summaryrefslogtreecommitdiff
path: root/systems/texlive/tlnet/tlpkg/tlperl/lib/unicore/Name.pm
blob: 3cb96e08888a695a513cd0fc26e93e44a3faf677 (plain)
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
# !!!!!!!   DO NOT EDIT THIS FILE   !!!!!!!
# This file is machine-generated by mktables from the Unicode
# database, Version 15.0.0.  Any changes made here will be lost!


# !!!!!!!   INTERNAL PERL USE ONLY   !!!!!!!
# This file is for internal use by core Perl only.  The format and even the
# name or existence of this file are subject to change without notice.  Don't
# use it directly.  Use Unicode::UCD to access the Unicode character data
# base.



package charnames;

# This module contains machine-generated tables and code for the
# algorithmically-determinable Unicode character names.  The following
# routines can be used to translate between name and code point and vice versa

{ # Closure

    # Matches legal code point.  4-6 hex numbers, If there are 6, the first
    # two must be 10; if there are 5, the first must not be a 0.  Written this
    # way to decrease backtracking.  The first regex allows the code point to
    # be at the end of a word, but to work properly, the word shouldn't end
    # with a valid hex character.  The second one won't match a code point at
    # the end of a word, and doesn't have the run-on issue
    my $run_on_code_point_re = qr/(?^aax: (?: 10[0-9A-F]{4} | [1-9A-F][0-9A-F]{4} | [0-9A-F]{4} ) \b)/;
    my $code_point_re = qr/(?^aa:\b(?^aax: (?: 10[0-9A-F]{4} | [1-9A-F][0-9A-F]{4} | [0-9A-F]{4} ) \b))/;

    # In the following hash, the keys are the bases of names which include
    # the code point in the name, like CJK UNIFIED IDEOGRAPH-4E01.  The value
    # of each key is another hash which is used to get the low and high ends
    # for each range of code points that apply to the name.
    my %names_ending_in_code_point = (
'CJK COMPATIBILITY IDEOGRAPH' => 
{
'high' => 
[
64109,
64217,
195101,
],
'low' => 
[
63744,
64112,
194560,
],
},
'CJK UNIFIED IDEOGRAPH' => 
{
'high' => 
[
19903,
40959,
173791,
177977,
178205,
183969,
191456,
201546,
205743,
],
'low' => 
[
13312,
19968,
131072,
173824,
177984,
178208,
183984,
196608,
201552,
],
},
'KHITAN SMALL SCRIPT CHARACTER' => 
{
'high' => 
[
101589,
],
'low' => 
[
101120,
],
},
'NUSHU CHARACTER' => 
{
'high' => 
[
111355,
],
'low' => 
[
110960,
],
},
'TANGUT IDEOGRAPH' => 
{
'high' => 
[
100343,
],
'low' => 
[
94208,
],
},
'TANGUT IDEOGRAPH SUPPLEMENT' => 
{
'high' => 
[
101640,
],
'low' => 
[
101632,
],
},

    );

    # The following hash is a copy of the previous one, except is for loose
    # matching, so each name has blanks and dashes squeezed out
    my %loose_names_ending_in_code_point = (
'CJKCOMPATIBILITYIDEOGRAPH' => 
{
'high' => 
[
64109,
64217,
195101,
],
'low' => 
[
63744,
64112,
194560,
],
},
'CJKUNIFIEDIDEOGRAPH' => 
{
'high' => 
[
19903,
40959,
173791,
177977,
178205,
183969,
191456,
201546,
205743,
],
'low' => 
[
13312,
19968,
131072,
173824,
177984,
178208,
183984,
196608,
201552,
],
},
'KHITANSMALLSCRIPTCHARACTER' => 
{
'high' => 
[
101589,
],
'low' => 
[
101120,
],
},
'NUSHUCHARACTER' => 
{
'high' => 
[
111355,
],
'low' => 
[
110960,
],
},
'TANGUTIDEOGRAPH' => 
{
'high' => 
[
100343,
],
'low' => 
[
94208,
],
},
'TANGUTIDEOGRAPHSUPPLEMENT' => 
{
'high' => 
[
101640,
],
'low' => 
[
101632,
],
},

    );

    # And the following array gives the inverse mapping from code points to
    # names.  Lowest code points are first
    @code_points_ending_in_code_point = (

