summaryrefslogtreecommitdiffstats
path: root/term.c
blob: 19eda90093b28b735f9cabb65d20581f83f1c76e (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
/* $Id$ */
/*
 * Copyright (c) 2008, 2009 Kristaps Dzonsons <kristaps@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.
 */
#include <assert.h>
#include <err.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "term.h"
#include "man.h"
#include "mdoc.h"

extern	int		  man_run(struct termp *, 
				const struct man *);
extern	int		  mdoc_run(struct termp *, 
				const struct mdoc *);

static	struct termp	 *term_alloc(enum termenc);
static	void		  term_free(struct termp *);
static	void		  term_pword(struct termp *, const char *, int);
static	void		  term_pescape(struct termp *, 
				const char *, int *, int);
static	void		  term_nescape(struct termp *,
				const char *, size_t);
static	void		  term_chara(struct termp *, char);
static	void		  term_stringa(struct termp *, 
				const char *, size_t);
static	int		  term_isopendelim(const char *, int);
static	int		  term_isclosedelim(const char *, int);


void *
ascii_alloc(void)
{

	return(term_alloc(TERMENC_ASCII));
}


int
terminal_man(void *arg, const struct man *man)
{
	struct termp	*p;

	p = (struct termp *)arg;
	if (NULL == p->symtab)
		p->symtab = term_ascii2htab();

	return(man_run(p, man));
}


int
terminal_mdoc(void *arg, const struct mdoc *mdoc)
{
	struct termp	*p;

	p = (struct termp *)arg;
	if (NULL == p->symtab)
		p->symtab = term_ascii2htab();

	return(mdoc_run(p, mdoc));
}


void
terminal_free(void *arg)
{

	term_free((struct termp *)arg);
}


static void
term_free(struct termp *p)
{

	if (p->buf)
		free(p->buf);
	if (TERMENC_ASCII == p->enc && p->symtab)
		term_asciifree(p->symtab);

	free(p);
}


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

	if (NULL == (p = malloc(sizeof(struct termp))))
		err(1, "malloc");
	bzero(p, sizeof(struct termp));
	p->maxrmargin = 78;
	p->enc = enc;
	return(p);
}


static int
term_isclosedelim(const char *p, int len)
{

	if (1 != len)
		return(0);

	switch (*p) {
	case('.'):
		/* FALLTHROUGH */
	case(','):
		/* FALLTHROUGH */
	case(';'):
		/* FALLTHROUGH */
	case(':'):
		/* FALLTHROUGH */
	case('?'):
		/* FALLTHROUGH */
	case('!'):
		/* FALLTHROUGH */
	case(')'):
		/* FALLTHROUGH */
	case(']'):
		/* FALLTHROUGH */
	case('}'):
		return(1);
	default:
		break;
	}

	return(0);
}


static int
term_isopendelim(const char *p, int len)
{

	if (1 != len)
		return(0);

	switch (*p) {
	case('('):
		/* FALLTHROUGH */
	case('['):
		/* FALLTHROUGH */
	case('{'):
		return(1);
	default:
		break;
	}

	return(0);
}


/*
 * 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.
 *
 * Specifically, a line is whatever's in p->buf of length p->col, which
 * is zeroed after this function returns.
 *
 * The variables TERMP_NOLPAD, TERMP_LITERAL and TERMP_NOBREAK are of
 * critical importance here.  Their behaviour follows:
 *
 *  - 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_NONOBREAK: don't newline when TERMP_NOBREAK is specified.
 *
 *  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.  Extremely long
 *  lines will cause the system to emit a warning (TODO: hyphenate, if
 *  possible).
 */
void
term_flushln(struct termp *p)
{
	int		 i, j;
	size_t		 vsz, vis, maxvis, mmax, 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->offset < p->rmargin);
	maxvis = p->rmargin - p->offset;
	mmax = p->maxrmargin - p->offset;
	bp = TERMP_NOBREAK & p->flags ? mmax : maxvis;
	vis = 0;

