Annotation of src/usr.bin/hexdump/parse.c, Revision 1.10
1.10 ! mpech 1: /* $OpenBSD: parse.c,v 1.9 2001/12/30 08:17:32 pvalchev Exp $ */
1.9 pvalchev 2: /* $NetBSD: parse.c,v 1.12 2001/12/07 13:37:39 bjh21 Exp $ */
1.2 deraadt 3:
1.1 deraadt 4: /*
1.9 pvalchev 5: * Copyright (c) 1989, 1993
6: * The Regents of the University of California. All rights reserved.
1.1 deraadt 7: *
8: * Redistribution and use in source and binary forms, with or without
9: * modification, are permitted provided that the following conditions
10: * are met:
11: * 1. Redistributions of source code must retain the above copyright
12: * notice, this list of conditions and the following disclaimer.
13: * 2. Redistributions in binary form must reproduce the above copyright
14: * notice, this list of conditions and the following disclaimer in the
15: * documentation and/or other materials provided with the distribution.
16: * 3. All advertising materials mentioning features or use of this software
17: * must display the following acknowledgement:
18: * This product includes software developed by the University of
19: * California, Berkeley and its contributors.
20: * 4. Neither the name of the University nor the names of its contributors
21: * may be used to endorse or promote products derived from this software
22: * without specific prior written permission.
23: *
24: * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
25: * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
26: * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
27: * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
28: * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
29: * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
30: * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
31: * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
32: * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
33: * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
34: * SUCH DAMAGE.
35: */
36:
37: #ifndef lint
38: /*static char sccsid[] = "from: @(#)parse.c 5.6 (Berkeley) 3/9/91";*/
1.10 ! mpech 39: static char rcsid[] = "$OpenBSD: parse.c,v 1.9 2001/12/30 08:17:32 pvalchev Exp $";
1.1 deraadt 40: #endif /* not lint */
41:
42: #include <sys/types.h>
43: #include <sys/file.h>
1.9 pvalchev 44:
45: #include <ctype.h>
46: #include <err.h>
47: #include <errno.h>
48: #include <fcntl.h>
1.1 deraadt 49: #include <stdio.h>
50: #include <stdlib.h>
51: #include <string.h>
1.9 pvalchev 52:
1.1 deraadt 53: #include "hexdump.h"
54:
55: FU *endfu; /* format at end-of-data */
56:
1.6 pvalchev 57: void
1.1 deraadt 58: addfile(name)
59: char *name;
60: {
1.8 mpech 61: char *p;
1.1 deraadt 62: FILE *fp;
1.9 pvalchev 63: int ch;
64: char buf[2048 + 1];
1.1 deraadt 65:
1.9 pvalchev 66: if ((fp = fopen(name, "r")) == NULL)
67: err(1, "fopen %s", name);
68: while (fgets(buf, sizeof(buf), fp)) {
69: if (!(p = strchr(buf, '\n'))) {
70: warnx("line too long.");
71: while ((ch = getchar()) != '\n' && ch != EOF);
1.1 deraadt 72: continue;
73: }
1.9 pvalchev 74: *p = '\0';
