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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
|
#!/usr/bin/env python3
"""Generator of the mapping from OpenType tags to BCP 47 tags and vice
versa.
It creates a ``const LangTag[]``, matching the tags from the OpenType
languages system tag list to the language subtags of the BCP 47 language
subtag registry, with some manual adjustments. The mappings are
supplemented with macrolanguages' sublanguages and retired codes'
replacements, according to BCP 47 and some manual additions where BCP 47
omits a retired code entirely.
Also generated is a function, ``hb_ot_ambiguous_tag_to_language``,
intended for use by ``hb_ot_tag_to_language``. It maps OpenType tags
back to BCP 47 tags. Ambiguous OpenType tags (those that correspond to
multiple BCP 47 tags) are listed here, except when the alphabetically
first BCP 47 tag happens to be the chosen disambiguated tag. In that
case, the fallback behavior will choose the right tag anyway.
usage: ./gen-tag-table.py languagetags language-subtag-registry
Input files:
* https://docs.microsoft.com/en-us/typography/opentype/spec/languagetags
* https://www.iana.org/assignments/language-subtag-registry/language-subtag-registry
"""
import collections
import html
from html.parser import HTMLParser
import itertools
import re
import sys
import unicodedata
if len (sys.argv) != 3:
sys.exit (__doc__)
def expect (condition, message=None):
if not condition:
if message is None:
raise AssertionError
raise AssertionError (message)
def write (s):
sys.stdout.flush ()
sys.stdout.buffer.write (s.encode ('utf-8'))
DEFAULT_LANGUAGE_SYSTEM = ''
# from https://www-01.sil.org/iso639-3/iso-639-3.tab
ISO_639_3_TO_1 = {
'aar': 'aa',
'abk': 'ab',
'afr': 'af',
'aka': 'ak',
'amh': 'am',
'ara': 'ar',
'arg': 'an',
'asm': 'as',
'ava': 'av',
'ave': 'ae',
'aym': 'ay',
'aze': 'az',
'bak': 'ba',
'bam': 'bm',
'bel': 'be',
'ben': 'bn',
'bis': 'bi',
'bod': 'bo',
'bos': 'bs',
'bre': 'br',
'bul': 'bg',
'cat': 'ca',
'ces': 'cs',
'cha': 'ch',
'che': 'ce',
'chu': 'cu',
'chv': 'cv',
'cor': 'kw',
'cos': 'co',
'cre': 'cr',
'cym': 'cy',
'dan': 'da',
'deu': 'de',
'div': 'dv',
'dzo': 'dz',
'ell': 'el',
'eng': 'en',
'epo': 'eo',
'est': 'et',
'eus': 'eu',
'ewe': 'ee',
'fao': 'fo',
'fas': 'fa',
'fij': 'fj',
'fin': 'fi',
'fra': 'fr',
'fry': 'fy',
'ful': 'ff',
'gla': 'gd',
'gle': 'ga',
'glg': 'gl',
'glv': 'gv',
'grn': 'gn',
'guj': 'gu',
'hat': 'ht',
'hau': 'ha',
'hbs': 'sh',
'heb': 'he',
'her': 'hz',
'hin': 'hi',
'hmo': 'ho',
'hrv': 'hr',
'hun': 'hu',
'hye': 'hy',
'ibo': 'ig',
'ido': 'io',
'iii': 'ii',
'iku': 'iu',
'ile': 'ie',
'ina': 'ia',
'ind': 'id',
'ipk': 'ik',
'isl': 'is',
'ita': 'it',
'jav': 'jv',
'jpn': 'ja',
'kal': 'kl',
'kan': 'kn',
'kas': 'ks',
'kat': 'ka',
'kau': 'kr',
'kaz': 'kk',
'khm': 'km',
'kik': 'ki',
'kin': 'rw',
'kir': 'ky',
'kom': 'kv',
'kon': 'kg',
'kor': 'ko',
'kua': 'kj',
'kur': 'ku',
'lao': 'lo',
'lat': 'la',
'lav': 'lv',
'lim': 'li',
'lin': 'ln',
'lit': 'lt',
'ltz': 'lb',
'lub': 'lu',
'lug': 'lg',
'mah': 'mh',
'mal': 'ml',
'mar': 'mr',
'mkd': 'mk',
'mlg': 'mg',
'mlt': 'mt',
'mol': 'mo',
'mon': 'mn',
'mri': 'mi',
'msa': 'ms',
'mya': 'my',
'nau': 'na',
'nav': 'nv',
'nbl': 'nr',
'nde': 'nd',
'ndo': 'ng',
'nep': 'ne',
'nld': 'nl',
'nno': 'nn',
'nob': 'nb',
'nor': 'no',
'nya': 'ny',
'oci': 'oc',
'oji': 'oj',
'ori': 'or',
'orm': 'om',
'oss': 'os',
'pan': 'pa',
'pli': 'pi',
'pol': 'pl',
'por': 'pt',
'pus': 'ps',
'que': 'qu',
'roh': 'rm',
'ron': 'ro',
'run': 'rn',
'rus': 'ru',
'sag': 'sg',
'san': 'sa',
'sin': 'si',
'slk': 'sk',
'slv': 'sl',
'sme': 'se',
'smo': 'sm',
'sna': 'sn',
'snd': 'sd',
'som': 'so',
'sot': 'st',
'spa': 'es',
'sqi': 'sq',
'srd': 'sc',
'srp': 'sr',
'ssw': 'ss',
'sun': 'su',
'swa': 'sw',
'swe': 'sv',
'tah': 'ty',
'tam': 'ta',
'tat': 'tt',
'tel': 'te',
'tgk': 'tg',
'tgl': 'tl',
'tha': 'th',
'tir': 'ti',
'ton': 'to',
'tsn': 'tn',
'tso': 'ts',
'tuk': 'tk',
'tur': 'tr',
'twi': 'tw',
'uig': 'ug',
'ukr': 'uk',
'urd': 'ur',
'uzb': 'uz',
'ven': 've',
'vie': 'vi',
'vol': 'vo',
'wln': 'wa',
'wol': 'wo',
'xho': 'xh',
'yid': 'yi',
'yor': 'yo',
'zha': 'za',
'zho': 'zh',
'zul': 'zu',
}
class LanguageTag (object):
"""A BCP 47 language tag.
