-
-
Notifications
You must be signed in to change notification settings - Fork 0
/
defmt.c
1475 lines (1419 loc) · 40.9 KB
/
defmt.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
#ifndef lint
static char Rcs_Id[] =
"$Id: defmt.c,v 1.65 2020-12-30 22:33:41-08 geoff Exp $";
#endif
/*
* defmt.c - Handle formatter constructs, mostly by scanning over them.
*
* This code originally resided in ispell.c, but was moved here to keep
* file sizes smaller.
*
* Copyright (c), 1983, by Pace Willisson
*
* Copyright 1992, 1993, 1999, 2001, Geoff Kuenning, Claremont, CA
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. All modifications to the source code must be clearly marked as
* such. Binary redistributions based on modified source code
* must be clearly marked as modified versions in the documentation
* and/or other materials provided with the distribution.
* 4. The code that causes the 'ispell -v' command to display a prominent
* link to the official ispell Web site may not be removed.
* 5. The name of Geoff Kuenning may not be used to endorse or promote
* products derived from this software without specific prior
* written permission.
*
* THIS SOFTWARE IS PROVIDED BY GEOFF KUENNING AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL GEOFF KUENNING OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* The TeX code is originally by Greg Schaffer, with many improvements from
* Ken Stevens. The nroff code is primarily from Pace Willisson, although
* other people have improved it.
*/
/*
* $Log: defmt.c,v $
* Revision 1.65 2020-12-30 22:33:41-08 geoff
* Support SQUEEZE_STRINGS.
*
* Revision 1.64 2015-02-08 16:09:24-08 geoff
* When skipping curly-braced environment arguments, allow nested curlies.
*
* Revision 1.63 2015-02-08 01:28:09-08 geoff
* Keep track of how many dollar signs were used to enter math mode, so
* that we only parse the same number on exit.
*
* Revision 1.62 2005-04-20 16:16:32-07 geoff
* Use inpossibilities to deal with the case where uppercase SS in German
* causes ambiguities.
*
* Revision 1.61 2005/04/14 14:38:23 geoff
* Update license.
*
* Revision 1.60 2001/11/28 22:39:26 geoff
* Add Ken Stevens's fix for newlines in \verb
*
* Revision 1.59 2001/09/06 00:30:29 geoff
* Many changes from Eli Zaretskii to support DJGPP compilation.
*
* Revision 1.58 2001/08/01 22:15:56 geoff
* When processing quoted strings inside HTML tags, don't handle
* ampersand sequences unless the quoted string is being spell-checked.
* That way, ampersands inside HREF links won't confuse the deformatter,
* but ampersand sequence inside ALT= tags will be handled correctly.
* Also, when skipping ampersand sequences inside quoted strings, give up
* the search for the semicolon if the closing quote is hit. This change
* makes us a bit more robust in the fact of HTML syntax errors.
*
* Revision 1.57 2001/07/25 21:51:47 geoff
* Minor license update.
*
* Revision 1.56 2001/07/23 20:24:03 geoff
* Update the copyright and the license.
*
* Revision 1.55 2000/08/22 10:52:25 geoff
* Fix a whole bunch of signed/unsigned compiler warnings.
*
* Revision 1.54 2000/08/22 00:11:25 geoff
* Add support for correct_verbose_mode.
*
* Revision 1.53 1999/11/04 08:16:54 geoff
* Add a few more special TeX sequences
*
* Revision 1.52 1999/01/18 03:28:27 geoff
* Turn many char declarations into unsigned char, so that we won't have
* sign-extension problems.
*
* Revision 1.51 1999/01/07 01:57:53 geoff
* Update the copyright.
*
* Revision 1.50 1999/01/03 01:46:28 geoff
* Add support for external deformatters.
*
* Revision 1.49 1998/07/07 02:30:53 geoff
* Implement the plus notation for adding to keyword lists
*
* Revision 1.48 1998/07/06 06:55:13 geoff
* Generalize the HTML tag routines to be handy keyword lookup routines,
* and fix some (but by no means all) of the TeX deformatting to take
* advantage of these routines to allow a bit more flexibility in
* processing private TeX commands.
*
* Revision 1.47 1998/07/06 05:34:10 geoff
* Add a few more TeX commands
*
* Revision 1.46 1997/12/01 00:53:47 geoff
* Add HTML support. Fix the "\ " bug again, this time (hopefully) right.
