1 /* $NetBSD: unvis.c,v 1.44 2014/09/26 15:43:36 roy 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 <sys/cdefs.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 1.44 2014/09/26 15:43:36 roy Exp $"); 38 #endif 39 #endif /* LIBC_SCCS and not lint */ 40 41 #include "namespace.h" 42 #include <sys/types.h> 43 44 #include <assert.h> 45 #include <ctype.h> 46 #include <stdint.h> 47 #include <stdio.h> 48 #include <errno.h> 49 #include <vis.h> 50 51 /* 52 * Return the number of elements in a statically-allocated array, 53 * __x. 54 */ 55 #define __arraycount(__x) (sizeof(__x) / sizeof(__x[0])) 56 57 #ifdef __weak_alias 58 __weak_alias(strnunvisx,_strnunvisx) 59 #endif 60 61 #if !HAVE_VIS 62 /* 63 * decode driven by state machine 64 */ 65 #define S_GROUND 0 /* haven't seen escape char */ 66 #define S_START 1 /* start decoding special sequence */ 67 #define S_META 2 /* metachar started (M) */ 68 #define S_META1 3 /* metachar more, regular char (-) */ 69 #define S_CTRL 4 /* control char started (^) */ 70 #define S_OCTAL2 5 /* octal digit 2 */ 71 #define S_OCTAL3 6 /* octal digit 3 */ 72 #define S_HEX 7 /* mandatory hex digit */ 73 #define S_HEX1 8 /* http hex digit */ 74 #define S_HEX2 9 /* http hex digit 2 */ 75 #define S_MIME1 10 /* mime hex digit 1 */ 76 #define S_MIME2 11 /* mime hex digit 2 */ 77 #define S_EATCRNL 12 /* mime eating CRNL */ 78 #define S_AMP 13 /* seen & */ 79 #define S_NUMBER 14 /* collecting number */ 80 #define S_STRING 15 /* collecting string */ 81 82 #define isoctal(c) (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7') 83 #define xtod(c) (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10)) 84 #define XTOD(c) (isdigit(c) ? (c - '0') : ((c - 'A') + 10)) 85 86 /* 87 * RFC 1866 88 */ 89 static const struct nv { 90 char name[7]; 91 uint8_t value; 92 } nv[] = { 93 { "AElig", 198 }, /* capital AE diphthong (ligature) */ 94 { "Aacute", 193 }, /* capital A, acute accent */ 95 { "Acirc", 194 }, /* capital A, circumflex accent */ 96 { "Agrave", 192 }, /* capital A, grave accent */ 97 { "Aring", 197 }, /* capital A, ring */ 98 { "Atilde", 195 }, /* capital A, tilde */ 99 { "Auml", 196 }, /* capital A, dieresis or umlaut mark */ 100 { "Ccedil", 199 }, /* capital C, cedilla */ 101 { "ETH", 208 }, /* capital Eth, Icelandic */ 102 { "Eacute", 201 }, /* capital E, acute accent */ 103 { "Ecirc", 202 }, /* capital E, circumflex accent */ 104 { "Egrave", 200 }, /* capital E, grave accent */ 105 { "Euml", 203 }, /* capital E, dieresis or umlaut mark */ 106 { "Iacute", 205 }, /* capital I, acute accent */ 107 { "Icirc", 206 }, /* capital I, circumflex accent */ 108 { "Igrave", 204 }, /* capital I, grave accent */ 109 { "Iuml", 207 }, /* capital I, dieresis or umlaut mark */ 110 { "Ntilde", 209 }, /* capital N, tilde */ 111 { "Oacute", 211 }, /* capital O, acute accent */ 112 { "Ocirc", 212 }, /* capital O, circumflex accent */ 113 { "Ograve", 210 }, /* capital O, grave accent */ 114 { "Oslash", 216 }, /* capital O, slash */ 115 { "Otilde", 213 }, /* capital O, tilde */ 116 { "Ouml", 214 }, /* capital O, dieresis or umlaut mark */ 117 { "THORN", 222 }, /* capital THORN, Icelandic */ 118 { "Uacute", 218 }, /* capital U, acute accent */ 119 { "Ucirc", 219 }, /* capital U, circumflex accent */ 120 { "Ugrave", 217 }, /* capital U, grave accent */ 121 { "Uuml", 220 }, /* capital U, dieresis or umlaut mark */ 122 { "Yacute", 221 }, /* capital Y, acute accent */ 123 { "aacute", 225 }, /* small a, acute accent */ 124 { "acirc", 226 }, /* small a, circumflex accent */ 125 { "acute", 180 }, /* acute accent */ 126 { "aelig", 230 }, /* small ae diphthong (ligature) */ 127 { "agrave", 224 }, /* small a, grave accent */ 128 { "amp", 38 }, /* ampersand */ 129 { "aring", 229 }, /* small a, ring */ 130 { "atilde", 227 }, /* small a, tilde */ 131 { "auml", 228 }, /* small a, dieresis or umlaut mark */ 132 { "brvbar", 166 }, /* broken (vertical) bar */ 133 { "ccedil", 231 }, /* small c, cedilla */ 134 { "cedil", 184 }, /* cedilla */ 135 { "cent", 162 }, /* cent sign */ 136 { "copy", 169 }, /* copyright sign */ 137 { "curren", 164 }, /* general currency sign */ 138 { "deg", 176 }, /* degree sign */ 139 { "divide", 247 }, /* divide sign */ 140 { "eacute", 233 }, /* small e, acute accent */ 141 { "ecirc", 234 }, /* small e, circumflex accent */ 142 { "egrave", 232 }, /* small e, grave accent */ 143 { "eth", 240 }, /* small eth, Icelandic */ 144 { "euml", 235 }, /* small e, dieresis or umlaut mark */ 145 { "frac12", 189 }, /* fraction one-half */ 146 { "frac14", 188 }, /* fraction one-quarter */ 147 { "frac34", 190 }, /* fraction three-quarters */ 148 { "gt", 62 }, /* greater than */ 149 { "iacute", 237 }, /* small i, acute accent */ 150 { "icirc", 238 }, /* small i, circumflex accent */ 151 { "iexcl", 161 }, /* inverted exclamation mark */ 152 { "igrave", 236 }, /* small i, grave accent */ 153 { "iquest", 191 }, /* inverted question mark */ 154 { "iuml", 239 }, /* small i, dieresis or umlaut mark */ 155 { "laquo", 171 }, /* angle quotation mark, left */ 156 { "lt", 60 }, /* less than */ 157 { "macr", 175 }, /* macron */ 158 { "micro", 181 }, /* micro sign */ 159 { "middot", 183 }, /* middle dot */ 160 { "nbsp", 160 }, /* no-break space */ 161 { "not", 172 }, /* not sign */ 162 { "ntilde", 241 }, /* small n, tilde */ 163 { "oacute", 243 }, /* small o, acute accent */ 164 { "ocirc", 244 }, /* small o, circumflex accent */ 165 { "ograve", 242 }, /* small o, grave accent */ 166 { "ordf", 170 }, /* ordinal indicator, feminine */ 167 { "ordm", 186 }, /* ordinal indicator, masculine */ 168 { "oslash", 248 }, /* small o, slash */ 169 { "otilde", 245 }, /* small o, tilde */ 170 { "ouml", 246 }, /* small o, dieresis or umlaut mark */ 171 { "para", 182 }, /* pilcrow (paragraph sign) */ 172 { "plusmn", 177 }, /* plus-or-minus sign */ 173 { "pound", 163 }, /* pound sterling sign */ 174 { "quot", 34 }, /* double quote */ 175 { "raquo", 187 }, /* angle quotation mark, right */ 176 { "reg", 174 }, /* registered sign */ 177 { "sect", 167 }, /* section sign */ 178 { "shy", 173 }, /* soft hyphen */ 179 { "sup1", 185 }, /* superscript one */ 180 { "sup2", 178 }, /* superscript two */ 181 { "sup3", 179 }, /* superscript three */ 182 { "szlig", 223 }, /* small sharp s, German (sz ligature) */ 183 { "thorn", 254 }, /* small thorn, Icelandic */ 184 { "times", 215 }, /* multiply sign */ 185 { "uacute", 250 }, /* small u, acute accent */ 186 { "ucirc", 251 }, /* small u, circumflex accent */ 187 { "ugrave", 249 }, /* small u, grave accent */ 188 { "uml", 168 }, /* umlaut (dieresis) */ 189 { "uuml", 252 }, /* small u, dieresis or umlaut mark */ 190 { "yacute", 253 }, /* small y, acute accent */ 191 { "yen", 165 }, /* yen sign */ 192 { "yuml", 255 }, /* small y, dieresis or umlaut mark */ 193 }; 194 195 /* 196 * unvis - decode characters previously encoded by vis 197 */ 198 int 199 unvis(char *cp, int c, int *astate, int flag) 200 { 201 unsigned char uc = (unsigned char)c; 202 unsigned char st, ia, is, lc; 203 204 /* 205 * Bottom 8 bits of astate hold the state machine state. 206 * Top 8 bits hold the current character in the http 1866 nv string decoding 207 */ 208 #define GS(a) ((a) & 0xff) 209 #define SS(a, b) (((uint32_t)(a) << 24) | (b)) 210 #define GI(a) ((uint32_t)(a) >> 24) 211 212 _DIAGASSERT(cp != NULL); 213 _DIAGASSERT(astate != NULL); 214 st = GS(*astate); 215 216 if (flag & UNVIS_END) { 217 switch (st) { 218 case S_OCTAL2: 219 case S_OCTAL3: 220 case S_HEX2: 221 *astate = SS(0, S_GROUND); 222 return UNVIS_VALID; 223 case S_GROUND: 224 return UNVIS_NOCHAR; 225 default: 226 return UNVIS_SYNBAD; 227 } 228 } 229 230 switch (st) { 231 232 case S_GROUND: 233 *cp = 0; 234 if ((flag & VIS_NOESCAPE) == 0 && c == '\\') { 235 *astate = SS(0, S_START); 236 return UNVIS_NOCHAR; 237 } 238 if ((flag & VIS_HTTP1808) && c == '%') { 239 *astate = SS(0, S_HEX1); 240 return UNVIS_NOCHAR; 241 } 242 if ((flag & VIS_HTTP1866) && c == '&') { 243 *astate = SS(0, S_AMP); 244 return UNVIS_NOCHAR; 245 } 246 if ((flag & VIS_MIMESTYLE) && c == '=') { 247 *astate = SS(0, S_MIME1); 248 return UNVIS_NOCHAR; 249 } 250 *cp = c; 251 return UNVIS_VALID; 252 253 case S_START: 254 switch(c) { 255 case '\\': 256 *cp = c; 257 *astate = SS(0, S_GROUND); 258 return UNVIS_VALID; 259 case '0': case '1': case '2': case '3': 260 case '4': case '5': case '6': case '7': 261 *cp = (c - '0'); 262 *astate = SS(0, S_OCTAL2); 263 return UNVIS_NOCHAR; 264 case 'M': 265 *cp = (char)0200; 266 *astate = SS(0, S_META); 267 return UNVIS_NOCHAR; 268 case '^': 269 *astate = SS(0, S_CTRL); 270 return UNVIS_NOCHAR; 271 case 'n': 272 *cp = '\n'; 273 *astate = SS(0, S_GROUND); 274 return UNVIS_VALID; 275 case 'r': 276 *cp = '\r'; 277 *astate = SS(0, S_GROUND); 278 