summaryrefslogtreecommitdiffstats
path: root/term.c
blob: 2e24eb3db4e118d05bdeee34c3c326fcf1788441 (plain) (blame)
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
/*	$Id$ */
/*
 * Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons <kristaps@bsd.lv>
 * Copyright (c) 2010, 2011 Ingo Schwarze <schwarze@openbsd.org>
 *
 * Permission to use, copy, modify, and distribute this software for any
 * purpose with or without fee is hereby granted, provided that the above
 * copyright notice and this permission notice appear in all copies.
 *
 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
 * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
 * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
 * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 */
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#include <sys/types.h>

#include <assert.h>
#include <ctype.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "mandoc.h"
#include "chars.h"
#include "out.h"
#include "term.h"
#include "main.h"

static	void		  spec(struct termp *, enum roffdeco,
				const char *, size_t);
static	void		  res(struct termp *, const char *, size_t);
static	void		  bufferc(struct termp *, char);
static	void		  adjbuf(struct termp *p, size_t);
static	void		  encode(struct termp *, const char *, size_t);


void
term_free(struct termp *p)
{

	if (p->buf)
		free(p->buf);
	if (p->symtab)
		chars_free(p->symtab);

	free(p);
}


void
term_begin(struct termp *p, term_margin head, 
		term_margin foot, const void *arg)
{

	p->headf = head;
	p->footf = foot;
	p->argf = arg;
	(*p->begin)(p);
}


void
term_end(struct termp *p)
{

	(*p->end)(p);
}


struct termp *
term_alloc(enum termenc enc)
{
	struct termp	*p;

	p = mandoc_calloc(1, sizeof(struct termp));
	p->enc = enc;
	return(p);
}


/*
 * Flush a line of text.  A "line" is loosely defined as being something
 * that should be followed by a newline, regardless of whether it's
 * broken apart by newlines getting there.  A line can also be a
 * fragment of a columnar list (`Bl -tag' or `Bl -column'), which does
 * not have a trailing newline.
 *
 * The following flags may be specified:
 *
 *  - TERMP_NOLPAD: when beginning to write the line, don't left-pad the
 *    offset value.  This is useful when doing columnar lists where the
 *    prior column has right-padded.
 *
 *  - TERMP_NOBREAK: this is the most important and is used when making
 *    columns.  In short: don't print a newline and instead pad to the
 *    right margin.  Used in conjunction with TERMP_NOLPAD.
 *
 *  - TERMP_TWOSPACE: when padding, make sure there are at least two
 *    space characters of padding.  Otherwise, rather break the line.
 *
 *  - TERMP_DANGLE: don't newline when TERMP_NOBREAK is specified and
 *    the line is overrun, and don't pad-right if it's underrun.
 *
 *  - TERMP_HANG: like TERMP_DANGLE, but doesn't newline when
 *    overruning, instead save the position and continue at that point
 *    when the next invocation.
 *
 *  In-line line breaking:
 *
 *  If TERMP_NOBREAK is specified and the line overruns the right
 *  margin, it will break and pad-right to the right margin after
 *  writing.  If maxrmargin is violated, it will break and continue
 *  writing from the right-margin, which will lead to the above scenario
 *  upon exit.  Otherwise, the line will break at the right margin.
 */
void
term_flushln(struct termp *p)
{
	int		 i;     /* current input position in p->buf */
	size_t		 vis;   /* current visual position on output */
	size_t		 vbl;   /* number of blanks to prepend to output */
	size_t		 vend;	/* end of word visual position on output */
	size_t		 bp;    /* visual right border position */
	size_t		 dv;    /* temporary for visual pos calculations */
	int		 j;     /* temporary loop index for p->buf */
	int		 jhy;	/* last hyph before overflow w/r/t j */
	size_t		 maxvis; /* output position of visible boundary */
	size_t		 mmax; /* used in calculating bp */

	/*
	 * First, establish the maximum columns of "visible" content.
	 * This is usually the difference between the right-margin and
	 * an indentation, but can be, for tagged lists or columns, a
	 * small set of values. 
	 */
	assert  (p->rmargin >= p->offset);
	dv     = p->rmargin - p->offset;
	maxvis = (int)dv > p->overstep ? dv - (size_t)p->overstep : 0;
	dv     = p->maxrmargin - p->offset;
	mmax   = (int)dv > p->overstep ? dv - (size_t)p->overstep : 0;

	bp = TERMP_NOBREAK & p->flags ? mmax : maxvis;

