unvis.c
1 /* $NetBSD: unvis.c,v 1.32 2010/11/27 21:22:11 christos 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 1.32 2010/11/27 21:22:11 christos Exp $"); 38 #endif 39 #endif /* LIBC_SCCS and not lint */ 40 41 #include <sys/types.h> 42 #include <stdint.h> 43 44 #include <assert.h> 45 #include <ctype.h> 46 #include <stdio.h> 47 #include <vis.h> 48 49 #ifdef __weak_alias 50 __weak_alias(strunvis,_strunvis) 51 #endif 52 53 #if !HAVE_VIS 54 /* 55 * decode driven by state machine 56 */ 57 #define S_GROUND 0 /* haven't seen escape char */ 58 #define S_START 1 /* start decoding special sequence */ 59 #define S_META 2 /* metachar started (M) */ 60 #define S_META1 3 /* metachar more, regular char (-) */ 61 #define S_CTRL 4 /* control char started (^) */ 62 #define S_OCTAL2 5 /* octal digit 2 */ 63 #define S_OCTAL3 6 /* octal digit 3 */ 64 #define S_HEX1 7 /* http hex digit */ 65 #define S_HEX2 8 /* http hex digit 2 */ 66 #define S_MIME1 9 /* mime hex digit 1 */ 67 #define S_MIME2 10 /* mime hex digit 2 */ 68 #define S_EATCRNL 11 /* mime eating CRNL */ 69 #define S_AMP 12 /* seen & */ 70 #define S_NUMBER 13 /* collecting number */ 71 #define S_STRING 14 /* collecting string */ 72 73 #define isoctal(c) (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7') 74 #define xtod(c) (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10)) 75 #define XTOD(c) (isdigit(c) ? (c - '0') : ((c - 'A') + 10)) 76 77 /* 78 * RFC 1866 79 */ 80 static const struct nv { 81 const char *name; 82 uint8_t value; 83 } nv[] = { 84 { "AElig", 198 }, /* capital AE diphthong (ligature) */ 85 { "Aacute", 193 }, /* capital A, acute accent */ 86 { "Acirc", 194 }, /* capital A, circumflex accent */ 87 { "Agrave", 192 }, /* capital A, grave accent */ 88 { "Aring", 197 }, /* capital A, ring */ 89 { "Atilde", 195 }, /* capital A, tilde */ 90 { "Auml", 196 }, /* capital A, dieresis or umlaut mark */ 91 { "Ccedil", 199 }, /* capital C, cedilla */ 92 { "ETH", 208 }, /* capital Eth, Icelandic */ 93 { "Eacute", 201 }, /* capital E, acute accent */ 94 { "Ecirc", 202 }, /* capital E, circumflex accent */ 95 { "Egrave", 200 }, /* capital E, grave accent */ 96 { "Euml", 203 }, /* capital E, dieresis or umlaut mark */ 97 { "Iacute", 205 }, /* capital I, acute accent */ 98 { "Icirc", 206 }, /* capital I, circumflex accent */ 99 { "Igrave", 204 }, /* capital I, grave accent */ 100 { "Iuml", 207 }, /* capital I, dieresis or umlaut mark */ 101 { "Ntilde", 209 }, /* capital N, tilde */ 102 { "Oacute", 211 }, /* capital O, acute accent */ 103 { "Ocirc", 212 }, /* capital O, circumflex accent */ 104 { "Ograve", 210 }, /* capital O, grave accent */ 105 { "Oslash", 216 }, /* capital O, slash */ 106 { "Otilde", 213 }, /* capital O, tilde */ 107 { "Ouml", 214 }, /* capital O, dieresis or umlaut mark */ 108 { "THORN", 222 }, /* capital THORN, Icelandic */ 109 { "Uacute", 218 }, /* capital U, acute accent */ 110 { "Ucirc", 219 }, /* capital U, circumflex accent */ 111 { "Ugrave", 217 }, /* capital U, grave accent */ 112 { "Uuml", 220 }, /* capital U, dieresis or umlaut mark */ 113 { "Yacute", 221 }, /* capital Y, acute accent */ 114 { "aacute", 225 }, /* small a, acute accent */ 115 { "acirc", 226 }, /* small a, circumflex accent */ 116 { "acute", 180 }, /* acute accent */ 117 { "aelig", 230 }, /* small ae diphthong (ligature) */ 118 { "agrave", 