
new = ParsingNode(self.current)
self.current.append(new)
self.current = new
def _Tright(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif self.in_string:
self._skip_token(scanner, token)
else:
self.current = self.current.parent
def _Ttranslate_next_string(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif self.in_string:
self._skip_token(scanner, token)
else:
self.current.append(Token('_', None))
def _Topen_multiline_string(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif self.in_string:
self._skip_token(scanner, token)
else:
self.string_started = self.current_line
self.in_string = '[['
def _Tclose_multiline_string(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif self.in_string and self.in_string != '[[':
self._skip_token(scanner, token)
else:
assert(self.in_string == '[[')
self._string_done()
def _Ttoggle_string(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif not self.in_string:
self.in_string = token
self.string_started = self.current_line
elif self.in_string != token:
self._skip_token(scanner, token)
else:
self._string_done()
def _Tconcat(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif self.in_string:
self._skip_token(scanner, token)
else:
self.current.append(Token('..', None))
def _Tidentifier(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif self.in_string:
self._skip_token(scanner, token)
else:
self.current.append(Token(token, None))
def _Tnewline(self, scanner, token):
self.current_line += 1
self._skip_token(scanner, token)
self.in_comment = False
if self.translator_comment:
self.current.append(
Token('TRANSLATOR_COMMENT', (self.translator_comment.strip(),)))
self.translator_comment = ''
def _Twhitespace(self, scanner, token):
self._skip_token(scanner, token)
def _Tcomment(self, scanner, token):
if self.in_comment:
self._skip_token(scanner, token)
elif self.in_string:
self._skip_token(scanner, token)
else:
if token.startswith('-- TRANSLATORS'):
self.translator_comment = 'TRANSLATORS'
self.in_comment = True
def emit_comments_and_line_numbers(occurences, lines):
comments = sorted(
set(f['translator_comment'] for f in occurences if 'translator_comment' in f))
for comment in comments:
lines.append('#: %s' % (comment))
for occurence in occurences:
lines.append('#: %s:%i' % (os.path.normpath(occurence['filename']),
occurence['line']))
def emit_gettext(occurences, lines):
emit_comments_and_line_numbers(occurences, lines)
occurence = occurences[0]
_format_msgid('msgid', occurence['msgid'], lines)
lines.extend(['msgstr ""', ''])
def emit_ngettext(occurences, lines):
emit_comments_and_line_numbers(occurences, lines)
occurence = occurences[0]
_format_msgid('msgid', occurence['msgid'], lines)
_format_msgid('msgid_plural', occurence['msgid_plural'], lines)
lines.append('msgstr[0] ""')
lines.extend(['msgstr[1] ""', ''])
def emit_pgettext(occurences, lines):
for context, ctx_occurences in itertools.groupby(occurences, key=lambda a: a['msgctxt']):
ctx_occurences = list(ctx_occurences)
emit_comments_and_line_numbers(ctx_occurences, lines)
occurence = ctx_occurences[0]
lines.append('msgctxt "%s"' % _escape_pot_string(occurence['msgctxt']))
_format_msgid('msgid', occurence['msgid'], lines)
lines.extend(['msgstr ""', ''])
EMIT_FUNCTIONS = {
'gettext': emit_gettext,
'ngettext': emit_ngettext,
'pgettext': emit_pgettext,
}
class Lua_GetText(object):
def __init__(self):
self.translatable_items = defaultdict(list)
def parse(self, contents, filename):
items = LuaParser().parse(contents)
for item in items:
item['filename'] = filename
self.translatable_items[item['msgid']].append(item)
@property
def found_something_to_translate(self):
return len(self.translatable_items.keys()) > 0
def merge(self, other_translatable_items):
for key in other_translatable_items:
our_translatable_items = self.translatable_items[key]
for finding in other_translatable_items[key]:
if isinstance(finding, dict):
our_translatable_items.append(finding)
else:
our_translatable_items.append({
'type': 'gettext',
'msgid': key,
'filename': finding[0],
'line': finding[1]
})
def __str__(self):
lines = []
sort_func = lambda i: [i.get(v, None) for v in (
'filename', 'line', 'msgid', 'msgid_plural', 'translator_comment')]
# Now output translatable_items sorted by filename, line number, type. But
# each msg_id must only be outputted exactly once.
all_translatable_items = []
for msgid in self.translatable_items:
all_translatable_items.extend(self.translatable_items[msgid])
all_translatable_items.sort(key=sort_func)
considered_msgids = set()
for translatable_item in all_translatable_items:
if translatable_item['msgid'] in considered_msgids:
continue
considered_msgids.add(translatable_item['msgid'])
occurences = self.translatable_items[translatable_item['msgid']]
occurences.sort(key=sort_func)
for type, type_occurences in itertools.groupby(occurences, key=lambda a: a['type']):
emit_function = EMIT_FUNCTIONS[type]
emit_function(list(type_occurences), lines)
return head + "\n".join(lines)
def gettext(text, filename):
t = Lua_GetText()
t.parse(text, filename)
return str(t)
if __name__ == '__main__':
import sys
t = Lua_GetText()
for fn in sys.argv[1:]:
t.parse(open(fn).read(), fn)
print t
|