1 | /* |
---|
2 | * Copyright (c) 1989, 1993 |
---|
3 | * The Regents of the University of California. All rights reserved. |
---|
4 | * |
---|
5 | * Redistribution and use in source and binary forms, with or without |
---|
6 | * modification, are permitted provided that the following conditions |
---|
7 | * are met: |
---|
8 | * 1. Redistributions of source code must retain the above copyright |
---|
9 | * notice, this list of conditions and the following disclaimer. |
---|
10 | * 2. Redistributions in binary form must reproduce the above copyright |
---|
11 | * notice, this list of conditions and the following disclaimer in the |
---|
12 | * documentation and/or other materials provided with the distribution. |
---|
13 | * 3. All advertising materials mentioning features or use of this software |
---|
14 | * must display the following acknowledgement: |
---|
15 | * This product includes software developed by the University of |
---|
16 | * California, Berkeley and its contributors. |
---|
17 | * 4. Neither the name of the University nor the names of its contributors |
---|
18 | * may be used to endorse or promote products derived from this software |
---|
19 | * without specific prior written permission. |
---|
20 | * |
---|
21 | * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND |
---|
22 | * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
---|
23 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
---|
24 | * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE |
---|
25 | * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL |
---|
26 | * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS |
---|
27 | * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) |
---|
28 | * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
---|
29 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY |
---|
30 | * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF |
---|
31 | * SUCH DAMAGE. |
---|
32 | */ |
---|
33 | |
---|
34 | #ifdef HAVE_CONFIG_H |
---|
35 | #include "config.h" |
---|
36 | #endif |
---|
37 | |
---|
38 | #ifndef lint |
---|
39 | #if 0 |
---|
40 | static char sccsid[] = "@(#)parse.c 8.1 (Berkeley) 6/6/93"; |
---|
41 | #include <sys/cdefs.h> |
---|
42 | __FBSDID("$FreeBSD: src/usr.bin/hexdump/parse.c,v 1.14 2006/08/09 19:12:10 maxim Exp $"); |
---|
43 | #endif |
---|
44 | #endif /* not lint */ |
---|
45 | |
---|
46 | #include <sys/types.h> |
---|
47 | |
---|
48 | #include <err.h> |
---|
49 | #include <fcntl.h> |
---|
50 | #include <stdio.h> |
---|
51 | #include <stdlib.h> |
---|
52 | #include <ctype.h> |
---|
53 | #include <string.h> |
---|
54 | |
---|
55 | #define index(s,c) strchr(s,c) |
---|
56 | |
---|
57 | #include "hexdump.h" |
---|
58 | |
---|
59 | #if RTEMS_REMOVED |
---|
60 | FU *endfu; /* format at end-of-data */ |
---|
61 | #endif |
---|
62 | |
---|
63 | void |
---|
64 | addfile(rtems_shell_hexdump_globals* globals, char *name) |
---|
65 | { |
---|
66 | unsigned char *p; |
---|
67 | FILE *fp; |
---|
68 | int ch; |
---|
69 | char buf[2048 + 1]; |
---|
70 | |
---|
71 | if ((fp = fopen(name, "r")) == NULL) |
---|
72 | err(exit_jump, 1, "%s", name); |
---|
73 | while (fgets(buf, sizeof(buf), fp)) { |
---|
74 | if (!(p = (unsigned char*)index(buf, '\n'))) { |
---|
75 | warnx("line too long"); |
---|
76 | while ((ch = getchar()) != '\n' && ch != EOF); |
---|
77 | continue; |
---|
78 | } |
---|
79 | *p = '\0'; |
---|
80 | for (p = (unsigned char*) buf; *p && isspace(*p); ++p); |
---|
81 | if (!*p || *p == '#') |
---|
82 | continue; |
---|
83 | add(globals, (char*)p); |
---|
84 | } |
---|
85 | (void)fclose(fp); |
---|
86 | } |
---|
87 | |
---|
88 | void |
---|
89 | add(rtems_shell_hexdump_globals* globals, const char *fmt) |
---|
90 | { |
---|
91 | unsigned const char *p, *savep; |
---|
92 | static FS **nextfs; |
---|
93 | FS *tfs; |
---|
94 | FU *tfu, **nextfu; |
---|
95 | |
---|
96 | /* start new linked list of format units */ |
---|
97 | if ((tfs = calloc(1, sizeof(FS))) == NULL) |
---|
98 | err(exit_jump, 1, NULL); |
---|
99 | if (!fshead) |
---|
100 | fshead = tfs; |
---|
101 | else |
---|
102 | *nextfs = tfs; |
---|
103 | nextfs = &tfs->nextfs; |
---|
104 | nextfu = &tfs->nextfu; |
---|
105 | |
---|
106 | /* take the format string and break it up into format units */ |
---|
107 | for (p = (unsigned const char*)fmt;;) { |
---|
108 | /* skip leading white space */ |
---|
109 | for (; isspace(*p); ++p); |
---|
110 | if (!*p) |
---|
111 | break; |
---|
112 | |
---|
113 | /* allocate a new format unit and link it in */ |
---|
114 | if ((tfu = calloc(1, sizeof(FU))) == NULL) |
---|
115 | err(exit_jump, 1, NULL); |
---|
116 | *nextfu = tfu; |
---|
117 | nextfu = &tfu->nextfu; |
---|
118 | tfu->reps = 1; |
---|
119 | |
---|
120 | /* if leading digit, repetition count */ |
---|
121 | if (isdigit(*p)) { |
---|
122 | for (savep = p; isdigit(*p); ++p); |
---|
123 | if (!isspace(*p) && *p != '/') |
---|
124 | badfmt(globals, fmt); |
---|
125 | /* may overwrite either white space or slash */ |
---|
126 | tfu->reps = atoi((char*)savep); |
---|
127 | tfu->flags = F_SETREP; |
---|
128 | /* skip trailing white space */ |
---|
129 | for (++p; isspace(*p); ++p); |
---|
130 | } |
---|
131 | |
---|
132 | /* skip slash and trailing white space */ |
---|
133 | if (*p == '/') |
---|
134 | while (isspace(*++p)); |
---|
135 | |
---|
136 | /* byte count */ |
---|
137 | if (isdigit(*p)) { |
---|
138 | for (savep = p; isdigit(*p); ++p); |
---|
139 | if (!isspace(*p)) |
---|
140 | badfmt(globals, fmt); |
---|
141 | tfu->bcnt = atoi((char*)savep); |
---|
142 | /* skip trailing white space */ |
---|
143 | for (++p; isspace(*p); ++p); |
---|
144 | } |
---|
145 | |
---|
146 | /* format */ |
---|
147 | if (*p != '"') |
---|
148 | badfmt(globals, fmt); |
---|
149 | for (savep = ++p; *p != '"';) |
---|
150 | if (*p++ == 0) |
---|
151 | badfmt(globals, fmt); |
---|
152 | if (!(tfu->fmt = malloc(p - savep + 1))) |
---|
153 | err(exit_jump, 1, NULL); |
---|
154 | (void) strncpy(tfu->fmt, (char*)savep, p - savep); |
---|
155 | tfu->fmt[p - savep] = '\0'; |
---|
156 | escape(tfu->fmt); |
---|
157 | p++; |
---|
158 | } |
---|
159 | } |
---|
160 | |
---|
161 | static const char *spec = ".#-+ 0123456789"; |
---|
162 | |
---|
163 | int |
---|
164 | size(rtems_shell_hexdump_globals* globals, FS *fs) |
---|
165 | { |
---|
166 | FU *fu; |
---|
167 | int bcnt, cursize; |
---|
168 | unsigned char *fmt; |
---|
169 | int prec; |
---|
170 | |
---|
171 | /* figure out the data block size needed for each format unit */ |
---|
172 | for (cursize = 0, fu = fs->nextfu; fu; fu = fu->nextfu) { |
---|
173 | if (fu->bcnt) { |
---|
174 | cursize += fu->bcnt * fu->reps; |
---|
175 | continue; |
---|
176 | } |
---|
177 | for (bcnt = prec = 0, fmt = (unsigned char*) fu->fmt; *fmt; ++fmt) { |
---|
178 | if (*fmt != '%') |
---|
179 | continue; |
---|
180 | /* |
---|
181 | * skip any special chars -- save precision in |
---|
182 | * case it's a %s format. |
---|
183 | */ |
---|
184 | while (index(spec + 1, *++fmt)); |
---|
185 | if (*fmt == '.' && isdigit(*++fmt)) { |
---|
186 | prec = atoi((char*)fmt); |
---|
187 | while (isdigit(*++fmt)); |
---|
188 | } |
---|
189 | switch(*fmt) { |
---|
190 | case 'c': |
---|
191 | bcnt += 1; |
---|
192 | break; |
---|
193 | case 'd': case 'i': case 'o': case 'u': |
---|
194 | case 'x': case 'X': |
---|
195 | bcnt += 4; |
---|
196 | break; |
---|
197 | case 'e': case 'E': case 'f': case 'g': case 'G': |
---|
198 | bcnt += 8; |
---|
199 | break; |
---|
200 | case 's': |
---|
201 | bcnt += prec; |
---|
202 | break; |
---|
203 | case '_': |
---|
204 | switch(*++fmt) { |
---|
205 | case 'c': case 'p': case 'u': |
---|
206 | bcnt += 1; |
---|
207 | break; |
---|
208 | } |
---|
209 | } |
---|
210 | } |
---|
211 | cursize += bcnt * fu->reps; |
---|
212 | } |
---|
213 | return (cursize); |
---|
214 | } |
---|
215 | |
---|
216 | void |
---|
217 | rewrite(rtems_shell_hexdump_globals* globals, FS *fs) |
---|
218 | { |
---|
219 | enum { NOTOKAY, USEBCNT, USEPREC } sokay; |
---|
220 | PR *pr, **nextpr; |
---|
221 | FU *fu; |
---|
222 | unsigned char *p1, *p2, *fmtp; |
---|
223 | char savech, cs[3]; |
---|
224 | int nconv, prec; |
---|
225 | size_t len; |
---|
226 | |
---|
227 | pr = NULL; |
---|
228 | nextpr = NULL; |
---|
229 | prec = 0; |
---|
230 | |
---|
231 | for (fu = fs->nextfu; fu; fu = fu->nextfu) { |
---|
232 | /* |
---|
233 | * Break each format unit into print units; each conversion |
---|
234 | * character gets its own. |
---|
235 | */ |
---|
236 | for (nconv = 0, fmtp = (unsigned char*)fu->fmt; *fmtp; nextpr = &pr->nextpr) { |
---|
237 | if ((pr = calloc(1, sizeof(PR))) == NULL) |
---|
238 | err(exit_jump, 1, NULL); |
---|
239 | if (!fu->nextpr) |
---|
240 | fu->nextpr = pr; |
---|
241 | else { |
---|
242 | if (nextpr) |
---|
243 | *nextpr = pr; |
---|
244 | } |
---|
245 | |
---|
246 | /* Skip preceding text and up to the next % sign. */ |
---|
247 | for (p1 = fmtp; *p1 && *p1 != '%'; ++p1); |
---|
248 | |
---|
249 | /* Only text in the string. */ |
---|
250 | if (!*p1) { |
---|
251 | pr->fmt = (char*)fmtp; |
---|
252 | pr->flags = F_TEXT; |
---|
253 | break; |
---|
254 | } |
---|
255 | |
---|
256 | /* |
---|
257 | * Get precision for %s -- if have a byte count, don't |
---|
258 | * need it. |
---|
259 | */ |
---|
260 | if (fu->bcnt) { |
---|
261 | sokay = USEBCNT; |
---|
262 | /* Skip to conversion character. */ |
---|
263 | for (++p1; index(spec, *p1); ++p1); |
---|
264 | } else { |
---|
265 | /* Skip any special chars, field width. */ |
---|
266 | while (index(spec + 1, *++p1)); |
---|
267 | if (*p1 == '.' && isdigit(*++p1)) { |
---|
268 | sokay = USEPREC; |
---|
269 | prec = atoi((char*)p1); |
---|
270 | while (isdigit(*++p1)); |
---|
271 | } else |
---|
272 | sokay = NOTOKAY; |
---|
273 | } |
---|
274 | |
---|
275 | p2 = p1 + 1; /* Set end pointer. */ |
---|
276 | cs[0] = *p1; /* Set conversion string. */ |
---|
277 | cs[1] = '\0'; |
---|
278 | |
---|
279 | /* |
---|
280 | * Figure out the byte count for each conversion; |
---|
281 | * rewrite the format as necessary, set up blank- |
---|
282 | * padding for end of data. |
---|
283 | */ |
---|
284 | switch(cs[0]) { |
---|
285 | case 'c': |
---|
286 | pr->flags = F_CHAR; |
---|
287 | switch(fu->bcnt) { |
---|
288 | case 0: case 1: |
---|
289 | pr->bcnt = 1; |
---|
290 | break; |
---|
291 | default: |
---|
292 | p1[1] = '\0'; |
---|
293 | badcnt(globals, (char*)p1); |
---|
294 | } |
---|
295 | break; |
---|
296 | case 'd': case 'i': |
---|
297 | pr->flags = F_INT; |
---|
298 | goto isint; |
---|
299 | case 'o': case 'u': case 'x': case 'X': |
---|
300 | pr->flags = F_UINT; |
---|
301 | isint: cs[2] = '\0'; |
---|
302 | cs[1] = cs[0]; |
---|
303 | cs[0] = 'q'; |
---|
304 | switch(fu->bcnt) { |
---|
305 | case 0: case 4: |
---|
306 | pr->bcnt = 4; |
---|
307 | break; |
---|
308 | case 1: |
---|
309 | pr->bcnt = 1; |
---|
310 | break; |
---|
311 | case 2: |
---|
312 | pr->bcnt = 2; |
---|
313 | break; |
---|
314 | default: |
---|
315 | p1[1] = '\0'; |
---|
316 | badcnt(globals, (char*)p1); |
---|
317 | } |
---|
318 | break; |
---|
319 | case 'e': case 'E': case 'f': case 'g': case 'G': |
---|
320 | pr->flags = F_DBL; |
---|
321 | switch(fu->bcnt) { |
---|
322 | case 0: case 8: |
---|
323 | pr->bcnt = 8; |
---|
324 | break; |
---|
325 | case 4: |
---|
326 | pr->bcnt = 4; |
---|
327 | break; |
---|
328 | default: |
---|
329 | if (fu->bcnt == sizeof(long double)) { |
---|
330 | cs[2] = '\0'; |
---|
331 | cs[1] = cs[0]; |
---|
332 | cs[0] = 'L'; |
---|
333 | pr->bcnt = sizeof(long double); |
---|
334 | } else { |
---|
335 | p1[1] = '\0'; |
---|
336 | badcnt(globals, (char*)p1); |
---|
337 | } |
---|
338 | } |
---|
339 | break; |
---|
340 | case 's': |
---|
341 | pr->flags = F_STR; |
---|
342 | switch(sokay) { |
---|
343 | case NOTOKAY: |
---|
344 | badsfmt(globals); |
---|
345 | case USEBCNT: |
---|
346 | pr->bcnt = fu->bcnt; |
---|
347 | break; |
---|
348 | case USEPREC: |
---|
349 | pr->bcnt = prec; |
---|
350 | break; |
---|
351 | } |
---|
352 | break; |
---|
353 | case '_': |
---|
354 | ++p2; |
---|
355 | switch(p1[1]) { |
---|
356 | case 'A': |
---|
357 | endfu = fu; |
---|
358 | fu->flags |= F_IGNORE; |
---|
359 | /* FALLTHROUGH */ |
---|
360 | case 'a': |
---|
361 | pr->flags = F_ADDRESS; |
---|
362 | ++p2; |
---|
363 | switch(p1[2]) { |
---|
364 | case 'd': case 'o': case'x': |
---|
365 | cs[0] = 'q'; |
---|
366 | cs[1] = p1[2]; |
---|
367 | cs[2] = '\0'; |
---|
368 | break; |
---|
369 | default: |
---|
370 | p1[3] = '\0'; |
---|
371 | badconv(globals, (char*)p1); |
---|
372 | } |
---|
373 | break; |
---|
374 | case 'c': |
---|
375 | pr->flags = F_C; |
---|
376 | /* cs[0] = 'c'; set in conv_c */ |
---|
377 | goto isint2; |
---|
378 | case 'p': |
---|
379 | pr->flags = F_P; |
---|
380 | cs[0] = 'c'; |
---|
381 | goto isint2; |
---|
382 | case 'u': |
---|
383 | pr->flags = F_U; |
---|
384 | /* cs[0] = 'c'; set in conv_u */ |
---|
385 | isint2: switch(fu->bcnt) { |
---|
386 | case 0: case 1: |
---|
387 | pr->bcnt = 1; |
---|
388 | break; |
---|
389 | default: |
---|
390 | p1[2] = '\0'; |
---|
391 | badcnt(globals, (char*)p1); |
---|
392 | } |
---|
393 | break; |
---|
394 | default: |
---|
395 | p1[2] = '\0'; |
---|
396 | badconv(globals, (char*)p1); |
---|
397 | } |
---|
398 | break; |
---|
399 | default: |
---|
400 | p1[1] = '\0'; |
---|
401 | badconv(globals, (char*)p1); |
---|
402 | } |
---|
403 | |
---|
404 | /* |
---|
405 | * Copy to PR format string, set conversion character |
---|
406 | * pointer, update original. |
---|
407 | */ |
---|
408 | savech = *p2; |
---|
409 | p1[0] = '\0'; |
---|
410 | len = strlen((char*)fmtp) + strlen(cs) + 1; |
---|
411 | if ((pr->fmt = calloc(1, len)) == NULL) |
---|
412 | err(exit_jump, 1, NULL); |
---|
413 | snprintf(pr->fmt, len, "%s%s", fmtp, cs); |
---|
414 | *p2 = savech; |
---|
415 | pr->cchar = pr->fmt + (p1 - fmtp); |
---|
416 | fmtp = p2; |
---|
417 | |
---|
418 | /* Only one conversion character if byte count. */ |
---|
419 | if (!(pr->flags&F_ADDRESS) && fu->bcnt && nconv++) |
---|
420 | errx(exit_jump, 1, "byte count with multiple conversion characters"); |
---|
421 | } |
---|
422 | /* |
---|
423 | * If format unit byte count not specified, figure it out |
---|
424 | * so can adjust rep count later. |
---|
425 | */ |
---|
426 | if (!fu->bcnt) |
---|
427 | for (pr = fu->nextpr; pr; pr = pr->nextpr) |
---|
428 | fu->bcnt += pr->bcnt; |
---|
429 | } |
---|
430 | if (pr) { |
---|
431 | free(pr); |
---|
432 | pr = NULL; |
---|
433 | } |
---|
434 | /* |
---|
435 | * If the format string interprets any data at all, and it's |
---|
436 | * not the same as the blocksize, and its last format unit |
