forked from itstool/itstool
-
Notifications
You must be signed in to change notification settings - Fork 0
/
itstool.in
executable file
·1648 lines (1542 loc) · 67 KB
/
itstool.in
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
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!@PYTHON@ -s
#
# Copyright (c) 2010-2018 Shaun McCance <shaunm@gnome.org>
#
# ITS Tool 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.
#
# ITS Tool 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 ITS Tool; if not, write to the Free Software Foundation, 59 Temple
# Place, Suite 330, Boston, MA 0211-1307 USA.
#
from __future__ import print_function
from __future__ import unicode_literals
VERSION="@VERSION@"
DATADIR="@DATADIR@"
import gettext
import hashlib
import libxml2
import optparse
import os
import os.path
import re
import sys
import time
import io
PY3 = sys.version_info[0] == 3
if PY3:
string_types = str,
def ustr(s, encoding=None):
if isinstance(s, str):
return s
elif encoding:
return str(s, encoding)
else:
return str(s)
ustr_type = str
else:
string_types = basestring,
ustr = ustr_type = unicode
NS_ITS = 'http://www.w3.org/2005/11/its'
NS_ITST = 'http://itstool.org/extensions/'
NS_BLANK = 'http://itstool.org/extensions/blank/'
NS_XLINK = 'http://www.w3.org/1999/xlink'
NS_XML = 'http://www.w3.org/XML/1998/namespace'
class NoneTranslations:
def gettext(self, message):
return None
def lgettext(self, message):
return None
def ngettext(self, msgid1, msgid2, n):
return None
def lngettext(self, msgid1, msgid2, n):
return None
def ugettext(self, message):
return None
def ungettext(self, msgid1, msgid2, n):
return None
class MessageList (object):
def __init__ (self):
self._messages = []
self._by_node = {}
self._has_credits = False
def add_message (self, message, node):
self._messages.append (message)
if node is not None:
self._by_node[node] = message
def add_credits(self):
if self._has_credits:
return
msg = Message()
msg.set_context('_')
msg.add_text('translator-credits')
msg.add_comment(Comment('Put one translator per line, in the form NAME <EMAIL>, YEAR1, YEAR2'))
self._messages.append(msg)
self._has_credits = True
def get_message_by_node (self, node):
return self._by_node.get(node, None)
def get_nodes_with_messages (self):
return list(self._by_node.keys())
def output (self, out):
msgs = []
msgdict = {}
for msg in self._messages:
key = (msg.get_context(), msg.get_string())
if key in msgdict:
for source in msg.get_sources():
msgdict[key].add_source(source)
for marker in msg.get_markers():
msgdict[key].add_marker(marker)
for comment in msg.get_comments():
msgdict[key].add_comment(comment)
for idvalue in msg.get_id_values():
msgdict[key].add_id_value(idvalue)
if msg.get_preserve_space():
msgdict[key].set_preserve_space()
if msg.get_locale_filter() is not None:
locale = msgdict[key].get_locale_filter()
if locale is not None:
msgdict[key].set_locale_filter('%s, %s' % (locale, msg.get_locale_filter()))
else:
msgdict[key].set_locale_filter(msg.get_locale_filter())
else:
msgs.append(msg)
msgdict[key] = msg
out.write('msgid ""\n')
out.write('msgstr ""\n')
out.write('"Project-Id-Version: PACKAGE VERSION\\n"\n')
out.write('"POT-Creation-Date: %s\\n"\n' % time.strftime("%Y-%m-%d %H:%M%z"))