Attributes:
subtags (List[str]): The list of subtags in this tag.
grandfathered (bool): Whether this tag is grandfathered. If
``true``, the entire lowercased tag is the ``language``
and the other subtag fields are empty.
language (str): The language subtag.
script (str): The script subtag.
region (str): The region subtag.
variant (str): The variant subtag.
Args:
tag (str): A BCP 47 language tag.
"""
def __init__ (self, tag):
global bcp_47
self.subtags = tag.lower ().split ('-')
self.grandfathered = tag.lower () in bcp_47.grandfathered
if self.grandfathered:
self.language = tag.lower ()
self.script = ''
self.region = ''
self.variant = ''
else:
self.language = self.subtags[0]
self.script = self._find_first (lambda s: len (s) == 4 and s[0] > '9', self.subtags)
self.region = self._find_first (lambda s: len (s) == 2 and s[0] > '9' or len (s) == 3 and s[0] <= '9', self.subtags[1:])
self.variant = self._find_first (lambda s: len (s) > 4 or len (s) == 4 and s[0] <= '9', self.subtags)
def __str__(self):
return '-'.join(self.subtags)
def __repr__ (self):
return 'LanguageTag(%r)' % str(self)
@staticmethod
def _find_first (function, sequence):
try:
return next (iter (filter (function, sequence)))
except StopIteration:
return None
def is_complex (self):
"""Return whether this tag is too complex to represent as a
``LangTag`` in the generated code.
Complex tags need to be handled in
``hb_ot_tags_from_complex_language``.
Returns:
Whether this tag is complex.
"""
return not (len (self.subtags) == 1
or self.grandfathered
and len (self.subtags[1]) != 3
and ot.from_bcp_47[self.subtags[0]] == ot.from_bcp_47[self.language])
def get_group (self):
"""Return the group into which this tag should be categorized in
``hb_ot_tags_from_complex_language``.
The group is the first letter of the tag, or ``'und'`` if this tag
should not be matched in a ``switch`` statement in the generated
code.
Returns:
This tag's group.
"""
return ('und'
if (self.language == 'und'
or self.variant in bcp_47.prefixes and len (bcp_47.prefixes[self.variant]) == 1)
else self.language[0])
class OpenTypeRegistryParser (HTMLParser):
"""A parser for the OpenType language system tag registry.
Attributes:
header (str): The "last updated" line of the registry.
names (Mapping[str, str]): A map of language system tags to the
names they are given in the registry.
ranks (DefaultDict[str, int]): A map of language system tags to
numbers. If a single BCP 47 tag corresponds to multiple
OpenType tags, the tags are ordered in increasing order by
rank. The rank is based on the number of BCP 47 tags
associated with a tag, though it may be manually modified.
to_bcp_47 (DefaultDict[str, AbstractSet[str]]): A map of
OpenType language system tags to sets of BCP 47 tags.
from_bcp_47 (DefaultDict[str, AbstractSet[str]]): ``to_bcp_47``
inverted. Its values start as unsorted sets;
``sort_languages`` converts them to sorted lists.
from_bcp_47_uninherited (Optional[Dict[str, AbstractSet[str]]]):
A copy of ``from_bcp_47``. It starts as ``None`` and is
populated at the beginning of the first call to
``inherit_from_macrolanguages``.
"""
def __init__ (self):
HTMLParser.__init__ (self)
self.header = ''
self.names = {}
self.ranks = collections.defaultdict (int)
self.to_bcp_47 = collections.defaultdict (set)
self.from_bcp_47 = collections.defaultdict (set)
