]> git.ipfire.org Git - thirdparty/util-linux.git/blob - text-utils/parse.c
Imported from util-linux-2.11o tarball.
[thirdparty/util-linux.git] / text-utils / parse.c
1 /*
2 * Copyright (c) 1989 The Regents of the University of California.
3 * 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 /* 1999-02-22 Arkadiusz Mi¶kiewicz <misiek@pld.ORG.PL>
35 * - added Native Language Support
36 */
37
38 #include <sys/types.h>
39 #include <sys/file.h>
40 #include <stdio.h>
41 #include <stdlib.h>
42 #include <ctype.h>
43 #include <string.h>
44 #include "hexdump.h"
45 #include "nls.h"
46
47 static void escape(char *p1);
48 static void badcnt(const char *s);
49 static void badsfmt(void);
50 static void badfmt(const char *fmt);
51 static void badconv(const char *ch);
52
53 FU *endfu; /* format at end-of-data */
54
55 void addfile(char *name)
56 {
57 char *p;
58 FILE *fp;
59 int ch;
60 char buf[2048 + 1];
61
62 if ((fp = fopen(name, "r")) == NULL) {
63 (void)fprintf(stderr, _("hexdump: can't read %s.\n"), name);
64 exit(1);
65 }
66 while (fgets(buf, sizeof(buf), fp)) {
67 if ((p = index(buf, '\n')) == NULL) {
68 (void)fprintf(stderr, _("hexdump: line too long.\n"));
69 while ((ch = getchar()) != '\n' && ch != EOF);
70 continue;
71 }
72 *p = '\0';
73 for (p = buf; *p && isspace((unsigned char)*p); ++p);
74 if (!*p || *p == '#')
75 continue;
76 add(p);
77 }
78 (void)fclose(fp);
79 }
80
81 void add(const char *fmt)
82 {
83 const char *p;
84 static FS **nextfs;
85 FS *tfs;
86 FU *tfu, **nextfu;
87 const char *savep;
88
89 /* Start new linked list of format units. */
90 tfs = emalloc(sizeof(FS));
91 if (!fshead)
92 fshead = tfs;
93 else
94 *nextfs = tfs;
95 nextfs = &tfs->nextfs;
96 nextfu = &tfs->nextfu;
97
98 /* Take the format string and break it up into format units. */
99 for (p = fmt;;) {
100 /* Skip leading white space. */
101 for (; isspace((unsigned char)*p); ++p);
102 if (!*p)
103 break;
104
105 /* Allocate a new format unit and link it in. */
106 tfu = emalloc(sizeof(FU));
107 *nextfu = tfu;
108 nextfu = &tfu->nextfu;
109 tfu->reps = 1;
110
111 /* If leading digit, repetition count. */
112 if (isdigit((unsigned char)*p)) {
113 for (savep = p; isdigit((unsigned char)*p); ++p);
114 if (!isspace((unsigned char)*p) && *p != '/')
115 badfmt(fmt);
116 /* may overwrite either white space or slash */
117 tfu->reps = atoi(savep);
118 tfu->flags = F_SETREP;
119 /* skip trailing white space */
120 for (++p; isspace((unsigned char)*p); ++p);
121 }
122
123 /* Skip slash and trailing white space. */
124 if (*p == '/')
125 while (isspace((unsigned char)*++p));
126
127 /* byte count */
128 if (isdigit((unsigned char)*p)) {
129 for (savep = p; isdigit((unsigned char)*p); ++p);
130 if (!isspace((unsigned char)*p))
131 badfmt(fmt);
132 tfu->bcnt = atoi(savep);
133 /* skip trailing white space */
134 for (++p; isspace((unsigned char)*p); ++p);
135 }
136
137 /* format */
138 if (*p != '"')
139 badfmt(fmt);
140 for (savep = ++p; *p != '"';)
141 if (*p++ == 0)
142 badfmt(fmt);
143 if (!(tfu->fmt = malloc(p - savep + 1)))
144 nomem();
145 (void) strncpy(tfu->fmt, savep, p - savep);
146 tfu->fmt[p - savep] = '\0';
147 escape(tfu->fmt);
148 p++;
149 }
150 }
151
152 static const char *spec = ".#-+ 0123456789";
153
154 int size(FS *fs)
155 {
156 FU *fu;
157 int bcnt, cursize;
158 char *fmt;
159 int prec;
160
161 /* figure out the data block size needed for each format unit */
162 for (cursize = 0, fu = fs->nextfu; fu; fu = fu->nextfu) {
163 if (fu->bcnt) {
164 cursize += fu->bcnt * fu->reps;
165 continue;
166 }
167 for (bcnt = prec = 0, fmt = fu->fmt; *fmt; ++fmt) {
168 if (*fmt != '%')
169 continue;
170 /*
171 * skip any special chars -- save precision in
172 * case it's a %s format.
173 */
174 while (index(spec + 1, *++fmt));
175 if (*fmt == '.' && isdigit((unsigned char)*++fmt)) {
176 prec = atoi(fmt);
177 while (isdigit((unsigned char)*++fmt));
178 }
179 switch(*fmt) {
180 case 'c':
181 bcnt += 1;
182 break;
183 case 'd': case 'i': case 'o': case 'u':
184 case 'x': case 'X':
185 bcnt += 4;
186 break;
187 case 'e': case 'E': case 'f': case 'g': case 'G':
188 bcnt += 8;
189 break;
190 case 's':
191 bcnt += prec;
192 break;
193 case '_':
194 switch(*++fmt) {
195 case 'c': case 'p': case 'u':
196 bcnt += 1;
197 break;
198 }
199 }
200 }
201 cursize += bcnt * fu->reps;
202 }
203 return(cursize);
204 }
205
206 void rewrite(FS *fs)
207 {
208 enum { NOTOKAY, USEBCNT, USEPREC } sokay;
209 PR *pr, **nextpr;
210 FU *fu;
211 char *p1, *p2;
212 char savech, *fmtp, cs[3];
213 int nconv, prec;
214
215 nextpr = NULL;
216 prec = 0;
217
218 for (fu = fs->nextfu; fu; fu = fu->nextfu) {
219 /*
220 * Break each format unit into print units; each
221 * conversion character gets its own.
222 */
223 for (nconv = 0, fmtp = fu->fmt; *fmtp; nextpr = &pr->nextpr) {
224 pr = emalloc(sizeof(PR));
225 if (!fu->nextpr)
226 fu->nextpr = pr;
227 else
228 *nextpr = pr;
229
230 /* Skip preceding text and up to the next % sign. */
231 for (p1 = fmtp; *p1 && *p1 != '%'; ++p1);
232
233 /* Only text in the string. */
234 if (!*p1) {
235 pr->fmt = fmtp;
236 pr->flags = F_TEXT;
237 break;
238 }
239
240 /*
241 * Get precision for %s -- if have a byte count, don't
242 * need it.
243 */
244 if (fu->bcnt) {
245 sokay = USEBCNT;
246 /* skip to conversion character */
247 for (++p1; index(spec, *p1); ++p1);
248 } else {
249 /* skip any special chars, field width */
250 while (index(spec + 1, *++p1));
251 if (*p1 == '.' &&
252 isdigit((unsigned char)*++p1)) {
253 sokay = USEPREC;
254 prec = atoi(p1);
255 while (isdigit((unsigned char)*++p1));
256 } else
257 sokay = NOTOKAY;
258 }
259
260 p2 = p1 + 1; /* Set end pointer. */
261 cs[0] = *p1; /* Set conversion string. */
262 cs[1] = 0;
263
264 /*
265 * Figure out the byte count for each conversion;
266 * rewrite the format as necessary, set up blank-
267 * padding for end of data.
268 */
269 switch(cs[0]) {
270 case 'c':
271 pr->flags = F_CHAR;
272 switch(fu->bcnt) {
273 case 0: case 1:
274 pr->bcnt = 1;
275 break;
276 default:
277 p1[1] = '\0';
278 badcnt(p1);
279 }
280 break;
281 case 'd': case 'i':
282 pr->flags = F_INT;
283 goto isint;
284 case 'o': case 'u': case 'x': case 'X':
285 pr->flags = F_UINT;
286 isint: cs[2] = '\0';
287 cs[1] = cs[0];
288 cs[0] = 'q';
289 switch(fu->bcnt) {
290 case 0: case 4:
291 pr->bcnt = 4;
292 break;
293 case 1:
294 pr->bcnt = 1;
295 break;
296 case 2:
297 pr->bcnt = 2;
298 break;
299 case 8:
300 pr->bcnt = 8;
301 break;
302 default:
303 p1[1] = '\0';
304 badcnt(p1);
305 }
306 break;
307 case 'e': case 'E': case 'f': case 'g': case 'G':
308 pr->flags = F_DBL;
309 switch(fu->bcnt) {
310 case 0: case 8:
311 pr->bcnt = 8;
312 break;
313 case 4:
314 pr->bcnt = 4;
315 break;
316 default:
317 p1[1] = '\0';
318 badcnt(p1);
319 }
320 break;
321 case 's':
322 pr->flags = F_STR;
323 switch(sokay) {
324 case NOTOKAY:
325 badsfmt();
326 case USEBCNT:
327 pr->bcnt = fu->bcnt;
328 break;
329 case USEPREC:
330 pr->bcnt = prec;
331 break;
332 }
333 break;
334 case '_':
335 ++p2;
336 switch(p1[1]) {
337 case 'A':
338 endfu = fu;
339 fu->flags |= F_IGNORE;
340 /* FALLTHROUGH */
341 case 'a':
342 pr->flags = F_ADDRESS;
343 ++p2;
344 switch(p1[2]) {
345 case 'd': case 'o': case'x':
346 cs[0] = 'q';
347 cs[1] = p1[2];
348 cs[2] = '\0';
349 break;
350 default:
351 p1[3] = '\0';
352 badconv(p1);
353 }
354 break;
355 case 'c':
356 pr->flags = F_C;
357 /* cs[0] = 'c'; set in conv_c */
358 goto isint2;
359 case 'p':
360 pr->flags = F_P;
361 cs[0] = 'c';
362 goto isint2;
363 case 'u':
364 pr->flags = F_U;
365 /* cs[0] = 'c'; set in conv_u */
366 isint2: switch(fu->bcnt) {
367 case 0: case 1:
368 pr->bcnt = 1;
369 break;
370 default:
371 p1[2] = '\0';
372 badcnt(p1);
373 }
374 break;
375 default:
376 p1[2] = '\0';
377 badconv(p1);
378 }
379 break;
380 default:
381 p1[1] = '\0';
382 badconv(p1);
383 }
384
385 /*
386 * Copy to PR format string, set conversion character
387 * pointer, update original.
388 */
389 savech = *p2;
390 p1[0] = '\0';
391 pr->fmt = emalloc(strlen(fmtp) + strlen(cs) + 1);
392 (void)strcpy(pr->fmt, fmtp);
393 (void)strcat(pr->fmt, cs);
394 *p2 = savech;
395 pr->cchar = pr->fmt + (p1 - fmtp);
396 fmtp = p2;
397
398 /* Only one conversion character if byte count */
399 if (!(pr->flags&F_ADDRESS) && fu->bcnt && nconv++) {
400 (void)fprintf(stderr,
401 _("hexdump: byte count with multiple conversion characters.\n"));
402 exit(1);
403 }
404 }
405 /*
406 * If format unit byte count not specified, figure it out
407 * so can adjust rep count later.
408 */
409 if (!fu->bcnt)
410 for (pr = fu->nextpr; pr; pr = pr->nextpr)
411 fu->bcnt += pr->bcnt;
412 }
413 /*
414 * If the format string interprets any data at all, and it's
415 * not the same as the blocksize, and its last format unit
416 * interprets any data at all, and has no iteration count,
417 * repeat it as necessary.
418 *
419 * If rep count is greater than 1, no trailing whitespace
420 * gets output from the last iteration of the format unit.
421 */
422 for (fu = fs->nextfu; fu; fu = fu->nextfu) {
423 if (!fu->nextfu && fs->bcnt < blocksize &&
424 !(fu->flags&F_SETREP) && fu->bcnt)
425 fu->reps += (blocksize - fs->bcnt) / fu->bcnt;
426 if (fu->reps > 1) {
427 for (pr = fu->nextpr;; pr = pr->nextpr)
428 if (!pr->nextpr)
429 break;
430 for (p1 = pr->fmt, p2 = NULL; *p1; ++p1)
431 p2 = isspace((unsigned char)*p1) ? p1 : NULL;
432 if (p2)
433 pr->nospace = p2;
434 }
435 }
436 }
437
438
439 static void escape(char *p1)
440 {
441 char *p2;
442
443 /* alphabetic escape sequences have to be done in place */
444 for (p2 = p1;; ++p1, ++p2) {
445 if (!*p1) {
446 *p2 = *p1;
447 break;
448 }
449 if (*p1 == '\\')
450 switch(*++p1) {
451 case 'a':
452 /* *p2 = '\a'; */
453 *p2 = '\007';
454 break;
455 case 'b':
456 *p2 = '\b';
457 break;
458 case 'f':
459 *p2 = '\f';
460 break;
461 case 'n':
462 *p2 = '\n';
463 break;
464 case 'r':
465 *p2 = '\r';
466 break;
467 case 't':
468 *p2 = '\t';
469 break;
470 case 'v':
471 *p2 = '\v';
472 break;
473 default:
474 *p2 = *p1;
475 break;
476 }
477 }
478 }
479
480 static void badcnt(const char *s)
481 {
482 (void)fprintf(stderr,
483 _("hexdump: bad byte count for conversion character %s.\n"), s);
484 exit(1);
485 }
486
487 static void badsfmt(void)
488 {
489 (void)fprintf(stderr,
490 _("hexdump: %%s requires a precision or a byte count.\n"));
491 exit(1);
492 }
493
494 static void badfmt(const char *fmt)
495 {
496 (void)fprintf(stderr, _("hexdump: bad format {%s}\n"), fmt);
497 exit(1);
498 }
499
500 static void badconv(const char *ch)
501 {
502 (void)fprintf(stderr, _("hexdump: bad conversion character %%%s.\n"), ch);
503 exit(1);
504 }