out.write('"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\\n"\n')
out.write('"Last-Translator: FULL NAME <EMAIL@ADDRESS>\\n"\n')
out.write('"Language-Team: LANGUAGE <LL@li.org>\\n"\n')
out.write('"MIME-Version: 1.0\\n"\n')
out.write('"Content-Type: text/plain; charset=UTF-8\\n"\n')
out.write('"Content-Transfer-Encoding: 8bit\\n"\n')
out.write('\n')
for msg in msgs:
out.write(msg.format())
out.write('\n')
class Comment (object):
def __init__ (self, text):
self._text = ustr(text)
assert(text is not None)
self._markers = []
def add_marker (self, marker):
self._markers.append(marker)
def get_markers (self):
return self._markers
def get_text (self):
return self._text
def format (self):
ret = ''
markers = {}
for marker in self._markers:
if marker not in markers:
ret += '#. (itstool) comment: ' + marker + '\n'
markers[marker] = marker
if '\n' in self._text:
doadd = False
for line in self._text.split('\n'):
if line != '':
doadd = True
if not doadd:
continue
ret += '#. %s\n' % line
else:
text = self._text
while len(text) > 72:
j = text.rfind(' ', 0, 72)
if j == -1:
j = text.find(' ')
if j == -1:
break
ret += '#. %s\n' % text[:j]
text = text[j+1:]
ret += '#. %s\n' % text
return ret
class Placeholder (object):
def __init__ (self, node):
self.node = node
self.name = ustr(node.name, 'utf-8')
class Message (object):
def __init__ (self):
self._message = []
self._empty = True
self._ctxt = None
self._placeholders = []
self._sources = []
self._markers = []
self._id_values = []
self._locale_filter = None
self._comments = []
self._preserve = False
def __repr__(self):
if self._empty:
return "Empty message"
return self.get_string()
def escape (self, text):
return text.replace('\\','\\\\').replace('"', "\\\"").replace("\n","\\n").replace("\t","\\t")
def add_text (self, text):
if len(self._message) == 0 or not(isinstance(self._message[-1], string_types)):
self._message.append('')
if not isinstance(text, ustr_type):
text = ustr(text, 'utf-8')
self._message[-1] += text.replace('&', '&').replace('<', '<').replace('>', '>')
if re.sub('\s+', ' ', text).strip() != '':
self._empty = False
def add_entity_ref (self, name):
self._message.append('&' + name + ';')
self._empty = False
def add_placeholder (self, node):
holder = Placeholder(node)
self._placeholders.append(holder)
self._message.append(holder)
def get_placeholder (self, name):
placeholder = 1
for holder in self._placeholders:
holdername = '%s-%i' % (holder.name, placeholder)
if holdername == ustr(name, 'utf-8'):
return holder
placeholder += 1
def add_start_tag (self, node):
if len(self._message) == 0 or not(isinstance(self._message[-1], string_types)):
self._message.append('')
if node.ns() is not None and node.ns().name is not None:
self._message[-1] += ('<%s:%s' % (ustr(node.ns().name, 'utf-8'), ustr(node.name, 'utf-8')))
else:
self._message[-1] += ('<%s' % ustr(node.name, 'utf-8'))
for prop in xml_attr_iter(node):
name = prop.name
if prop.ns() is not None:
name = prop.ns().name + ':' + name
atval = prop.content
if not isinstance(atval, ustr_type):
atval = ustr(atval, 'utf-8')
atval = atval.replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"')
self._message += " %s=\"%s\"" % (name, atval)
if node.children is not None:
self._message[-1] += '>'
else:
self._message[-1] += '/>'