*
* Revision 1.45 1995/11/08 05:09:29 geoff
* Add the new interactive mode ("askverbose").
*
* Revision 1.44 1995/11/08 04:32:51 geoff
* Modify the HTML support to be stylistically more consistent and to
* interoperate more cleanly with the nroff and TeX modes.
*
* Revision 1.43 1995/10/25 04:05:31 geoff
* html-mode code added by Gerry Tierney <gtierney@nova.ucd.ie> 14th of
* Oct '95.
*
* Revision 1.42 1995/10/25 03:35:42 geoff
* After skipping over a backslash sequence, make sure that we don't skip
* over the first character of the following word. Also, support the
* verbatim environment of LaTex.
*
* Revision 1.41 1995/08/05 23:19:47 geoff
* Get rid of an obsolete comment. Add recognition of documentclass and
* usepackage for Latex2e support.
*
* Revision 1.40 1995/03/06 02:42:43 geoff
* Change TeX backslash processing so that it only assumes alpha
* characters and the commonly-used "@" character are part of macro
* names, and so that any other backslashed character (specifically
* dollar signs) is skipped.
*
* Revision 1.39 1995/01/08 23:23:54 geoff
* Fix typos in a couple of comments.
*
* Revision 1.38 1995/01/03 19:24:14 geoff
* Add code to handle the LaTeX \verb command.
*
* Revision 1.37 1994/12/27 23:08:54 geoff
* Fix a bug in TeX backslash processing that caused ispell to become
* confused when it encountered an optional argument to a
* double-backslash command. Be a little smarter about scanning for
* curly-brace matches, so that we avoid missing a math-mode transition
* during the scan.
*
* Revision 1.36 1994/10/25 05:46:34 geoff
* Recognize a few more Latex commands: pagestyle, pagenumbering,
* setcounter, addtocounter, setlength, addtolength, settowidth.
*
* Revision 1.35 1994/10/18 04:03:19 geoff
* Add code to skip hex numbers if they're preceded by '0x'.
*
* Revision 1.34 1994/10/04 03:51:24 geoff
* Modify the parsing so that TeX commands are ignored even within
* comments, but do not affect the overall parsing state. (This is
* slightly imperfect, in that some types of modality are ignored when
* comments are entered. But it should solve nearly all the problems
* with commented-out TeX commands.) This also fixes a couple of minor
* bugs with TeX deformatting.
*
* Revision 1.33 1994/10/03 17:06:07 geoff
* Remember to use contextoffset when reporting complete misses
*
* Revision 1.32 1994/08/31 05:58:41 geoff
* Report the offset-within-line correctly in -a mode even if the line is
* longer than BUFSIZ characters.
*
* Revision 1.31 1994/05/25 04:29:28 geoff
* If two boundary characters appear in a row, consider it the end of the
* word.
*
* Revision 1.30 1994/05/17 06:44:08 geoff
* Add the new argument to all calls to good and compoundgood.
*
* Revision 1.29 1994/03/16 06:30:41 geoff
* Don't lose track of math mode when an array environment is embedded.
*
* Revision 1.28 1994/03/15 05:31:57 geoff
* Add TeX_strncmp, which allows us to handle AMS-TeX constructs like
* \endroster without getting confused.
*
* Revision 1.27 1994/02/14 00:34:53 geoff
* Pass length arguments to correct().
*
* Revision 1.26 1994/01/25 07:11:25 geoff
* Get rid of all old RCS log lines in preparation for the 3.1 release.