	/*
	 * If in the standard case (left-justified), then begin with our
	 * indentation, otherwise (columns, etc.) just start spitting
	 * out text.
	 */

	if ( ! (p->flags & TERMP_NOLPAD))
		/* LINTED */
		for (j = 0; j < (int)p->offset; j++)
			putchar(' ');

	for (i = 0; i < (int)p->col; 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).
		 */

		/* LINTED */
		for (j = i, vsz = 0; j < (int)p->col; j++) {
			if (' ' == p->buf[j])
				break;
			else if (8 == p->buf[j])
				j += 1;
			else
				vsz++;
		}

		/*
		 * Do line-breaking.  If we're greater than our
		 * break-point and already in-line, break to the next
		 * line and start writing.  If we're at the line start,
		 * then write out the word (TODO: hyphenate) and break
		 * in a subsequent loop invocation.
		 */

		if ( ! (TERMP_NOBREAK & p->flags)) {
			if (vis && vis + vsz > bp) {
				putchar('\n');
				for (j = 0; j < (int)p->offset; j++)
					putchar(' ');
				vis = 0;
			} 
		} else if (vis && vis + vsz > bp) {
			putchar('\n');
			for (j = 0; j < (int)p->rmargin; j++)
				putchar(' ');
			vis = p->rmargin - p->offset;
		}

		/* 
		 * Write out the word and a trailing space.  Omit the
		 * space if we're the last word in the line or beyond
		 * our breakpoint.
		 */

		for ( ; i < (int)p->col; i++) {
			if (' ' == p->buf[i])
				break;
			putchar(p->buf[i]);
		}
		vis += vsz;
		if (i < (int)p->col && vis <= bp) {
			putchar(' ');
			vis++;
		}
	}

	/*
	 * If we've overstepped our maximum visible no-break space, then
	 * cause a newline and offset at the right margin.
	 */

	if ((TERMP_NOBREAK & p->flags) && vis >= maxvis) {
		if ( ! (TERMP_NONOBREAK & p->flags)) {
			putchar('\n');
			for (i = 0; i < (int)p->rmargin; i++)
				putchar(' ');
		}
		p->col = 0;
		return;
	}

	/*
	 * If we're not to right-marginalise it (newline), then instead
	 * pad to the right margin and stay off.
	 */

	if (p->flags & TERMP_NOBREAK) {
		if ( ! (TERMP_NONOBREAK & p->flags))
			for ( ; vis < maxvis; vis++)
				putchar(' ');
	} else
		putchar('\n');

	p->col = 0;
}


/* 
 * 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) {
		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);
	putchar('\n');
}


/*
 * Break apart a word into "pwords" (partial-words, usually from
 * breaking up a phrase into individual words) and, eventually, put them
 * into the output buffer.  If we're a literal word, then don't break up
 * the word and put it verbatim into the output buffer.
 */
void
term_word(struct termp *p, const char *word)
{
	int 		 i, j, len;

	len = (int)strlen(word);

	if (p->flags & TERMP_LITERAL) {
		term_pword(p, word, len);
		return;
	}

	/* LINTED */
	for (j = i = 0; i < len; i++) {
		if (' ' != word[i]) {
			j++;
			continue;
		} 
		
		/* Escaped spaces don't delimit... */
		if (i && ' ' == word[i] && '\\' == word[i - 1]) {
			j++;
			continue;
		}

		if (0 == j)
			continue;
		assert(i >= j);
		term_pword(p, &word[i - j], j);
		j = 0;
	}
	if (j > 0) {
		assert(i >= j);
		term_pword(p, &word[i - j], j);
	}
}


/*
 * Determine the symbol indicated by an escape sequences, that is, one
 * starting with a backslash.  Once done, we pass this value into the
 * output buffer by way of the symbol table.
 */
static void
term_nescape(struct termp *p, const char *word, size_t len)
{
	const char	*rhs;
	size_t		 sz;

	if (NULL == (rhs = term_a2ascii(p->symtab, word, len, &sz))) 
		return;
	term_stringa(p, rhs, sz);
}


/*
 * Handle an escape sequence: determine its length and pass it to the
 * escape-symbol look table.  Note that we assume mdoc(3) has validated
 * the escape sequence (we assert upon badly-formed escape sequences).
 */
static void
term_pescape(struct termp *p, const char *word, int *i, int len)
{
	int		 j;

	if (++(*i) >= len)
		return;

	if ('(' == word[*i]) {
		(*i)++;
		if (*i + 1 >= len)
			return;

		term_nescape(p, &word[*i], 2);
		(*i)++;
		return;

	} else if ('*' == word[*i]) { 
		(*i)++;
		if (*i >= len)
			return;

		switch (word[*i]) {
		case ('('):
			(*i)++;
			if (*i + 1 >= len)
				return;

			term_nescape(p, &word[*i], 2);
			(*i)++;
			return;
		case ('['):
			break;
		default:
			term_nescape(p, &word[*i], 1);
			return;
		}
	
	} else if ('f' == word[*i]) {
		(*i)++;
		if (*i >= len)
			return;
		switch (word[*i]) {
		case ('B'):
			p->flags |= TERMP_BOLD;
			break;
		case ('I'):
			p->flags |= TERMP_UNDER;
			break;
		case ('P'):
			/* FALLTHROUGH */
		case ('R'):
			p->flags &= ~TERMP_STYLE;
			break;
		default:
			break;
		}
		return;

	} else if ('[' != word[*i]) {
		term_nescape(p, &word[*i], 1);
		return;
	}

	(*i)++;
	for (j = 0; word[*i] && ']' != word[*i]; (*i)++, j++)
		/* Loop... */ ;

	if (0 == word[*i])
		return;

	term_nescape(p, &word[*i - j], (size_t)j);
}


/*
 * 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.
 */
static void
term_pword(struct termp *p, const char *word, int len)
{
	int		 i;

	if (term_isclosedelim(word, len))
		if ( ! (TERMP_IGNDELIM & p->flags))
			p->flags |= TERMP_NOSPACE;

	if ( ! (TERMP_NOSPACE & p->flags))
		term_chara(p, ' ');

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

	/* 
	 * If ANSI (word-length styling), then apply our style now,
	 * before the word.
	 */

	for (i = 0; i < len; i++) {
		if ('\\' == word[i]) {
			term_pescape(p, word, &i, len);
			continue;
		}

		if (TERMP_STYLE & p->flags) {
			if (TERMP_BOLD & p->flags) {
				term_chara(p, word[i]);
				term_chara(p, 8);
			}
			if (TERMP_UNDER & p->flags) {
				term_chara(p, '_');
				term_chara(p, 8);
			}
		}

		term_chara(p, word[i]);
	}

	if (term_isopendelim(word, len))
		p->flags |= TERMP_NOSPACE;
}


/*
 * Like term_chara() but for arbitrary-length buffers.  Resize the
 * buffer by a factor of two (if the buffer is less than that) or the
 * buffer's size.
 */
static void
term_stringa(struct termp *p, const char *c, size_t sz)
{
	size_t		 s;

	if (0 == sz)
		return;

	assert(c);
	if (p->col + sz >= p->maxcols) {
		if (0 == p->maxcols)
			p->maxcols = 256;
		s = sz > p->maxcols * 2 ? sz : p->maxcols * 2;
		p->buf = realloc(p->buf, s);
		if (NULL == p->buf)
			err(1, "realloc");
		p->maxcols = s;
	}

	(void)memcpy(&p->buf[(int)p->col], c, sz);
	p->col += sz;
}


/*
 * Insert a single character into the line-buffer.  If the buffer's
 * space is exceeded, then allocate more space by doubling the buffer
 * size.
 */
static void
term_chara(struct termp *p, char c)
{
	size_t		 s;

	if (p->col + 1 >= p->maxcols) {
		if (0 == p->maxcols)
			p->maxcols = 256;
		s = p->maxcols * 2;
		p->buf = realloc(p->buf, s);
		if (NULL == p->buf)
			err(1, "realloc");
		p->maxcols = s;
	}
	p->buf[(int)(p->col)++] = c;
}