def add_end_tag (self, node):
if node.children is not None:
if len(self._message) == 0 or not(isinstance(self._message[-1], string_types)):
self._message.append('')
if node.ns() is not None and node.ns().name is not None:
self._message[-1] += ('</%s:%s>' % (ustr(node.ns().name, 'utf-8'), ustr(node.name, 'utf-8')))
else:
self._message[-1] += ('</%s>' % ustr(node.name, 'utf-8'))
def is_empty (self):
return self._empty
def get_context (self):
return self._ctxt
def set_context (self, ctxt):
self._ctxt = ctxt
def add_source (self, source):
if not isinstance(source, ustr_type):
source = ustr(source, 'utf-8')
self._sources.append(source)
def get_sources (self):
return self._sources
def add_marker (self, marker):
if not isinstance(marker, ustr_type):
marker = ustr(marker, 'utf-8')
self._markers.append(marker)
def get_markers (self):
return self._markers
def add_id_value(self, id_value):
self._id_values.append(id_value)
def get_id_values(self):
return self._id_values
def add_comment (self, comment):
if comment is not None:
self._comments.append(comment)
def get_comments (self):
return self._comments
def get_string (self):
message = ''
placeholder = 1
for msg in self._message:
if isinstance(msg, string_types):
message += msg
elif isinstance(msg, Placeholder):
message += '<_:%s-%i/>' % (msg.name, placeholder)
placeholder += 1
if not self._preserve:
message = re.sub('\s+', ' ', message).strip()
return message
def get_preserve_space (self):
return self._preserve
def set_preserve_space (self, preserve=True):
self._preserve = preserve
def get_locale_filter(self):
return self._locale_filter
def set_locale_filter(self, locale):
self._locale_filter = locale
def format (self):
ret = ''
markers = {}
for marker in self._markers:
if marker not in markers:
ret += '#. (itstool) path: ' + marker + '\n'
markers[marker] = marker
for idvalue in self._id_values:
ret += '#. (itstool) id: ' + idvalue + '\n'
if self._locale_filter is not None:
ret += '#. (itstool) ' + self._locale_filter[1] + ' locale: ' + self._locale_filter[0] + '\n'
comments = []
commentsdict = {}
for comment in self._comments:
key = comment.get_text()
if key in commentsdict:
for marker in comment.get_markers():
commentsdict[key].add_marker(marker)
else:
comments.append(comment)
commentsdict[key] = comment
for i in range(len(comments)):
if i != 0:
ret += '#.\n'
ret += comments[i].format()
for source in self._sources:
ret += '#: %s\n' % source
if self._preserve:
ret += '#, no-wrap\n'
if self._ctxt is not None:
ret += 'msgctxt "%s"\n' % self._ctxt
message = self.get_string()
if self._preserve:
ret += 'msgid ""\n'
lines = message.split('\n')
for line, no in zip(lines, list(range(len(lines)))):
if no == len(lines) - 1:
ret += '"%s"\n' % self.escape(line)
else:
ret += '"%s\\n"\n' % self.escape(line)
else:
ret += 'msgid "%s"\n' % self.escape(message)
ret += 'msgstr ""\n'
return ret
def xml_child_iter (node):
child = node.children
while child is not None:
yield child
child = child.next
def xml_attr_iter (node):
attr = node.get_properties()
while attr is not None:
yield attr
attr = attr.next
def xml_is_ns_name (node, ns, name):
if node.type != 'element':
return False
return node.name == name and node.ns() is not None and node.ns().content == ns
def xml_get_node_path(node):