*
*/
#include <ctype.h>
#include "config.h"
#include "ispell.h"
#include "proto.h"
#include "msgs.h"
static unsigned char *
skiptoword P ((unsigned char * bufp));
unsigned char * skipoverword P ((unsigned char * bufp));
void checkline P ((FILE * ofile));
static int TeX_math_end P ((unsigned char ** bufp));
static int TeX_math_begin P ((unsigned char ** bufp));
static int TeX_LR_begin P ((unsigned char ** bufp));
static int TeX_LR_check P ((int begin_p, unsigned char ** bufp));
static void TeX_skip_args P ((unsigned char ** bufp));
static int TeX_math_check P ((int cont_char, unsigned char ** bufp));
static void TeX_skip_parens P ((unsigned char ** bufp));
static void TeX_open_paren P ((unsigned char ** bufp));
static void TeX_skip_check P ((unsigned char ** bufp));
static int TeX_strncmp P ((unsigned char * a, char * b, int n));
int init_keyword_table P ((char * rawtags, char * envvar,
char * deftags, int ignorecase, struct kwtable * keywords));
static int keyword_in_list P ((unsigned char * string,
unsigned char * stringend, struct kwtable * keywords));
static int tagcmp P ((unsigned char ** a, unsigned char ** b));
#define ISTEXTERM(c) (((c) == TEXLEFTCURLY) || \
((c) == TEXRIGHTCURLY) || \
((c) == TEXLEFTSQUARE) || \
((c) == TEXRIGHTSQUARE))
#define ISMATHCH(c) (((c) == TEXBACKSLASH) || \
((c) == TEXDOLLAR) || \
((c) == TEXPERCENT))
static int TeX_comment = 0;
static int wordadjust; /* Stringchar difference in word len */
/*
* The following variables are used to save the parsing state when
* processing comments. This allows comments to be parsed without
* affecting the overall nesting.
*/
static int save_math_mode;
static char save_LaTeX_Mode;
/*
* The following variable indicates whether math mode was entered with
* a single or double dollar sign. Each time math mode is entered
* with dollar signs, it is shifted left by one bit, and it is shifted
* right on math exit. If the low-order bit is a 1, math mode was
* entered with a double dollar; otherwise it was entered with a
* single dollar. Note that this is a kludge that breaks on illegal
* syntax.
*/
static unsigned int math_mode_dollars = 0;
/*
* The following variables are used by the deformatter to keep
* track of keywords that may indicate text to be ignored.
*/
static unsigned char *
keywordbuf; /* Scratch buffer for keyword comparison */
static unsigned int
maxkeywordlen; /* Length of longest keyword */
static unsigned char * skiptoword (bufp) /* Skip to beginning of a word */
unsigned char * bufp;
{
unsigned char * htmltagstart; /* Beginning of an HTML tag */
unsigned char * htmlsubfield = bufp;
/* Ptr to start of subfield name */
while (*bufp
&& ((!isstringch (bufp, 0) && !iswordch (chartoichar (*bufp)))
|| isboundarych (chartoichar (*bufp))
|| (tflag == DEFORMAT_TEX && ((math_mode & 1) || LaTeX_Mode != 'P'))
|| (insidehtml & (HTML_IN_SPEC | HTML_ISIGNORED)) != 0
|| ((insidehtml & HTML_IN_TAG) != 0
&& (insidehtml
& (HTML_IN_QUOTE | HTML_CHECKING_QUOTE))
!= (HTML_IN_QUOTE | HTML_CHECKING_QUOTE))
)
)
{
/*
* HTML deformatting
*/
if (tflag == DEFORMAT_SGML)
{
if ((insidehtml & HTML_IN_TAG) != 0 && *bufp == HTMLQUOTE)
{
if (insidehtml & HTML_IN_QUOTE)
insidehtml &= ~(HTML_IN_QUOTE | HTML_CHECKING_QUOTE);
else
insidehtml |= HTML_IN_QUOTE;
htmlsubfield = NULL;
}
else if ((insidehtml & (HTML_IN_TAG | HTML_IN_QUOTE))
== HTML_IN_TAG
&& *bufp == HTMLTAGEND)
insidehtml &=
~(HTML_IN_TAG | HTML_IN_ENDTAG | HTML_CHECKING_QUOTE);
/*
* If we are checking an HTML file, we want to ignore any HTML
* tags. These should start with a '<' and end with a '>', so
* we simply skip over anything between these two symbols. If
* we reach the end of the line before finding a matching '>',
* we set 'insidehtml' appropriately.
*/
else if ((insidehtml & HTML_IN_TAG) == 0
&& *bufp == HTMLTAGSTART)
{
insidehtml |= HTML_IN_TAG;
bufp++;
if (*bufp == HTMLSLASH)
{
bufp++;
insidehtml |= HTML_IN_ENDTAG;
}
htmltagstart = bufp;
/*
* We found the start of an HTML tag. Skip to the end
* of the tag. We assume that all tags are made up of
* purely alphabetic characters.
*/
while (isalpha (*bufp))
bufp++;
/*
* Check to see if this is an ignored tag, and set
* HTML_IGNORE properly.
*/
if (keyword_in_list (htmltagstart, bufp, &htmlignorelist))
{
/*
* Note that we use +/- here, rather than Boolean
* operators. This is quite deliberate, because
* it allows us to properly handle nested HTML
* constructs that are supposed to be ignored.
