summaryrefslogtreecommitdiff
path: root/usr.bin/hexdump/parse.c
blob: 0fbdc9b7e51685988785fa58de5abcb542ba6377 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
/*	$OpenBSD: parse.c,v 1.13 2003/06/12 20:58:09 deraadt Exp $	*/
/*	$NetBSD: parse.c,v 1.12 2001/12/07 13:37:39 bjh21 Exp $	*/

/*
 * Copyright (c) 1989, 1993
 *	The Regents of the University of California.  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. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS 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 THE REGENTS 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.
 */

#ifndef lint
/*static char sccsid[] = "from: @(#)parse.c	5.6 (Berkeley) 3/9/91";*/
static char rcsid[] = "$OpenBSD: parse.c,v 1.13 2003/06/12 20:58:09 deraadt Exp $";
#endif /* not lint */

#include <sys/types.h>
#include <sys/file.h>

#include <ctype.h>
#include <err.h>
#include <errno.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "hexdump.h"

FU *endfu;					/* format at end-of-data */

void
addfile(char *name)
{
	char *p;
	FILE *fp;
	int ch;
	char buf[2048 + 1];

	if ((fp = fopen(name, "r")) == NULL)
		err(1, "fopen %s", name);
	while (fgets(buf, sizeof(buf), fp)) {
		if (!(p = strchr(buf, '\n'))) {
			warnx("line too long.");
			while ((ch = getchar()) != '\n' && ch != EOF);
			continue;
		}
		*p = '\0';
		for (p = buf; *p && isspace((unsigned char)*p); ++p);
		if (!*p || *p == '#')
			continue;
		add(p);
	}
	(void)fclose(fp);
}

void
add(const char *fmt)
{
	const char *p;
	static FS **nextfs;
	FS *tfs;
	FU *tfu, **nextfu;
	const char *savep;

	/* start new linked list of format units */
	tfs = emalloc(sizeof(FS));
	if (!fshead)
		fshead = tfs;
	else
		*nextfs = tfs;
	nextfs = &tfs->nextfs;
	nextfu = &tfs->nextfu;

	/* take the format string and break it up into format units */
	for (p = fmt;;) {
		/* skip leading white space */
		for (; isspace((unsigned char)*p); ++p);
		if (!*p)
			break;

		/* allocate a new format unit and link it in */
		tfu = emalloc(sizeof(FU));
		*nextfu = tfu;
		nextfu = &tfu->nextfu;
		tfu->reps = 1;

		/* if leading digit, repetition count */
		if (isdigit((unsigned char)*p)) {
			for (savep = p; isdigit((unsigned char)*p); ++p);
			if (!isspace((unsigned char)*p) && *p != '/')
				badfmt(fmt);
			/* may overwrite either white space or slash */
			tfu->reps = atoi(savep);
			tfu->flags = F_SETREP;
			/* skip trailing white space */
			for (++p; isspace((unsigned char)*p); ++p);
		}

		/* skip slash and trailing white space */
		if (*p == '/')
			while (isspace((unsigned char)*++p));

		/* byte count */
		if (isdigit((unsigned char)*p)) {
			for (savep = p; isdigit((unsigned char)*p); ++p);
			if (!isspace((unsigned char)*p))
				badfmt(fmt);
			tfu->bcnt = atoi(savep);
			/* skip trailing white space */
			for (++p; isspace((unsigned char)*p); ++p);
		}

		/* format */
		if (*p != '"')
			badfmt(fmt);
		for (savep = ++p; *p != '"';)
			if (*p++ == 0)
				badfmt(fmt);
		if (!(tfu->fmt = malloc(p - savep + 1)))
			nomem();
		(void) strncpy(tfu->fmt, savep, p - savep);
		tfu->fmt[p - savep] = '\0';
		escape(tfu->fmt);
		p++;
	}
}

static const char *spec = ".#-+ 0123456789";

int
size(FS *fs)
{
	FU *fu;
	int bcnt, cursize;
	char *fmt;
	int prec;