# The built-in nodePath() method only does numeric indexes
# when necessary for disambiguation. For various reasons,
# we prefer always using indexes.
name = node.name
if node.ns() is not None and node.ns().name is not None:
name = node.ns().name + ':' + name
if node.type == 'attribute':
name = '@' + name
name = '/' + name
if node.type == 'element' and node.parent.type == 'element':
count = 1
prev = node.previousElementSibling()
while prev is not None:
if prev.name == node.name:
if prev.ns() is None:
if node.ns() is None:
count += 1
else:
if node.ns() is not None:
if prev.ns().name == node.ns().name:
count += 1
prev = prev.previousElementSibling()
name = '%s[%i]' % (name, count)
if node.parent.type == 'element':
name = xml_get_node_path(node.parent) + name
return name
def xml_error_catcher(doc, error):
doc._xml_err += " %s" % error
def fix_node_ns (node, nsdefs):
childnsdefs = nsdefs.copy()
nsdef = node.nsDefs()
while nsdef is not None:
nextnsdef = nsdef.next
if nsdef.name in nsdefs and nsdefs[nsdef.name] == nsdef.content:
node.removeNsDef(nsdef.content)
else:
childnsdefs[nsdef.name] = nsdef.content
nsdef = nextnsdef
for child in xml_child_iter(node):
if child.type == 'element':
fix_node_ns(child, childnsdefs)
class LocNote (object):
def __init__(self, locnote=None, locnoteref=None, locnotetype=None, space=False):
self.locnote = locnote
self.locnoteref = locnoteref
self.locnotetype = locnotetype
if self.locnotetype != 'alert':
self.locnotetype = 'description'
self._preserve_space=space
def __repr__(self):
if self.locnote is not None:
if self._preserve_space:
return self.locnote
else:
return re.sub('\s+', ' ', self.locnote).strip()
elif self.locnoteref is not None:
return '(itstool) link: ' + re.sub('\s+', ' ', self.locnoteref).strip()
return ''
class Document (object):
def __init__ (self, filename, messages, load_dtd=False, keep_entities=False):
self._xml_err = ''
libxml2.registerErrorHandler(xml_error_catcher, self)
try:
ctxt = libxml2.createFileParserCtxt(filename)
except:
sys.stderr.write('Error: cannot open XML file %s\n' % filename)
sys.exit(1)
ctxt.lineNumbers(1)
self._load_dtd = load_dtd
self._keep_entities = keep_entities
if load_dtd:
ctxt.loadSubset(1)
if keep_entities:
ctxt.loadSubset(1)
ctxt.ctxtUseOptions(libxml2.XML_PARSE_DTDLOAD)
ctxt.replaceEntities(0)
else:
ctxt.replaceEntities(1)
ctxt.parseDocument()
self._filename = filename
self._doc = ctxt.doc()
self._localrules = []
def pre_process (node):
for child in xml_child_iter(node):
if xml_is_ns_name(child, 'http://www.w3.org/2001/XInclude', 'include'):
if child.nsProp('parse', None) == 'text':
child.xincludeProcessTree()
elif xml_is_ns_name(child, NS_ITS, 'rules'):
if child.hasNsProp('href', NS_XLINK):
href = child.nsProp('href', NS_XLINK)
fileref = os.path.join(os.path.dirname(filename), href)
if not os.path.exists(fileref):
if opts.itspath is not None:
for pathdir in opts.itspath:
fileref = os.path.join(pathdir, href)
if os.path.exists(fileref):
break
if not os.path.exists(fileref):
sys.stderr.write('Error: Could not locate ITS file %s\n' % href)
sys.exit(1)
hctxt = libxml2.createFileParserCtxt(fileref)
hctxt.replaceEntities(1)
hctxt.parseDocument()
root = hctxt.doc().getRootElement()
version = None
if root.hasNsProp('version', None):
version = root.nsProp('version', None)
else:
sys.stderr.write('Warning: ITS file %s missing version attribute\n' %
os.path.basename(href))
if version is not None and version not in ('1.0', '2.0'):
sys.stderr.write('Warning: Skipping ITS file %s with unknown version %s\n' %
(os.path.basename(href), root.nsProp('version', None)))
else:
self._localrules.append(root)