*/
if (insidehtml & HTML_IN_ENDTAG)
insidehtml -= HTML_IGNORE;
else
insidehtml += HTML_IGNORE;
}
htmlsubfield = NULL;
if (bufp > htmltagstart)
bufp--;
}
else if ((insidehtml & (HTML_IN_TAG | HTML_IN_QUOTE))
== HTML_IN_TAG)
{
if (htmlsubfield == NULL && isalpha (*bufp))
htmlsubfield = bufp;
else if (htmlsubfield != NULL && !isalpha (*bufp))
{
if (bufp != htmlsubfield
&& keyword_in_list (htmlsubfield, bufp, &htmlchecklist))
insidehtml |= HTML_CHECKING_QUOTE;
htmlsubfield = NULL;
}
}
/*
* Skip over quoted entities such as """. These all
* start with an ampersand and end with a semi-colon. We
* do not need to worry about them extending over more
* than one line. We also don't need to worry about them
* being string characters, because the isstringch() test
* above would have already broken us out of the enclosing
* loop in that case.
*
* A complication is that quoted entities are only
* interpreted in some quoted strings. For example,
* they're valid in ALT= tags but not in HREF tags, where
* ampersands have an entirely different meaning. We deal
* with the problem by only interpreting HTMLSPECSTART if
* we are checking the quoted string.
*/
else if ((insidehtml & HTML_IN_SPEC) != 0
|| (*bufp == HTMLSPECSTART
&& ((insidehtml & HTML_CHECKING_QUOTE)
|| (insidehtml & HTML_IN_QUOTE) == 0)))
{
while (*bufp != HTMLSPECEND && *bufp != '\0')
{
if ((insidehtml & HTML_IN_QUOTE) && *bufp == HTMLQUOTE)
{
/*
* The quoted string ended before the
* ampersand sequence finished. The HTML is
* probably incorrect, but it would be a
* mistake to keep skipping until we reach the
* next random semicolon. Instead, just stop
* skipping right here.
*/
insidehtml &= ~(HTML_IN_QUOTE | HTML_CHECKING_QUOTE);
break;
}
bufp++;
}
if (*bufp == '\0')
insidehtml |= HTML_IN_SPEC;
else
insidehtml &= ~HTML_IN_SPEC;
}
}
else if (tflag == DEFORMAT_TEX) /* TeX or LaTeX stuff */
{
/* Odd numbers mean we are in "math mode" */
/* Even numbers mean we are in LR or */
/* paragraph mode */
if (*bufp == TEXPERCENT && LaTeX_Mode != 'v')
{
if (!TeX_comment)
{
save_math_mode = math_mode;
save_LaTeX_Mode = LaTeX_Mode;
math_mode = 0;
LaTeX_Mode = 'P';
TeX_comment = 1;
}
}
else if (math_mode & 1)
{
if ((LaTeX_Mode == 'e' && TeX_math_check('e', &bufp))
|| (LaTeX_Mode == 'm' && TeX_LR_check(1, &bufp)))
math_mode--; /* end math mode */
else
{
while (*bufp && !ISMATHCH(*bufp))
bufp++;
if (*bufp == 0)
break;
if (TeX_math_end(&bufp))
math_mode--;
}
if (math_mode < 0)
{
(void) fprintf (stderr, DEFMT_C_TEX_MATH_ERROR,
MAYBE_CR (stderr));
math_mode = 0;
}
}
else
{
if (math_mode > 1
&& *bufp == TEXRIGHTCURLY
&& (math_mode < (math_mode & 127) * 128))
math_mode--; /* re-enter math */
else if (LaTeX_Mode == 'm'
|| (math_mode && (math_mode >= (math_mode & 127) * 128)
&& (TeX_strncmp(bufp, "\\end", 4)
== 0)))
{
if (TeX_LR_check(0, &bufp))
math_mode--;
}
else if (LaTeX_Mode == 'b' && TeX_math_check('b', &bufp))
{
/* continued begin */
math_mode++;
}
else if (LaTeX_Mode == 'r')
{
/* continued "reference" */
TeX_skip_parens(&bufp);
LaTeX_Mode = 'P';
}
else if (LaTeX_Mode == 'v')
{
/* continued "verb" */
while (*bufp != save_LaTeX_Mode && *bufp != '\0')
bufp++;
if (*bufp != 0)
LaTeX_Mode = 'P';
}
else if (TeX_math_begin(&bufp))
/* checks references and */
/* skips \ commands */
math_mode++;
}
if (*bufp == 0)
break;
}
else if (tflag == DEFORMAT_NROFF) /* nroff deformatting */
{
if (*bufp == NRBACKSLASH)
{
switch ( bufp[1] )
{
case 'f':
if(bufp[2] == NRLEFTPAREN)
{
/* font change: \f(XY */
bufp += 5;
}
else
{
/* ) */
/* font change: \fX */
bufp += 3;
}
continue;
case 's':
/* size change */
bufp += 2;
if (*bufp == '+' || *bufp == '-')
bufp++;