self.from_bcp_47_uninherited = None
# Whether the parser is in a <td> element
self._td = False
# Whether the parser is after a <br> element within the current <tr> element
self._br = False
# The text of the <td> elements of the current <tr> element.
self._current_tr = []
def handle_starttag (self, tag, attrs):
if tag == 'br':
self._br = True
elif tag == 'meta':
for attr, value in attrs:
if attr == 'name' and value == 'updated_at':
self.header = self.get_starttag_text ()
break
elif tag == 'td':
self._td = True
self._current_tr.append ('')
elif tag == 'tr':
self._br = False
self._current_tr = []
def handle_endtag (self, tag):
if tag == 'td':
self._td = False
elif tag == 'tr' and self._current_tr:
expect (2 <= len (self._current_tr) <= 3)
name = self._current_tr[0].strip ()
tag = self._current_tr[1].strip ("\t\n\v\f\r '")
rank = 0
if len (tag) > 4:
expect (tag.endswith (' (deprecated)'), 'ill-formed OpenType tag: %s' % tag)
name += ' (deprecated)'
tag = tag.split (' ')[0]
rank = 1
self.names[tag] = re.sub (' languages$', '', name)
if not self._current_tr[2]:
return
iso_codes = self._current_tr[2].strip ()
self.to_bcp_47[tag].update (ISO_639_3_TO_1.get (code, code) for code in iso_codes.replace (' ', '').split (','))
rank += 2 * len (self.to_bcp_47[tag])
self.ranks[tag] = rank
def handle_data (self, data):
if self._td and not self._br:
self._current_tr[-1] += data
def handle_charref (self, name):
self.handle_data (html.unescape ('&#%s;' % name))
def handle_entityref (self, name):
self.handle_data (html.unescape ('&%s;' % name))
def parse (self, filename):
"""Parse the OpenType language system tag registry.
Args:
filename (str): The file name of the registry.
"""
with open (filename, encoding='utf-8') as f:
self.feed (f.read ())
expect (self.header)
for tag, iso_codes in self.to_bcp_47.items ():
for iso_code in iso_codes:
self.from_bcp_47[iso_code].add (tag)
def add_language (self, bcp_47_tag, ot_tag):
"""Add a language as if it were in the registry.
Args:
bcp_47_tag (str): A BCP 47 tag. If the tag is more than just
a language subtag, and if the language subtag is a
macrolanguage, then new languages are added corresponding
to the macrolanguages' individual languages with the
remainder of the tag appended.
ot_tag (str): An OpenType language system tag.
"""
global bcp_47
self.to_bcp_47[ot_tag].add (bcp_47_tag)
self.from_bcp_47[bcp_47_tag].add (ot_tag)
if bcp_47_tag.lower () not in bcp_47.grandfathered:
try:
[macrolanguage, suffix] = bcp_47_tag.split ('-', 1)
if macrolanguage in bcp_47.macrolanguages:
s = set ()
for language in bcp_47.macrolanguages[macrolanguage]:
if language.lower () not in bcp_47.grandfathered:
s.add ('%s-%s' % (language, suffix))
bcp_47.macrolanguages['%s-%s' % (macrolanguage, suffix)] = s
except ValueError:
pass
@staticmethod
def _remove_language (tag_1, dict_1, dict_2):
for tag_2 in dict_1.pop (tag_1):
dict_2[tag_2].remove (tag_1)
if not dict_2[tag_2]:
del dict_2[tag_2]
def remove_language_ot (self, ot_tag):
"""Remove an OpenType tag from the registry.
Args:
ot_tag (str): An OpenType tag.
"""
self._remove_language (ot_tag, self.to_bcp_47, self.from_bcp_47)
def remove_language_bcp_47 (self, bcp_47_tag):
"""Remove a BCP 47 tag from the registry.
Args:
bcp_47_tag (str): A BCP 47 tag.
"""
self._remove_language (bcp_47_tag, self.from_bcp_47, self.to_bcp_47)
def inherit_from_macrolanguages (self):
"""Copy mappings from macrolanguages to individual languages.
If a BCP 47 tag for an individual mapping has no OpenType
mapping but its macrolanguage does, the mapping is copied to
the individual language. For example, als (Tosk Albanian) has no
explicit mapping, so it inherits from sq (Albanian) the mapping
to SQI.
However, if an OpenType tag maps to a BCP 47 macrolanguage and
some but not all of its individual languages, the mapping is not
inherited from the macrolanguage to the missing individual
languages. For example, INUK (Nunavik Inuktitut) is mapped to
ike (Eastern Canadian Inuktitut) and iu (Inuktitut) but not to
ikt (Inuinnaqtun, which is an individual language of iu), so
this method does not add a mapping from ikt to INUK.
If a BCP 47 tag for a macrolanguage has no OpenType mapping but
some of its individual languages do, their mappings are copied
to the macrolanguage.
"""
global bcp_47
first_time = self.from_bcp_47_uninherited is None
if first_time:
self.from_bcp_47_uninherited = dict (self.from_bcp_47)
for macrolanguage, languages in dict (bcp_47.macrolanguages).items ():
ot_macrolanguages = {
ot_macrolanguage for ot_macrolanguage in self.from_bcp_47_uninherited.get (macrolanguage, set ())
}
blocked_ot_macrolanguages = set ()
if 'retired code' not in bcp_47.scopes.get (macrolanguage, ''):
for ot_macrolanguage in ot_macrolanguages:
round_trip_macrolanguages = {
l for l in self.to_bcp_47[ot_macrolanguage]
if 'retired code' not in bcp_47.scopes.get (l, '')
}
round_trip_languages = {
l for l in languages
if 'retired code' not in bcp_47.scopes.get (l, '')
}
intersection = round_trip_macrolanguages & round_trip_languages
if intersection and intersection != round_trip_languages:
blocked_ot_macrolanguages.add (ot_macrolanguage)
if ot_macrolanguages:
for ot_macrolanguage in ot_macrolanguages:
if ot_macrolanguage not in blocked_ot_macrolanguages:
for language in languages:
self.add_language (language, ot_macrolanguage)
if not blocked_ot_macrolanguages:
self.ranks[ot_macrolanguage] += 1
elif first_time:
for language in languages:
if language in self.from_bcp_47_uninherited:
ot_macrolanguages |= self.from_bcp_47_uninherited[language]
else:
ot_macrolanguages.clear ()
if not ot_macrolanguages:
break
for ot_macrolanguage in ot_macrolanguages:
self.add_language (macrolanguage, ot_macrolanguage)
def sort_languages (self):
"""Sort the values of ``from_bcp_47`` in ascending rank order."""
for language, tags in self.from_bcp_47.items ():
self.from_bcp_47[language] = sorted (tags,
key=lambda t: (self.ranks[t] + rank_delta (language, t), t))
ot = OpenTypeRegistryParser ()
class BCP47Parser (object):
"""A parser for the BCP 47 subtag registry.