version = None
if child.hasNsProp('version', None):
version = child.nsProp('version', None)
else:
root = child.doc.getRootElement()
if root.hasNsProp('version', NS_ITS):
version = root.nsProp('version', NS_ITS)
else:
sys.stderr.write('Warning: Local ITS rules missing version attribute\n')
if version is not None and version not in ('1.0', '2.0'):
sys.stderr.write('Warning: Skipping local ITS rules with unknown version %s\n' %
version)
else:
self._localrules.append(child)
pre_process(child)
pre_process(self._doc)
try:
self._check_errors()
except libxml2.parserError as e:
sys.stderr.write('Error: Could not parse document:\n%s\n' % ustr(e))
sys.exit(1)
self._msgs = messages
self._its_translate_nodes = {}
self._its_within_text_nodes = {}
self._its_locale_filters = {}
self._its_id_values = {}
self._its_loc_notes = {}
self._its_preserve_space_nodes = {}
self._itst_drop_nodes = {}
self._itst_contexts = {}
self._its_lang = {}
self._itst_lang_attr = {}
self._itst_credits = None
self._its_externals = {}
def __del__ (self):
self._doc.freeDoc()
def _check_errors(self):
if self._xml_err:
raise libxml2.parserError(self._xml_err)
def register_its_params(self, xpath, rules, params={}):
for child in xml_child_iter(rules):
if xml_is_ns_name(child, NS_ITS, 'param'):
name = child.nsProp('name', None)
if name in params:
value = params[name]
else:
value = child.getContent()
xpath.xpathRegisterVariable(name, None, value)
def apply_its_rule(self, rule, xpath):
if rule.type != 'element':
return
if xml_is_ns_name(rule, NS_ITS, 'translateRule'):
if rule.nsProp('selector', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
self._its_translate_nodes[node] = rule.nsProp('translate', None)
elif xml_is_ns_name(rule, NS_ITS, 'withinTextRule'):
if rule.nsProp('selector', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
self._its_within_text_nodes[node] = rule.nsProp('withinText', None)
elif xml_is_ns_name(rule, NS_ITST, 'preserveSpaceRule'):
if rule.nsProp('selector', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
val = rule.nsProp('preserveSpace', None)
if val == 'yes':
self._its_preserve_space_nodes[node] = 'preserve'
elif xml_is_ns_name(rule, NS_ITS, 'preserveSpaceRule'):
if rule.nsProp('selector', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
self._its_preserve_space_nodes[node] = rule.nsProp('space', None)
elif xml_is_ns_name(rule, NS_ITS, 'localeFilterRule'):
if rule.nsProp('selector', None) is not None:
if rule.hasNsProp('localeFilterList', None):
lst = rule.nsProp('localeFilterList', None)
else:
lst = '*'
if rule.hasNsProp('localeFilterType', None):
typ = rule.nsProp('localeFilterType', None)
else:
typ = 'include'
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
self._its_locale_filters[node] = (lst, typ)
elif xml_is_ns_name(rule, NS_ITST, 'dropRule'):
if rule.nsProp('selector', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
self._itst_drop_nodes[node] = rule.nsProp('drop', None)
elif xml_is_ns_name(rule, NS_ITS, 'idValueRule'):
sel = rule.nsProp('selector', None)
idv = rule.nsProp('idValue', None)
if sel is not None and idv is not None:
for node in self._try_xpath_eval(xpath, sel):
try:
oldnode = xpath.contextNode()
except:
oldnode = None
xpath.setContextNode(node)
idvalue = self._try_xpath_eval(xpath, idv)
if isinstance(idvalue, string_types):
self._its_id_values[node] = idvalue
else:
for val in idvalue:
self._its_id_values[node] = val.content
break
xpath.setContextNode(oldnode)
pass
elif xml_is_ns_name(rule, NS_ITST, 'contextRule'):
if rule.nsProp('selector', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
if rule.hasNsProp('context', None):