/* This looks weird 'cause we
** assume *bufp is now a digit.
*/
bufp++;
if (isdigit (*bufp))
bufp++;
continue;
default:
if (bufp[1] == NRLEFTPAREN)
{
/* extended char set */
/* escape: \(XX */
/* ) */
bufp += 4;
continue;
}
else if (bufp[1] == NRSTAR)
{
if (bufp[2] == NRLEFTPAREN)
bufp += 5;
else
bufp += 3;
continue;
}
break;
}
}
}
/*
* Skip hex numbers, but not if we're in non-terse askmode.
* (In that case, we'd lose sync if we skipped hex.)
*/
if (*bufp == '0'
&& (bufp[1] == 'x' || bufp[1] == 'X')
&& (terse || !aflag))
{
bufp += 2;
while (isxdigit (*bufp))
bufp++;
}
else
bufp++;
}
if (*bufp == '\0')
{
if (TeX_comment)
{
math_mode = save_math_mode;
LaTeX_Mode = save_LaTeX_Mode;
TeX_comment = 0;
}
}
return bufp;
}
/*
* Return a pointer to the end of a word. As a side effect, sets
* wordadjust to reflect the difference between the true length of the
* word in bytes and its apparent length in characters; this is used
* for the SQUEEZE_STRINGS option.
*/
unsigned char * skipoverword (bufp) /* Return pointer to end of a word */
register unsigned char *
bufp; /* Start of word -- MUST BE A REAL START */
{
register unsigned char *
lastboundary;
register int scharlen; /* Length of a string character */
lastboundary = NULL;
wordadjust = 0;
for ( ; ; )
{
if (*bufp == '\0')
{
if (TeX_comment)
{
math_mode = save_math_mode;
LaTeX_Mode = save_LaTeX_Mode;
TeX_comment = 0;
}
break;
}
else if (l_isstringch(bufp, scharlen, 0))
{
bufp += scharlen;
lastboundary = NULL;
if (chartypes[defstringgroup].options & SQUEEZE_STRINGS)
wordadjust += scharlen - 1;
}
/*
** Note that we get here if a character satisfies
** isstringstart() but isn't in the string table; this
** allows string characters to start with word characters.
*/
else if (iswordch (chartoichar (*bufp)))
{
bufp++;
lastboundary = NULL;
}
else if (isboundarych (chartoichar (*bufp)))
{
if (lastboundary == NULL)
lastboundary = bufp;
else if (lastboundary == bufp - 1)
break; /* Double boundary -- end of word */
bufp++;