	/*
	 * Indent the first line of a paragraph.
	 */
	vbl = p->flags & TERMP_NOLPAD ? (size_t)0 : p->offset;

	vis = vend = 0;
	i = 0;

	while (i < (int)p->col) {
		/*
		 * Handle literal tab characters: collapse all
		 * subsequent tabs into a single huge set of spaces.
		 */
		while (i < (int)p->col && '\t' == p->buf[i]) {
			vend = (vis / p->tabwidth + 1) * p->tabwidth;
			vbl += vend - vis;
			vis = vend;
			i++;
		}

		/*
		 * Count up visible word characters.  Control sequences
		 * (starting with the CSI) aren't counted.  A space
		 * generates a non-printing word, which is valid (the
		 * space is printed according to regular spacing rules).
		 */

		for (j = i, jhy = 0; j < (int)p->col; j++) {
			if ((j && ' ' == p->buf[j]) || '\t' == p->buf[j])
				break;

			/* Back over the the last printed character. */
			if (8 == p->buf[j]) {
				assert(j);
				vend -= (*p->width)(p, p->buf[j - 1]);
				continue;
			}

			/* Regular word. */
			/* Break at the hyphen point if we overrun. */
			if (vend > vis && vend < bp && 
					ASCII_HYPH == p->buf[j])
				jhy = j;

			vend += (*p->width)(p, p->buf[j]);
		}

		/*
		 * Find out whether we would exceed the right margin.
		 * If so, break to the next line.
		 */
		if (vend > bp && 0 == jhy && vis > 0) {
			vend -= vis;
			(*p->endline)(p);
			if (TERMP_NOBREAK & p->flags) {
				p->viscol = p->rmargin;
				(*p->advance)(p, p->rmargin);
				vend += p->rmargin - p->offset;
			} else {
				p->viscol = 0;
				vbl = p->offset;
			}

			/* Remove the p->overstep width. */

			bp += (size_t)p->overstep;
			p->overstep = 0;
		}

		/* Write out the [remaining] word. */
		for ( ; i < (int)p->col; i++) {
			if (vend > bp && jhy > 0 && i > jhy)
				break;
			if ('\t' == p->buf[i])
				break;
			if (' ' == p->buf[i]) {
				j = i;
				while (' ' == p->buf[i])
					i++;
				dv = (size_t)(i - j) * (*p->width)(p, ' ');
				vbl += dv;
				vend += dv;
				break;
			}
			if (ASCII_NBRSP == p->buf[i]) {
				vbl += (*p->width)(p, ' ');
				continue;
			}

			/*
			 * Now we definitely know there will be
			 * printable characters to output,
			 * so write preceding white space now.
			 */
			if (vbl) {
				(*p->advance)(p, vbl);
				p->viscol += vbl;
				vbl = 0;
			}

			if (ASCII_HYPH == p->buf[i]) {
				(*p->letter)(p, '-');
				p->viscol += (*p->width)(p, '-');
			} else {
				(*p->letter)(p, p->buf[i]);
				p->viscol += (*p->width)(p, p->buf[i]);
			}
		}
		vis = vend;
	}

	/*
	 * If there was trailing white space, it was not printed;
	 * so reset the cursor position accordingly.
	 */
	vis -= vbl;

	p->col = 0;
	p->overstep = 0;

	if ( ! (TERMP_NOBREAK & p->flags)) {
		p->viscol = 0;
		(*p->endline)(p);
		return;
	}

	if (TERMP_HANG & p->flags) {
		/* We need one blank after the tag. */
		p->overstep = (int)(vis - maxvis + (*p->width)(p, ' '));

		/*
		 * Behave exactly the same way as groff:
		 * If we have overstepped the margin, temporarily move
		 * it to the right and flag the rest of the line to be
		 * shorter.
		 * If we landed right at the margin, be happy.
		 * If we are one step before the margin, temporarily
		 * move it one step LEFT and flag the rest of the line
		 * to be longer.
		 */
		if (p->overstep >= -1) {
			assert((int)maxvis + p->overstep >= 0);
			maxvis += (size_t)p->overstep;
		} else
			p->overstep = 0;

	} else if (TERMP_DANGLE & p->flags)
		return;

	/* Right-pad. */
	if (maxvis > vis +
	    ((TERMP_TWOSPACE & p->flags) ? (*p->width)(p, ' ') : 0)) {
		p->viscol += maxvis - vis;
		(*p->advance)(p, maxvis - vis);
		vis += (maxvis - vis);
	} else {	/* ...or newline break. */
		(*p->endline)(p);
		p->viscol = p->rmargin;
		(*p->advance)(p, p->rmargin);
	}
}


