summaryrefslogtreecommitdiff
path: root/Build/source/texk/web2c/luatexdir/lang/texlang.w
blob: bd519af632ab8192a136c0ce982805ebcc717be8 (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
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
% texlang.w
%
% Copyright 2006-2012 Taco Hoekwater <taco@@luatex.org>
%
% This file is part of LuaTeX.
%
% LuaTeX 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 2 of the License, or (at your
% option) any later version.
%
% LuaTeX 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 Lesser General Public
% License for more details.
%
% You should have received a copy of the GNU General Public License along
% with LuaTeX; if not, see <http://www.gnu.org/licenses/>.

@ @c

#include "ptexlib.h"
#include <string.h>
#include "lua/luatex-api.h"

@ Low-level helpers

@ @c
#define unVERBOSE

#define MAX_TEX_LANGUAGES  16384

static struct tex_language *tex_languages[MAX_TEX_LANGUAGES] = { NULL };

static int next_lang_id = 0;

struct tex_language *new_language(int n)
{
    struct tex_language *lang;
    unsigned l;
    if (n >= 0) {
        l = (unsigned) n;
        if (l != (MAX_TEX_LANGUAGES - 1))
            if (next_lang_id <= n)
                next_lang_id = n + 1;
    } else {
        while (tex_languages[next_lang_id] != NULL)
            next_lang_id++;
        l = (unsigned) next_lang_id++;
    }
    if (l < (MAX_TEX_LANGUAGES - 1) && tex_languages[l] == NULL) {
        lang = xmalloc(sizeof(struct tex_language));
        tex_languages[l] = lang;
        lang->id = (int) l;
        lang->exceptions = 0;
        lang->patterns = NULL;
        lang->pre_hyphen_char = '-';
        lang->post_hyphen_char = 0;
        lang->pre_exhyphen_char = 0;
        lang->post_exhyphen_char = 0;
        lang->hyphenation_min = -1;
        if (saving_hyph_codes_par) {
            hj_codes_from_lc_codes(l); /* for now, we might just use specific value for whatever task */
        }
        return lang;
    } else {
        return NULL;
    }
}

struct tex_language *get_language(int n)
{
    if (n >= 0 && n < MAX_TEX_LANGUAGES) {
        if (tex_languages[n] != NULL) {
            return tex_languages[n];
        } else {
            return new_language(n);
        }
    } else {
        return NULL;
    }
}

@ @c
void set_pre_hyphen_char(int n, int v)
{
    struct tex_language *l = get_language((int) n);
    if (l != NULL)
        l->pre_hyphen_char = (int) v;
}

void set_post_hyphen_char(int n, int v)
{
    struct tex_language *l = get_language((int) n);
    if (l != NULL)
        l->post_hyphen_char = (int) v;
}

void set_pre_exhyphen_char(int n, int v)
{
    struct tex_language *l = get_language((int) n);
    if (l != NULL)
        l->pre_exhyphen_char = (int) v;
}

void set_post_exhyphen_char(int n, int v)
{
    struct tex_language *l = get_language((int) n);
    if (l != NULL)
        l->post_exhyphen_char = (int) v;
}

int get_pre_hyphen_char(int n)
{
    struct tex_language *l = get_language((int) n);
    if (l == NULL)
        return -1;
    return (int) l->pre_hyphen_char;
}

int get_post_hyphen_char(int n)
{
    struct tex_language *l = get_language((int) n);
    if (l == NULL)
        return -1;
    return (int) l->post_hyphen_char;
}

int get_pre_exhyphen_char(int n)
{
    struct tex_language *l = get_language((int) n);
    if (l == NULL)
        return -1;
    return (int) l->pre_exhyphen_char;
}

int get_post_exhyphen_char(int n)
{
    struct tex_language *l = get_language((int) n);
    if (l == NULL)
        return -1;
    return (int) l->post_exhyphen_char;
}

void set_hyphenation_min(int n, int v)
{
    struct tex_language *l = get_language((int) n);
    if (l != NULL)
        l->hyphenation_min = (int) v;
}

int get_hyphenation_min(int n)
{
    struct tex_language *l = get_language((int) n);
    if (l == NULL)
        return -1;
    return (int) l->hyphenation_min;
}

void load_patterns(struct tex_language *lang, const unsigned char *buff)
{
    if (lang == NULL || buff == NULL || strlen((const char *) buff) == 0)
        return;
    if (lang->patterns == NULL) {
        lang->patterns = hnj_hyphen_new();
    }
    hnj_hyphen_load(lang->patterns, buff);
}

void clear_patterns(struct tex_language *lang)
{
    if (lang == NULL)
        return;
    if (lang->patterns != NULL) {
        hnj_hyphen_clear(lang->patterns);
    }
}

void load_tex_patterns(int curlang, halfword head)
{
    char *s = tokenlist_to_cstring(head, 1, NULL);
    load_patterns(get_language(curlang), (unsigned char *) s);
}

@ @c
#define STORE_CHAR(l,x) do { \
    unsigned xx = get_hj_code(l,x); \
    if (!xx || xx <= 32) { \
        xx = x; \
    } \
    uindex = uni2string(uindex, xx); \
} while (0)

@ Cleans one word which is returned in |cleaned|, returns the new offset into
|buffer|

@c
const char *clean_hyphenation(int id, const char *buff, char **cleaned)
{
    int items = 0;
    unsigned char word[MAX_WORD_LEN + 1]; /* work buffer for bytes */
    unsigned uword[MAX_WORD_LEN + 1] = { 0 };  /* work buffer for unicode */
    int u = 0; /* unicode buffer value */
    int i = 0; /* index into buffer */
    char *uindex = (char *)word;
    const char *s = buff;

    while (*s && !isspace((unsigned char)*s)) {
        word[i++] = (unsigned)*s;
        s++;
        if ((s-buff)>MAX_WORD_LEN) {
            /* todo: this is too strict, should count unicode, not bytes */
            *cleaned = NULL;
            tex_error("exception too long", NULL);
            return s;
        }
    }
    /* now convert the input to unicode */
    word[i] = '\0';
    utf2uni_strcpy(uword, (const char *)word);

    /* build the new word string */
    i = 0;
    while (uword[i]>0) {
        u = uword[i++];
        if (u == '-') {        /* skip */
        } else if (u == '=') {
            STORE_CHAR(id,'-');
        } else if (u == '{') {
            u = uword[i++];
            items = 0;
            while (u && u != '}') {
                u = uword[i++];
            }
            if (u == '}') {
                items++;
                u = uword[i++];
            }
            while (u && u != '}') {
                u = uword[i++];
            }
            if (u == '}') {
                items++;
                u = uword[i++];
            }
            if (u == '{') {
                u = uword[i++];
            }
            while (u && u != '}') {
                STORE_CHAR(id,u);
                u = uword[i++];
            }
            if (u == '}') {
                items++;
            }
            if (items != 3) {   /* syntax error */
                *cleaned = NULL;
                tex_error("exception syntax error", NULL);
                return s;
            }
        } else {
            STORE_CHAR(id,u);
        }
    }
    *uindex = '\0';
    *cleaned = xstrdup((char *) word);
    return s;
}

@ @c
void load_hyphenation(struct tex_language *lang, const unsigned char *buff)
{
    const char *s;
    const char *value;
    char *cleaned;
    int id ;
    if (lang == NULL)
        return;
    if (lang->exceptions == 0) {
        lua_newtable(Luas);
        lang->exceptions = luaL_ref(Luas, LUA_REGISTRYINDEX);
    }
    lua_rawgeti(Luas, LUA_REGISTRYINDEX, lang->exceptions);
    s = (const char *) buff;
    id = lang->id;
    while (*s) {
        while (isspace((unsigned char)*s))
            s++;
        if (*s) {
            value = s;
            s = clean_hyphenation(id, s, &cleaned);
            if (cleaned != NULL) {
                if ((s - value) > 0) {
                    lua_pushstring(Luas, cleaned);
                    lua_pushlstring(Luas, value, (size_t) (s - value));
                    lua_rawset(Luas, -3);
                }
                free(cleaned);
            } else {
#ifdef VERBOSE
                formatted_warning("hyphenation","skipping invalid hyphenation exception: %s", value);
#endif
            }
        }
    }
}

void clear_hyphenation(struct tex_language *lang)
{
    if (lang == NULL)
        return;
    if (lang->exceptions != 0) {
        luaL_unref(Luas, LUA_REGISTRYINDEX, lang->exceptions);
        lang->exceptions = 0;
    }
}

void load_tex_hyphenation(int curlang, halfword head)
{
    char *s = tokenlist_to_cstring(head, 1, NULL);
    load_hyphenation(get_language(curlang), (unsigned char *) s);
}

@ @c
halfword insert_discretionary(halfword t, halfword pre, halfword post, halfword replace, int penalty)
{
    halfword g, n;
    int f;
    n = new_node(disc_node, syllable_disc);
    disc_penalty(n) = penalty;
    try_couple_nodes(n, vlink(t));
    couple_nodes(t, n);
    if (replace != null)
        f = font(replace);
    else
        f = get_cur_font();     /* for compound words following explicit hyphens */
    for (g = pre; g != null; g = vlink(g)) {
        font(g) = f;
        if (node_attr(t) != null) {
            delete_attribute_ref(node_attr(g));
            node_attr(g) = node_attr(t);
            attr_list_ref(node_attr(t)) += 1;
        }
    }
    for (g = post; g != null; g = vlink(g)) {
        font(g) = f;
        if (node_attr(t) != null) {
            delete_attribute_ref(node_attr(g));
            node_attr(g) = node_attr(t);
            attr_list_ref(node_attr(t)) += 1;
        }
    }
    for (g = replace; g != null; g = vlink(g)) {
        if (node_attr(t) != null) {
            delete_attribute_ref(node_attr(g));
            node_attr(g) = node_attr(t);
            attr_list_ref(node_attr(t)) += 1;
        }
    }
    if (node_attr(t) != null) {
        delete_attribute_ref(node_attr(vlink(t)));
        node_attr(vlink(t)) = node_attr(t);
        attr_list_ref(node_attr(t)) += 1;
    }
    t = vlink(t);
    set_disc_field(pre_break(t), pre);
    set_disc_field(post_break(t), post);
    set_disc_field(no_break(t), replace);
    return t;
}

halfword insert_syllable_discretionary(halfword t, lang_variables * lan)
{
    halfword g, n;
    n = new_node(disc_node, syllable_disc);
    disc_penalty(n) = hyphen_penalty_par;
    couple_nodes(n, vlink(t));
    couple_nodes(t, n);
    delete_attribute_ref(node_attr(n));
    if (node_attr(t) != null) {
        node_attr(n) = node_attr(t);
        attr_list_ref(node_attr(t))++;
    } else {
        node_attr(n) = null;
    }
    if (lan->pre_hyphen_char > 0) {
        g = raw_glyph_node();
        set_to_character(g);
        character(g) = lan->pre_hyphen_char;
        font(g) = font(t);
        lang_data(g) = lang_data(t);
        if (node_attr(t) != null) {
            node_attr(g) = node_attr(t);
            attr_list_ref(node_attr(t))++;
        }
        set_disc_field(pre_break(n), g);
    }

    if (lan->post_hyphen_char > 0) {
        t = vlink(n);
        g = raw_glyph_node();
        set_to_character(g);
        character(g) = lan->post_hyphen_char;
        font(g) = font(t);
        lang_data(g) = lang_data(t);
        if (node_attr(t) != null) {
            node_attr(g) = node_attr(t);
            attr_list_ref(node_attr(t)) += 1;
        }
        set_disc_field(post_break(n), g);
    }
    return n;
}

@ @c
halfword compound_word_break(halfword t, int clang)
{
    halfword disc = null;
    halfword pre = null;
    halfword pos = null;
    halfword pre_exhyphen_char = get_pre_exhyphen_char(clang);
    halfword post_exhyphen_char = get_post_exhyphen_char(clang);
    if (pre_exhyphen_char > 0)
        pre = insert_character(null,pre_exhyphen_char);
    if (post_exhyphen_char > 0)
        pos = insert_character(null,post_exhyphen_char);
    disc = insert_discretionary(t,pre,pos,null,ex_hyphen_penalty_par);
    subtype(disc) = automatic_disc;
    set_automatic_disc_penalty(disc);
    return disc;
}

halfword insert_complex_discretionary(halfword t, lang_variables * lan,
                                      halfword pre, halfword pos,
                                      halfword replace)
{
    (void) lan;
    return insert_discretionary(t,pre,pos,replace,hyphen_penalty_par);
}

halfword insert_character(halfword t, int c)
{
    halfword p;
    p = new_node(glyph_node, 0);
    set_to_character(p);
    character(p) = c;
    if (t != null) {
        couple_nodes(t, p);
    }
    return p;
}

@ @c
void set_disc_field(halfword f, halfword t)
{
    if (t != null) {
        /*
            couple_nodes(f, t); // better not expose f as prev pointer
        */
        vlink(f) = t ;
        alink(t) = null ;
        tlink(f) = tail_of_list(t);
    } else {
        vlink(f) = null;
        tlink(f) = null;
    }
}

@ @c
static char *hyphenation_exception(int exceptions, char *w)
{
    char *ret = NULL;
    lua_checkstack(Luas, 2);
    lua_rawgeti(Luas, LUA_REGISTRYINDEX, exceptions);
    if (lua_istable(Luas, -1)) {   /* ?? */
        lua_pushstring(Luas, w);   /* word table */
        lua_rawget(Luas, -2);
        if (lua_type(Luas, -1) == LUA_TSTRING) {
            ret = xstrdup(lua_tostring(Luas, -1));
        }
        lua_pop(Luas, 2);
    } else {
        lua_pop(Luas, 1);
    }
    return ret;
}

@ @c
char *exception_strings(struct tex_language *lang)
{
    const char *value;
    size_t size = 0, current = 0;
    size_t l = 0;
    char *ret = NULL;
    if (lang->exceptions == 0)
        return NULL;
    lua_checkstack(Luas, 2);
    lua_rawgeti(Luas, LUA_REGISTRYINDEX, lang->exceptions);
    if (lua_istable(Luas, -1)) {
        /* iterate and join */
        lua_pushnil(Luas);         /* first key */
        while (lua_next(Luas, -2) != 0) {
            value = lua_tolstring(Luas, -1, &l);
            if (current + 2 + l > size) {
                ret = xrealloc(ret, (unsigned) ((size + size / 5) + current + l + 1024));
                size = (size + size / 5) + current + l + 1024;
            }
            *(ret + current) = ' ';
            strcpy(ret + current + 1, value);
            current += l + 1;
            lua_pop(Luas, 1);
        }
    }
    return ret;
}

@ the sequence from |wordstart| to |r| can contain only normal characters it
could be faster to modify a halfword pointer and return an integer

@c
static halfword find_exception_part(unsigned int *j, unsigned int *uword, int len)
{
    halfword g = null, gg = null;
    register unsigned i = *j;
    i++;                        /* this puts uword[i] on the |{| */
    while (i < (unsigned) len && uword[i + 1] != '}') {
        if (g == null) {
            gg = new_char(0, (int) uword[i + 1]);
            g = gg;
        } else {
            halfword s = new_char(0, (int) uword[i + 1]);
            couple_nodes(g, s);
            g = vlink(g);
        }
        i++;
    }
    *j = ++i;
    return gg;
}

static int count_exception_part(unsigned int *j, unsigned int *uword, int len)
{
    int ret = 0;
    register unsigned i = *j;
    i++;                        /* this puts uword[i] on the |{| */
    while (i < (unsigned) len && uword[i + 1] != '}') {
        ret++;
        i++;
    }
    *j = ++i;
    return ret;
}

@ @c
static const char *PAT_ERROR[] = {
    "Exception discretionaries should contain three pairs of braced items.",
    "No intervening spaces are allowed.",
    NULL
};

/*
    The exceptions are taken as-is: no min values are taken into account. One can
    add normal patterns on-the-fly if needed.
*/

static void do_exception(halfword wordstart, halfword r, char *replacement)
{
    unsigned i;
    halfword t;
    unsigned len;
    int clang;
    lang_variables langdata;
    unsigned uword[MAX_WORD_LEN + 1] = { 0 };
    utf2uni_strcpy(uword, replacement);
    len = u_length(uword);
    i = 0;
    t = wordstart;
    clang = char_lang(wordstart);
    langdata.pre_hyphen_char = get_pre_hyphen_char(clang);
    langdata.post_hyphen_char = get_post_hyphen_char(clang);

    for (i = 0; i < len; i++) {
        if (uword[i + 1] == '-') {      /* a hyphen follows */
            while (vlink(t) != r && (type(t) != glyph_node || !is_simple_character(t)))
                t = vlink(t);
            if (vlink(t) == r)
                break;
            insert_syllable_discretionary(t, &langdata);
            t = vlink(t);       /* skip the new disc */
        } else if (uword[i + 1] == '=') {
            /* do nothing ? */
            t = vlink(t);
        } else if (uword[i + 1] == '{') {
            halfword gg, hh, replace = null;
            int repl;
            gg = find_exception_part(&i, uword, (int) len);
            if (i == len || uword[i + 1] != '{') {
                tex_error("broken pattern 1", PAT_ERROR);
            }
            hh = find_exception_part(&i, uword, (int) len);
            if (i == len || uword[i + 1] != '{') {
                tex_error("broken pattern 2", PAT_ERROR);
            }
            repl = count_exception_part(&i, uword, (int) len);
            if (i == len) {
                tex_error("broken pattern 3", PAT_ERROR);
            }
            /*i++;  *//* jump over the last right brace */
            if (vlink(t) == r)
                break;
            if (repl > 0) {
                halfword q = t;
                replace = vlink(q);
                while (repl > 0 && q != null) {
                    q = vlink(q);
                    if (type(q) == glyph_node) {
                        repl--;
                    }
                }
                try_couple_nodes(t, vlink(q));
                vlink(q) = null;
            }
            t = insert_discretionary(t, gg, hh, replace, hyphen_penalty_par);
            t = vlink(t);       /* skip the new disc */
        } else {
            t = vlink(t);
        }
    }
}

@ This is a documentation section from the pascal web file. It is not true any
more, but I do not have time right now to rewrite it -- Taco

When the line-breaking routine is unable to find a feasible sequence of
breakpoints, it makes a second pass over the paragraph, attempting to hyphenate
the hyphenatable words. The goal of hyphenation is to insert discretionary
material into the paragraph so that there are more potential places to break.

The general rules for hyphenation are somewhat complex and technical, because we
want to be able to hyphenate words that are preceded or followed by punctuation
marks, and because we want the rules to work for languages other than English. We
also must contend with the fact that hyphens might radically alter the ligature
and kerning structure of a word.

A sequence of characters will be considered for hyphenation only if it belongs to
a ``potentially hyphenatable part'' of the current paragraph. This is a sequence
of nodes $p_0p_1\ldots p_m$ where $p_0$ is a glue node, $p_1\ldots p_{m-1}$ are
either character or ligature or whatsit or implicit kern nodes, and $p_m$ is a
glue or penalty or insertion or adjust or mark or whatsit or explicit kern node.
(Therefore hyphenation is disabled by boxes, math formulas, and discretionary
nodes already inserted by the user.) The ligature nodes among $p_1\ldots p_{m-1}$
are effectively expanded into the original non-ligature characters; the kern
nodes and whatsits are ignored. Each character |c| is now classified as either a
nonletter (if |lc_code(c)=0|), a lowercase letter (if |lc_code(c)=c|), or an
uppercase letter (otherwise); an uppercase letter is treated as if it were
|lc_code(c)| for purposes of hyphenation. The characters generated by $p_1\ldots
p_{m-1}$ may begin with nonletters; let $c_1$ be the first letter that is not in
the middle of a ligature. Whatsit nodes preceding $c_1$ are ignored; a whatsit
found after $c_1$ will be the terminating node $p_m$. All characters that do not
have the same font as $c_1$ will be treated as nonletters. The |hyphen_char| for
that font must be between 0 and 255, otherwise hyphenation will not be attempted.
\TeX\ looks ahead for as many consecutive letters $c_1\ldots c_n$ as possible;
however, |n| must be less than 64, so a character that would otherwise be
$c_{64}$ is effectively not a letter. Furthermore $c_n$ must not be in the middle
of a ligature. In this way we obtain a string of letters $c_1\ldots c_n$ that are
generated by nodes $p_a\ldots p_b$, where |1<=a<=b+1<=m|. If |n>=l_hyf+r_hyf|,
this string qualifies for hyphenation; however, |uc_hyph| must be positive, if
$c_1$ is uppercase.

The hyphenation process takes place in three stages. First, the candidate
sequence $c_1\ldots c_n$ is found; then potential positions for hyphens are
determined by referring to hyphenation tables; and finally, the nodes $p_a\ldots
p_b$ are replaced by a new sequence of nodes that includes the discretionary
breaks found.

Fortunately, we do not have to do all this calculation very often, because of the
way it has been taken out of \TeX's inner loop. For example, when the second
edition of the author's 700-page book {\sl Seminumerical Algorithms} was typeset
by \TeX, only about 1.2 hyphenations needed to be @^Knuth, Donald Ervin@> tried
per paragraph, since the line breaking algorithm needed to use two passes on only
about 5 per cent of the paragraphs.

When a word been set up to contain a candidate for hyphenation, \TeX\ first looks
to see if it is in the user's exception dictionary. If not, hyphens are inserted
based on patterns that appear within the given word, using an algorithm due to
Frank~M. Liang. @^Liang, Franklin Mark@>

@ This is incompatible with TEX because the first word of a paragraph can be
hyphenated, but most european users seem to agree that prohibiting hyphenation
there was not the best idea ever.

@c
/*
    More strict: \hyphenationbounds

    0 = not strict
    1 = strict start
    2 = strict end
    3 = strict start and strict end

    \parindent0pt \hsize=1.1cm
    12-34-56 \par
    12-34-\hbox{56} \par
    12-34-\vrule width 1em height 1.5ex \par
    12-\hbox{34}-56 \par
    12-\vrule width 1em height 1.5ex-56 \par
    \hjcode`\1=`\1 \hjcode`\2=`\2 \hjcode`\3=`\3 \hjcode`\4=`\4 \vskip.5cm
    12-34-56 \par
    12-34-\hbox{56} \par
    12-34-\vrule width 1em height 1.5ex \par
    12-\hbox{34}-56 \par
    12-\vrule width 1em height 1.5ex-56 \par

*/

static halfword find_next_wordstart(halfword r, halfword first_language, halfword strict_bound)
{
    register int l;
    register int start_ok = 1;
    int mathlevel = 1;
    int chr ;
    halfword t ;
    while (r != null) {
        switch (type(r)) {
        case boundary_node:
            if (subtype(r) == word_boundary) {
                start_ok = 1;
            }
            break;
        case hlist_node: /* new > 0.95 */
        case vlist_node: /* new > 0.95 */
        case rule_node:  /* new > 0.95 */
        case dir_node:
        case whatsit_node:
            if (strict_bound == 1 || strict_bound == 3) {
                start_ok = 0;
            }
            break;
        case glue_node:
            start_ok = 1;
            break;
        case math_node:
            while (mathlevel > 0) {
                r = vlink(r);
                if (r == null)
                    return r;
                if (type(r) == math_node) {
                    if (subtype(r) == before) {
                        mathlevel++;
                    } else {
                        mathlevel--;
                    }
                }
            }
            break;
        case glyph_node:
            if (is_simple_character(r)) {
                chr = character(r) ;
                if (chr == ex_hyphen_char_par) {
                    /*
                        We only accept an explicit hyphen when there is a preceding glyph and
                        we skip a sequence of explicit hyphens as that normally indicates a
                        -- or --- ligature in which case we can in a worse case usage get bad
                        node lists later on due to messed up ligature building as these dashes
                        are ligatures in base fonts. This is a side effect of the separating the
                        hyphenation, ligaturing and kerning steps. A test is cmr with ------.
                    */
                    t = vlink(r) ;
                    if ((start_ok == 0) && (t!=null) && (type(t) == glyph_node) && (character(t) != ex_hyphen_char_par)) {
                        compound_word_break(r, char_lang(r));
                        start_ok = 1 ;
                    } else {
                        start_ok = 0;
                    }
                } else if (start_ok && (char_lang(r)>=first_language) && ((l = get_hj_code(char_lang(r),chr)) > 0)) {
                    if (char_uchyph(r) || l == chr || l <= 32) {
                        return r;
                    } else {
                        start_ok = 0;
                    }
                }
            }
            break;
        default:
            start_ok = 0;
            break;
        }
        r = vlink(r);
    }
    return r;
}

@ @c
static int valid_wordend(halfword s, halfword strict_bound)
{
    register halfword r = s;
    register int clang = char_lang(s);
    if (r == null)
        return 1;
    while ( (r != null) &&
           (    (type(r) == glyph_node && is_simple_character(r) && clang == char_lang(r))
             || (type(r) == kern_node && (subtype(r) == normal))
            )
           ) {
        r = vlink(r);
    }
    if (r == null || (type(r) == glyph_node && is_simple_character(r) && clang != char_lang(r))
                  ||  type(r) == glue_node
                  ||  type(r) == penalty_node
                  || (type(r) == kern_node && (subtype(r) == explicit_kern || /* so why not italic correction ? */
                                               subtype(r) == italic_kern   ||
                                               subtype(r) == accent_kern   ))
                  ||  ((type(r) == hlist_node   || /* new > 0.95 */
                        type(r) == vlist_node   || /* new > 0.95 */
                        type(r) == rule_node    || /* new > 0.95 */
                        type(r) == dir_node     || /* new > 0.97 */
                        type(r) == whatsit_node ||
                        type(r) == ins_node     || /* yes or no strict test */
                        type(r) == adjust_node     /* yes or no strict test */
                       ) && ! (strict_bound == 2 || strict_bound == 3))
                  ||  type(r) == boundary_node
        )
        return 1;
    return 0;
}

@ @c
void hnj_hyphenation(halfword head, halfword tail)
{
    int lchar, i;
    struct tex_language *lang;
    lang_variables langdata;
    char utf8word[(4 * MAX_WORD_LEN) + 1] = { 0 };
    int wordlen = 0;
    char *hy = utf8word;
    char *replacement = NULL;
    boolean explicit_hyphen = false;
    halfword first_language = first_valid_language_par;
    halfword strict_bound = hyphenation_bounds_par;
    halfword s, r = head, wordstart = null, save_tail1 = null, left = null, right = null;

    /* this first movement assures two things:
     \item{a)} that we won't waste lots of time on something that has been
      handled already (in that case, none of the glyphs match |simple_character|).
     \item{b)} that the first word can be hyphenated. if the movement was
     not explicit, then the indentation at the start of a paragraph
     list would make |find_next_wordstart()| look too far ahead.
     */

    while (r != null && (type(r) != glyph_node || !is_simple_character(r))) {
        r = vlink(r);
    }
    /* this will make |r| a glyph node with subtype character */
    r = find_next_wordstart(r,first_language,strict_bound);
    if (r == null)
        return;

    assert(tail != null);
    save_tail1 = vlink(tail);
    s = new_penalty(0,word_penalty);
    couple_nodes(tail, s);

    while (r != null) {         /* could be while(1), but let's be paranoid */
        int clang, lhmin, rhmin, hmin;
        halfword hyf_font;
        halfword end_word = r;
        wordstart = r;
        assert(is_simple_character(wordstart));
        hyf_font = font(wordstart);
        if (hyphen_char(hyf_font) < 0)  /* for backward compat */
            hyf_font = 0;
        clang = char_lang(wordstart);
        lhmin = char_lhmin(wordstart);
        rhmin = char_rhmin(wordstart);
        hmin = get_hyphenation_min(clang);
        langdata.pre_hyphen_char = get_pre_hyphen_char(clang);
        langdata.post_hyphen_char = get_post_hyphen_char(clang);
        while (    r != null
                && type(r) == glyph_node
                && is_simple_character(r)
                && clang == char_lang(r)
                && (    (     (clang >= first_language)
                           && (lchar = get_hj_code(clang,character(r))) > 0
                        )
                     || (     character(r) == ex_hyphen_char_par
                           && (lchar = ex_hyphen_char_par)
                        )
                   )
              ) {
            if (character(r) == ex_hyphen_char_par) {
                explicit_hyphen = true;
            }
            wordlen++;
            if (lchar <= 32) {
                if (lchar == 32) {
                    lchar = 0 ;
                }
                if (wordlen <= lhmin) {
                    lhmin = lhmin - lchar + 1 ;
                    if (lhmin < 0)
                        lhmin = 1;
                }
                if (wordlen >= rhmin) {
                    rhmin = rhmin - lchar + 1 ;
                    if (rhmin < 0)
                        rhmin = 1;
                }
                hmin = hmin - lchar + 1 ;
                if (hmin < 0)
                    rhmin = 1;
                lchar = character(r) ;
            }
            hy = uni2string(hy, (unsigned) lchar);
            /* this should not be needed  any more */
            /*if (vlink(r)!=null) alink(vlink(r))=r; */
            end_word = r;
            r = vlink(r);
        }
        if (     valid_wordend(r,strict_bound)
              && clang >= first_language
              && wordlen >= lhmin + rhmin
              && (hmin <= 0 || wordlen >= hmin)
              && (hyf_font != 0)
              && (lang = tex_languages[clang]) != NULL
           ) {
            *hy = 0;
            if (    lang->exceptions != 0
                 && (replacement = hyphenation_exception(lang->exceptions, utf8word)) != NULL
               ) {
#ifdef VERBOSE
                formatted_warning("hyphenation","replacing %s (c=%d) by %s", utf8word, clang, replacement);
#endif
                do_exception(wordstart, r, replacement);
                free(replacement);
            } else if (explicit_hyphen == true) {
                /*
                    insert an explicit discretionary after each of the last in a
                    set of explicit hyphens
                */
                halfword rr = r;
#ifdef VERBOSE
                formatted_warning("hyphenation","explicit hyphen(s) found in %s (c=%d)", utf8word, clang);
#endif
                while (rr != wordstart) {
                if (is_simple_character(rr)) {
                        if (character(rr) == ex_hyphen_char_par) {
                            compound_word_break(rr, clang);
                            while (character(alink(rr)) == ex_hyphen_char_par)
                                rr = alink(rr);
                            if (rr == wordstart)
                                break;
                        }
                    }
                    rr = alink(rr);
                }
            } else if (lang->patterns != NULL) {
                left = wordstart;
                for (i = lhmin; i > 1; i--) {
                    left = vlink(left);
                    while (!is_simple_character(left)) {
                        left = vlink(left);
                    }
                    /*
                    if (!left)
                        break ;
                    */
                    /* what is left overruns right .. a bit messy */
                }
                right = r;
                for (i = rhmin; i > 0; i--) {
                    right = alink(right);
                    while (!is_simple_character(right)) {
                        right = alink(right);
                    }
                    /*
                    if (!right)
                        break ;
                    */
                    /* what is right overruns left .. a bit messy */
                }
                /* maybe an extra check ... */
                /* |if (left && right) {| */
#ifdef VERBOSE
                    formatted_warning("hyphenation","hyphenate %s (c=%d,l=%d,r=%d) from %c to %c",
                        utf8word, clang, lhmin, rhmin, character(left), character(right));
#endif
                    (void) hnj_hyphen_hyphenate(lang->patterns, wordstart, end_word, wordlen, left, right, &langdata);
                /* |}| */
            }
        }
        explicit_hyphen = false;
        wordlen = 0;
        hy = utf8word;
        if (r == null)
            break;
        r = find_next_wordstart(r,first_language,strict_bound);
    }
    flush_node(vlink(tail));
    vlink(tail) = save_tail1;
}

@ @c
void new_hyphenation(halfword head, halfword tail)
{
    register int callback_id = 0;
    if (head == null || vlink(head) == null)
        return;
    fix_node_list(head);
    callback_id = callback_defined(hyphenate_callback);
    if (callback_id > 0) {
        if (!get_callback(Luas, callback_id)) {
            lua_pop(Luas, 2);
            return;
        }
        nodelist_to_lua(Luas, head);
        nodelist_to_lua(Luas, tail);
        if (lua_pcall(Luas, 2, 0, 0) != 0) {
            formatted_warning("hyphenation","bad specification: %s",lua_tostring(Luas, -1));
            lua_pop(Luas, 2);
            lua_error(Luas);
            return;
        }
        lua_pop(Luas, 1);
    } else if (callback_id == 0) {
        hnj_hyphenation(head, tail);
    }
}

@ dumping and undumping languages

@c
#define dump_string(a)                \
  if (a!=NULL) {                      \
      x = (int)strlen(a)+1;           \
    dump_int(x);  dump_things(*a, x); \
  } else {                            \
    x = 0; dump_int(x);               \
  }

static void dump_one_language(int i)
{
    char *s = NULL;
    int x = 0;
    struct tex_language *lang;
    lang = tex_languages[i];
    dump_int(lang->id);
    dump_int(lang->pre_hyphen_char);
    dump_int(lang->post_hyphen_char);
    dump_int(lang->pre_exhyphen_char);
    dump_int(lang->post_exhyphen_char);
    dump_int(lang->hyphenation_min);
    if (lang->patterns != NULL) {
        s = (char *) hnj_serialize(lang->patterns);
    }
    dump_string(s);
    if (s != NULL) {
        free(s);
        s = NULL;
    }
    if (lang->exceptions != 0)
        s = exception_strings(lang);
    dump_string(s);
    if (s != NULL) {
        free(s);
    }
    free(lang);
}

void dump_language_data(void)
{
    int i;
    dump_int(next_lang_id);
    for (i = 0; i < next_lang_id; i++) {
        if (tex_languages[i]) {
            dump_int(1);
            dump_one_language(i);
        } else {
            dump_int(0);
        }
    }
}

static void undump_one_language(int i)
{
    char *s = NULL;
    int x = 0;
    struct tex_language *lang = get_language(i);
    undump_int(x);
    lang->id = x;
    undump_int(x);
    lang->pre_hyphen_char = x;
    undump_int(x);
    lang->post_hyphen_char = x;
    undump_int(x);
    lang->pre_exhyphen_char = x;
    undump_int(x);
    lang->post_exhyphen_char = x;
    undump_int(x);
    lang->hyphenation_min = x;
    /* patterns */
    undump_int(x);
    if (x > 0) {
        s = xmalloc((unsigned) x);
        undump_things(*s, x);
        load_patterns(lang, (unsigned char *) s);
        free(s);
    }
    /* exceptions */
    undump_int(x);
    if (x > 0) {
        s = xmalloc((unsigned) x);
        undump_things(*s, x);
        load_hyphenation(lang, (unsigned char *) s);
        free(s);
    }
}

void undump_language_data(void)
{
    int i, x, numlangs;
    undump_int(numlangs);
    next_lang_id = numlangs;
    for (i = 0; i < numlangs; i++) {
        undump_int(x);
        if (x == 1) {
            undump_one_language(i);
        }
    }
}

@ When \TeX\ has scanned `\.{\\hyphenation}', it calls on a procedure named
|new_hyph_exceptions| to do the right thing.

@c
void new_hyph_exceptions(void)
{                               /* enters new exceptions */
    (void) scan_toks(false, true);
    load_tex_hyphenation(language_par, def_ref);
    flush_list(def_ref);
}

@ Similarly, when \TeX\ has scanned `\.{\\patterns}', it calls on a
procedure named |new_patterns|.

@c
void new_patterns(void)
{                               /* initializes the hyphenation pattern data */
    (void) scan_toks(false, true);
    load_tex_patterns(language_par, def_ref);
    flush_list(def_ref);
}

@ `\.{\\prehyphenchar}', sets the |pre_break| character, and
`\.{\\posthyphenchar}' the |post_break| character. Their respective defaults are
ascii hyphen ("-") and zero (nul).

@c
void new_pre_hyphen_char(void)
{
    scan_optional_equals();
    scan_int();
    set_pre_hyphen_char(language_par, cur_val);
}

void new_post_hyphen_char(void)
{
    scan_optional_equals();
    scan_int();
    set_post_hyphen_char(language_par, cur_val);
}

@ `\.{\\preexhyphenchar}', sets the |pre_break| character, and
`\.{\\postexhyphenchar}' the |post_break| character. Their defaults are both zero
(nul).

@c
void new_pre_exhyphen_char(void)
{
    scan_optional_equals();
    scan_int();
    set_pre_exhyphen_char(language_par, cur_val);
}

void new_post_exhyphen_char(void)
{
    scan_optional_equals();
    scan_int();
    set_post_exhyphen_char(language_par, cur_val);
}

void new_hyphenation_min(void)
{
    scan_optional_equals();
    scan_int();
    set_hyphenation_min(language_par, cur_val);
}

void new_hj_code(void)
{
    int i ;
    scan_int();
    i = cur_val;
    scan_optional_equals();
    scan_int();
    set_hj_code(language_par, i, cur_val, -1);
}