}
else
break; /* End of the word */
}
/*
** If the word ended in one or more boundary characters,
** the address of the first of these is in lastboundary, and it
** is the end of the word. Otherwise, bufp is the end.
*/
return (lastboundary != NULL) ? lastboundary : bufp;
}
void checkline (ofile)
FILE * ofile;
{
unsigned char * currentchar; /* Location in contextbufs */
register unsigned char *
p;
register unsigned char *
endp;
int hadlf;
register int len;
register int i;
int ilen;
unsigned char * wordstart; /* Where current word started */
currentchar = filteredbuf;
len = strlen ((char *) filteredbuf) - 1;
hadlf = filteredbuf[len] == '\n';
if (hadlf)
{
filteredbuf[len] = '\0';
contextbufs[0][len] = '\0';
}
if (tflag == DEFORMAT_NROFF)
{
/* skip over .if */
if (*currentchar == NRDOT
&& (strncmp ((char *) currentchar + 1, "if t", 4) == 0
|| strncmp ((char *) currentchar + 1, "if n", 4) == 0))
{
copyout (¤tchar,5);
while (*currentchar
&& myspace (chartoichar (*currentchar)))
copyout (¤tchar, 1);
}
/* skip over .ds XX or .nr XX */
if (*currentchar == NRDOT
&& (strncmp ((char *) currentchar + 1, "ds ", 3) == 0
|| strncmp ((char *) currentchar + 1, "de ", 3) == 0
|| strncmp ((char *) currentchar + 1, "nr ", 3) == 0))
{
copyout (¤tchar, 4);
while (*currentchar
&& myspace (chartoichar (*currentchar)))
copyout(¤tchar, 1);
while (*currentchar
&& !myspace (chartoichar (*currentchar)))
copyout(¤tchar, 1);
if (*currentchar == 0)
{
if (!lflag && hadlf)
(void) putc ('\n', ofile);
return;
}
}
}
/* if this is a formatter command, skip over it */
if (tflag == DEFORMAT_NROFF && *currentchar == NRDOT)
{
while (*currentchar && !myspace (chartoichar (*currentchar)))
{
if (!aflag && !lflag)
(void) putc (*currentchar, ofile);
currentchar++;
}
if (*currentchar == 0)
{
if (!lflag && hadlf)
(void) putc ('\n', ofile);
return;
}
}
for ( ; ; contextoffset -= wordadjust)
{
wordstart = skiptoword (currentchar);
if (wordstart != currentchar)
copyout (¤tchar, wordstart - currentchar);
if (*currentchar == 0)
break;
p = ctoken;
endp = skipoverword (currentchar);
while (currentchar < endp && p < ctoken + sizeof ctoken - 1)
*p++ = *currentchar++;
*p = 0;
if (strtoichar (itoken, ctoken, INPUTWORDLEN * sizeof (ichar_t), 0))
(void) fprintf (stderr, WORD_TOO_LONG ((char *) ctoken));
ilen = icharlen (itoken);
if (lflag)
{
if (ilen > minword
&& !good (itoken, 0, 0, 0, 0)
&& !cflag && !compoundgood (itoken, 0))
(void) fprintf (ofile, "%s\n", (char *) ctoken);
}
else
{
if (aflag)
{
if (ilen <= minword)
{
/* matched because of minword */
if (!terse)
{
if (askverbose)
(void) fprintf (ofile, "ok\n");
else
{
if (correct_verbose_mode)
(void) fprintf (ofile, "* %s\n", ctoken );
else
(void) fprintf (ofile, "*\n");
}
}
continue;
}
if (good (itoken, 0, 0, 0, 0))
{
if (hits[0].prefix == NULL
&& hits[0].suffix == NULL)
{
/* perfect match */
if (!terse)
{
if (askverbose)
(void) fprintf (ofile, "ok\n");
else
{
if (correct_verbose_mode)
(void) fprintf (ofile, "* %s\n", ctoken );
else
(void) fprintf (ofile, "*\n");
}
}
}
else if (!terse)
{
/* matched because of root */
if (askverbose)
(void) fprintf (ofile,
"ok (derives from root %s)\n",
(char *) hits[0].dictent->word);
else
{
if (correct_verbose_mode)
(void) fprintf (ofile, "+ %s %s\n",
ctoken, hits[0].dictent->word);
else
(void) fprintf (ofile, "+ %s\n",
hits[0].dictent->word);
}
}
}
else if (compoundgood (itoken, 0))
{
/* compound-word match */
if (!terse)
{
if (askverbose)
(void) fprintf (ofile, "ok (compound word)\n");
else
{
if (correct_verbose_mode)
(void) fprintf (ofile, "- %s\n", ctoken);
else
(void) fprintf (ofile, "-\n");
}
}
}
else
{
makepossibilities (itoken);
if (inpossibilities (ctoken)) /* Kludge for German, etc. */
{
/* might not be perfect match, but we'll lie */
if (!terse)
{
if (askverbose)
(void) fprintf (ofile, "ok\n");
else
{
if (correct_verbose_mode)
(void) fprintf (ofile, "* %s\n", ctoken );
else
(void) fprintf (ofile, "*\n");
}
}
}
else if (pcount)
