1 /* $NetBSD: unvis.c,v 1.41 2012/12/15 04:29:53 matt Exp $ */
2
3 /*-
4 * Copyright (c) 1989, 1993
5 * The Regents of the University of California. All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 * 3. Neither the name of the University nor the names of its contributors
16 * may be used to endorse or promote products derived from this software
17 * without specific prior written permission.
18 *
19 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
20 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
21 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
22 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
23 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
24 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
25 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
26 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
27 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
28 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
29 * SUCH DAMAGE.
30 */
31
32 #include "config.h"
33 #if defined(LIBC_SCCS) && !defined(lint)
34 #if 0
35 static char sccsid[] = "@(#)unvis.c 8.1 (Berkeley) 6/4/93";
36 #else
37 __RCSID("$NetBSD: unvis.c,v 1.41 2012/12/15 04:29:53 matt Exp $");
38 #endif
39 #endif /* LIBC_SCCS and not lint */
40
41 #include <sys/types.h>
42
43 #include <assert.h>
44 #include <ctype.h>
45 #ifdef HAVE_STDINT_H
46 #include <stdint.h>
47 #endif
48 #include <stdio.h>
49 #include <errno.h>
50 #include <vis.h>
51
52 #ifdef __weak_alias
53 __weak_alias(strnunvisx,_strnunvisx)
54 #endif
55
56 #if !HAVE_VIS
57 /*
58 * decode driven by state machine
59 */
60 #define S_GROUND 0 /* haven't seen escape char */
61 #define S_START 1 /* start decoding special sequence */
62 #define S_META 2 /* metachar started (M) */
63 #define S_META1 3 /* metachar more, regular char (-) */
64 #define S_CTRL 4 /* control char started (^) */
65 #define S_OCTAL2 5 /* octal digit 2 */
66 #define S_OCTAL3 6 /* octal digit 3 */
67 #define S_HEX 7 /* mandatory hex digit */
68 #define S_HEX1 8 /* http hex digit */
69 #define S_HEX2 9 /* http hex digit 2 */
70 #define S_MIME1 10 /* mime hex digit 1 */
71 #define S_MIME2 11 /* mime hex digit 2 */
72 #define S_EATCRNL 12 /* mime eating CRNL */
73 #define S_AMP 13 /* seen & */
74 #define S_NUMBER 14 /* collecting number */
75 #define S_STRING 15 /* collecting string */
76
77 #define isoctal(c) (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
78 #define xtod(c) (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10))
79 #define XTOD(c) (isdigit(c) ? (c - '0') : ((c - 'A') + 10))
80
81 /*
82 * RFC 1866
83 */
84 static const struct nv {
85 char name[7];
86 uint8_t value;
87 } nv[] = {
88 { "AElig", 198 }, /* capital AE diphthong (ligature) */
89 { "Aacute", 193 }, /* capital A, acute accent */
90 { "Acirc", 194 }, /* capital A, circumflex accent */
91 { "Agrave", 192 }, /* capital A, grave accent */
92 { "Aring", 197 }, /* capital A, ring */
93 { "Atilde", 195 }, /* capital A, tilde */
94 { "Auml", 196 }, /* capital A, dieresis or umlaut mark */
95 { "Ccedil", 199 }, /* capital C, cedilla */
96 { "ETH", 208 }, /* capital Eth, Icelandic */
97 { "Eacute", 201 }, /* capital E, acute accent */
98 { "Ecirc", 202 }, /* capital E, circumflex accent */
99 { "Egrave", 200 }, /* capital E, grave accent */
100 { "Euml", 203 }, /* capital E, dieresis or umlaut mark */
101 { "Iacute", 205 }, /* capital I, acute accent */
102 { "Icirc", 206 }, /* capital I, circumflex accent */
103 { "Igrave", 204 }, /* capital I, grave accent */
104 { "Iuml", 207 }, /* capital I, dieresis or umlaut mark */
105 { "Ntilde", 209 }, /* capital N, tilde */
106 { "Oacute", 211 }, /* capital O, acute accent */
107 { "Ocirc", 212 }, /* capital O, circumflex accent */
108 { "Ograve", 210 }, /* capital O, grave accent */
109 { "Oslash", 216 }, /* capital O, slash */
110 { "Otilde", 213 }, /* capital O, tilde */
111 { "Ouml", 214 }, /* capital O, dieresis or umlaut mark */
112 { "THORN", 222 }, /* capital THORN, Icelandic */
113 { "Uacute", 218 }, /* capital U, acute accent */
114 { "Ucirc", 219 }, /* capital U, circumflex accent */
115 { "Ugrave", 217 }, /* capital U, grave accent */
116 { "Uuml", 220 }, /* capital U, dieresis or umlaut mark */
117 { "Yacute", 221 }, /* capital Y, acute accent */
118 { "aacute", 225 }, /* small a, acute accent */
119 { "acirc", 226 }, /* small a, circumflex accent */
120 { "acute", 180 }, /* acute accent */
121 { "aelig", 230 }, /* small ae diphthong (ligature) */
122 { "agrave", 224 }, /* small a, grave accent */
123 { "amp", 38 }, /* ampersand */
124 { "aring", 229 }, /* small a, ring */
125 { "atilde", 227 }, /* small a, tilde */
126 { "auml", 228 }, /* small a, dieresis or umlaut mark */
127 { "brvbar", 166 }, /* broken (vertical) bar */
128 { "ccedil", 231 }, /* small c, cedilla */
129 { "cedil", 184 }, /* cedilla */
130 { "cent", 162 }, /* cent sign */
131 { "copy", 169 }, /* copyright sign */
132 { "curren", 164 }, /* general currency sign */
133 { "deg", 176 }, /* degree sign */
134 { "divide", 247 }, /* divide sign */
135 { "eacute", 233 }, /* small e, acute accent */
136 { "ecirc", 234 }, /* small e, circumflex accent */
137 { "egrave", 232 }, /* small e, grave accent */
138 { "eth", 240 }, /* small eth, Icelandic */
139 { "euml", 235 }, /* small e, dieresis or umlaut mark */
140 { "frac12", 189 }, /* fraction one-half */
141 { "frac14", 188 }, /* fraction one-quarter */
142 { "frac34", 190 }, /* fraction three-quarters */
143 { "gt", 62 }, /* greater than */
144 { "iacute", 237 }, /* small i, acute accent */
145 { "icirc", 238 }, /* small i, circumflex accent */
146 { "iexcl", 161 }, /* inverted exclamation mark */
147 { "igrave", 236 }, /* small i, grave accent */
148 { "iquest", 191 }, /* inverted question mark */
149 { "iuml", 239 }, /* small i, dieresis or umlaut mark */
150 { "laquo", 171 }, /* angle quotation mark, left */
151 { "lt", 60 }, /* less than */
152 { "macr", 175 }, /* macron */
153 { "micro", 181 }, /* micro sign */
154 { "middot", 183 }, /* middle dot */
155 { "nbsp", 160 }, /* no-break space */
156 { "not", 172 }, /* not sign */
157 { "ntilde", 241 }, /* small n, tilde */
158 { "oacute", 243 }, /* small o, acute accent */
159 { "ocirc", 244 }, /* small o, circumflex accent */
160 { "ograve", 242 }, /* small o, grave accent */
161 { "ordf", 170 }, /* ordinal indicator, feminine */
162 { "ordm", 186 }, /* ordinal indicator, masculine */
163 { "oslash", 248 }, /* small o, slash */
164 { "otilde", 245 }, /* small o, tilde */
165 { "ouml", 246 }, /* small o, dieresis or umlaut mark */
166 { "para", 182 }, /* pilcrow (paragraph sign) */
167 { "plusmn", 177 }, /* plus-or-minus sign */
168 { "pound", 163 }, /* pound sterling sign */
169 { "quot", 34 }, /* double quote */
170 { "raquo", 187 }, /* angle quotation mark, right */
171 { "reg", 174 }, /* registered sign */
172 { "sect", 167 }, /* section sign */
173 { "shy", 173 }, /* soft hyphen */
174 { "sup1", 185 }, /* superscript one */
175 { "sup2", 178 }, /* superscript two */
176 { "sup3", 179 }, /* superscript three */
177 { "szlig", 223 }, /* small sharp s, German (sz ligature) */
178 { "thorn", 254 }, /* small thorn, Icelandic */
179 { "times", 215 }, /* multiply sign */
180 { "uacute", 250 }, /* small u, acute accent */
181 { "ucirc", 251 }, /* small u, circumflex accent */
182 { "ugrave", 249 }, /* small u, grave accent */
183 { "uml", 168 }, /* umlaut (dieresis) */
184 { "uuml", 252 }, /* small u, dieresis or umlaut mark */
185 { "yacute", 253 }, /* small y, acute accent */
186 { "yen", 165 }, /* yen sign */
187 { "yuml", 255 }, /* small y, dieresis or umlaut mark */
188 };
189
190 /*
191 * unvis - decode characters previously encoded by vis
192 */
193 int
unvis(char * cp,int c,int * astate,int flag)194 unvis(char *cp, int c, int *astate, int flag)
195 {
196 unsigned char uc = (unsigned char)c;
197 unsigned char st, ia, is, lc;
198
199 /*
200 * Bottom 8 bits of astate hold the state machine state.
201 * Top 8 bits hold the current character in the http 1866 nv string decoding
202 */
203 #define GS(a) ((a) & 0xff)
204 #define SS(a, b) (((uint32_t)(a) << 24) | (b))
205 #define GI(a) ((uint32_t)(a) >> 24)
206
207 _DIAGASSERT(cp != NULL);
208 _DIAGASSERT(astate != NULL);
209 st = GS(*astate);
210
211 if (flag & UNVIS_END) {
212 switch (st) {
213 case S_OCTAL2:
214 case S_OCTAL3:
215 case S_HEX2:
216 *astate = SS(0, S_GROUND);
217 return UNVIS_VALID;
218 case S_GROUND:
219 return UNVIS_NOCHAR;
220 default:
221 return UNVIS_SYNBAD;
222 }
223 }
224
225 switch (st) {
226
227 case S_GROUND:
228 *cp = 0;
229 if ((flag & VIS_NOESCAPE) == 0 && c == '\\') {
230 *astate = SS(0, S_START);
231 return UNVIS_NOCHAR;
232 }
233 if ((flag & VIS_HTTP1808) && c == '%') {
234 *astate = SS(0, S_HEX1);
235 return UNVIS_NOCHAR;
236 }
237 if ((flag & VIS_HTTP1866) && c == '&') {
238 *astate = SS(0, S_AMP);
239 return UNVIS_NOCHAR;
240 }
241 if ((flag & VIS_MIMESTYLE) && c == '=') {
242 *astate = SS(0, S_MIME1);
243 return UNVIS_NOCHAR;
244 }
245 *cp = c;
246 return UNVIS_VALID;
247
248 case S_START:
249 switch(c) {
250 case '\\':
251 *cp = c;
252 *astate = SS(0, S_GROUND);
253 return UNVIS_VALID;
254 case '0': case '1': case '2': case '3':
255 case '4': case '5': case '6': case '7':
256 *cp = (c - '0');
257 *astate = SS(0, S_OCTAL2);
258 return UNVIS_NOCHAR;
259 case 'M':
260 *cp = (char)0200;
261 *astate = SS(0, S_META);
262 return UNVIS_NOCHAR;
263 case '^':
264 *astate = SS(0, S_CTRL);
265 return UNVIS_NOCHAR;
266 case 'n':
267 *cp = '\n';
268 *astate = SS(0, S_GROUND);
269 return UNVIS_VALID;
270 case 'r':
271 *cp = '\r';
272 *astate = SS(0, S_GROUND);
273 return UNVIS_VALID;
274 case 'b':
275 *cp = '\b';
276 *astate = SS(0, S_GROUND);
277 return UNVIS_VALID;
278 case 'a':
279 *cp = '\007';
280 *astate = SS(0, S_GROUND);
281 return UNVIS_VALID;
282 case 'v':
283 *cp = '\v';
284 *astate = SS(0, S_GROUND);
285 return UNVIS_VALID;
286 case 't':
287 *cp = '\t';
288 *astate = SS(0, S_GROUND);
289 return UNVIS_VALID;
290 case 'f':
291 *cp = '\f';
292 *astate = SS(0, S_GROUND);
293 return UNVIS_VALID;
294 case 's':
295 *cp = ' ';
296 *astate = SS(0, S_GROUND);
297 return UNVIS_VALID;
298 case 'E':
299 *cp = '\033';
300 *astate = SS(0, S_GROUND);
301 return UNVIS_VALID;
302 case 'x':
303 *astate = SS(0, S_HEX);
304 return UNVIS_NOCHAR;
305 case '\n':
306 /*
307 * hidden newline
308 */
309 *astate = SS(0, S_GROUND);
310 return UNVIS_NOCHAR;
311 case '$':
312 /*
313 * hidden marker
314 */
315 *astate = SS(0, S_GROUND);
316 return UNVIS_NOCHAR;
317 }
318 goto bad;
319
320 case S_META:
321 if (c == '-')
322 *astate = SS(0, S_META1);
323 else if (c == '^')
324 *astate = SS(0, S_CTRL);
325 else
326 goto bad;
327 return UNVIS_NOCHAR;
328
329 case S_META1:
330 *astate = SS(0, S_GROUND);
331 *cp |= c;
332 return UNVIS_VALID;
333
334 case S_CTRL:
335 if (c == '?')
336 *cp |= 0177;
337 else
338 *cp |= c & 037;
339 *astate = SS(0, S_GROUND);
340 return UNVIS_VALID;
341
342 case S_OCTAL2: /* second possible octal digit */
343 if (isoctal(uc)) {
344 /*
345 * yes - and maybe a third
346 */
347 *cp = (*cp << 3) + (c - '0');
348 *astate = SS(0, S_OCTAL3);
349 return UNVIS_NOCHAR;
350 }
351 /*
352 * no - done with current sequence, push back passed char
353 */
354 *astate = SS(0, S_GROUND);
355 return UNVIS_VALIDPUSH;
356
357 case S_OCTAL3: /* third possible octal digit */
358 *astate = SS(0, S_GROUND);
359 if (isoctal(uc)) {
360 *cp = (*cp << 3) + (c - '0');
361 return UNVIS_VALID;
362 }
363 /*
364 * we were done, push back passed char
365 */
366 return UNVIS_VALIDPUSH;
367
368 case S_HEX:
369 if (!isxdigit(uc))
370 goto bad;
371 /*FALLTHROUGH*/
372 case S_HEX1:
373 if (isxdigit(uc)) {
374 *cp = xtod(uc);
375 *astate = SS(0, S_HEX2);
376 return UNVIS_NOCHAR;
377 }
378 /*
379 * no - done with current sequence, push back passed char
380 */
381 *astate = SS(0, S_GROUND);
382 return UNVIS_VALIDPUSH;
383
384 case S_HEX2:
385 *astate = S_GROUND;
386 if (isxdigit(uc)) {
387 *cp = xtod(uc) | (*cp << 4);
388 return UNVIS_VALID;
389 }
390 return UNVIS_VALIDPUSH;
391
392 case S_MIME1:
393 if (uc == '\n' || uc == '\r') {
394 *astate = SS(0, S_EATCRNL);
395 return UNVIS_NOCHAR;
396 }
397 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
398 *cp = XTOD(uc);
399 *astate = SS(0, S_MIME2);
400 return UNVIS_NOCHAR;
401 }
402 goto bad;
403
404 case S_MIME2:
405 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
406 *astate = SS(0, S_GROUND);