75: for (p = buf; *p && isspace((unsigned char)*p); ++p);
1.1 deraadt 76: if (!*p || *p == '#')
77: continue;
78: add(p);
79: }
80: (void)fclose(fp);
81: }
82:
1.6 pvalchev 83: void
1.1 deraadt 84: add(fmt)
1.9 pvalchev 85: const char *fmt;
1.1 deraadt 86: {
1.9 pvalchev 87: const char *p;
1.1 deraadt 88: static FS **nextfs;
89: FS *tfs;
90: FU *tfu, **nextfu;
1.9 pvalchev 91: const char *savep;
1.1 deraadt 92:
93: /* start new linked list of format units */
1.9 pvalchev 94: tfs = emalloc(sizeof(FS));
1.1 deraadt 95: if (!fshead)
96: fshead = tfs;
97: else
98: *nextfs = tfs;
99: nextfs = &tfs->nextfs;
100: nextfu = &tfs->nextfu;
101:
102: /* take the format string and break it up into format units */
103: for (p = fmt;;) {
104: /* skip leading white space */
1.9 pvalchev 105: for (; isspace((unsigned char)*p); ++p);
1.1 deraadt 106: if (!*p)
107: break;
108:
109: /* allocate a new format unit and link it in */
1.9 pvalchev 110: tfu = emalloc(sizeof(FU));
1.1 deraadt 111: *nextfu = tfu;
112: nextfu = &tfu->nextfu;
113: tfu->reps = 1;
114:
115: /* if leading digit, repetition count */
1.9 pvalchev 116: if (isdigit((unsigned char)*p)) {
117: for (savep = p; isdigit((unsigned char)*p); ++p);
118: if (!isspace((unsigned char)*p) && *p != '/')
119: badfmt(fmt);
1.1 deraadt 120: /* may overwrite either white space or slash */
121: tfu->reps = atoi(savep);
122: tfu->flags = F_SETREP;
123: /* skip trailing white space */
1.9 pvalchev 124: for (++p; isspace((unsigned char)*p); ++p);
1.1 deraadt 125: }
126:
127: /* skip slash and trailing white space */
128: if (*p == '/')
1.9 pvalchev 129: while (isspace((unsigned char)*++p));
1.1 deraadt 130:
131: /* byte count */
1.9 pvalchev 132: if (isdigit((unsigned char)*p)) {
133: for (savep = p; isdigit((unsigned char)*p); ++p);
134: if (!isspace((unsigned char)*p))
135: badfmt(fmt);
1.1 deraadt 136: tfu->bcnt = atoi(savep);
137: /* skip trailing white space */
1.9 pvalchev 138: for (++p; isspace((unsigned char)*p); ++p);
1.1 deraadt 139: }
140:
141: /* format */
142: if (*p != '"')
1.9 pvalchev 143: badfmt(fmt);
1.1 deraadt 144: for (savep = ++p; *p != '"';)
145: if (*p++ == 0)
1.9 pvalchev 146: badfmt(fmt);
1.1 deraadt 147: if (!(tfu->fmt = malloc(p - savep + 1)))
1.9 pvalchev 148: nomem();
1.1 deraadt 149: (void) strncpy(tfu->fmt, savep, p - savep);
150: tfu->fmt[p - savep] = '\0';
151: escape(tfu->fmt);
152: p++;
153: }
154: }
155:
1.7 mickey 156: static const char *spec = ".#-+ 0123456789";
1.9 pvalchev 157:
1.6 pvalchev 158: int
1.1 deraadt 159: size(fs)
160: FS *fs;
161: {
1.8 mpech 162: FU *fu;
163: int bcnt, cursize;
164: char *fmt;
1.1 deraadt 165: int prec;
166:
167: /* figure out the data block size needed for each format unit */
168: for (cursize = 0, fu = fs->nextfu; fu; fu = fu->nextfu) {
169: if (fu->bcnt) {
170: cursize += fu->bcnt * fu->reps;
171: continue;
172: }
173: for (bcnt = prec = 0, fmt = fu->fmt; *fmt; ++fmt) {
174: if (*fmt != '%')
175: continue;
176: /*
177: * skip any special chars -- save precision in
178: * case it's a %s format.
179: */
1.3 millert 180: while (strchr(spec + 1, *++fmt));
1.9 pvalchev 181: if (*fmt == '.' && isdigit((unsigned char)*++fmt)) {
1.1 deraadt 182: prec = atoi(fmt);
1.9 pvalchev 183: while (isdigit((unsigned char)*++fmt));
1.1 deraadt 184: }
185: switch(*fmt) {
186: case 'c':
187: bcnt += 1;
188: break;
189: case 'd': case 'i': case 'o': case 'u':
190: case 'x': case 'X':
191: bcnt += 4;
192: break;
193: case 'e': case 'E': case 'f': case 'g': case 'G':
194: bcnt += 8;
195: break;
196: case 's':
197: bcnt += prec;
198: break;
199: case '_':
200: switch(*++fmt) {
201: case 'c': case 'p': case 'u':
202: bcnt += 1;
203: break;
204: }
205: }
206: }
207: cursize += bcnt * fu->reps;
208: }
1.9 pvalchev 209: return (cursize);
1.1 deraadt 210: }
211:
1.6 pvalchev 212: void
1.1 deraadt 213: rewrite(fs)
214: FS *fs;
215: {
216: enum { NOTOKAY, USEBCNT, USEPREC } sokay;
1.8 mpech 217: PR *pr, **nextpr;
218: FU *fu;
219: char *p1, *p2;
1.9 pvalchev 220: char savech, *fmtp, cs[3];
1.1 deraadt 221: int nconv, prec;
222:
1.9 pvalchev 223: nextpr = NULL;
224: prec = 0;
1.1 deraadt 225: for (fu = fs->nextfu; fu; fu = fu->nextfu) {
226: /*
1.9 pvalchev 227: * Break each format unit into print units; each conversion
228: * character gets its own.
1.1 deraadt 229: */
230: for (nconv = 0, fmtp = fu->fmt; *fmtp; nextpr = &pr->nextpr) {
1.9 pvalchev 231: pr = emalloc(sizeof(PR));
1.1 deraadt 232: if (!fu->nextpr)
233: fu->nextpr = pr;
234: else
235: *nextpr = pr;
236:
1.9 pvalchev 237: /* Skip preceding text and up to the next % sign. */
1.1 deraadt 238: for (p1 = fmtp; *p1 && *p1 != '%'; ++p1);
239:
1.9 pvalchev 240: /* Only text in the string. */
1.1 deraadt 241: if (!*p1) {
242: pr->fmt = fmtp;
243: pr->flags = F_TEXT;
244: break;
245: }
246:
247: /*
1.9 pvalchev 248: * Get precision for %s -- if have a byte count, don't
1.1 deraadt 249: * need it.
250: */
251: if (fu->bcnt) {
252: sokay = USEBCNT;
1.9 pvalchev 253: /* Skip to conversion character. */
1.3 millert 254: for (++p1; strchr(spec, *p1); ++p1);
1.1 deraadt 255: } else {
1.9 pvalchev 256: /* Skip any special chars, field width. */
1.3 millert 257: while (strchr(spec + 1, *++p1));
1.9 pvalchev 258: if (*p1 == '.' &&
259: isdigit((unsigned char)*++p1)) {
1.1 deraadt 260: sokay = USEPREC;
261: prec = atoi(p1);
1.9 pvalchev 262: while (isdigit((unsigned char)*++p1))
263: continue;
264: } else
1.1 deraadt 265: sokay = NOTOKAY;
266: }
267:
1.9 pvalchev 268: p2 = p1 + 1; /* Set end pointer. */
269: cs[0] = *p1; /* Set conversion string. */
270: cs[1] = '\0';
1.1 deraadt 271:
272: /*
1.9 pvalchev 273: * Figure out the byte count for each conversion;
1.1 deraadt 274: * rewrite the format as necessary, set up blank-
275: * padding for end of data.
276: */
1.9 pvalchev 277: switch(cs[0]) {
1.1 deraadt 278: case 'c':
279: pr->flags = F_CHAR;
280: switch(fu->bcnt) {
281: case 0: case 1:
282: pr->bcnt = 1;
283: break;
284: default:
1.9 pvalchev 285: p1[1] = '\0';
286: badcnt(p1);
1.1 deraadt 287: }
288: break;
289: case 'd': case 'i':
290: pr->flags = F_INT;
1.9 pvalchev 291: goto isint;
1.1 deraadt 292: case 'o': case 'u': case 'x': case 'X':
293: pr->flags = F_UINT;
1.9 pvalchev 294: isint: cs[2] = '\0';
295: cs[1] = cs[0];
296: cs[0] = 'q';
297: switch(fu->bcnt) {
1.1 deraadt 298: case 0: case 4:
299: pr->bcnt = 4;
300: break;
301: case 1:
302: pr->bcnt = 1;
303: break;
304: case 2:
305: pr->bcnt = 2;
306: break;
1.9 pvalchev 307: case 8:
308: pr->bcnt = 8;
309: break;
1.1 deraadt 310: default:
1.9 pvalchev 311: p1[1] = '\0';
312: badcnt(p1);
1.1 deraadt 313: }
314: break;
315: case 'e': case 'E': case 'f': case 'g': case 'G':
316: pr->flags = F_DBL;
317: switch(fu->bcnt) {
318: case 0: case 8:
319: pr->bcnt = 8;
320: break;
321: case 4:
322: pr->bcnt = 4;
323: break;
324: default:
1.9 pvalchev 325: p1[1] = '\0';
326: badcnt(p1);
1.1 deraadt 327: }
328: break;
329: case 's':
330: pr->flags = F_STR;
331: switch(sokay) {
332: case NOTOKAY:
1.9 pvalchev 333: badsfmt();
1.1 deraadt 334: case USEBCNT:
335: pr->bcnt = fu->bcnt;
336: break;
337: case USEPREC:
338: pr->bcnt = prec;
339: break;
340: }
341: break;
342: case '_':
343: ++p2;
344: switch(p1[1]) {
345: case 'A':
346: endfu = fu;
347: fu->flags |= F_IGNORE;
348: /* FALLTHROUGH */
349: case 'a':
350: pr->flags = F_ADDRESS;
351: ++p2;
352: switch(p1[2]) {
353: case 'd': case 'o': case'x':
1.9 pvalchev 354: cs[0] = 'q';
355: cs[1] = p1[2];
356: cs[2] = '\0';
1.1 deraadt 357: break;
358: default:
359: p1[3] = '\0';
1.9 pvalchev 360: badconv(p1);
1.1 deraadt 361: }
362: break;
363: case 'c':
364: pr->flags = F_C;
1.9 pvalchev 365: /* cs[0] = 'c'; set in conv_c */
366: goto isint2;
1.1 deraadt 367: case 'p':
368: pr->flags = F_P;
1.9 pvalchev 369: cs[0] = 'c';
370: goto isint2;
1.1 deraadt 371: case 'u':
372: pr->flags = F_U;
1.9 pvalchev 373: /* cs[0] = 'c'; set in conv_u */
374: isint2: switch(fu->bcnt) {
1.1 deraadt 375: case 0: case 1:
376: pr->bcnt = 1;
377: break;
378: default:
379: p1[2] = '\0';
1.9 pvalchev 380: badcnt(p1);
1.1 deraadt 381: }
382: break;
383: default:
384: p1[2] = '\0';
1.9 pvalchev 385: badconv(p1);
1.1 deraadt 386: }
387: break;
388: default:
1.9 pvalchev 389: p1[1] = '\0';
390: badconv(p1);
1.1 deraadt 391: }
392:
393: /*
1.9 pvalchev 394: * Copy to PR format string, set conversion character
1.1 deraadt 395: * pointer, update original.
396: */
397: savech = *p2;
1.9 pvalchev 398: p1[0] = '\0';
399: pr->fmt = emalloc(strlen(fmtp) + strlen(cs) + 1);
400: (void)strcpy(pr->fmt, fmtp);
401: (void)strcat(pr->fmt, cs);
1.1 deraadt 402: *p2 = savech;
403: pr->cchar = pr->fmt + (p1 - fmtp);
404: fmtp = p2;
405:
1.9 pvalchev 406: /* Only one conversion character if byte count. */
1.7 mickey 407: if (!(pr->flags&F_ADDRESS) && fu->bcnt && nconv++)
408: errx(1,
1.9 pvalchev 409: "byte count with multiple conversion characters");
1.1 deraadt 410: }
411: /*
1.9 pvalchev 412: * If format unit byte count not specified, figure it out
1.1 deraadt 413: * so can adjust rep count later.
414: */
415: if (!fu->bcnt)
416: for (pr = fu->nextpr; pr; pr = pr->nextpr)
417: fu->bcnt += pr->bcnt;
418: }
419: /*
1.9 pvalchev 420: * If the format string interprets any data at all, and it's
1.1 deraadt 421: * not the same as the blocksize, and its last format unit
422: * interprets any data at all, and has no iteration count,
423: * repeat it as necessary.
424: *
1.9 pvalchev 425: * If, rep count is greater than 1, no trailing whitespace
1.1 deraadt 426: * gets output from the last iteration of the format unit.
427: */
1.9 pvalchev 428: for (fu = fs->nextfu; fu; fu = fu->nextfu) {
1.1 deraadt 429: if (!fu->nextfu && fs->bcnt < blocksize &&
430: !(fu->flags&F_SETREP) && fu->bcnt)
431: fu->reps += (blocksize - fs->bcnt) / fu->bcnt;
432: if (fu->reps > 1) {
433: for (pr = fu->nextpr;; pr = pr->nextpr)
434: if (!pr->nextpr)
435: break;
436: for (p1 = pr->fmt, p2 = NULL; *p1; ++p1)
1.9 pvalchev 437: p2 = isspace((unsigned char)*p1) ? p1 : NULL;
1.1 deraadt 438: if (p2)
439: pr->nospace = p2;
440: }
441: }
1.9 pvalchev 442: #ifdef DEBUG
443: for (fu = fs->nextfu; fu; fu = fu->nextfu) {
444: (void)printf("fmt:");
445: for (pr = fu->nextpr; pr; pr = pr->nextpr)
446: (void)printf(" {%s}", pr->fmt);
447: (void)printf("\n");
448: }
449: #endif
1.1 deraadt 450: }
451:
1.6 pvalchev 452: void
1.1 deraadt 453: escape(p1)
1.8 mpech 454: char *p1;
1.1 deraadt 455: {
1.8 mpech 456: char *p2;
1.1 deraadt 457:
458: /* alphabetic escape sequences have to be done in place */
459: for (p2 = p1;; ++p1, ++p2) {
460: if (!*p1) {
461: *p2 = *p1;
462: break;
463: }
464: if (*p1 == '\\')
465: switch(*++p1) {
466: case 'a':
467: /* *p2 = '\a'; */
468: *p2 = '\007';
469: break;
470: case 'b':
471: *p2 = '\b';
472: break;
473: case 'f':
474: *p2 = '\f';
475: break;
476: case 'n':
477: *p2 = '\n';
478: break;
479: case 'r':
480: *p2 = '\r';
481: break;
482: case 't':
483: *p2 = '\t';
484: break;
485: case 'v':
486: *p2 = '\v';
487: break;
488: default:
489: *p2 = *p1;
490: break;
491: }
492: }
1.9 pvalchev 493: }
494:
495: void
496: badcnt(s)
497: char *s;
498: {
499: errx(1, "%s: bad byte count", s);
500: }
501:
502: void
503: badsfmt()
504: {
1.10 ! mpech 505: errx(1, "%%s: requires a precision or a byte count");
1.9 pvalchev 506: }
507:
508: void
509: badfmt(fmt)
510: const char *fmt;
511: {
1.10 ! mpech 512: errx(1, "\"%s\": bad format", fmt);
1.9 pvalchev 513: }
514:
515: void
516: badconv(ch)
517: char *ch;
518: {
1.10 ! mpech 519: errx(1, "%%%s: bad conversion character", ch);
1.1 deraadt 520: }