---|
437 | * interprets any data at all, and has no iteration count, |
---|
438 | * repeat it as necessary. |
---|
439 | * |
---|
440 | * If, rep count is greater than 1, no trailing whitespace |
---|
441 | * gets output from the last iteration of the format unit. |
---|
442 | */ |
---|
443 | for (fu = fs->nextfu; fu; fu = fu->nextfu) { |
---|
444 | if (!fu->nextfu && fs->bcnt < blocksize && |
---|
445 | !(fu->flags&F_SETREP) && fu->bcnt) |
---|
446 | fu->reps += (blocksize - fs->bcnt) / fu->bcnt; |
---|
447 | if (fu->reps > 1) { |
---|
448 | for (pr = fu->nextpr;; pr = pr->nextpr) |
---|
449 | if (!pr->nextpr) |
---|
450 | break; |
---|
451 | for (p1 = (unsigned char*)pr->fmt, p2 = NULL; *p1; ++p1) |
---|
452 | p2 = isspace(*p1) ? p1 : NULL; |
---|
453 | if (p2) |
---|
454 | pr->nospace = (char*)p2; |
---|
455 | } |
---|
456 | } |
---|
457 | #ifdef DEBUG |
---|
458 | for (fu = fs->nextfu; fu; fu = fu->nextfu) { |
---|
459 | (void)printf("fmt:"); |
---|
460 | for (pr = fu->nextpr; pr; pr = pr->nextpr) |
---|
461 | (void)printf(" {%s}", pr->fmt); |
---|
462 | (void)printf("\n"); |
---|
463 | } |
---|
464 | #endif |
---|
465 | } |
---|
466 | |
---|
467 | void |
---|
468 | escape(char *p1) |
---|
469 | { |
---|
470 | char *p2; |
---|
471 | |
---|
472 | /* alphabetic escape sequences have to be done in place */ |
---|
473 | for (p2 = p1;; ++p1, ++p2) { |
---|
474 | if (!*p1) { |
---|
475 | *p2 = *p1; |
---|
476 | break; |
---|
477 | } |
---|
478 | if (*p1 == '\\') |
---|
479 | switch(*++p1) { |
---|
480 | case 'a': |
---|
481 | /* *p2 = '\a'; */ |
---|
482 | *p2 = '\007'; |
---|
483 | break; |
---|
484 | case 'b': |
---|
485 | *p2 = '\b'; |
---|
486 | break; |
---|
487 | case 'f': |
---|
488 | *p2 = '\f'; |
---|
489 | break; |
---|
490 | case 'n': |
---|
491 | *p2 = '\n'; |
---|
492 | break; |
---|
493 | case 'r': |
---|
494 | *p2 = '\r'; |
---|
495 | break; |
---|
496 | case 't': |
---|
497 | *p2 = '\t'; |
---|
498 | break; |
---|
499 | case 'v': |
---|
500 | *p2 = '\v'; |
---|
501 | break; |
---|
502 | default: |
---|
503 | *p2 = *p1; |
---|
504 | break; |
---|
505 | } |
---|
506 | } |
---|
507 | } |
---|
508 | |
---|
509 | void |
---|
510 | badcnt(rtems_shell_hexdump_globals* globals, char *s) |
---|
511 | { |
---|
512 | errx(exit_jump, 1, "%s: bad byte count", s); |
---|
513 | } |
---|
514 | |
---|
515 | void |
---|
516 | badsfmt(rtems_shell_hexdump_globals* globals) |
---|
517 | { |
---|
518 | errx(exit_jump, 1, "%%s: requires a precision or a byte count"); |
---|
519 | } |
---|
520 | |
---|
521 | void |
---|
522 | badfmt(rtems_shell_hexdump_globals* globals, const char *fmt) |
---|
523 | { |
---|
524 | errx(exit_jump, 1, "\"%s\": bad format", fmt); |
---|
525 | } |
---|
526 | |
---|
527 | void |
---|
528 | badconv(rtems_shell_hexdump_globals* globals, char *ch) |
---|
529 | { |
---|
530 | errx(exit_jump, 1, "%%%s: bad conversion character", ch); |
---|
531 | } |
---|