{
'high' => 19903,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 13312,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
{
'high' => 40959,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 19968,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
{
'high' => 64109,
'legal' => 
'
 -0123456789ABCDEFGHIJKLMOPRTY',
'low' => 63744,
'name' => 'CJK COMPATIBILITY IDEOGRAPH',
},
{
'high' => 64217,
'legal' => 
'
 -0123456789ABCDEFGHIJKLMOPRTY',
'low' => 64112,
'name' => 'CJK COMPATIBILITY IDEOGRAPH',
},
{
'high' => 100343,
'legal' => 
'
 -0123456789ABCDEFGHINOPRTU',
'low' => 94208,
'name' => 'TANGUT IDEOGRAPH',
},
{
'high' => 101589,
'legal' => 
'
 -0123456789ABCDEFHIKLMNPRST',
'low' => 101120,
'name' => 'KHITAN SMALL SCRIPT CHARACTER',
},
{
'high' => 101640,
'legal' => 
'
 -0123456789ABCDEFGHILMNOPRSTU',
'low' => 101632,
'name' => 'TANGUT IDEOGRAPH SUPPLEMENT',
},
{
'high' => 111355,
'legal' => 
'
 -0123456789ABCDEFHNRSTU',
'low' => 110960,
'name' => 'NUSHU CHARACTER',
},
{
'high' => 173791,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 131072,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
{
'high' => 177977,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 173824,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
{
'high' => 178205,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 177984,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
{
'high' => 183969,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 178208,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
{
'high' => 191456,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 183984,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
{
'high' => 195101,
'legal' => 
'
 -0123456789ABCDEFGHIJKLMOPRTY',
'low' => 194560,
'name' => 'CJK COMPATIBILITY IDEOGRAPH',
},
{
'high' => 201546,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 196608,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
{
'high' => 205743,
'legal' => 
'
 -0123456789ABCDEFGHIJKNOPRU',
'low' => 201552,
'name' => 'CJK UNIFIED IDEOGRAPH',
},
,

    );

    # Is exportable, make read-only
    Internals::SvREADONLY(@code_points_ending_in_code_point, 1);

    # Convert from code point to Jamo short name for use in composing Hangul
    # syllable names
    my %Jamo = (
4352 => 'G',
4353 => 'GG',
4354 => 'N',
4355 => 'D',
4356 => 'DD',
4357 => 'R',
4358 => 'M',
4359 => 'B',
4360 => 'BB',
4361 => 'S',
4362 => 'SS',
4363 => '',
4364 => 'J',
4365 => 'JJ',
4366 => 'C',
4367 => 'K',
4368 => 'T',
4369 => 'P',
4370 => 'H',
4449 => 'A',
4450 => 'AE',
4451 => 'YA',
4452 => 'YAE',
4453 => 'EO',
4454 => 'E',
4455 => 'YEO',
4456 => 'YE',
4457 => 'O',
4458 => 'WA',
4459 => 'WAE',
4460 => 'OE',
4461 => 'YO',
4462 => 'U',
4463 => 'WEO',
4464 => 'WE',
4465 => 'WI',
4466 => 'YU',
4467 => 'EU',
4468 => 'YI',
4469 => 'I',
4520 => 'G',
4521 => 'GG',
4522 => 'GS',
4523 => 'N',
4524 => 'NJ',
4525 => 'NH',
4526 => 'D',
4527 => 'L',
4528 => 'LG',
4529 => 'LM',
4530 => 'LB',
4531 => 'LS',
4532 => 'LT',
4533 => 'LP',
4534 => 'LH',
4535 => 'M',
4536 => 'B',
4537 => 'BS',
4538 => 'S',
4539 => 'SS',
4540 => 'NG',
4541 => 'J',
4542 => 'C',
4543 => 'K',
4544 => 'T',
4545 => 'P',
4546 => 'H',

    );

    # Leading consonant (can be null)
    my %Jamo_L = (
'' => 11,
'B' => 7,
'BB' => 8,
'C' => 14,
'D' => 3,
'DD' => 4,
'G' => 0,
'GG' => 1,
'H' => 18,
'J' => 12,
'JJ' => 13,
'K' => 15,
'M' => 6,
'N' => 2,
'P' => 17,
'R' => 5,
'S' => 9,
'SS' => 10,
'T' => 16,

    );

    # Vowel
    my %Jamo_V = (
'A' => 0,
'AE' => 1,
'E' => 5,
'EO' => 4,
'EU' => 18,
'I' => 20,
'O' => 8,
'OE' => 11,
'U' => 13,
'WA' => 9,
'WAE' => 10,
'WE' => 15,
'WEO' => 14,
'WI' => 16,
'YA' => 2,
'YAE' => 3,
'YE' => 7,
'YEO' => 6,
'YI' => 19,
'YO' => 12,
'YU' => 17,

    );