/* 
 * A newline only breaks an existing line; it won't assert vertical
 * space.  All data in the output buffer is flushed prior to the newline
 * assertion.
 */
void
term_newln(struct termp *p)
{

	p->flags |= TERMP_NOSPACE;
	if (0 == p->col && 0 == p->viscol) {
		p->flags &= ~TERMP_NOLPAD;
		return;
	}
	term_flushln(p);
	p->flags &= ~TERMP_NOLPAD;
}


/*
 * Asserts a vertical space (a full, empty line-break between lines).
 * Note that if used twice, this will cause two blank spaces and so on.
 * All data in the output buffer is flushed prior to the newline
 * assertion.
 */
void
term_vspace(struct termp *p)
{

	term_newln(p);
	p->viscol = 0;
	(*p->endline)(p);
}


static void
numbered(struct termp *p, const char *word, size_t len)
{
	const char	*rhs;

	rhs = chars_num2char(word, len);
	if (rhs) 
		encode(p, rhs, 1);
}


static void
spec(struct termp *p, enum roffdeco d, const char *word, size_t len)
{
	const char	*rhs;
	size_t		 sz;

	rhs = chars_spec2str(p->symtab, word, len, &sz);
	if (rhs) 
		encode(p, rhs, sz);
	else if (DECO_SSPECIAL == d)
		encode(p, word, len);
}


static void
res(struct termp *p, const char *word, size_t len)
{
	const char	*rhs;
	size_t		 sz;

	rhs = chars_res2str(p->symtab, word, len, &sz);
	if (rhs)
		encode(p, rhs, sz);
}


void
term_fontlast(struct termp *p)
{
	enum termfont	 f;

	f = p->fontl;
	p->fontl = p->fontq[p->fonti];
	p->fontq[p->fonti] = f;
}


void
term_fontrepl(struct termp *p, enum termfont f)
{

	p->fontl = p->fontq[p->fonti];
	p->fontq[p->fonti] = f;
}


void
term_fontpush(struct termp *p, enum termfont f)
{

	assert(p->fonti + 1 < 10);
	p->fontl = p->fontq[p->fonti];
	p->fontq[++p->fonti] = f;
}


const void *
term_fontq(struct termp *p)
{

	return(&p->fontq[p->fonti]);
}


enum termfont
term_fonttop(struct termp *p)
{

	return(p->fontq[p->fonti]);
}


void
term_fontpopq(struct termp *p, const void *key)
{

	while (p->fonti >= 0 && key != &p->fontq[p->fonti])
		p->fonti--;
	assert(p->fonti >= 0);
}


void
term_fontpop(struct termp *p)
{

	assert(p->fonti);
	p->fonti--;
}


/*
 * Handle pwords, partial words, which may be either a single word or a
 * phrase that cannot be broken down (such as a literal string).  This
 * handles word styling.
 */
void
term_word(struct termp *p, const char *word)
{
	const char	*sv, *seq;
	size_t		 ssz;
	enum roffdeco	 deco;

	sv = word;

	if (DELIM_CLOSE == mandoc_isdelim(word))
		if ( ! (TERMP_IGNDELIM & p->flags))
			p->flags |= TERMP_NOSPACE;

	if ( ! (TERMP_NOSPACE & p->flags)) {
		if ( ! (TERMP_KEEP & p->flags)) {
			if (TERMP_PREKEEP & p->flags)
				p->flags |= TERMP_KEEP;
			bufferc(p, ' ');
			if (TERMP_SENTENCE & p->flags)
				bufferc(p, ' ');
		} else
			bufferc(p, ASCII_NBRSP);
	}

	if ( ! (p->flags & TERMP_NONOSPACE))
		p->flags &= ~TERMP_NOSPACE;
	else
		p->flags |= TERMP_NOSPACE;

	p->flags &= ~(TERMP_SENTENCE | TERMP_IGNDELIM);

	while (*word) {
		if ((ssz = strcspn(word, "\\")) > 0)
			encode(p, word, ssz);

		word += (int)ssz;
		if ('\\' != *word)
			continue;

		seq = ++word;
		word += a2roffdeco(&deco, &seq, &ssz);

		switch (deco) {
		case (DECO_NUMBERED):
			numbered(p, seq, ssz);
			break;
		case (DECO_RESERVED):
			res(p, seq, ssz);
			break;
		case (DECO_SPECIAL):
			/* FALLTHROUGH */
		case (DECO_SSPECIAL):
			spec(p, deco, seq, ssz);
			break;
		case (DECO_BOLD):
			term_fontrepl(p, TERMFONT_BOLD);
			break;
		case (DECO_ITALIC):
			term_fontrepl(p, TERMFONT_UNDER);
			break;
		case (DECO_ROMAN):
			term_fontrepl(p, TERMFONT_NONE);
			break;
		case (DECO_PREVIOUS):
			term_fontlast(p);
			break;
		default:
			break;
		}