Attributes:
header (str): The "File-Date" line of the registry.
names (Mapping[str, str]): A map of subtags to the names they
are given in the registry. Each value is a
``'\\n'``-separated list of names.
scopes (Mapping[str, str]): A map of language subtags to strings
suffixed to language names, including suffixes to explain
language scopes.
macrolanguages (DefaultDict[str, AbstractSet[str]]): A map of
language subtags to the sets of language subtags which
inherit from them. See
``OpenTypeRegistryParser.inherit_from_macrolanguages``.
prefixes (DefaultDict[str, AbstractSet[str]]): A map of variant
subtags to their prefixes.
grandfathered (AbstractSet[str]): The set of grandfathered tags,
normalized to lowercase.
"""
def __init__ (self):
self.header = ''
self.names = {}
self.scopes = {}
self.macrolanguages = collections.defaultdict (set)
self.prefixes = collections.defaultdict (set)
self.grandfathered = set ()
def parse (self, filename):
"""Parse the BCP 47 subtag registry.
Args:
filename (str): The file name of the registry.
"""
with open (filename, encoding='utf-8') as f:
subtag_type = None
subtag = None
deprecated = False
has_preferred_value = False
line_buffer = ''
for line in itertools.chain (f, ['']):
line = line.rstrip ()
if line.startswith (' '):
line_buffer += line[1:]
continue
line, line_buffer = line_buffer, line
if line.startswith ('Type: '):
subtag_type = line.split (' ')[1]
deprecated = False
has_preferred_value = False
elif line.startswith ('Subtag: ') or line.startswith ('Tag: '):
subtag = line.split (' ')[1]
if subtag_type == 'grandfathered':
self.grandfathered.add (subtag.lower ())
elif line.startswith ('Description: '):
description = line.split (' ', 1)[1].replace (' (individual language)', '')
description = re.sub (r' (\(family\)|\((individual |macro)language\)|languages)$', '',
description)
if subtag in self.names:
self.names[subtag] += '\n' + description
else:
self.names[subtag] = description
elif subtag_type == 'language' or subtag_type == 'grandfathered':
if line.startswith ('Scope: '):
scope = line.split (' ')[1]
if scope == 'macrolanguage':
scope = ' [macrolanguage]'
elif scope == 'collection':
scope = ' [collection]'
else:
continue
self.scopes[subtag] = scope
elif line.startswith ('Deprecated: '):
self.scopes[subtag] = ' (retired code)' + self.scopes.get (subtag, '')
deprecated = True
elif deprecated and line.startswith ('Comments: see '):
# If a subtag is split into multiple replacement subtags,
# it essentially represents a macrolanguage.
for language in line.replace (',', '').split (' ')[2:]:
self._add_macrolanguage (subtag, language)
elif line.startswith ('Preferred-Value: '):
# If a subtag is deprecated in favor of a single replacement subtag,
# it is either a dialect or synonym of the preferred subtag. Either
# way, it is close enough to the truth to consider the replacement
# the macrolanguage of the deprecated language.
has_preferred_value = True
macrolanguage = line.split (' ')[1]
self._add_macrolanguage (macrolanguage, subtag)
elif not has_preferred_value and line.startswith ('Macrolanguage: '):
self._add_macrolanguage (line.split (' ')[1], subtag)
elif subtag_type == 'variant':
if line.startswith ('Deprecated: '):
self.scopes[subtag] = ' (retired code)' + self.scopes.get (subtag, '')
elif line.startswith ('Prefix: '):
self.prefixes[subtag].add (line.split (' ')[1])
elif line.startswith ('File-Date: '):
self.header = line
expect (self.header)
def _add_macrolanguage (self, macrolanguage, language):
global ot
if language not in ot.from_bcp_47:
for l in self.macrolanguages.get (language, set ()):
self._add_macrolanguage (macrolanguage, l)
if macrolanguage not in ot.from_bcp_47:
for ls in list (self.macrolanguages.values ()):
if macrolanguage in ls:
ls.add (language)
return
self.macrolanguages[macrolanguage].add (language)
def remove_extra_macrolanguages (self):
"""Make every language have at most one macrolanguage."""
inverted = collections.defaultdict (list)
for macrolanguage, languages in self.macrolanguages.items ():
for language in languages:
inverted[language].append (macrolanguage)
for language, macrolanguages in inverted.items ():
if len (macrolanguages) > 1:
macrolanguages.sort (key=lambda ml: len (self.macrolanguages[ml]))
biggest_macrolanguage = macrolanguages.pop ()
for macrolanguage in macrolanguages:
self._add_macrolanguage (biggest_macrolanguage, macrolanguage)
def _get_name_piece (self, subtag):
"""Return the first name of a subtag plus its scope suffix.
Args:
subtag (str): A BCP 47 subtag.
Returns:
The name form of ``subtag``.
"""
return self.names[subtag].split ('\n')[0] + self.scopes.get (subtag, '')
def get_name (self, lt):
"""Return the names of the subtags in a language tag.
Args:
lt (LanguageTag): A BCP 47 language tag.
Returns:
The name form of ``lt``.
"""
name = self._get_name_piece (lt.language)
if lt.script:
name += '; ' + self._get_name_piece (lt.script.title ())
if lt.region:
name += '; ' + self._get_name_piece (lt.region.upper ())
if lt.variant:
name += '; ' + self._get_name_piece (lt.variant)
return name
bcp_47 = BCP47Parser ()
ot.parse (sys.argv[1])
bcp_47.parse (sys.argv[2])
ot.add_language ('ary', 'MOR')
ot.add_language ('ath', 'ATH')
ot.add_language ('bai', 'BML')
ot.ranks['BAL'] = ot.ranks['KAR'] + 1
ot.add_language ('ber', 'BBR')
ot.remove_language_ot ('PGR')
ot.add_language ('el-polyton', 'PGR')
bcp_47.names['flm'] = 'Falam Chin'
bcp_47.scopes['flm'] = ' (retired code)'
bcp_47.macrolanguages['flm'] = {'cfm'}
ot.ranks['FNE'] = ot.ranks['TNE'] + 1
ot.add_language ('und-fonipa', 'IPPH')
ot.add_language ('und-fonnapa', 'APPH')
ot.add_language ('ga-Latg', 'IRT')
ot.add_language ('hy-arevmda', 'HYE')
ot.remove_language_ot ('KGE')
ot.add_language ('und-Geok', 'KGE')
ot.add_language ('kht', 'KHN')
ot.names['KHN'] = ot.names['KHT'] + ' (Microsoft fonts)'
ot.ranks['KHN'] = ot.ranks['KHT'] + 1
ot.ranks['LCR'] = ot.ranks['MCR'] + 1
ot.names['MAL'] = 'Malayalam Traditional'
ot.ranks['MLR'] += 1
bcp_47.names['mhv'] = 'Arakanese'
bcp_47.scopes['mhv'] = ' (retired code)'
ot.add_language ('mnw-TH', 'MONT')
ot.add_language ('no', 'NOR')
ot.add_language ('oc-provenc', 'PRO')
ot.remove_language_ot ('QUZ')
ot.add_language ('qu', 'QUZ')
ot.add_language ('qub', 'QWH')
ot.add_language ('qud', 'QVI')
ot.add_language ('qug', 'QVI')
ot.add_language ('qul', 'QUH')
ot.add_language ('qup', 'QVI')
ot.add_language ('qur', 'QWH')
ot.add_language ('qus', 'QUH')
ot.add_language ('quw', 'QVI')
ot.add_language ('qux', 'QWH')
ot.add_language ('qva', 'QWH')
ot.add_language ('qvh', 'QWH')
ot.add_language ('qvj', 'QVI')
ot.add_language ('qvl', 'QWH')
ot.add_language ('qvm', 'QWH')
ot.add_language ('qvn', 'QWH')
ot.add_language ('qvo', 'QVI')
ot.add_language ('qvp', 'QWH')
ot.add_language ('qvw', 'QWH')
ot.add_language ('qvz', 'QVI')
ot.add_language ('qwa', 'QWH')
ot.add_language ('qws', 'QWH')
ot.add_language ('qxa', 'QWH')
ot.add_language ('qxc', 'QWH')
ot.add_language ('qxh', 'QWH')
ot.add_language ('qxl', 'QVI')
ot.add_language ('qxn', 'QWH')
ot.add_language ('qxo', 'QWH')
ot.add_language ('qxr', 'QVI')
ot.add_language ('qxt', 'QWH')
ot.add_language ('qxw', 'QWH')
bcp_47.macrolanguages['ro-MD'].add ('mo')
ot.remove_language_ot ('SYRE')
ot.remove_language_ot ('SYRJ')
ot.remove_language_ot ('SYRN')
ot.add_language ('und-Syre', 'SYRE')
ot.add_language ('und-Syrj', 'SYRJ')
ot.add_language ('und-Syrn', 'SYRN')
bcp_47.names['xst'] = "Silt'e"
bcp_47.scopes['xst'] = ' (retired code)'
bcp_47.macrolanguages['xst'] = {'stv', 'wle'}
ot.add_language ('xwo', 'TOD')
ot.remove_language_ot ('ZHH')
ot.remove_language_ot ('ZHP')
ot.remove_language_ot ('ZHT')
ot.remove_language_ot ('ZHTM')
bcp_47.macrolanguages['zh'].remove ('lzh')
bcp_47.macrolanguages['zh'].remove ('yue')
ot.add_language ('zh-Hant-MO', 'ZHH')
ot.add_language ('zh-Hant-MO', 'ZHTM')
ot.add_language ('zh-Hant-HK', 'ZHH')
ot.add_language ('zh-Hans', 'ZHS')
ot.add_language ('zh-Hant', 'ZHT')
ot.add_language ('zh-HK', 'ZHH')
ot.add_language ('zh-MO', 'ZHH')
ot.add_language ('zh-MO', 'ZHTM')
ot.add_language ('zh-TW', 'ZHT')
ot.add_language ('lzh', 'ZHT')
ot.add_language ('lzh-Hans', 'ZHS')
ot.add_language ('yue', 'ZHH')
ot.add_language ('yue-Hans', 'ZHS')
def rank_delta (bcp_47, ot):
"""Return a delta to apply to a BCP 47 tag's rank.
Most OpenType tags have a constant rank, but a few have ranks that
depend on the BCP 47 tag.
Args:
bcp_47 (str): A BCP 47 tag.
ot (str): An OpenType tag to.
Returns:
A number to add to ``ot``'s rank when sorting ``bcp_47``'s
OpenType equivalents.
"""
if bcp_47 == 'ak' and ot == 'AKA':
return -1
if bcp_47 == 'tw' and ot == 'TWI':
return -1
return 0
disambiguation = {
'ALT': 'alt',
'ARK': 'rki',
'ATH': 'ath',
'BHI': 'bhb',
'BLN': 'bjt',
'BTI': 'beb',
'CCHN': 'cco',
'CMR': 'swb',
'CPP': 'crp',
'CRR': 'crx',
'DUJ': 'dwu',
'ECR': 'crj',
'HAL': 'cfm',
'HND': 'hnd',
'HYE': 'hyw',
'KIS': 'kqs',
'KUI': 'uki',
'LRC': 'bqi',
'NDB': 'nd',
'NIS': 'njz',
'PLG': 'pce',
'PRO': 'pro',
'QIN': 'bgr',
'QUH': 'quh',
'QVI': 'qvi',
'QWH': 'qwh',
'SIG': 'stv',
'SRB': 'sr',
'SXT': 'xnj',
'ZHH': 'zh-HK',
'ZHS': 'zh-Hans',
'ZHT': 'zh-Hant',
'ZHTM': 'zh-MO',
}
ot.inherit_from_macrolanguages ()
bcp_47.remove_extra_macrolanguages ()
ot.inherit_from_macrolanguages ()
ot.names[DEFAULT_LANGUAGE_SYSTEM] = '*/'
ot.ranks[DEFAULT_LANGUAGE_SYSTEM] = max (ot.ranks.values ()) + 1
for tricky_ot_tag in filter (lambda tag: re.match ('[A-Z]{3}$', tag), ot.names):
possible_bcp_47_tag = tricky_ot_tag.lower ()
if possible_bcp_47_tag in bcp_47.names and not ot.from_bcp_47[possible_bcp_47_tag]:
ot.add_language (possible_bcp_47_tag, DEFAULT_LANGUAGE_SYSTEM)
bcp_47.macrolanguages[possible_bcp_47_tag] = set ()
ot.sort_languages ()
print ('/* == Start of generated table == */')
print ('/*')
print (' * The following table is generated by running:')
print (' *')
print (' * %s languagetags language-subtag-registry' % sys.argv[0])
print (' *')
print (' * on files with these headers:')
print (' *')
print (' * %s' % ot.header.strip ())
print (' * %s' % bcp_47.header)
print (' */')
print ()
print ('#ifndef HB_OT_TAG_TABLE_HH')
print ('#define HB_OT_TAG_TABLE_HH')
print ()
def hb_tag (tag):
"""Convert a tag to ``HB_TAG`` form.
Args:
tag (str): An OpenType tag.
Returns:
A snippet of C++ representing ``tag``.
"""
if tag == DEFAULT_LANGUAGE_SYSTEM:
return 'HB_TAG_NONE\t '
return "HB_TAG('%s','%s','%s','%s')" % tuple (('%-4s' % tag)[:4])
def get_variant_set (name):
"""Return a set of variant language names from a name.
Args:
name (str): A list of language names from the BCP 47 registry,
joined on ``'\\n'``.
Returns:
A set of normalized language names.
"""
return set (unicodedata.normalize ('NFD', n.replace ('\u2019', "'"))
.encode ('ASCII', 'ignore')
.strip ()
for n in re.split ('[\n(),]', name) if n)
def language_name_intersection (a, b):
"""Return the names in common between two language names.
Args:
a (str): A list of language names from the BCP 47 registry,
joined on ``'\\n'``.
b (str): A list of language names from the BCP 47 registry,
joined on ``'\\n'``.
Returns:
The normalized language names shared by ``a`` and ``b``.
"""
return get_variant_set (a).intersection (get_variant_set (b))
def get_matching_language_name (intersection, candidates):
return next (iter (c for c in candidates if not intersection.isdisjoint (get_variant_set (c))))
def same_tag (bcp_47_tag, ot_tags):
return len (bcp_47_tag) == 3 and len (ot_tags) == 1 and bcp_47_tag == ot_tags[0].lower ()
for language_len in (2, 3):
if language_len == 3:
print ('#ifndef HB_NO_LANGUAGE_LONG')
print ('static const LangTag ot_languages%d[] = {' % language_len)
for language, tags in sorted (ot.from_bcp_47.items ()):
if language == '' or '-' in language:
continue
if len(language) != language_len: continue
commented_out = same_tag (language, tags)
for i, tag in enumerate (tags, start=1):
print ('%s{%s,\t%s},' % ('/*' if commented_out else ' ', hb_tag (language), hb_tag (tag)), end='')
if commented_out:
print ('*/', end='')
print ('\t/* ', end='')
bcp_47_name = bcp_47.names.get (language, '')
bcp_47_name_candidates = bcp_47_name.split ('\n')
ot_name = ot.names[tag]
scope = bcp_47.scopes.get (language, '')
if tag == DEFAULT_LANGUAGE_SYSTEM:
write (f'{bcp_47_name_candidates[0]}{scope} != {ot.names[language.upper ()]}')
else:
intersection = language_name_intersection (bcp_47_name, ot_name)
if not intersection:
write ('%s%s -> %s' % (bcp_47_name_candidates[0], scope, ot_name))
else:
name = get_matching_language_name (intersection, bcp_47_name_candidates)
bcp_47.names[language] = name
write ('%s%s' % (name if len (name) > len (ot_name) else ot_name, scope))
print (' */')
print ('};')
if language_len == 3:
print ('#endif')
print ()
print ('/**')
print (' * hb_ot_tags_from_complex_language:')
print (' * @lang_str: a BCP 47 language tag to convert.')