return UNVIS_VALID; 279 case 'b': 280 *cp = '\b'; 281 *astate = SS(0, S_GROUND); 282 return UNVIS_VALID; 283 case 'a': 284 *cp = '\007'; 285 *astate = SS(0, S_GROUND); 286 return UNVIS_VALID; 287 case 'v': 288 *cp = '\v'; 289 *astate = SS(0, S_GROUND); 290 return UNVIS_VALID; 291 case 't': 292 *cp = '\t'; 293 *astate = SS(0, S_GROUND); 294 return UNVIS_VALID; 295 case 'f': 296 *cp = '\f'; 297 *astate = SS(0, S_GROUND); 298 return UNVIS_VALID; 299 case 's': 300 *cp = ' '; 301 *astate = SS(0, S_GROUND); 302 return UNVIS_VALID; 303 case 'E': 304 *cp = '\033'; 305 *astate = SS(0, S_GROUND); 306 return UNVIS_VALID; 307 case 'x': 308 *astate = SS(0, S_HEX); 309 return UNVIS_NOCHAR; 310 case '\n': 311 /* 312 * hidden newline 313 */ 314 *astate = SS(0, S_GROUND); 315 return UNVIS_NOCHAR; 316 case '$': 317 /* 318 * hidden marker 319 */ 320 *astate = SS(0, S_GROUND); 321 return UNVIS_NOCHAR; 322 default: 323 if (isgraph(c)) { 324 *cp = c; 325 *astate = SS(0, S_GROUND); 326 return UNVIS_VALID; 327 } 328 } 329 goto bad; 330 331 case S_META: 332 if (c == '-') 333 *astate = SS(0, S_META1); 334 else if (c == '^') 335 *astate = SS(0, S_CTRL); 336 else 337 goto bad; 338 return UNVIS_NOCHAR; 339 340 case S_META1: 341 *astate = SS(0, S_GROUND); 342 *cp |= c; 343 return UNVIS_VALID; 344 345 case S_CTRL: 346 if (c == '?') 347 *cp |= 0177; 348 else 349 *cp |= c & 037; 350 *astate = SS(0, S_GROUND); 351 return UNVIS_VALID; 352 353 case S_OCTAL2: /* second possible octal digit */ 354 if (isoctal(uc)) { 355 /* 356 * yes - and maybe a third 357 */ 358 *cp = (*cp << 3) + (c - '0'); 359 *astate = SS(0, S_OCTAL3); 360 return UNVIS_NOCHAR; 361 } 362 /* 363 * no - done with current sequence, push back passed char 364 */ 365 *astate = SS(0, S_GROUND); 366 return UNVIS_VALIDPUSH; 367 368 case S_OCTAL3: /* third possible octal digit */ 369 *astate = SS(0, S_GROUND); 370 if (isoctal(uc)) { 371 *cp = (*cp << 3) + (c - '0'); 372 return UNVIS_VALID; 373 } 374 /* 375 * we were done, push back passed char 376 */ 377 return UNVIS_VALIDPUSH; 378 379 case S_HEX: 380 if (!isxdigit(uc)) 381 goto bad; 382 /*FALLTHROUGH*/ 383 case S_HEX1: 384 if (isxdigit(uc)) { 385 *cp = xtod(uc); 386 *astate = SS(0, S_HEX2); 387 return UNVIS_NOCHAR; 388 } 389 /* 390 * no - done with current sequence, push back passed char 391 */ 392 *astate = SS(0, S_GROUND); 393 return UNVIS_VALIDPUSH; 394 395 case S_HEX2: 396 *astate = S_GROUND; 397 if (isxdigit(uc)) { 398 *cp = xtod(uc) | (*cp << 4); 399 return UNVIS_VALID; 400 } 401 return UNVIS_VALIDPUSH; 402 403 case S_MIME1: 404 if (uc == '\n' || uc == '\r') { 405 *astate = SS(0, S_EATCRNL); 406 return UNVIS_NOCHAR; 407 } 408 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) { 409 *cp = XTOD(uc); 410 *astate = SS(0, S_MIME2); 411 return UNVIS_NOCHAR; 412 } 413 goto bad; 414 415 case S_MIME2: 416 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) { 417 *astate = SS(0, S_GROUND); 