self._itst_contexts[node] = rule.nsProp('context', None)
elif rule.hasNsProp('contextPointer', None):
try:
oldnode = xpath.contextNode()
except:
oldnode = None
xpath.setContextNode(node)
ctxt = self._try_xpath_eval(xpath, rule.nsProp('contextPointer', None))
if isinstance(ctxt, string_types):
self._itst_contexts[node] = ctxt
else:
for ctxt in ctxt:
self._itst_contexts[node] = ctxt.content
break
xpath.setContextNode(oldnode)
elif xml_is_ns_name(rule, NS_ITS, 'locNoteRule'):
locnote = None
notetype = rule.nsProp('locNoteType', None)
for child in xml_child_iter(rule):
if xml_is_ns_name(child, NS_ITS, 'locNote'):
locnote = LocNote(locnote=child.content, locnotetype=notetype)
break
if locnote is None:
if rule.hasNsProp('locNoteRef', None):
locnote = LocNote(locnoteref=rule.nsProp('locNoteRef', None), locnotetype=notetype)
if rule.nsProp('selector', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
if locnote is not None:
self._its_loc_notes.setdefault(node, []).append(locnote)
else:
if rule.hasNsProp('locNotePointer', None):
sel = rule.nsProp('locNotePointer', None)
ref = False
elif rule.hasNsProp('locNoteRefPointer', None):
sel = rule.nsProp('locNoteRefPointer', None)
ref = True
else:
continue
try:
oldnode = xpath.contextNode()
except:
oldnode = None
xpath.setContextNode(node)
note = self._try_xpath_eval(xpath, sel)
if isinstance(note, string_types):
if ref:
nodenote = LocNote(locnoteref=note, locnotetype=notetype)
else:
nodenote = LocNote(locnote=note, locnotetype=notetype)
self._its_loc_notes.setdefault(node, []).append(nodenote)
else:
for note in note:
if ref:
nodenote = LocNote(locnoteref=note.content, locnotetype=notetype)
else:
nodenote = LocNote(locnote=note.content, locnotetype=notetype,
space=self.get_preserve_space(note))
self._its_loc_notes.setdefault(node, []).append(nodenote)
break
xpath.setContextNode(oldnode)
elif xml_is_ns_name(rule, NS_ITS, 'langRule'):
if rule.nsProp('selector', None) is not None and rule.nsProp('langPointer', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('selector', None)):
try:
oldnode = xpath.contextNode()
except:
oldnode = None
xpath.setContextNode(node)
res = self._try_xpath_eval(xpath, rule.nsProp('langPointer', None))
if len(res) > 0:
self._its_lang[node] = res[0].content
# We need to construct language attributes, not just read
# language information. Technically, langPointer could be
# any XPath expression. But if it looks like an attribute
# accessor, just use the attribute name.
if rule.nsProp('langPointer', None)[0] == '@':
self._itst_lang_attr[node] = rule.nsProp('langPointer', None)[1:]
xpath.setContextNode(oldnode)
elif xml_is_ns_name(rule, NS_ITST, 'credits'):
if rule.nsProp('appendTo', None) is not None:
for node in self._try_xpath_eval(xpath, rule.nsProp('appendTo', None)):
self._itst_credits = (node, rule)
break
elif (xml_is_ns_name(rule, NS_ITS, 'externalResourceRefRule') or
xml_is_ns_name(rule, NS_ITST, 'externalRefRule')):
sel = rule.nsProp('selector', None)
if xml_is_ns_name(rule, NS_ITS, 'externalResourceRefRule'):
ptr = rule.nsProp('externalResourceRefPointer', None)
else:
ptr = rule.nsProp('refPointer', None)
if sel is not None and ptr is not None:
for node in self._try_xpath_eval(xpath, sel):
try:
oldnode = xpath.contextNode()
except:
oldnode = None
xpath.setContextNode(node)
res = self._try_xpath_eval(xpath, ptr)
if len(res) > 0:
self._its_externals[node] = res[0].content
xpath.setContextNode(oldnode)
def apply_its_rules(self, builtins, params={}):
if builtins:
dirs = []
ddir = os.getenv('XDG_DATA_HOME', '')
if ddir == '':
ddir = os.path.join(os.path.expanduser('~'), '.local', 'share')
dirs.append(ddir)