    # Optional trailing consonant
    my %Jamo_T = (
'B' => 17,
'BS' => 18,
'C' => 23,
'D' => 7,
'G' => 1,
'GG' => 2,
'GS' => 3,
'H' => 27,
'J' => 22,
'K' => 24,
'L' => 8,
'LB' => 11,
'LG' => 9,
'LH' => 15,
'LM' => 10,
'LP' => 14,
'LS' => 12,
'LT' => 13,
'M' => 16,
'N' => 4,
'NG' => 21,
'NH' => 6,
'NJ' => 5,
'P' => 26,
'S' => 19,
'SS' => 20,
'T' => 25,

    );

    # Computed re that splits up a Hangul name into LVT or LV syllables
    my $syllable_re = qr/(|B|BB|C|D|DD|G|GG|H|J|JJ|K|M|N|P|R|S|SS|T)(A|AE|E|EO|EU|I|O|OE|U|WA|WAE|WE|WEO|WI|YA|YAE|YE|YEO|YI|YO|YU)(B|BS|C|D|G|GG|GS|H|J|K|L|LB|LG|LH|LM|LP|LS|LT|M|N|NG|NH|NJ|P|S|SS|T)?/;

    my $HANGUL_SYLLABLE = "HANGUL SYLLABLE ";
    my $loose_HANGUL_SYLLABLE = "HANGULSYLLABLE";

    # These constants names and values were taken from the Unicode standard,
    # version 5.1, section 3.12.  They are used in conjunction with Hangul
    # syllables
    my $SBase = 0xAC00;
    my $LBase = 0x1100;
    my $VBase = 0x1161;
    my $TBase = 0x11A7;
    my $SCount = 11172;
    my $LCount = 19;
    my $VCount = 21;
    my $TCount = 28;
    my $NCount = $VCount * $TCount;

    sub name_to_code_point_special {
        my ($name, $loose) = @_;

        # Returns undef if not one of the specially handled names; otherwise
        # returns the code point equivalent to the input name
        # $loose is non-zero if to use loose matching, 'name' in that case
        # must be input as upper case with all blanks and dashes squeezed out.

        if ((! $loose && $name =~ s/$HANGUL_SYLLABLE//)
            || ($loose && $name =~ s/$loose_HANGUL_SYLLABLE//))
        {
            return if $name !~ qr/^$syllable_re$/;
            my $L = $Jamo_L{$1};
            my $V = $Jamo_V{$2};
            my $T = (defined $3) ? $Jamo_T{$3} : 0;
            return ($L * $VCount + $V) * $TCount + $T + $SBase;
        }

        # Name must end in 'code_point' for this to handle.
        return if (($loose && $name !~ /^ (.*?) ($run_on_code_point_re) $/x)
                   || (! $loose && $name !~ /^ (.*) ($code_point_re) $/x));

        my $base = $1;
        my $code_point = CORE::hex $2;
        my $names_ref;

        if ($loose) {
            $names_ref = \%loose_names_ending_in_code_point;
        }
        else {
            return if $base !~ s/-$//;
            $names_ref = \%names_ending_in_code_point;
        }

        # Name must be one of the ones which has the code point in it.
        return if ! $names_ref->{$base};

        # Look through the list of ranges that apply to this name to see if
        # the code point is in one of them.
        for (my $i = 0; $i < scalar @{$names_ref->{$base}{'low'}}; $i++) {
            return if $names_ref->{$base}{'low'}->[$i] > $code_point;
            next if $names_ref->{$base}{'high'}->[$i] < $code_point;

            # Here, the code point is in the range.
            return $code_point;
        }

        # Here, looked like the name had a code point number in it, but
        # did not match one of the valid ones.
        return;
    }

    sub code_point_to_name_special {
        my $code_point = shift;

        # Returns the name of a code point if algorithmically determinable;
        # undef if not

        # If in the Hangul range, calculate the name based on Unicode's
        # algorithm
        if ($code_point >= $SBase && $code_point <= $SBase + $SCount -1) {
            use integer;
            my $SIndex = $code_point - $SBase;
            my $L = $LBase + $SIndex / $NCount;
            my $V = $VBase + ($SIndex % $NCount) / $TCount;
            my $T = $TBase + $SIndex % $TCount;
            $name = "$HANGUL_SYLLABLE$Jamo{$L}$Jamo{$V}";
            $name .= $Jamo{$T} if $T != $TBase;
            return $name;
        }

        # Look through list of these code points for one in range.
        foreach my $hash (@code_points_ending_in_code_point) {
            return if $code_point < $hash->{'low'};
            if ($code_point <= $hash->{'high'}) {
                return sprintf("%s-%04X", $hash->{'name'}, $code_point);
            }
        }
        return;            # None found
    }
} # End closure

1;