	/* figure out the data block size needed for each format unit */
	for (cursize = 0, fu = fs->nextfu; fu; fu = fu->nextfu) {
		if (fu->bcnt) {
			cursize += fu->bcnt * fu->reps;
			continue;
		}
		for (bcnt = prec = 0, fmt = fu->fmt; *fmt; ++fmt) {
			if (*fmt != '%')
				continue;
			/*
			 * skip any special chars -- save precision in
			 * case it's a %s format.
			 */
			while (strchr(spec + 1, *++fmt));
			if (*fmt == '.' && isdigit((unsigned char)*++fmt)) {
				prec = atoi(fmt);
				while (isdigit((unsigned char)*++fmt));
			}
			switch(*fmt) {
			case 'c':
				bcnt += 1;
				break;
			case 'd': case 'i': case 'o': case 'u':
			case 'x': case 'X':
				bcnt += 4;
				break;
			case 'e': case 'E': case 'f': case 'g': case 'G':
				bcnt += 8;
				break;
			case 's':
				bcnt += prec;
				break;
			case '_':
				switch(*++fmt) {
				case 'c': case 'p': case 'u':
					bcnt += 1;
					break;
				}
			}
		}
		cursize += bcnt * fu->reps;
	}
	return (cursize);
}

void
rewrite(FS *fs)
{
	enum { NOTOKAY, USEBCNT, USEPREC } sokay;
	PR *pr, **nextpr;
	FU *fu;
	char *p1, *p2;
	char savech, *fmtp, cs[3];
	int nconv, prec;
	size_t len;

	nextpr = NULL;
	prec = 0;
	for (fu = fs->nextfu; fu; fu = fu->nextfu) {
		/*
		 * Break each format unit into print units; each conversion
		 * character gets its own.
		 */
		for (nconv = 0, fmtp = fu->fmt; *fmtp; nextpr = &pr->nextpr) {
			pr = emalloc(sizeof(PR));
			if (!fu->nextpr)
				fu->nextpr = pr;
			else
				*nextpr = pr;

			/* Skip preceding text and up to the next % sign. */
			for (p1 = fmtp; *p1 && *p1 != '%'; ++p1);

			/* Only text in the string. */
			if (!*p1) {
				pr->fmt = fmtp;
				pr->flags = F_TEXT;
				break;
			}

			/*
			 * Get precision for %s -- if have a byte count, don't
			 * need it.
			 */
			if (fu->bcnt) {
				sokay = USEBCNT;
				/* Skip to conversion character. */
				for (++p1; strchr(spec, *p1); ++p1);
			} else {
				/* Skip any special chars, field width. */
				while (strchr(spec + 1, *++p1));
				if (*p1 == '.' &&
				    isdigit((unsigned char)*++p1)) {
					sokay = USEPREC;
					prec = atoi(p1);
					while (isdigit((unsigned char)*++p1))
						continue;
				} else
					sokay = NOTOKAY;
			}

			p2 = p1 + 1;		/* Set end pointer. */
			cs[0] = *p1;		/* Set conversion string. */
			cs[1] = '\0';

			/*
			 * Figure out the byte count for each conversion;
			 * rewrite the format as necessary, set up blank-
			 * padding for end of data.
			 */
			switch(cs[0]) {
			case 'c':
				pr->flags = F_CHAR;
				switch(fu->bcnt) {
				case 0: case 1:
					pr->bcnt = 1;
					break;
				default:
					p1[1] = '\0';
					badcnt(p1);
				}
				break;
			case 'd': case 'i':
				pr->flags = F_INT;
				goto isint;
			case 'o': case 'u': case 'x': case 'X':
				pr->flags = F_UINT;
isint:				cs[2] = '\0';
				cs[1] = cs[0];
				cs[0] = 'q';
				switch(fu->bcnt) {
				case 0: case 4:
					pr->bcnt = 4;
					break;
				case 1:
					pr->bcnt = 1;
					break;
				case 2:
					pr->bcnt = 2;
					break;
				case 8:
					pr->bcnt = 8;
					break;
				default:
					p1[1] = '\0';
					badcnt(p1);
				}
				break;
			case 'e': case 'E': case 'f': case 'g': case 'G':
				pr->flags = F_DBL;
				switch(fu->bcnt) {
				case 0: case 8:
					pr->bcnt = 8;
					break;
				case 4:
					pr->bcnt = 4;
					break;
				default:
					p1[1] = '\0';
					badcnt(p1);
				}
				break;
			case 's':
				pr->flags = F_STR;
				switch(sokay) {
				case NOTOKAY:
					badsfmt();
				case USEBCNT:
					pr->bcnt = fu->bcnt;
					break;
				case USEPREC:
					pr->bcnt = prec;
					break;
				}
				break;
			case '_':
				++p2;
				switch(p1[1]) {
				case 'A':
					endfu = fu;
					fu->flags |= F_IGNORE;
					/* FALLTHROUGH */
				case 'a':
					pr->flags = F_ADDRESS;
					++p2;
					switch(p1[2]) {
					case 'd': case 'o': case'x':
						cs[0] = 'q';
						cs[1] = p1[2];
						cs[2] = '\0';
						break;
					default:
						p1[3] = '\0';
						badconv(p1);
					}
					break;
				case 'c':
					pr->flags = F_C;
					/* cs[0] = 'c';	set in conv_c */
					goto isint2;
				case 'p':
					pr->flags = F_P;
					cs[0] = 'c';
					goto isint2;
				case 'u':
					pr->flags = F_U;
					/* cs[0] = 'c';	set in conv_u */
isint2:					switch(fu->bcnt) {
					case 0: case 1:
						pr->bcnt = 1;
						break;
					default:
						p1[2] = '\0';
						badcnt(p1);
					}
					break;
				default:
					p1[2] = '\0';
					badconv(p1);
				}
				break;
			default:
				p1[1] = '\0';
				badconv(p1);
			}