224 }, /* small a, grave accent */ 119 { "amp", 38 }, /* ampersand */ 120 { "aring", 229 }, /* small a, ring */ 121 { "atilde", 227 }, /* small a, tilde */ 122 { "auml", 228 }, /* small a, dieresis or umlaut mark */ 123 { "brvbar", 166 }, /* broken (vertical) bar */ 124 { "ccedil", 231 }, /* small c, cedilla */ 125 { "cedil", 184 }, /* cedilla */ 126 { "cent", 162 }, /* cent sign */ 127 { "copy", 169 }, /* copyright sign */ 128 { "curren", 164 }, /* general currency sign */ 129 { "deg", 176 }, /* degree sign */ 130 { "divide", 247 }, /* divide sign */ 131 { "eacute", 233 }, /* small e, acute accent */ 132 { "ecirc", 234 }, /* small e, circumflex accent */ 133 { "egrave", 232 }, /* small e, grave accent */ 134 { "eth", 240 }, /* small eth, Icelandic */ 135 { "euml", 235 }, /* small e, dieresis or umlaut mark */ 136 { "frac12", 189 }, /* fraction one-half */ 137 { "frac14", 188 }, /* fraction one-quarter */ 138 { "frac34", 190 }, /* fraction three-quarters */ 139 { "gt", 62 }, /* greater than */ 140 { "iacute", 237 }, /* small i, acute accent */ 141 { "icirc", 238 }, /* small i, circumflex accent */ 142 { "iexcl", 161 }, /* inverted exclamation mark */ 143 { "igrave", 236 }, /* small i, grave accent */ 144 { "iquest", 191 }, /* inverted question mark */ 145 { "iuml", 239 }, /* small i, dieresis or umlaut mark */ 146 { "laquo", 171 }, /* angle quotation mark, left */ 147 { "lt", 60 }, /* less than */ 148 { "macr", 175 }, /* macron */ 149 { "micro", 181 }, /* micro sign */ 150 { "middot", 183 }, /* middle dot */ 151 { "nbsp", 160 }, /* no-break space */ 152 { "not", 172 }, /* not sign */ 153 { "ntilde", 241 }, /* small n, tilde */ 154 { "oacute", 243 }, /* small o, acute accent */ 155 { "ocirc", 244 }, /* small o, circumflex accent */ 156 { "ograve", 242 }, /* small o, grave accent */ 157 { "ordf", 170 }, /* ordinal indicator, feminine */ 158 { "ordm", 186 }, /* ordinal indicator, masculine */ 159 { "oslash", 248 }, /* small o, slash */ 160 { "otilde", 245 }, /* small o, tilde */ 161 { "ouml", 246 }, /* small o, dieresis or umlaut mark */ 162 { "para", 182 }, /* pilcrow (paragraph sign) */ 163 { "plusmn", 177 }, /* plus-or-minus sign */ 164 { "pound", 163 }, /* pound sterling sign */ 165 { "quot", 34 }, /* double quote */ 166 { "raquo", 187 }, /* angle quotation mark, right */ 167 { "reg", 174 }, /* registered sign */ 168 { "sect", 167 }, /* section sign */ 169 { "shy", 173 }, /* soft hyphen */ 170 { "sup1", 185 }, /* superscript one */ 171 { "sup2", 178 }, /* superscript two */ 172 { "sup3", 179 }, /* superscript three */ 173 { "szlig", 223 }, /* small sharp s, German (sz ligature) */ 174 { "thorn", 254 }, /* small thorn, Icelandic */ 175 { "times", 215 }, /* multiply sign */ 176 { "uacute", 250 }, /* small u, acute accent */ 177 { "ucirc", 251 }, /* small u, circumflex accent */ 178 { "ugrave", 249 }, /* small u, grave accent */ 179 { "uml", 168 }, /* umlaut (dieresis) */ 180 { "uuml", 252 }, /* small u, dieresis or umlaut mark */ 181 { "yacute", 253 }, /* small y, acute accent */ 182 { "yen", 165 }, /* yen sign */ 183 { "yuml", 255 }, /* small y, dieresis or umlaut mark */ 184 }; 185 186 /* 187 * unvis - decode characters previously encoded by vis 188 */ 189 int 190 unvis(char *cp, int c, int *astate, int flag) 191 { 192 unsigned char uc = (unsigned char)c; 193 unsigned char st, ia, is, lc; 194 195 /* 196 * Bottom 8 bits of astate hold the state machine state. 