{
/*
** print & or ?, ctoken, then
** character offset, possibility
** count, and the possibilities.
*/
if (askverbose)
(void) fprintf (ofile, "how about");
else
(void) fprintf (ofile, "%c %s %d %d",
easypossibilities ? '&' : '?',
(char *) ctoken,
easypossibilities,
(int) (wordstart - filteredbuf + contextoffset));
for (i = 0; i < MAXPOSSIBLE; i++)
{
if (possibilities[i][0] == 0)
break;
(void) fprintf (ofile, "%c %s",
i ? ',' : ':', possibilities[i]);
}
(void) fprintf (ofile, "\n");
}
else
{
/*
** No possibilities found for word TOKEN
*/
if (askverbose)
(void) fprintf (ofile, "not found\n");
else
(void) fprintf (ofile, "# %s %d\n",
(char *) ctoken,
(int) (wordstart - filteredbuf + contextoffset));
}
}
}
else
{
if (!quit)
correct (ctoken, sizeof ctoken, itoken, sizeof itoken,
¤tchar);
}
}
if (!aflag && !lflag)
(void) fprintf (ofile, "%s", (char *) ctoken);
}
if (!lflag && hadlf)
(void) putc ('\n', ofile);
}
/* must check for \begin{mbox} or whatever makes new text region. */
static int TeX_math_end (bufp)
unsigned char ** bufp;
{
if (**bufp == TEXDOLLAR)
{
if ((*bufp)[1] == TEXDOLLAR && (math_mode_dollars & 1) != 0)
(*bufp)++;
math_mode_dollars >>= 1;
return 1;
}
else if (**bufp == TEXPERCENT)
{
if (!TeX_comment)
{
save_math_mode = math_mode;
save_LaTeX_Mode = LaTeX_Mode;
math_mode = 0;
LaTeX_Mode = 'P';
TeX_comment = 1;
}
return 0;
}
/* processing extended TeX command */
(*bufp)++;
if (**bufp == TEXRIGHTPAREN || **bufp == TEXRIGHTSQUARE)
return 1;
if (TeX_LR_begin (bufp)) /* check for switch back to LR mode */
return 1;
if (TeX_strncmp (*bufp, "end", 3) == 0)
/* find environment that is ending */
return TeX_math_check ('e', bufp);
else
return 0;
}
static int TeX_math_begin (bufp)
unsigned char ** bufp;
{
int didskip = 0;
if (**bufp == TEXDOLLAR)
{
math_mode_dollars <<= 1;
if ((*bufp)[1] == TEXDOLLAR)
{
math_mode_dollars |= 1;
(*bufp)++;
}
return 1;
}
while (**bufp == TEXBACKSLASH)
{
didskip = 1;
(*bufp)++; /* check for null char here? */
if (**bufp == TEXLEFTPAREN || **bufp == TEXLEFTSQUARE)
return 1;
else if (!isalpha(**bufp) && **bufp != '@')
{
(*bufp)++;
continue;
}
else if (TeX_strncmp (*bufp, "begin", 5) == 0)
{
if (TeX_math_check ('b', bufp))
return 1;
else
(*bufp)--;
}
else
{
TeX_skip_check (bufp);
return 0;
}
}
/*
* Ignore references for the tib (1) bibliography system, that
* is, text between a ``[.'' or ``<.'' and ``.]'' or ``.>''.
* We don't care whether they match, tib doesn't care either.
*
* A limitation is that the entire tib reference must be on one
* line, or we break down and check the remainder anyway.
*/
if ((**bufp == TEXLEFTSQUARE || **bufp == TEXLEFTANGLE)
&& (*bufp)[1] == TEXDOT)
{
(*bufp)++;
while (**bufp)
{
if (*(*bufp)++ == TEXDOT
&& (**bufp == TEXRIGHTSQUARE || **bufp == TEXRIGHTANGLE))
return TeX_math_begin (bufp);
}
return 0;
}
else if (didskip)
{
/*
* If we've skipped over anything, it's possible that we are
* pointing at an important character. If so, we need to back up
* one byte, because our caller will increment bufp. Yes,
* this is a kludge. This whole TeX deformatter is a mess.
*/
(*bufp)--;
}
return 0;
}
static int TeX_LR_begin (bufp)
unsigned char ** bufp;
{
if ((TeX_strncmp (*bufp, "mbox", 4) == 0)
|| (TeX_strncmp (*bufp, "makebox", 7) == 0)
|| (TeX_strncmp (*bufp, "text", 4) == 0)
|| (TeX_strncmp (*bufp, "intertext", 9) == 0)
|| (TeX_strncmp (*bufp, "fbox", 4) == 0)
|| (TeX_strncmp (*bufp, "framebox", 8) == 0))