		if (DECO_NOSPACE == deco && '\0' == *word)
			p->flags |= TERMP_NOSPACE;
	}

	if (DELIM_OPEN == mandoc_isdelim(sv))
		p->flags |= TERMP_NOSPACE;
}


static void
adjbuf(struct termp *p, size_t sz)
{

	if (0 == p->maxcols)
		p->maxcols = 1024;
	while (sz >= p->maxcols)
		p->maxcols <<= 2;

	p->buf = mandoc_realloc(p->buf, p->maxcols);
}


static void
bufferc(struct termp *p, char c)
{

	if (p->col + 1 >= p->maxcols)
		adjbuf(p, p->col + 1);

	p->buf[(int)p->col++] = c;
}


static void
encode(struct termp *p, const char *word, size_t sz)
{
	enum termfont	  f;
	int		  i;

	/*
	 * Encode and buffer a string of characters.  If the current
	 * font mode is unset, buffer directly, else encode then buffer
	 * character by character.
	 */

	if (TERMFONT_NONE == (f = term_fonttop(p))) {
		if (p->col + sz >= p->maxcols) 
			adjbuf(p, p->col + sz);
		memcpy(&p->buf[(int)p->col], word, sz);
		p->col += sz;
		return;
	}

	/* Pre-buffer, assuming worst-case. */

	if (p->col + 1 + (sz * 3) >= p->maxcols)
		adjbuf(p, p->col + 1 + (sz * 3));

	for (i = 0; i < (int)sz; i++) {
		if ( ! isgraph((u_char)word[i])) {
			p->buf[(int)p->col++] = word[i];
			continue;
		}

		if (TERMFONT_UNDER == f)
			p->buf[(int)p->col++] = '_';
		else
			p->buf[(int)p->col++] = word[i];

		p->buf[(int)p->col++] = 8;
		p->buf[(int)p->col++] = word[i];
	}
}


size_t
term_len(const struct termp *p, size_t sz)
{

	return((*p->width)(p, ' ') * sz);
}


size_t
term_strlen(const struct termp *p, const char *cp)
{
	size_t		 sz, ssz, rsz, i;
	enum roffdeco	 d;
	const char	*seq, *rhs;

	for (sz = 0; '\0' != *cp; )
		/*
		 * Account for escaped sequences within string length
		 * calculations.  This follows the logic in term_word()
		 * as we must calculate the width of produced strings.
		 */
		if ('\\' == *cp) {
			seq = ++cp;
			cp += a2roffdeco(&d, &seq, &ssz);

			switch (d) {
			case (DECO_RESERVED):
				rhs = chars_res2str
					(p->symtab, seq, ssz, &rsz);
				break;
			case (DECO_SPECIAL):
				/* FALLTHROUGH */
			case (DECO_SSPECIAL):
				rhs = chars_spec2str
					(p->symtab, seq, ssz, &rsz);

				/* Allow for one-char escapes. */
				if (DECO_SSPECIAL != d || rhs)
					break;

				rhs = seq;
				rsz = ssz;
				break;
			default:
				rhs = NULL;
				break;
			}

			if (rhs)
				for (i = 0; i < rsz; i++)
					sz += (*p->width)(p, *rhs++);
		} else if (ASCII_NBRSP == *cp) {
			sz += (*p->width)(p, ' ');
			cp++;
		} else if (ASCII_HYPH == *cp) {
			sz += (*p->width)(p, '-');
			cp++;
		} else
			sz += (*p->width)(p, *cp++);

	return(sz);
}


/* ARGSUSED */
size_t
term_vspan(const struct termp *p, const struct roffsu *su)
{
	double		 r;

	switch (su->unit) {
	case (SCALE_CM):
		r = su->scale * 2;
		break;
	case (SCALE_IN):
		r = su->scale * 6;
		break;
	case (SCALE_PC):
		r = su->scale;
		break;
	case (SCALE_PT):
		r = su->scale / 8;
		break;
	case (SCALE_MM):
		r = su->scale / 1000;
		break;
	case (SCALE_VS):
		r = su->scale;
		break;
	default:
		r = su->scale - 1;
		break;
	}

	if (r < 0.0)
		r = 0.0;
	return(/* LINTED */(size_t)
			r);
}


size_t
term_hspan(const struct termp *p, const struct roffsu *su)
{
	double		 v;

	v = ((*p->hspan)(p, su));
	if (v < 0.0)
		v = 0.0;
	return((size_t) /* LINTED */
			v);
}