kc3-lang/libbsd/src/unvis.c
Tag
-
Show log
Commit
-
Hash : 50b50a43
Author :
Date : 2021-03-02T05:18:04
vis: Add prototypes for strnvis() and strnunvis() variants Warned-by: gcc
-
src/unvis.c
-
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582
/* $NetBSD: unvis.c,v 1.44 2014/09/26 15:43:36 roy Exp $ */ /*- * Copyright (c) 1989, 1993 * The Regents of the University of California. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #include <sys/cdefs.h> #include <sys/types.h> #include <assert.h> #include <ctype.h> #include <stdint.h> #include <stdio.h> #include <errno.h> #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wcpp" #include <vis.h> #pragma GCC diagnostic pop #include "local-link.h" #ifdef __weak_alias __weak_alias(strnunvisx,_strnunvisx) #endif #define _DIAGASSERT(x) /* * decode driven by state machine */ #define S_GROUND 0 /* haven't seen escape char */ #define S_START 1 /* start decoding special sequence */ #define S_META 2 /* metachar started (M) */ #define S_META1 3 /* metachar more, regular char (-) */ #define S_CTRL 4 /* control char started (^) */ #define S_OCTAL2 5 /* octal digit 2 */ #define S_OCTAL3 6 /* octal digit 3 */ #define S_HEX 7 /* mandatory hex digit */ #define S_HEX1 8 /* http hex digit */ #define S_HEX2 9 /* http hex digit 2 */ #define S_MIME1 10 /* mime hex digit 1 */ #define S_MIME2 11 /* mime hex digit 2 */ #define S_EATCRNL 12 /* mime eating CRNL */ #define S_AMP 13 /* seen & */ #define S_NUMBER 14 /* collecting number */ #define S_STRING 15 /* collecting string */ #define isoctal(c) \ (((unsigned char)(c)) >= '0' && ((unsigned char)(c)) <= '7') #define xtod(c) (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10)) #define XTOD(c) (isdigit(c) ? (c - '0') : ((c - 'A') + 10)) /* * RFC 1866 */ static const struct nv { char name[7]; uint8_t value; } nv[] = { { "AElig", 198 }, /* capital AE diphthong (ligature) */ { "Aacute", 193 }, /* capital A, acute accent */ { "Acirc", 194 }, /* capital A, circumflex accent */ { "Agrave", 192 }, /* capital A, grave accent */ { "Aring", 197 }, /* capital A, ring */ { "Atilde", 195 }, /* capital A, tilde */ { "Auml", 196 }, /* capital A, dieresis or umlaut mark */ { "Ccedil", 199 }, /* capital C, cedilla */ { "ETH", 208 }, /* capital Eth, Icelandic */ { "Eacute", 201 }, /* capital E, acute accent */ { "Ecirc", 202 }, /* capital E, circumflex accent */ { "Egrave", 200 }, /* capital E, grave accent */ { "Euml", 203 }, /* capital E, dieresis or umlaut mark */ { "Iacute", 205 }, /* capital I, acute accent */ { "Icirc", 206 }, /* capital I, circumflex accent */ { "Igrave", 204 }, /* capital I, grave accent */ { "Iuml", 207 }, /* capital I, dieresis or umlaut mark */ { "Ntilde", 209 }, /* capital N, tilde */ { "Oacute", 211 }, /* capital O, acute accent */ { "Ocirc", 212 }, /* capital O, circumflex accent */ { "Ograve", 210 }, /* capital O, grave accent */ { "Oslash", 216 }, /* capital O, slash */ { "Otilde", 213 }, /* capital O, tilde */ { "Ouml", 214 }, /* capital O, dieresis or umlaut mark */ { "THORN", 222 }, /* capital THORN, Icelandic */ { "Uacute", 218 }, /* capital U, acute accent */ { "Ucirc", 219 }, /* capital U, circumflex accent */ { "Ugrave", 217 }, /* capital U, grave accent */ { "Uuml", 220 }, /* capital U, dieresis or umlaut mark */ { "Yacute", 221 }, /* capital Y, acute accent */ { "aacute", 225 }, /* small a, acute accent */ { "acirc", 226 }, /* small a, circumflex accent */ { "acute", 180 }, /* acute accent */ { "aelig", 230 }, /* small ae diphthong (ligature) */ { "agrave", 224 }, /* small a, grave accent */ { "amp", 38 }, /* ampersand */ { "aring", 229 }, /* small a, ring */ { "atilde", 227 }, /* small a, tilde */ { "auml", 228 }, /* small a, dieresis or umlaut mark */ { "brvbar", 166 }, /* broken (vertical) bar */ { "ccedil", 231 }, /* small c, cedilla */ { "cedil", 184 }, /* cedilla */ { "cent", 162 }, /* cent sign */ { "copy", 169 }, /* copyright sign */ { "curren", 164 }, /* general currency sign */ { "deg", 176 }, /* degree sign */ { "divide", 247 }, /* divide sign */ { "eacute", 233 }, /* small e, acute accent */ { "ecirc", 234 }, /* small e, circumflex accent */ { "egrave", 232 }, /* small e, grave accent */ { "eth", 240 }, /* small eth, Icelandic */ { "euml", 235 }, /* small e, dieresis or umlaut mark */ { "frac12", 189 }, /* fraction one-half */ { "frac14", 188 }, /* fraction one-quarter */ { "frac34", 190 }, /* fraction three-quarters */ { "gt", 62 }, /* greater than */ { "iacute", 237 }, /* small i, acute accent */ { "icirc", 238 }, /* small i, circumflex accent */ { "iexcl", 161 }, /* inverted exclamation mark */ { "igrave", 236 }, /* small i, grave accent */ { "iquest", 191 }, /* inverted question mark */ { "iuml", 239 }, /* small i, dieresis or umlaut mark */ { "laquo", 171 }, /* angle quotation mark, left */ { "lt", 60 }, /* less than */ { "macr", 175 }, /* macron */ { "micro", 181 }, /* micro sign */ { "middot", 183 }, /* middle dot */ { "nbsp", 160 }, /* no-break space */ { "not", 172 }, /* not sign */ { "ntilde", 241 }, /* small n, tilde */ { "oacute", 243 }, /* small o, acute accent */ { "ocirc", 244 }, /* small o, circumflex accent */ { "ograve", 242 }, /* small o, grave accent */ { "ordf", 170 }, /* ordinal indicator, feminine */ { "ordm", 186 }, /* ordinal indicator, masculine */ { "oslash", 248 }, /* small o, slash */ { "otilde", 245 }, /* small o, tilde */ { "ouml", 246 }, /* small o, dieresis or umlaut mark */ { "para", 182 }, /* pilcrow (paragraph sign) */ { "plusmn", 177 }, /* plus-or-minus sign */ { "pound", 163 }, /* pound sterling sign */ { "quot", 34 }, /* double quote */ { "raquo", 187 }, /* angle quotation mark, right */ { "reg", 174 }, /* registered sign */ { "sect", 167 }, /* section sign */ { "shy", 173 }, /* soft hyphen */ { "sup1", 185 }, /* superscript one */ { "sup2", 178 }, /* superscript two */ { "sup3", 179 }, /* superscript three */ { "szlig", 223 }, /* small sharp s, German (sz ligature) */ { "thorn", 254 }, /* small thorn, Icelandic */ { "times", 215 }, /* multiply sign */ { "uacute", 250 }, /* small u, acute accent */ { "ucirc", 251 }, /* small u, circumflex accent */ { "ugrave", 249 }, /* small u, grave accent */ { "uml", 168 }, /* umlaut (dieresis) */ { "uuml", 252 }, /* small u, dieresis or umlaut mark */ { "yacute", 253 }, /* small y, acute accent */ { "yen", 165 }, /* yen sign */ { "yuml", 255 }, /* small y, dieresis or umlaut mark */ }; /* * unvis - decode characters previously encoded by vis */ int unvis(char *cp, int c, int *astate, int flag) { unsigned char uc = (unsigned char)c; unsigned char st, ia, is, lc; /* * Bottom 8 bits of astate hold the state machine state. * Top 8 bits hold the current character in the http 1866 nv string decoding */ #define GS(a) ((a) & 0xff) #define SS(a, b) (((uint32_t)(a) << 24) | (b)) #define GI(a) ((uint32_t)(a) >> 24) _DIAGASSERT(cp != NULL); _DIAGASSERT(astate != NULL); st = GS(*astate); if (flag & UNVIS_END) { switch (st) { case S_OCTAL2: case S_OCTAL3: case S_HEX2: *astate = SS(0, S_GROUND); return UNVIS_VALID; case S_GROUND: return UNVIS_NOCHAR; default: return UNVIS_SYNBAD; } } switch (st) { case S_GROUND: *cp = 0; if ((flag & VIS_NOESCAPE) == 0 && c == '\\') { *astate = SS(0, S_START); return UNVIS_NOCHAR; } if ((flag & VIS_HTTP1808) && c == '%') { *astate = SS(0, S_HEX1); return UNVIS_NOCHAR; } if ((flag & VIS_HTTP1866) && c == '&') { *astate = SS(0, S_AMP); return UNVIS_NOCHAR; } if ((flag & VIS_MIMESTYLE) && c == '=') { *astate = SS(0, S_MIME1); return UNVIS_NOCHAR; } *cp = c; return UNVIS_VALID; case S_START: switch(c) { case '\\': *cp = c; *astate = SS(0, S_GROUND); return UNVIS_VALID; case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': *cp = (c - '0'); *astate = SS(0, S_OCTAL2); return UNVIS_NOCHAR; case 'M': *cp = (char)0200; *astate = SS(0, S_META); return UNVIS_NOCHAR; case '^': *astate = SS(0, S_CTRL); return UNVIS_NOCHAR; case 'n': *cp = '\n'; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 'r': *cp = '\r'; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 'b': *cp = '\b'; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 'a': *cp = '\007'; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 'v': *cp = '\v'; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 't': *cp = '\t'; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 'f': *cp = '\f'; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 's': *cp = ' '; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 'E': *cp = '\033'; *astate = SS(0, S_GROUND); return UNVIS_VALID; case 'x': *astate = SS(0, S_HEX); return UNVIS_NOCHAR; case '\n': /* * hidden newline */ *astate = SS(0, S_GROUND); return UNVIS_NOCHAR; case '$': /* * hidden marker */ *astate = SS(0, S_GROUND); return UNVIS_NOCHAR; default: if (isgraph(c)) { *cp = c; *astate = SS(0, S_GROUND); return UNVIS_VALID; } } goto bad; case S_META: if (c == '-') *astate = SS(0, S_META1); else if (c == '^') *astate = SS(0, S_CTRL); else goto bad; return UNVIS_NOCHAR; case S_META1: *astate = SS(0, S_GROUND); *cp |= c; return UNVIS_VALID; case S_CTRL: if (c == '?') *cp |= 0177; else *cp |= c & 037; *astate = SS(0, S_GROUND); return UNVIS_VALID; case S_OCTAL2: /* second possible octal digit */ if (isoctal(uc)) { /* * yes - and maybe a third */ *cp = (*cp << 3) + (c - '0'); *astate = SS(0, S_OCTAL3); return UNVIS_NOCHAR; } /* * no - done with current sequence, push back passed char */ *astate = SS(0, S_GROUND); return UNVIS_VALIDPUSH; case S_OCTAL3: /* third possible octal digit */ *astate = SS(0, S_GROUND); if (isoctal(uc)) { *cp = (*cp << 3) + (c - '0'); return UNVIS_VALID; } /* * we were done, push back passed char */ return UNVIS_VALIDPUSH; case S_HEX: if (!isxdigit(uc)) goto bad; /*FALLTHROUGH*/ case S_HEX1: if (isxdigit(uc)) { *cp = xtod(uc); *astate = SS(0, S_HEX2); return UNVIS_NOCHAR; } /* * no - done with current sequence, push back passed char */ *astate = SS(0, S_GROUND); return UNVIS_VALIDPUSH; case S_HEX2: *astate = S_GROUND; if (isxdigit(uc)) { *cp = xtod(uc) | (*cp << 4); return UNVIS_VALID; } return UNVIS_VALIDPUSH; case S_MIME1: if (uc == '\n' || uc == '\r') { *astate = SS(0, S_EATCRNL); return UNVIS_NOCHAR; } if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) { *cp = XTOD(uc); *astate = SS(0, S_MIME2); return UNVIS_NOCHAR; } goto bad; case S_MIME2: if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) { *astate = SS(0, S_GROUND); *cp = XTOD(uc) | (*cp << 4); return UNVIS_VALID; } goto bad; case S_EATCRNL: switch (uc) { case '\r': case '\n': return UNVIS_NOCHAR; case '=': *astate = SS(0, S_MIME1); return UNVIS_NOCHAR; default: *cp = uc; *astate = SS(0, S_GROUND); return UNVIS_VALID; } case S_AMP: *cp = 0; if (uc == '#') { *astate = SS(0, S_NUMBER); return UNVIS_NOCHAR; } *astate = SS(0, S_STRING); /*FALLTHROUGH*/ case S_STRING: ia = *cp; /* index in the array */ is = GI(*astate); /* index in the string */ lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */ if (uc == ';') uc = '\0'; for (; ia < __arraycount(nv); ia++) { if (is != 0 && nv[ia].name[is - 1] != lc) goto bad; if (nv[ia].name[is] == uc) break; } if (ia == __arraycount(nv)) goto bad; if (uc != 0) { *cp = ia; *astate = SS(is + 1, S_STRING); return UNVIS_NOCHAR; } *cp = nv[ia].value; *astate = SS(0, S_GROUND); return UNVIS_VALID; case S_NUMBER: if (uc == ';') return UNVIS_VALID; if (!isdigit(uc)) goto bad; *cp += (*cp * 10) + uc - '0'; return UNVIS_NOCHAR; default: bad: /* * decoder in unknown state - (probably uninitialized) */ *astate = SS(0, S_GROUND); return UNVIS_SYNBAD; } } /* * strnunvisx - decode src into dst * * Number of chars decoded into dst is returned, -1 on error. * Dst is null terminated. */ int strnunvisx(char *dst, size_t dlen, const char *src, int flag) { char c; char t = '\0', *start = dst; int state = 0; _DIAGASSERT(src != NULL); _DIAGASSERT(dst != NULL); #define CHECKSPACE() \ do { \ if (dlen-- == 0) { \ errno = ENOSPC; \ return -1; \ } \ } while (/*CONSTCOND*/0) while ((c = *src++) != '\0') { again: switch (unvis(&t, c, &state, flag)) { case UNVIS_VALID: CHECKSPACE(); *dst++ = t; break; case UNVIS_VALIDPUSH: CHECKSPACE(); *dst++ = t; goto again; case 0: case UNVIS_NOCHAR: break; case UNVIS_SYNBAD: errno = EINVAL; return -1; default: _DIAGASSERT(/*CONSTCOND*/0); errno = EINVAL; return -1; } } if (unvis(&t, c, &state, UNVIS_END) == UNVIS_VALID) { CHECKSPACE(); *dst++ = t; } CHECKSPACE(); *dst = '\0'; return (int)(dst - start); } int strunvisx(char *dst, const char *src, int flag) { return strnunvisx(dst, (size_t)~0, src, flag); } int strunvis(char *dst, const char *src) { return strnunvisx(dst, (size_t)~0, src, 0); } /* * NetBSD added an strnvis and unfortunately made it incompatible with the * existing one in OpenBSD and Freedesktop's libbsd (the former having existed * for over ten years). Despite this incompatibility being reported during * development (see http://gnats.netbsd.org/44977) they still shipped it. * Even more unfortunately FreeBSD and later MacOS picked up this incompatible * implementation. * * Provide both implementations and default for now on the historical one to * avoid breakage, we will switch to the NetBSD one in libbsd 0.10.0 or so. * * OpenBSD, 2001: strnunvis(char *dst, const char *src, size_t dlen); * NetBSD: 2012, strnunvis(char *dst, size_t dlen, const char *src); */ ssize_t strnunvis_openbsd(char *, const char *, size_t); ssize_t strnunvis_openbsd(char *dst, const char *src, size_t dlen) { return strnunvisx(dst, dlen, src, 0); } libbsd_symver_default(strnunvis, strnunvis_openbsd, LIBBSD_0.2); int strnunvis_netbsd(char *, size_t, const char *); int strnunvis_netbsd(char *dst, size_t dlen, const char *src) { return strnunvisx(dst, dlen, src, 0); } libbsd_symver_variant(strnunvis, strnunvis_netbsd, LIBBSD_0.9.1);