			/*
			 * Copy to PR format string, set conversion character
			 * pointer, update original.
			 */
			savech = *p2;
			p1[0] = '\0';
			len = strlen(fmtp) + strlen(cs) + 1;
			pr->fmt = emalloc(len);
			snprintf(pr->fmt, len, "%s%s", fmtp, cs);
			*p2 = savech;
			pr->cchar = pr->fmt + (p1 - fmtp);
			fmtp = p2;

			/* Only one conversion character if byte count. */
			if (!(pr->flags&F_ADDRESS) && fu->bcnt && nconv++)
				errx(1,
			    "byte count with multiple conversion characters");
		}
		/*
		 * If format unit byte count not specified, figure it out
		 * so can adjust rep count later.
		 */
		if (!fu->bcnt)
			for (pr = fu->nextpr; pr; pr = pr->nextpr)
				fu->bcnt += pr->bcnt;
	}
	/*
	 * If the format string interprets any data at all, and it's
	 * not the same as the blocksize, and its last format unit
	 * interprets any data at all, and has no iteration count,
	 * repeat it as necessary.
	 *
	 * If, rep count is greater than 1, no trailing whitespace
	 * gets output from the last iteration of the format unit.
	 */
	for (fu = fs->nextfu; fu; fu = fu->nextfu) {
		if (!fu->nextfu && fs->bcnt < blocksize &&
		    !(fu->flags&F_SETREP) && fu->bcnt)
			fu->reps += (blocksize - fs->bcnt) / fu->bcnt;
		if (fu->reps > 1) {
			for (pr = fu->nextpr;; pr = pr->nextpr)
				if (!pr->nextpr)
					break;
			for (p1 = pr->fmt, p2 = NULL; *p1; ++p1)
				p2 = isspace((unsigned char)*p1) ? p1 : NULL;
			if (p2)
				pr->nospace = p2;
		}
	}
#ifdef DEBUG
	for (fu = fs->nextfu; fu; fu = fu->nextfu) {
		(void)printf("fmt:");
		for (pr = fu->nextpr; pr; pr = pr->nextpr)
			(void)printf(" {%s}", pr->fmt);
		(void)printf("\n");
	}
#endif
}

void
escape(char *p1)
{
	char *p2;

	/* alphabetic escape sequences have to be done in place */
	for (p2 = p1;; ++p1, ++p2) {
		if (!*p1) {
			*p2 = *p1;
			break;
		}
		if (*p1 == '\\')
			switch(*++p1) {
			case 'a':
			     /* *p2 = '\a'; */
				*p2 = '\007';
				break;
			case 'b':
				*p2 = '\b';
				break;
			case 'f':
				*p2 = '\f';
				break;
			case 'n':
				*p2 = '\n';
				break;
			case 'r':
				*p2 = '\r';
				break;
			case 't':
				*p2 = '\t';
				break;
			case 'v':
				*p2 = '\v';
				break;
			default:
				*p2 = *p1;
				break;
			}
	}
}

void
badcnt(char *s)
{
	errx(1, "%s: bad byte count", s);
}

void
badsfmt(void)
{
	errx(1, "%%s: requires a precision or a byte count");
}

void
badfmt(const char *fmt)
{
	errx(1, "\"%s\": bad format", fmt);
}

void
badconv(char *ch)
{
	errx(1, "%%%s: bad conversion character", ch);
}