197 * Top 8 bits hold the current character in the http 1866 nv string decoding 198 */ 199 #define GS(a) ((a) & 0xff) 200 #define SS(a, b) (((uint32_t)(a) << 24) | (b)) 201 #define GI(a) ((uint32_t)(a) >> 24) 202 203 _DIAGASSERT(cp != NULL); 204 _DIAGASSERT(astate != NULL); 205 st = GS(*astate); 206 207 if (flag & UNVIS_END) { 208 switch (st) { 209 case S_OCTAL2: 210 case S_OCTAL3: 211 case S_HEX2: 212 *astate = SS(0, S_GROUND); 213 return UNVIS_VALID; 214 case S_GROUND: 215 return UNVIS_NOCHAR; 216 default: 217 return UNVIS_SYNBAD; 218 } 219 } 220 221 switch (st) { 222 223 case S_GROUND: 224 *cp = 0; 225 if ((flag & VIS_NOESCAPE) == 0 && c == '\\') { 226 *astate = SS(0, S_START); 227 return UNVIS_NOCHAR; 228 } 229 if ((flag & VIS_HTTP1808) && c == '%') { 230 *astate = SS(0, S_HEX1); 231 return UNVIS_NOCHAR; 232 } 233 if ((flag & VIS_HTTP1866) && c == '&') { 234 *astate = SS(0, S_AMP); 235 return UNVIS_NOCHAR; 236 } 237 if ((flag & VIS_MIMESTYLE) && c == '=') { 238 *astate = SS(0, S_MIME1); 239 return UNVIS_NOCHAR; 240 } 241 *cp = c; 242 return UNVIS_VALID; 243 244 case S_START: 245 switch(c) { 246 case '\\': 247 *cp = c; 248 *astate = SS(0, S_GROUND); 249 return UNVIS_VALID; 250 case '0': case '1': case '2': case '3': 251 case '4': case '5': case '6': case '7': 252 *cp = (c - '0'); 253 *astate = SS(0, S_OCTAL2); 254 return UNVIS_NOCHAR; 255 case 'M': 256 *cp = (char)0200; 257 *astate = SS(0, S_META); 258 return UNVIS_NOCHAR; 259 case '^': 260 *astate = SS(0, S_CTRL); 261 return UNVIS_NOCHAR; 262 case 'n': 263 *cp = '\n'; 264 *astate = SS(0, S_GROUND); 265 return UNVIS_VALID; 266 case 'r': 267 *cp = '\r'; 268 *astate = SS(0, S_GROUND); 269 return UNVIS_VALID; 270 case 'b': 271 *cp = '\b'; 272 *astate = SS(0, S_GROUND); 273 return UNVIS_VALID; 274 case 'a': 275 *cp = '\007'; 276 *astate = SS(0, S_GROUND); 277 return UNVIS_VALID; 278 case 'v': 279 *cp = '\v'; 280 *astate = SS(0, S_GROUND); 281 return UNVIS_VALID; 282 case 't': 283 *cp = '\t'; 284 *astate = SS(0, S_GROUND); 285 return UNVIS_VALID; 286 case 'f': 287 *cp = '\f'; 288 *astate = SS(0, S_GROUND); 289 return UNVIS_VALID; 290 case 's': 291 *cp = ' '; 292 *astate = SS(0, S_GROUND); 293 return UNVIS_VALID; 294 case 'E': 295 *cp = '\033'; 296 *astate = SS(0, S_GROUND); 297 return UNVIS_VALID; 298 case '\n': 299 /* 300 * hidden newline 301 */ 302 *astate = SS(0, S_GROUND); 303 return UNVIS_NOCHAR; 304 case '$': 305 /* 306 * hidden marker 307 */ 308 *astate = SS(0, S_GROUND); 309 return UNVIS_NOCHAR; 310 } 311 goto bad; 312 313 case S_META: 314 if (c == '-') 315 *astate = SS(0, S_META1); 316 else if (c == '^') 317 *astate = SS(0, S_CTRL); 318 else 319 goto bad; 320 return UNVIS_NOCHAR; 321 322 case S_META1: 323 *astate = SS(0, S_GROUND); 324 *cp |= c; 325 return UNVIS_VALID; 326 327 case S_CTRL: 328 if (c == '?') 