print (' * @limit: a pointer to the end of the substring of @lang_str to consider for')
print (' * conversion.')
print (' * @count: maximum number of language tags to retrieve (IN) and actual number of')
print (' * language tags retrieved (OUT). If no tags are retrieved, it is not modified.')
print (' * @tags: array of size at least @language_count to store the language tag')
print (' * results')
print (' *')
print (' * Converts a multi-subtag BCP 47 language tag to language tags.')
print (' *')
print (' * Return value: Whether any language systems were retrieved.')
print (' **/')
print ('static inline bool')
print ('hb_ot_tags_from_complex_language (const char *lang_str,')
print ('\t\t\t\t const char *limit,')
print ('\t\t\t\t unsigned int *count /* IN/OUT */,')
print ('\t\t\t\t hb_tag_t *tags /* OUT */)')
print ('{')
def print_subtag_matches (subtag, string, new_line):
if subtag:
if new_line:
print ()
print ('\t&& ', end='')
print ('subtag_matches (%s, limit, "-%s", %i)' % (string, subtag, 1 + len (subtag)), end='')
complex_tags = collections.defaultdict (list)
for initial, group in itertools.groupby ((lt_tags for lt_tags in [
(LanguageTag (language), tags)
for language, tags in sorted (ot.from_bcp_47.items (),
key=lambda i: (-len (i[0]), i[0]))
] if lt_tags[0].is_complex ()),
key=lambda lt_tags: lt_tags[0].get_group ()):
complex_tags[initial] += group
# Calculate the min length of the subtags outside the switch
min_subtag_len = 100
for initial, items in sorted (complex_tags.items ()):
if initial != 'und':
continue
for lt, tags in items:
if not tags:
continue
subtag_len = 0
subtag_len += 1 + len (lt.script) if lt.script is not None else 0
subtag_len += 1 + len (lt.region) if lt.region is not None else 0
subtag_len += 1 + len (lt.variant) if lt.variant is not None else 0
min_subtag_len = min(subtag_len, min_subtag_len)
print (' if (limit - lang_str >= %d)' % (min_subtag_len + 2))
print (' {')
print (" const char *p = strchr (lang_str, '-');")
print (" if (!p || p >= limit || limit - p < %i) goto out;" % min_subtag_len)
for initial, items in sorted (complex_tags.items ()):
if initial != 'und':
continue
for lt, tags in items:
if not tags:
continue
if lt.variant in bcp_47.prefixes:
expect (next (iter (bcp_47.prefixes[lt.variant])) == lt.language,
'%s is not a valid prefix of %s' % (lt.language, lt.variant))
print (' if (', end='')
print_subtag_matches (lt.script, 'p', False)
print_subtag_matches (lt.region, 'p', False)
print_subtag_matches (lt.variant, 'p', False)
print (')')
print (' {')
write (' /* %s */' % bcp_47.get_name (lt))
print ()
if len (tags) == 1:
write (' tags[0] = %s; /* %s */' % (hb_tag (tags[0]), ot.names[tags[0]]))
print ()
print (' *count = 1;')
else:
print (' hb_tag_t possible_tags[] = {')
for tag in tags:
write (' %s, /* %s */' % (hb_tag (tag), ot.names[tag]))
print ()
print (' };')
print (' for (i = 0; i < %s && i < *count; i++)' % len (tags))
print ('\ttags[i] = possible_tags[i];')
print (' *count = i;')
print (' return true;')
print (' }')
print (' }')
print ('out:')
print (' switch (lang_str[0])')
print (' {')
for initial, items in sorted (complex_tags.items ()):
if initial == 'und':
continue
print (" case '%s':" % initial)
for lt, tags in items:
if not tags:
continue
print (' if (', end='')
script = lt.script
region = lt.region
if lt.grandfathered:
print ('0 == strcmp (&lang_str[1], "%s")' % lt.language[1:], end='')
else:
string_literal = lt.language[1:] + '-'
if script:
string_literal += script
script = None
if region:
string_literal += '-' + region
region = None
if string_literal[-1] == '-':
print ('0 == strncmp (&lang_str[1], "%s", %i)' % (string_literal, len (string_literal)), end='')
else:
print ('lang_matches (&lang_str[1], limit, "%s", %i)' % (string_literal, len (string_literal)), end='')
print_subtag_matches (script, 'lang_str', True)
print_subtag_matches (region, 'lang_str', True)
print_subtag_matches (lt.variant, 'lang_str', True)
print (')')
print (' {')
write (' /* %s */' % bcp_47.get_name (lt))
print ()
if len (tags) == 1:
write (' tags[0] = %s; /* %s */' % (hb_tag (tags[0]), ot.names[tags[0]]))
print ()
print (' *count = 1;')
else:
print (' unsigned int i;')
print (' hb_tag_t possible_tags[] = {')
for tag in tags:
write ('\t%s, /* %s */' % (hb_tag (tag), ot.names[tag]))
print ()
print (' };')
print (' for (i = 0; i < %s && i < *count; i++)' % len (tags))
print ('\ttags[i] = possible_tags[i];')
print (' *count = i;')
print (' return true;')
print (' }')
print (' break;')
print (' }')
print (' return false;')
print ('}')
print ()
print ('/**')
print (' * hb_ot_ambiguous_tag_to_language')
print (' * @tag: A language tag.')