407 *cp = XTOD(uc) | (*cp << 4);
408 return UNVIS_VALID;
409 }
410 goto bad;
411
412 case S_EATCRNL:
413 switch (uc) {
414 case '\r':
415 case '\n':
416 return UNVIS_NOCHAR;
417 case '=':
418 *astate = SS(0, S_MIME1);
419 return UNVIS_NOCHAR;
420 default:
421 *cp = uc;
422 *astate = SS(0, S_GROUND);
423 return UNVIS_VALID;
424 }
425
426 case S_AMP:
427 *cp = 0;
428 if (uc == '#') {
429 *astate = SS(0, S_NUMBER);
430 return UNVIS_NOCHAR;
431 }
432 *astate = SS(0, S_STRING);
433 /*FALLTHROUGH*/
434
435 case S_STRING:
436 ia = *cp; /* index in the array */
437 is = GI(*astate); /* index in the string */
438 lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */
439
440 if (uc == ';')
441 uc = '\0';
442
443 for (; ia < __arraycount(nv); ia++) {
444 if (is != 0 && nv[ia].name[is - 1] != lc)
445 goto bad;
446 if (nv[ia].name[is] == uc)
447 break;
448 }
449
450 if (ia == __arraycount(nv))
451 goto bad;
452
453 if (uc != 0) {
454 *cp = ia;
455 *astate = SS(is + 1, S_STRING);
456 return UNVIS_NOCHAR;
457 }
458
459 *cp = nv[ia].value;
460 *astate = SS(0, S_GROUND);
461 return UNVIS_VALID;
462
463 case S_NUMBER:
464 if (uc == ';')
465 return UNVIS_VALID;
466 if (!isdigit(uc))
467 goto bad;
468 *cp += (*cp * 10) + uc - '0';
469 return UNVIS_NOCHAR;
470
471 default:
472 bad:
473 /*
474 * decoder in unknown state - (probably uninitialized)
475 */
476 *astate = SS(0, S_GROUND);
477 return UNVIS_SYNBAD;
478 }
479 }
480
481 /*
482 * strnunvisx - decode src into dst
483 *
484 * Number of chars decoded into dst is returned, -1 on error.
485 * Dst is null terminated.
486 */
487
488 int
strnunvisx(char * dst,size_t dlen,const char * src,int flag)489 strnunvisx(char *dst, size_t dlen, const char *src, int flag)
490 {
491 char c;
492 char t = '\0', *start = dst;
493 int state = 0;
494
495 _DIAGASSERT(src != NULL);
496 _DIAGASSERT(dst != NULL);
497 #define CHECKSPACE() \
498 do { \
499 if (dlen-- == 0) { \
500 errno = ENOSPC; \
501 return -1; \
502 } \
503 } while (/*CONSTCOND*/0)
504
505 while ((c = *src++) != '\0') {
506 again:
507 switch (unvis(&t, c, &state, flag)) {
508 case UNVIS_VALID:
509 CHECKSPACE();
510 *dst++ = t;
511 break;
512 case UNVIS_VALIDPUSH:
513 CHECKSPACE();
514 *dst++ = t;
515 goto again;
516 case 0:
517 case UNVIS_NOCHAR:
518 break;
519 case UNVIS_SYNBAD:
520 errno = EINVAL;
521 return -1;
522 default:
523 _DIAGASSERT(/*CONSTCOND*/0);
524 errno = EINVAL;
525 return -1;
526 }
527 }
528 if (unvis(&t, c, &state, UNVIS_END) == UNVIS_VALID) {
529 CHECKSPACE();
530 *dst++ = t;
531 }
532 CHECKSPACE();
533 *dst = '\0';
534 return (int)(dst - start);
535 }
536
537 int
strunvisx(char * dst,const char * src,int flag)538 strunvisx(char *dst, const char *src, int flag)
539 {
540 return strnunvisx(dst, (size_t)~0, src, flag);
541 }
542
543 int
strunvis(char * dst,const char * src)544 strunvis(char *dst, const char *src)
545 {
546 return strnunvisx(dst, (size_t)~0, src, 0);
547 }
548
549 int
strnunvis(char * dst,size_t dlen,const char * src)550 strnunvis(char *dst, size_t dlen, const char *src)
551 {
552 return strnunvisx(dst, dlen, src, 0);
553 }
554 #endif
555