329 *cp |= 0177; 330 else 331 *cp |= c & 037; 332 *astate = SS(0, S_GROUND); 333 return UNVIS_VALID; 334 335 case S_OCTAL2: /* second possible octal digit */ 336 if (isoctal(uc)) { 337 /* 338 * yes - and maybe a third 339 */ 340 *cp = (*cp << 3) + (c - '0'); 341 *astate = SS(0, S_OCTAL3); 342 return UNVIS_NOCHAR; 343 } 344 /* 345 * no - done with current sequence, push back passed char 346 */ 347 *astate = SS(0, S_GROUND); 348 return UNVIS_VALIDPUSH; 349 350 case S_OCTAL3: /* third possible octal digit */ 351 *astate = SS(0, S_GROUND); 352 if (isoctal(uc)) { 353 *cp = (*cp << 3) + (c - '0'); 354 return UNVIS_VALID; 355 } 356 /* 357 * we were done, push back passed char 358 */ 359 return UNVIS_VALIDPUSH; 360 361 case S_HEX1: 362 if (isxdigit(uc)) { 363 *cp = xtod(uc); 364 *astate = SS(0, S_HEX2); 365 return UNVIS_NOCHAR; 366 } 367 /* 368 * no - done with current sequence, push back passed char 369 */ 370 *astate = SS(0, S_GROUND); 371 return UNVIS_VALIDPUSH; 372 373 case S_HEX2: 374 *astate = S_GROUND; 375 if (isxdigit(uc)) { 376 *cp = xtod(uc) | (*cp << 4); 377 return UNVIS_VALID; 378 } 379 return UNVIS_VALIDPUSH; 380 381 case S_MIME1: 382 if (uc == '\n' || uc == '\r') { 383 *astate = SS(0, S_EATCRNL); 384 return UNVIS_NOCHAR; 385 } 386 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) { 387 *cp = XTOD(uc); 388 *astate = SS(0, S_MIME2); 389 return UNVIS_NOCHAR; 390 } 391 goto bad; 392 393 case S_MIME2: 394 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) { 395 *astate = SS(0, S_GROUND); 396 *cp = XTOD(uc) | (*cp << 4); 397 return UNVIS_VALID; 398 } 399 goto bad; 400 401 case S_EATCRNL: 402 switch (uc) { 403 case '\r': 404 case '\n': 405 return UNVIS_NOCHAR; 406 case '=': 407 *astate = SS(0, S_MIME1); 408 return UNVIS_NOCHAR; 409 default: 410 *cp = uc; 411 *astate = SS(0, S_GROUND); 412 return UNVIS_VALID; 413 } 414 415 case S_AMP: 416 *cp = 0; 417 if (uc == '#') { 418 *astate = SS(0, S_NUMBER); 419 return UNVIS_NOCHAR; 420 } 421 *astate = SS(0, S_STRING); 422 /*FALLTHROUGH*/ 423 424 case S_STRING: 425 ia = *cp; /* index in the array */ 426 is = GI(*astate); /* index in the string */ 427 lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */ 428 429 if (uc == ';') 430 uc = '\0'; 431 432 for (; ia < __arraycount(nv); ia++) { 433 if (is != 0 && nv[ia].name[is - 1] != lc) 434 goto bad; 435 if (nv[ia].name[is] == uc) 436 break; 437 } 438 439 if (*cp == __arraycount(nv)) 440 goto bad; 441 442 if (uc != 0) { 443 *cp = ia; 444 *astate = SS(is + 1, S_STRING); 445 return UNVIS_NOCHAR; 446 } 447 448 *cp = nv[ia].value; 449 *astate = SS(0, S_GROUND); 450 return UNVIS_VALID; 451 452 case S_NUMBER: 453 if (uc == ';') 454 return UNVIS_VALID; 455 if (!isdigit(uc)) 456 goto bad; 457 *cp += (*cp * 10) + uc - '0'; 458 return UNVIS_NOCHAR; 459 460 default: 461 bad: 462 /* 463 * decoder in unknown state - (probably uninitialized) 464 */ 465 *astate = SS(0, S_GROUND); 466 return UNVIS_SYNBAD; 467 } 468 } 469 470 /* 471 * strunvis - decode src into dst 472 * 473 * Number of chars decoded into dst is returned, -1 on error. 474 * Dst is null terminated. 475 */ 476 477 int 478 strunvisx(char *dst, const char *src, int flag) 479 { 480 char c; 481 char *start = dst; 482 int state = 0; 483 484 _DIAGASSERT(src != NULL); 485 _DIAGASSERT(dst != NULL); 486 487 while ((c = *src++) != '\0') { 488 again: 489 switch (unvis(dst, c, &state, flag)) { 490 case UNVIS_VALID: 491 dst++; 492 break; 493 case UNVIS_VALIDPUSH: 494 dst++; 495 goto again; 496 case 0: 497 case UNVIS_NOCHAR: 498 break; 499 default: 500 return (-1); 501 } 502 } 503 if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID) 504 dst++; 505 *dst = '\0'; 506 return (int)(dst - start); 507 } 508 509 int 510 strunvis(char *dst, const char *src) 511 { 512 return strunvisx(dst, src, 0); 513 } 514 #endif