print (' *')
print (' * Converts @tag to a BCP 47 language tag if it is ambiguous (it corresponds to')
print (' * many language tags) and the best tag is not the first (sorted alphabetically,')
print (' * with two-letter tags having priority over all three-letter tags), or if the')
print (' * best tag consists of multiple subtags, or if the best tag does not appear in')
print (' * #ot_languages2 or #ot_languages3.')
print (' *')
print (' * Return value: The #hb_language_t corresponding to the BCP 47 language tag,')
print (' * or #HB_LANGUAGE_INVALID if @tag is not ambiguous.')
print (' **/')
print ('static inline hb_language_t')
print ('hb_ot_ambiguous_tag_to_language (hb_tag_t tag)')
print ('{')
print (' switch (tag)')
print (' {')
def verify_disambiguation_dict ():
"""Verify and normalize ``disambiguation``.
``disambiguation`` is a map of ambiguous OpenType language system
tags to the particular BCP 47 tags they correspond to. This function
checks that all its keys really are ambiguous and that each key's
value is valid for that key. It checks that no ambiguous tag is
missing, except when it can figure out which BCP 47 tag is the best
by itself.
It modifies ``disambiguation`` to remove keys whose values are the
same as those that the fallback would return anyway, and to add
ambiguous keys whose disambiguations it determined automatically.
Raises:
AssertionError: Verification failed.
"""
global bcp_47
global disambiguation
global ot
for ot_tag, bcp_47_tags in ot.to_bcp_47.items ():
if ot_tag == DEFAULT_LANGUAGE_SYSTEM:
primary_tags = []
else:
primary_tags = list (t for t in bcp_47_tags if t not in bcp_47.grandfathered and ot.from_bcp_47.get (t)[0] == ot_tag)
if len (primary_tags) == 1:
expect (ot_tag not in disambiguation, 'unnecessary disambiguation for OT tag: %s' % ot_tag)
if '-' in primary_tags[0]:
disambiguation[ot_tag] = primary_tags[0]
else:
first_tag = sorted ((t for t in bcp_47_tags if t not in bcp_47.grandfathered and ot_tag in ot.from_bcp_47.get (t)),
key=lambda t: (len (t), t))[0]
if primary_tags[0] != first_tag:
disambiguation[ot_tag] = primary_tags[0]
elif len (primary_tags) == 0:
expect (ot_tag not in disambiguation, 'There is no possible valid disambiguation for %s' % ot_tag)
else:
original_languages = [t for t in primary_tags if t in ot.from_bcp_47_uninherited and 'retired code' not in bcp_47.scopes.get (t, '')]
if len (original_languages) == 1:
macrolanguages = original_languages
else:
macrolanguages = [t for t in primary_tags if bcp_47.scopes.get (t) == ' [macrolanguage]']
if len (macrolanguages) != 1:
macrolanguages = list (t for t in primary_tags if bcp_47.scopes.get (t) == ' [collection]')
if len (macrolanguages) != 1:
macrolanguages = list (t for t in primary_tags if 'retired code' not in bcp_47.scopes.get (t, ''))
if len (macrolanguages) != 1:
macrolanguages = list (t for t in primary_tags if t.lower () == ISO_639_3_TO_1.get (ot_tag.lower (), ot_tag.lower ()))
if len (macrolanguages) != 1:
macrolanguages = list (t for t in primary_tags if '-' not in t)
if len (macrolanguages) != 1:
expect (ot_tag in disambiguation, 'ambiguous OT tag: %s %s' % (ot_tag, sorted (primary_tags)))
expect (disambiguation[ot_tag] in bcp_47_tags,
'%s is not a valid disambiguation for %s' % (disambiguation[ot_tag], ot_tag))
elif ot_tag not in disambiguation:
disambiguation[ot_tag] = macrolanguages[0]
if '-' not in disambiguation[ot_tag]:
different_bcp_47_tags = sorted ((t for t in bcp_47_tags if not same_tag (t, ot.from_bcp_47.get (t))),
key=lambda t: (len (t), t))
if different_bcp_47_tags and disambiguation[ot_tag] == different_bcp_47_tags[0]:
del disambiguation[ot_tag]
for ot_tag in disambiguation.keys ():
expect (ot_tag in ot.to_bcp_47, 'unknown OT tag: %s' % ot_tag)
verify_disambiguation_dict ()
for ot_tag, bcp_47_tag in sorted (disambiguation.items ()):
write (' case %s: /* %s */' % (hb_tag (ot_tag), ot.names[ot_tag]))
print ()
write (' return hb_language_from_string (\"%s\", -1); /* %s */' % (bcp_47_tag, bcp_47.get_name (LanguageTag (bcp_47_tag))))
print ()
print (' default:')
print (' return HB_LANGUAGE_INVALID;')
print (' }')
print ('}')
print ()
print ('#endif /* HB_OT_TAG_TABLE_HH */')
print ()
print ('/* == End of generated table == */')
|