ddir = os.getenv('XDG_DATA_DIRS', '')
if ddir == '':
if DATADIR not in ('/usr/local/share', '/usr/share'):
ddir += DATADIR + ':'
ddir += '/usr/local/share:/usr/share'
dirs.extend(ddir.split(':'))
ddone = {}
for ddir in dirs:
itsdir = os.path.join(ddir, 'itstool', 'its')
if not os.path.exists(itsdir):
continue
for dfile in os.listdir(itsdir):
if dfile.endswith('.its'):
if not ddone.get(dfile, False):
self.apply_its_file(os.path.join(itsdir, dfile), params=params)
ddone[dfile] = True
self.apply_local_its_rules(params=params)
def apply_its_file(self, filename, params={}):
doc = libxml2.parseFile(filename)
root = doc.getRootElement()
if not xml_is_ns_name(root, NS_ITS, 'rules'):
return
version = None
if root.hasNsProp('version', None):
version = root.nsProp('version', None)
else:
sys.stderr.write('Warning: ITS file %s missing version attribute\n' %
os.path.basename(filename))
if version is not None and version not in ('1.0', '2.0'):
sys.stderr.write('Warning: Skipping ITS file %s with unknown version %s\n' %
(os.path.basename(filename), root.nsProp('version', None)))
return
matched = True
for match in xml_child_iter(root):
if xml_is_ns_name(match, NS_ITST, 'match'):
matched = False
xpath = self._doc.xpathNewContext()
par = match
nss = {}
while par is not None:
nsdef = par.nsDefs()
while nsdef is not None:
if nsdef.name is not None:
if nsdef.name not in nss:
nss[nsdef.name] = nsdef.content
xpath.xpathRegisterNs(nsdef.name, nsdef.content)
nsdef = nsdef.next
par = par.parent
if match.hasNsProp('selector', None):
if len(self._try_xpath_eval(xpath, match.nsProp('selector', None))) > 0:
matched = True
break
if matched == False:
return
for rule in xml_child_iter(root):
xpath = self._doc.xpathNewContext()
par = match
nss = {}
while par is not None:
nsdef = par.nsDefs()
while nsdef is not None:
if nsdef.name is not None:
if nsdef.name not in nss:
nss[nsdef.name] = nsdef.content
xpath.xpathRegisterNs(nsdef.name, nsdef.content)
nsdef = nsdef.next
par = par.parent
self.register_its_params(xpath, root, params=params)
self.apply_its_rule(rule, xpath)
def apply_local_its_rules(self, params={}):
for rules in self._localrules:
def reg_ns(xpath, node):
if node.parent is not None:
reg_ns(xpath, node.parent)
nsdef = node.nsDefs()
while nsdef is not None:
if nsdef.name is not None:
xpath.xpathRegisterNs(nsdef.name, nsdef.content)
nsdef = nsdef.next
xpath = self._doc.xpathNewContext()
reg_ns(xpath, rules)
self.register_its_params(xpath, rules, params=params)
for rule in xml_child_iter(rules):
if rule.type != 'element':
continue
if rule.nsDefs() is not None:
rule_xpath = self._doc.xpathNewContext()
reg_ns(rule_xpath, rule)
self.register_its_params(rule_xpath, rules, params=params)
else:
rule_xpath = xpath
self.apply_its_rule(rule, rule_xpath)
def _append_credits(self, parent, node, trdata):
if xml_is_ns_name(node, NS_ITST, 'for-each'):
select = node.nsProp('select', None)
if select == 'years':
for year in trdata[2].split(','):
for child in xml_child_iter(node):
self._append_credits(parent, child, trdata + (year.strip(),))
elif xml_is_ns_name(node, NS_ITST, 'value-of'):
select = node.nsProp('select', None)
val = None
if select == 'name':
val = trdata[0]
elif select == 'email':
val = trdata[1]
elif select == 'years':
val = trdata[2]
elif select == 'year' and len(trdata) == 4:
val = trdata[3]
if val is not None:
if not PY3:
val = val.encode('utf-8')
parent.addContent(val)
else:
newnode = node.copyNode(2)
parent.addChild(newnode)
for child in xml_child_iter(node):
self._append_credits(newnode, child, trdata)
def merge_credits(self, translations, language, node):
if self._itst_credits is None:
return
# Dear Python, please implement pgettext.
# http://bugs.python.org/issue2504
# Sincerely, Shaun
trans = translations.ugettext('_\x04translator-credits')
if trans is None or trans == 'translator-credits':
return
regex = re.compile('(.*) \<(.*)\>, (.*)')
for credit in trans.split('\n'):
match = regex.match(credit)
if not match:
continue
trdata = match.groups()
for node in xml_child_iter(self._itst_credits[1]):
self._append_credits(self._itst_credits[0], node, trdata)
def join_translations(self, translations, node=None, strict=False):
is_root = False
if node is None:
is_root = True
self.generate_messages(comments=False)
node = self._doc.getRootElement()
if node is None or node.type != 'element':
return
if self.get_itst_drop(node) == 'yes':
prev = node.prev
node.unlinkNode()
node.freeNode()
if prev is not None and prev.isBlankNode():
prev.unlinkNode()
prev.freeNode()
return
msg = self._msgs.get_message_by_node(node)
if msg is None:
self.translate_attrs(node, node)
children = [child for child in xml_child_iter(node)]
for child in children:
self.join_translations(translations, node=child, strict=strict)
else:
prevnode = None
if node.prev is not None and node.prev.type == 'text':
prevtext = node.prev.content
if re.sub('\s+', '', prevtext) == '':
prevnode = node.prev
for lang in sorted(list(translations.keys()), reverse=True):
locale = self.get_its_locale_filter(node)
lmatch = match_locale_list(locale[0], lang)
if (locale[1] == 'include' and not lmatch) or (locale[1] == 'exclude' and lmatch):
continue
newnode = self.get_translated(node, translations[lang], strict=strict, lang=lang)
if newnode != node:
newnode.setProp('xml:lang', lang)
node.addNextSibling(newnode)
if prevnode is not None:
node.addNextSibling(prevnode.copyNode(0))
if is_root:
# Because of the way we create nodes and rewrite the document,
# we end up with lots of redundant namespace definitions. We
# kill them off in one fell swoop at the end.
fix_node_ns(node, {})
self._check_errors()
def merge_translations(self, translations, language, node=None, strict=False):
is_root = False
if node is None:
is_root = True
self.generate_messages(comments=False)
node = self._doc.getRootElement()
if node is None or node.type != 'element':
return
drop = False
locale = self.get_its_locale_filter(node)
if locale[1] == 'include':
if locale[0] != '*':
if not match_locale_list(locale[0], language):
drop = True
elif locale[1] == 'exclude':
if match_locale_list(locale[0], language):
drop = True
if self.get_itst_drop(node) == 'yes' or drop:
prev = node.prev
node.unlinkNode()
node.freeNode()
if prev is not None and prev.isBlankNode():
prev.unlinkNode()
prev.freeNode()
return
if is_root:
self.merge_credits(translations, language, node)
msg = self._msgs.get_message_by_node(node)
if msg is None:
self.translate_attrs(node, node)
children = [child for child in xml_child_iter(node)]
for child in children:
self.merge_translations(translations, language, node=child, strict=strict)
else:
newnode = self.get_translated(node, translations, strict=strict, lang=language)
if newnode != node:
self.translate_attrs(node, newnode)
node.replaceNode(newnode)
if is_root:
# Apply language attributes to untranslated nodes. We don't do
# this before processing, because then these attributes would
# be copied into the new nodes. We apply the attribute without
# checking whether it was translated, because any that were will
# just be floating around, unattached to a document.
for lcnode in self._msgs.get_nodes_with_messages():
attr = self._itst_lang_attr.get(lcnode)
if attr is None:
continue
origlang = None
lcpar = lcnode
while lcpar is not None:
origlang = self._its_lang.get(lcpar)
if origlang is not None:
break
lcpar = lcpar.parent
if origlang is not None:
lcnode.setProp(attr, origlang)
# And then set the language attribute on the root node.
if language is not None:
attr = self._itst_lang_attr.get(node)
if attr is not None:
node.setProp(attr, language)
# Because of the way we create nodes and rewrite the document,
# we end up with lots of redundant namespace definitions. We
# kill them off in one fell swoop at the end.
fix_node_ns(node, {})
self._check_errors()
def translate_attrs(self, oldnode, newnode):
trans_attrs = [attr for attr in xml_attr_iter(oldnode) if self._its_translate_nodes.get(attr, 'no') == 'yes']
for attr in trans_attrs: