-
-
Notifications
You must be signed in to change notification settings - Fork 39
/
bidi.c
1940 lines (1737 loc) · 61.3 KB
/
bidi.c
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
/* Low-level bidirectional buffer-scanning functions for GNU Emacs.
Copyright (C) 2000-2001, 2004-2005, 2009-2011
Free Software Foundation, Inc.
This file is part of GNU Emacs.
GNU Emacs is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
GNU Emacs is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */
/* Written by Eli Zaretskii <eliz@gnu.org>.
A sequential implementation of the Unicode Bidirectional algorithm,
as per UAX#9, a part of the Unicode Standard.
Unlike the reference and most other implementations, this one is
designed to be called once for every character in the buffer or
string.
The main entry point is bidi_move_to_visually_next. Each time it
is called, it finds the next character in the visual order, and
returns its information in a special structure. The caller is then
expected to process this character for display or any other
purposes, and call bidi_move_to_visually_next for the next
character. See the comments in bidi_move_to_visually_next for more
details about its algorithm that finds the next visual-order
character by resolving their levels on the fly.
The two other entry points are bidi_paragraph_init and
bidi_mirror_char. The first determines the base direction of a
paragraph, while the second returns the mirrored version of its
argument character.
If you want to understand the code, you will have to read it
together with the relevant portions of UAX#9. The comments include
references to UAX#9 rules, for that very reason.
A note about references to UAX#9 rules: if the reference says
something like "X9/Retaining", it means that you need to refer to
rule X9 and to its modifications decribed in the "Implementation
Notes" section of UAX#9, under "Retaining Format Codes". */
#include <config.h>
#include <stdio.h>
#include <setjmp.h>
#include "lisp.h"
#include "buffer.h"
#include "character.h"
#include "dispextern.h"
static int bidi_initialized = 0;
static Lisp_Object bidi_type_table, bidi_mirror_table;
#define LRM_CHAR 0x200E
#define RLM_CHAR 0x200F
#define BIDI_EOB -1
/* Local data structures. (Look in dispextern.h for the rest.) */
/* What we need to know about the current paragraph. */
struct bidi_paragraph_info {
EMACS_INT start_bytepos; /* byte position where it begins */
EMACS_INT end_bytepos; /* byte position where it ends */
int embedding_level; /* its basic embedding level */
bidi_dir_t base_dir; /* its base direction */
};
/* Data type for describing the bidirectional character categories. */
typedef enum {
UNKNOWN_BC,
NEUTRAL,
WEAK,
STRONG
} bidi_category_t;
extern int bidi_ignore_explicit_marks_for_paragraph_level EXTERNALLY_VISIBLE;
int bidi_ignore_explicit_marks_for_paragraph_level = 1;
static Lisp_Object paragraph_start_re, paragraph_separate_re;
static Lisp_Object Qparagraph_start, Qparagraph_separate;
static void
bidi_initialize (void)
{
#include "biditype.h"
#include "bidimirror.h"
int i;
bidi_type_table = Fmake_char_table (Qnil, make_number (STRONG_L));
staticpro (&bidi_type_table);
for (i = 0; i < sizeof bidi_type / sizeof bidi_type[0]; i++)
char_table_set_range (bidi_type_table, bidi_type[i].from, bidi_type[i].to,
make_number (bidi_type[i].type));
bidi_mirror_table = Fmake_char_table (Qnil, Qnil);
staticpro (&bidi_mirror_table);
for (i = 0; i < sizeof bidi_mirror / sizeof bidi_mirror[0]; i++)
char_table_set (bidi_mirror_table, bidi_mirror[i].from,
make_number (bidi_mirror[i].to));
Qparagraph_start = intern ("paragraph-start");
staticpro (&Qparagraph_start);
paragraph_start_re = Fsymbol_value (Qparagraph_start);
if (!STRINGP (paragraph_start_re))
paragraph_start_re = build_string ("\f\\|[ \t]*$");
staticpro (¶graph_start_re);
Qparagraph_separate = intern ("paragraph-separate");
staticpro (&Qparagraph_separate);
paragraph_separate_re = Fsymbol_value (Qparagraph_separate);
if (!STRINGP (paragraph_separate_re))
paragraph_separate_re = build_string ("[ \t\f]*$");
staticpro (¶graph_separate_re);
bidi_initialized = 1;
}
/* Return the bidi type of a character CH, subject to the current
directional OVERRIDE. */
static inline bidi_type_t
bidi_get_type (int ch, bidi_dir_t override)
{
bidi_type_t default_type;
if (ch == BIDI_EOB)
return NEUTRAL_B;
if (ch < 0 || ch > MAX_CHAR)
abort ();
default_type = (bidi_type_t) XINT (CHAR_TABLE_REF (bidi_type_table, ch));
if (override == NEUTRAL_DIR)
return default_type;
switch (default_type)
{
/* Although UAX#9 does not tell, it doesn't make sense to
override NEUTRAL_B and LRM/RLM characters. */
case NEUTRAL_B:
case LRE:
case LRO:
case RLE:
case RLO:
case PDF:
return default_type;
default:
switch (ch)
{
case LRM_CHAR:
case RLM_CHAR:
return default_type;
default:
if (override == L2R) /* X6 */
return STRONG_L;
else if (override == R2L)
return STRONG_R;
else
abort (); /* can't happen: handled above */
}
}
}
static void
bidi_check_type (bidi_type_t type)
{
if (type < UNKNOWN_BT || type > NEUTRAL_ON)
abort ();
}
/* Given a bidi TYPE of a character, return its category. */
static inline bidi_category_t
bidi_get_category (bidi_type_t type)
{
switch (type)
{
case UNKNOWN_BT:
return UNKNOWN_BC;
case STRONG_L:
case STRONG_R:
case STRONG_AL:
case LRE:
case LRO:
case RLE:
case RLO:
return STRONG;
case PDF: /* ??? really?? */
case WEAK_EN:
case WEAK_ES:
case WEAK_ET:
case WEAK_AN:
case WEAK_CS:
case WEAK_NSM:
case WEAK_BN:
return WEAK;
case NEUTRAL_B:
case NEUTRAL_S:
case NEUTRAL_WS:
case NEUTRAL_ON:
return NEUTRAL;
default:
abort ();
}
}
/* Return the mirrored character of C, if it has one. If C has no
mirrored counterpart, return C.
Note: The conditions in UAX#9 clause L4 regarding the surrounding
context must be tested by the caller. */
int
bidi_mirror_char (int c)
{
Lisp_Object val;
if (c == BIDI_EOB)
return c;
if (c < 0 || c > MAX_CHAR)
abort ();
val = CHAR_TABLE_REF (bidi_mirror_table, c);
if (INTEGERP (val))
{
int v = XINT (val);
if (v < 0 || v > MAX_CHAR)
abort ();
return v;
}
return c;
}
/* Copy the bidi iterator from FROM to TO. To save cycles, this only
copies the part of the level stack that is actually in use. */
static inline void
bidi_copy_it (struct bidi_it *to, struct bidi_it *from)
{
int i;
/* Copy everything except the level stack and beyond. */
memcpy (to, from, offsetof (struct bidi_it, level_stack[0]));
/* Copy the active part of the level stack. */
to->level_stack[0] = from->level_stack[0]; /* level zero is always in use */
for (i = 1; i <= from->stack_idx; i++)
to->level_stack[i] = from->level_stack[i];
}
/* Caching the bidi iterator states. */
#define BIDI_CACHE_CHUNK 200
static struct bidi_it *bidi_cache;
static size_t bidi_cache_size = 0;
static size_t elsz = sizeof (struct bidi_it);
static int bidi_cache_idx; /* next unused cache slot */
static int bidi_cache_last_idx; /* slot of last cache hit */
static inline void
bidi_cache_reset (void)
{
bidi_cache_idx = 0;
bidi_cache_last_idx = -1;
}
static inline void
bidi_cache_shrink (void)
{
if (bidi_cache_size > BIDI_CACHE_CHUNK)
{
bidi_cache_size = BIDI_CACHE_CHUNK;
bidi_cache =
(struct bidi_it *) xrealloc (bidi_cache, bidi_cache_size * elsz);
}
bidi_cache_reset ();
}
static inline void
bidi_cache_fetch_state (int idx, struct bidi_it *bidi_it)
{
int current_scan_dir = bidi_it->scan_dir;
if (idx < 0 || idx >= bidi_cache_idx)
abort ();
bidi_copy_it (bidi_it, &bidi_cache[idx]);
bidi_it->scan_dir = current_scan_dir;
bidi_cache_last_idx = idx;
}
/* Find a cached state with a given CHARPOS and resolved embedding
level less or equal to LEVEL. if LEVEL is -1, disregard the
resolved levels in cached states. DIR, if non-zero, means search
in that direction from the last cache hit. */
static inline int
bidi_cache_search (EMACS_INT charpos, int level, int dir)
{
int i, i_start;
if (bidi_cache_idx)
{
if (charpos < bidi_cache[bidi_cache_last_idx].charpos)
{
dir = -1;
i_start = bidi_cache_last_idx - 1;
}
else if (charpos > (bidi_cache[bidi_cache_last_idx].charpos
+ bidi_cache[bidi_cache_last_idx].nchars - 1))
{
dir = 1;
i_start = bidi_cache_last_idx + 1;
}
else if (dir)
i_start = bidi_cache_last_idx;
else
{
dir = -1;
i_start = bidi_cache_idx - 1;
}
if (dir < 0)
{
/* Linear search for now; FIXME! */
for (i = i_start; i >= 0; i--)
if (bidi_cache[i].charpos <= charpos
&& charpos < bidi_cache[i].charpos + bidi_cache[i].nchars
&& (level == -1 || bidi_cache[i].resolved_level <= level))
return i;
}
else
{
for (i = i_start; i < bidi_cache_idx; i++)
if (bidi_cache[i].charpos <= charpos
&& charpos < bidi_cache[i].charpos + bidi_cache[i].nchars
&& (level == -1 || bidi_cache[i].resolved_level <= level))
return i;
}
}
return -1;
}
/* Find a cached state where the resolved level changes to a value
that is lower than LEVEL, and return its cache slot index. DIR is
the direction to search, starting with the last used cache slot.
BEFORE, if non-zero, means return the index of the slot that is
``before'' the level change in the search direction. That is,
given the cached levels like this:
1122333442211
AB C
and assuming we are at the position cached at the slot marked with
C, searching backwards (DIR = -1) for LEVEL = 2 will return the
index of slot B or A, depending whether BEFORE is, respectively,
non-zero or zero. */
static int
bidi_cache_find_level_change (int level, int dir, int before)
{
if (bidi_cache_idx)
{
int i = dir ? bidi_cache_last_idx : bidi_cache_idx - 1;
int incr = before ? 1 : 0;
if (!dir)
dir = -1;
else if (!incr)
i += dir;
if (dir < 0)
{
while (i >= incr)
{
if (bidi_cache[i - incr].resolved_level >= 0
&& bidi_cache[i - incr].resolved_level < level)
return i;
i--;
}
}
else
{
while (i < bidi_cache_idx - incr)
{
if (bidi_cache[i + incr].resolved_level >= 0
&& bidi_cache[i + incr].resolved_level < level)
return i;
i++;
}
}
}
return -1;
}
static inline void
bidi_cache_iterator_state (struct bidi_it *bidi_it, int resolved)
{
int idx;
/* We should never cache on backward scans. */
if (bidi_it->scan_dir == -1)
abort ();
idx = bidi_cache_search (bidi_it->charpos, -1, 1);
if (idx < 0)
{
idx = bidi_cache_idx;
/* Enlarge the cache as needed. */
if (idx >= bidi_cache_size)
{
bidi_cache_size += BIDI_CACHE_CHUNK;
bidi_cache =
(struct bidi_it *) xrealloc (bidi_cache, bidi_cache_size * elsz);
}
/* Character positions should correspond to cache positions 1:1.
If we are outside the range of cached positions, the cache is
useless and must be reset. */
if (idx > 0 &&
(bidi_it->charpos > (bidi_cache[idx - 1].charpos
+ bidi_cache[idx - 1].nchars)
|| bidi_it->charpos < bidi_cache[0].charpos))
{
bidi_cache_reset ();
idx = 0;
}
if (bidi_it->nchars <= 0)
abort ();
bidi_copy_it (&bidi_cache[idx], bidi_it);
if (!resolved)
bidi_cache[idx].resolved_level = -1;
}
else
{
/* Copy only the members which could have changed, to avoid
costly copying of the entire struct. */
bidi_cache[idx].type = bidi_it->type;
bidi_check_type (bidi_it->type);
bidi_cache[idx].type_after_w1 = bidi_it->type_after_w1;
bidi_check_type (bidi_it->type_after_w1);
if (resolved)
bidi_cache[idx].resolved_level = bidi_it->resolved_level;
else
bidi_cache[idx].resolved_level = -1;
bidi_cache[idx].invalid_levels = bidi_it->invalid_levels;
bidi_cache[idx].invalid_rl_levels = bidi_it->invalid_rl_levels;
bidi_cache[idx].next_for_neutral = bidi_it->next_for_neutral;
bidi_cache[idx].next_for_ws = bidi_it->next_for_ws;
bidi_cache[idx].ignore_bn_limit = bidi_it->ignore_bn_limit;
}
bidi_cache_last_idx = idx;
if (idx >= bidi_cache_idx)
bidi_cache_idx = idx + 1;
}
static inline bidi_type_t
bidi_cache_find (EMACS_INT charpos, int level, struct bidi_it *bidi_it)
{
int i = bidi_cache_search (charpos, level, bidi_it->scan_dir);
if (i >= 0)
{
bidi_dir_t current_scan_dir = bidi_it->scan_dir;
bidi_copy_it (bidi_it, &bidi_cache[i]);
bidi_cache_last_idx = i;
/* Don't let scan direction from from the cached state override
the current scan direction. */
bidi_it->scan_dir = current_scan_dir;
return bidi_it->type;
}
return UNKNOWN_BT;
}
static inline int
bidi_peek_at_next_level (struct bidi_it *bidi_it)
{
if (bidi_cache_idx == 0 || bidi_cache_last_idx == -1)
abort ();
return bidi_cache[bidi_cache_last_idx + bidi_it->scan_dir].resolved_level;
}
/* Check if buffer position CHARPOS/BYTEPOS is the end of a paragraph.
Value is the non-negative length of the paragraph separator
following the buffer position, -1 if position is at the beginning
of a new paragraph, or -2 if position is neither at beginning nor
at end of a paragraph. */
static EMACS_INT
bidi_at_paragraph_end (EMACS_INT charpos, EMACS_INT bytepos)
{
Lisp_Object sep_re;
Lisp_Object start_re;
EMACS_INT val;
sep_re = paragraph_separate_re;
start_re = paragraph_start_re;
val = fast_looking_at (sep_re, charpos, bytepos, ZV, ZV_BYTE, Qnil);
if (val < 0)
{
if (fast_looking_at (start_re, charpos, bytepos, ZV, ZV_BYTE, Qnil) >= 0)
val = -1;
else
val = -2;
}
return val;
}
/* Determine the start-of-run (sor) directional type given the two
embedding levels on either side of the run boundary. Also, update
the saved info about previously seen characters, since that info is
generally valid for a single level run. */
static inline void
bidi_set_sor_type (struct bidi_it *bidi_it, int level_before, int level_after)
{
int higher_level = level_before > level_after ? level_before : level_after;
/* The prev_was_pdf gork is required for when we have several PDFs
in a row. In that case, we want to compute the sor type for the
next level run only once: when we see the first PDF. That's
because the sor type depends only on the higher of the two levels
that we find on the two sides of the level boundary (see UAX#9,
clause X10), and so we don't need to know the final embedding
level to which we descend after processing all the PDFs. */
if (!bidi_it->prev_was_pdf || level_before < level_after)
/* FIXME: should the default sor direction be user selectable? */
bidi_it->sor = (higher_level & 1) != 0 ? R2L : L2R;
if (level_before > level_after)
bidi_it->prev_was_pdf = 1;
bidi_it->prev.type = UNKNOWN_BT;
bidi_it->last_strong.type = bidi_it->last_strong.type_after_w1 =
bidi_it->last_strong.orig_type = UNKNOWN_BT;
bidi_it->prev_for_neutral.type = bidi_it->sor == R2L ? STRONG_R : STRONG_L;
bidi_it->prev_for_neutral.charpos = bidi_it->charpos;
bidi_it->prev_for_neutral.bytepos = bidi_it->bytepos;
bidi_it->next_for_neutral.type = bidi_it->next_for_neutral.type_after_w1 =
bidi_it->next_for_neutral.orig_type = UNKNOWN_BT;
bidi_it->ignore_bn_limit = 0; /* meaning it's unknown */
}
/* Perform initializations for reordering a new line of bidi text. */
static void
bidi_line_init (struct bidi_it *bidi_it)
{
bidi_it->scan_dir = 1; /* FIXME: do we need to have control on this? */
bidi_it->resolved_level = bidi_it->level_stack[0].level;
bidi_it->level_stack[0].override = NEUTRAL_DIR; /* X1 */
bidi_it->invalid_levels = 0;
bidi_it->invalid_rl_levels = -1;
bidi_it->next_en_pos = -1;
bidi_it->next_for_ws.type = UNKNOWN_BT;
bidi_set_sor_type (bidi_it,
bidi_it->paragraph_dir == R2L ? 1 : 0,
bidi_it->level_stack[0].level); /* X10 */
bidi_cache_reset ();
}
/* Fetch and return the character at BYTEPOS/CHARPOS. If that
character is covered by a display string, treat the entire run of
covered characters as a single character u+FFFC, and return their
combined length in CH_LEN and NCHARS. DISP_POS specifies the
character position of the next display string, or -1 if not yet
computed. When the next character is at or beyond that position,
the function updates DISP_POS with the position of the next display
string. */
static inline int
bidi_fetch_char (EMACS_INT bytepos, EMACS_INT charpos, EMACS_INT *disp_pos,
int frame_window_p, EMACS_INT *ch_len, EMACS_INT *nchars)
{
int ch;
/* FIXME: Support strings in addition to buffers. */
/* If we got past the last known position of display string, compute
the position of the next one. That position could be at BYTEPOS. */
if (charpos < ZV && charpos > *disp_pos)
*disp_pos = compute_display_string_pos (charpos, frame_window_p);
/* Fetch the character at BYTEPOS. */
if (bytepos >= ZV_BYTE)
{
ch = BIDI_EOB;
*ch_len = 1;
*nchars = 1;
*disp_pos = ZV;
}
else if (charpos >= *disp_pos)
{
EMACS_INT disp_end_pos;
/* We don't expect to find ourselves in the middle of a display
property. Hopefully, it will never be needed. */
if (charpos > *disp_pos)
abort ();
/* Return the Unicode Object Replacement Character to represent
the entire run of characters covered by the display
string. */
ch = 0xFFFC;
disp_end_pos = compute_display_string_end (*disp_pos);
*nchars = disp_end_pos - *disp_pos;
*ch_len = CHAR_TO_BYTE (disp_end_pos) - bytepos;
}
else
{
ch = FETCH_MULTIBYTE_CHAR (bytepos);
*nchars = 1;
*ch_len = CHAR_BYTES (ch);
}
/* If we just entered a run of characters covered by a display
string, compute the position of the next display string. */
if (charpos + *nchars <= ZV && charpos + *nchars > *disp_pos)
*disp_pos = compute_display_string_pos (charpos + *nchars, frame_window_p);
return ch;
}
/* Find the beginning of this paragraph by looking back in the buffer.
Value is the byte position of the paragraph's beginning. */
static EMACS_INT
bidi_find_paragraph_start (EMACS_INT pos, EMACS_INT pos_byte)
{
Lisp_Object re = paragraph_start_re;
EMACS_INT limit = ZV, limit_byte = ZV_BYTE;
while (pos_byte > BEGV_BYTE
&& fast_looking_at (re, pos, pos_byte, limit, limit_byte, Qnil) < 0)
{
/* FIXME: What if the paragraph beginning is covered by a
display string? And what if a display string covering some
of the text over which we scan back includes
paragraph_start_re? */
pos = find_next_newline_no_quit (pos - 1, -1);
pos_byte = CHAR_TO_BYTE (pos);
}
return pos_byte;
}
/* Determine the base direction, a.k.a. base embedding level, of the
paragraph we are about to iterate through. If DIR is either L2R or
R2L, just use that. Otherwise, determine the paragraph direction
from the first strong directional character of the paragraph.
NO_DEFAULT_P non-zero means don't default to L2R if the paragraph
has no strong directional characters and both DIR and
bidi_it->paragraph_dir are NEUTRAL_DIR. In that case, search back
in the buffer until a paragraph is found with a strong character,
or until hitting BEGV. In the latter case, fall back to L2R. This
flag is used in current-bidi-paragraph-direction.
Note that this function gives the paragraph separator the same
direction as the preceding paragraph, even though Emacs generally
views the separartor as not belonging to any paragraph. */
void
bidi_paragraph_init (bidi_dir_t dir, struct bidi_it *bidi_it, int no_default_p)
{
EMACS_INT bytepos = bidi_it->bytepos;
EMACS_INT pstartbyte;
/* Special case for an empty buffer. */
if (bytepos == BEGV_BYTE && bytepos == ZV_BYTE)
dir = L2R;
/* We should never be called at EOB or before BEGV. */
else if (bytepos >= ZV_BYTE || bytepos < BEGV_BYTE)
abort ();
if (dir == L2R)
{
bidi_it->paragraph_dir = L2R;
bidi_it->new_paragraph = 0;
}
else if (dir == R2L)
{
bidi_it->paragraph_dir = R2L;
bidi_it->new_paragraph = 0;
}
else if (dir == NEUTRAL_DIR) /* P2 */
{
int ch;
EMACS_INT ch_len, nchars;
EMACS_INT pos, disp_pos = -1;
bidi_type_t type;
if (!bidi_initialized)
bidi_initialize ();
/* If we are inside a paragraph separator, we are just waiting
for the separator to be exhausted; use the previous paragraph
direction. But don't do that if we have been just reseated,
because we need to reinitialize below in that case. */
if (!bidi_it->first_elt
&& bidi_it->charpos < bidi_it->separator_limit)
return;
/* If we are on a newline, get past it to where the next
paragraph might start. But don't do that at BEGV since then
we are potentially in a new paragraph that doesn't yet
exist. */
pos = bidi_it->charpos;
if (bytepos > BEGV_BYTE && FETCH_CHAR (bytepos) == '\n')
{
bytepos++;
pos++;
}
/* We are either at the beginning of a paragraph or in the
middle of it. Find where this paragraph starts. */
pstartbyte = bidi_find_paragraph_start (pos, bytepos);
bidi_it->separator_limit = -1;
bidi_it->new_paragraph = 0;
/* The following loop is run more than once only if NO_DEFAULT_P
is non-zero. */
do {
bytepos = pstartbyte;
pos = BYTE_TO_CHAR (bytepos);
ch = bidi_fetch_char (bytepos, pos, &disp_pos, bidi_it->frame_window_p,
&ch_len, &nchars);
type = bidi_get_type (ch, NEUTRAL_DIR);
for (pos += nchars, bytepos += ch_len;
/* NOTE: UAX#9 says to search only for L, AL, or R types
of characters, and ignore RLE, RLO, LRE, and LRO.
However, I'm not sure it makes sense to omit those 4;
should try with and without that to see the effect. */
(bidi_get_category (type) != STRONG)
|| (bidi_ignore_explicit_marks_for_paragraph_level
&& (type == RLE || type == RLO
|| type == LRE || type == LRO));
type = bidi_get_type (ch, NEUTRAL_DIR))
{
if (bytepos >= ZV_BYTE)
{
/* Pretend there's a paragraph separator at end of
buffer. */
type = NEUTRAL_B;
break;
}
if (type == NEUTRAL_B && bidi_at_paragraph_end (pos, bytepos) >= -1)
break;
/* Fetch next character and advance to get past it. */
ch = bidi_fetch_char (bytepos, pos, &disp_pos,
bidi_it->frame_window_p, &ch_len, &nchars);
pos += nchars;
bytepos += ch_len;
}
if (type == STRONG_R || type == STRONG_AL) /* P3 */
bidi_it->paragraph_dir = R2L;
else if (type == STRONG_L)
bidi_it->paragraph_dir = L2R;
if (no_default_p && bidi_it->paragraph_dir == NEUTRAL_DIR)
{
/* If this paragraph is at BEGV, default to L2R. */
if (pstartbyte == BEGV_BYTE)
bidi_it->paragraph_dir = L2R; /* P3 and HL1 */
else
{
EMACS_INT prevpbyte = pstartbyte;
EMACS_INT p = BYTE_TO_CHAR (pstartbyte), pbyte = pstartbyte;
/* Find the beginning of the previous paragraph, if any. */
while (pbyte > BEGV_BYTE && prevpbyte >= pstartbyte)
{
/* FXIME: What if p is covered by a display
string? See also a FIXME inside
bidi_find_paragraph_start. */
p--;
pbyte = CHAR_TO_BYTE (p);
prevpbyte = bidi_find_paragraph_start (p, pbyte);
}
pstartbyte = prevpbyte;
}
}
} while (no_default_p && bidi_it->paragraph_dir == NEUTRAL_DIR);
}
else
abort ();
/* Contrary to UAX#9 clause P3, we only default the paragraph
direction to L2R if we have no previous usable paragraph
direction. This is allowed by the HL1 clause. */
if (bidi_it->paragraph_dir != L2R && bidi_it->paragraph_dir != R2L)
bidi_it->paragraph_dir = L2R; /* P3 and HL1 ``higher-level protocols'' */
if (bidi_it->paragraph_dir == R2L)
bidi_it->level_stack[0].level = 1;
else
bidi_it->level_stack[0].level = 0;
bidi_line_init (bidi_it);
}
/* Do whatever UAX#9 clause X8 says should be done at paragraph's
end. */
static inline void
bidi_set_paragraph_end (struct bidi_it *bidi_it)
{
bidi_it->invalid_levels = 0;
bidi_it->invalid_rl_levels = -1;
bidi_it->stack_idx = 0;
bidi_it->resolved_level = bidi_it->level_stack[0].level;
}
/* Initialize the bidi iterator from buffer/string position CHARPOS. */
void
bidi_init_it (EMACS_INT charpos, EMACS_INT bytepos, int frame_window_p,
struct bidi_it *bidi_it)
{
if (! bidi_initialized)
bidi_initialize ();
bidi_it->charpos = charpos;
bidi_it->bytepos = bytepos;
bidi_it->frame_window_p = frame_window_p;
bidi_it->nchars = -1; /* to be computed in bidi_resolve_explicit_1 */
bidi_it->first_elt = 1;
bidi_set_paragraph_end (bidi_it);
bidi_it->new_paragraph = 1;
bidi_it->separator_limit = -1;
bidi_it->type = NEUTRAL_B;
bidi_it->type_after_w1 = NEUTRAL_B;
bidi_it->orig_type = NEUTRAL_B;
bidi_it->prev_was_pdf = 0;
bidi_it->prev.type = bidi_it->prev.type_after_w1 =
bidi_it->prev.orig_type = UNKNOWN_BT;
bidi_it->last_strong.type = bidi_it->last_strong.type_after_w1 =
bidi_it->last_strong.orig_type = UNKNOWN_BT;
bidi_it->next_for_neutral.charpos = -1;
bidi_it->next_for_neutral.type =
bidi_it->next_for_neutral.type_after_w1 =
bidi_it->next_for_neutral.orig_type = UNKNOWN_BT;
bidi_it->prev_for_neutral.charpos = -1;
bidi_it->prev_for_neutral.type =
bidi_it->prev_for_neutral.type_after_w1 =
bidi_it->prev_for_neutral.orig_type = UNKNOWN_BT;
bidi_it->sor = L2R; /* FIXME: should it be user-selectable? */
bidi_it->disp_pos = -1; /* invalid/unknown */
bidi_cache_shrink ();
}
/* Push the current embedding level and override status; reset the
current level to LEVEL and the current override status to OVERRIDE. */
static inline void
bidi_push_embedding_level (struct bidi_it *bidi_it,
int level, bidi_dir_t override)
{
bidi_it->stack_idx++;
if (bidi_it->stack_idx >= BIDI_MAXLEVEL)
abort ();
bidi_it->level_stack[bidi_it->stack_idx].level = level;
bidi_it->level_stack[bidi_it->stack_idx].override = override;
}
/* Pop the embedding level and directional override status from the
stack, and return the new level. */
static inline int
bidi_pop_embedding_level (struct bidi_it *bidi_it)
{
/* UAX#9 says to ignore invalid PDFs. */
if (bidi_it->stack_idx > 0)
bidi_it->stack_idx--;
return bidi_it->level_stack[bidi_it->stack_idx].level;
}
/* Record in SAVED_INFO the information about the current character. */
static inline void
bidi_remember_char (struct bidi_saved_info *saved_info,
struct bidi_it *bidi_it)
{
saved_info->charpos = bidi_it->charpos;
saved_info->bytepos = bidi_it->bytepos;
saved_info->type = bidi_it->type;
bidi_check_type (bidi_it->type);
saved_info->type_after_w1 = bidi_it->type_after_w1;
bidi_check_type (bidi_it->type_after_w1);
saved_info->orig_type = bidi_it->orig_type;
bidi_check_type (bidi_it->orig_type);
}
/* Resolve the type of a neutral character according to the type of
surrounding strong text and the current embedding level. */
static inline bidi_type_t
bidi_resolve_neutral_1 (bidi_type_t prev_type, bidi_type_t next_type, int lev)
{
/* N1: European and Arabic numbers are treated as though they were R. */
if (next_type == WEAK_EN || next_type == WEAK_AN)
next_type = STRONG_R;
if (prev_type == WEAK_EN || prev_type == WEAK_AN)
prev_type = STRONG_R;
if (next_type == prev_type) /* N1 */
return next_type;
else if ((lev & 1) == 0) /* N2 */
return STRONG_L;
else
return STRONG_R;
}
static inline int
bidi_explicit_dir_char (int ch)
{
bidi_type_t ch_type;
if (!bidi_initialized)
abort ();
ch_type = (bidi_type_t) XINT (CHAR_TABLE_REF (bidi_type_table, ch));
return (ch_type == LRE || ch_type == LRO
|| ch_type == RLE || ch_type == RLO
|| ch_type == PDF);
}
/* A helper function for bidi_resolve_explicit. It advances to the
next character in logical order and determines the new embedding
level and directional override, but does not take into account
empty embeddings. */
static int
bidi_resolve_explicit_1 (struct bidi_it *bidi_it)
{
int curchar;
bidi_type_t type;
int current_level;
int new_level;
bidi_dir_t override;
/* If reseat()'ed, don't advance, so as to start iteration from the
position where we were reseated. bidi_it->bytepos can be less
than BEGV_BYTE after reseat to BEGV. */
if (bidi_it->bytepos < BEGV_BYTE
|| bidi_it->first_elt)
{
bidi_it->first_elt = 0;
if (bidi_it->charpos < BEGV)
bidi_it->charpos = BEGV;
bidi_it->bytepos = CHAR_TO_BYTE (bidi_it->charpos);
}
else if (bidi_it->bytepos < ZV_BYTE) /* don't move at ZV */
{
/* Advance to the next character, skipping characters covered by
display strings (nchars > 1). */
if (bidi_it->nchars <= 0)
abort ();
bidi_it->charpos += bidi_it->nchars;
if (bidi_it->ch_len == 0)
abort ();
bidi_it->bytepos += bidi_it->ch_len;
}
current_level = bidi_it->level_stack[bidi_it->stack_idx].level; /* X1 */
override = bidi_it->level_stack[bidi_it->stack_idx].override;
new_level = current_level;
if (bidi_it->bytepos >= ZV_BYTE)
{
curchar = BIDI_EOB;
bidi_it->ch_len = 1;
bidi_it->nchars = 1;
bidi_it->disp_pos = ZV;
}
else
{
/* Fetch the character at BYTEPOS. If it is covered by a
display string, treat the entire run of covered characters as
a single character u+FFFC. */
curchar = bidi_fetch_char (bidi_it->bytepos, bidi_it->charpos,
&bidi_it->disp_pos, bidi_it->frame_window_p,
&bidi_it->ch_len, &bidi_it->nchars);
}
bidi_it->ch = curchar;
/* Don't apply directional override here, as all the types we handle
below will not be affected by the override anyway, and we need
the original type unaltered. The override will be applied in
bidi_resolve_weak. */
type = bidi_get_type (curchar, NEUTRAL_DIR);
bidi_it->orig_type = type;
bidi_check_type (bidi_it->orig_type);
if (type != PDF)
bidi_it->prev_was_pdf = 0;
bidi_it->type_after_w1 = UNKNOWN_BT;
switch (type)
{
case RLE: /* X2 */
case RLO: /* X4 */
bidi_it->type_after_w1 = type;