418 *cp = XTOD(uc) | (*cp << 4); 419 return UNVIS_VALID; 420 } 421 goto bad; 422 423 case S_EATCRNL: 424 switch (uc) { 425 case '\r': 426 case '\n': 427 return UNVIS_NOCHAR; 428 case '=': 429 *astate = SS(0, S_MIME1); 430 return UNVIS_NOCHAR; 431 default: 432 *cp = uc; 433 *astate = SS(0, S_GROUND); 434 return UNVIS_VALID; 435 } 436 437 case S_AMP: 438 *cp = 0; 439 if (uc == '#') { 440 *astate = SS(0, S_NUMBER); 441 return UNVIS_NOCHAR; 442 } 443 *astate = SS(0, S_STRING); 444 /*FALLTHROUGH*/ 445 446 case S_STRING: 447 ia = *cp; /* index in the array */ 448 is = GI(*astate); /* index in the string */ 449 lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */ 450 451 if (uc == ';') 452 uc = '\0'; 453 454 for (; ia < __arraycount(nv); ia++) { 455 if (is != 0 && nv[ia].name[is - 1] != lc) 456 goto bad; 457 if (nv[ia].name[is] == uc) 458 break; 459 } 460 461 if (ia == __arraycount(nv)) 462 goto bad; 463 464 if (uc != 0) { 465 *cp = ia; 466 *astate = SS(is + 1, S_STRING); 467 return UNVIS_NOCHAR; 468 } 469 470 *cp = nv[ia].value; 471 *astate = SS(0, S_GROUND); 472 return UNVIS_VALID; 473 474 case S_NUMBER: 475 if (uc == ';') 476 return UNVIS_VALID; 477 if (!isdigit(uc)) 478 goto bad; 479 *cp += (*cp * 10) + uc - '0'; 480 return UNVIS_NOCHAR; 481 482 default: 483 bad: 484 /* 485 * decoder in unknown state - (probably uninitialized) 486 */ 487 *astate = SS(0, S_GROUND); 488 return UNVIS_SYNBAD; 489 } 490 } 491 492 /* 493 * strnunvisx - decode src into dst 494 * 495 * Number of chars decoded into dst is returned, -1 on error. 496 * Dst is null terminated. 497 */ 498 499 int 500 strnunvisx(char *dst, size_t dlen, const char *src, int flag) 501 { 502 char c; 503 char t = '\0', *start = dst; 504 int state = 0; 505 506 _DIAGASSERT(src != NULL); 507 _DIAGASSERT(dst != NULL); 508 #define CHECKSPACE() \ 509 do { \ 510 if (dlen-- == 0) { \ 511 errno = ENOSPC; \ 512 return -1; \ 513 } \ 514 } while (/*CONSTCOND*/0) 515 516 while ((c = *src++) != '\0') { 517 again: 518 switch (unvis(&t, c, &state, flag)) { 519 case UNVIS_VALID: 520 CHECKSPACE(); 521 *dst++ = t; 522 break; 523 case UNVIS_VALIDPUSH: 524 CHECKSPACE(); 525 *dst++ = t; 526 goto again; 527 case 0: 528 case UNVIS_NOCHAR: 529 break; 530 case UNVIS_SYNBAD: 531 errno = EINVAL; 532 return -1; 533 default: 534 _DIAGASSERT(/*CONSTCOND*/0); 535 errno = EINVAL; 536 return -1; 537 } 538 } 539 if (unvis(&t, c, &state, UNVIS_END) == UNVIS_VALID) { 540 CHECKSPACE(); 541 *dst++ = t; 542 } 543 CHECKSPACE(); 544 *dst = '\0'; 545 return (int)(dst - start); 546 } 547 548 int 549 strunvisx(char *dst, const char *src, int flag) 550 { 551 return strnunvisx(dst, (size_t)~0, src, flag); 552 } 553 554 int 555 strunvis(char *dst, const char *src) 556 { 557 return strnunvisx(dst, (size_t)~0, src, 0); 558 } 559 560 int 561 strnunvis(char *dst, size_t dlen, const char *src) 562 { 563 return strnunvisx(dst, dlen, src, 0); 564 } 565 #endif 566