1 /* @(#)unvis.c 8.1 (Berkeley) 6/4/93 */
2 /* $NetBSD: unvis.c,v 1.44 2014/09/26 15:43:36 roy Exp $ */
5 * Copyright (c) 1989, 1993
6 * The Regents of the University of California. All rights reserved.
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
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. Neither the name of the University nor the names of its contributors
17 * may be used to endorse or promote products derived from this software
18 * without specific prior written permission.
20 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
21 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
22 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
23 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
24 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
25 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
26 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
28 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
29 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
33 #include "namespace.h"
34 #include <sys/types.h>
44 * Return the number of elements in a statically-allocated array,
47 #define __arraycount(__x) (sizeof(__x) / sizeof(__x[0]))
50 __weak_alias(strnunvisx,_strnunvisx)
55 * decode driven by state machine
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_HEX 7 /* mandatory hex digit */
65 #define S_HEX1 8 /* http hex digit */
66 #define S_HEX2 9 /* http hex digit 2 */
67 #define S_MIME1 10 /* mime hex digit 1 */
68 #define S_MIME2 11 /* mime hex digit 2 */
69 #define S_EATCRNL 12 /* mime eating CRNL */
70 #define S_AMP 13 /* seen & */
71 #define S_NUMBER 14 /* collecting number */
72 #define S_STRING 15 /* collecting string */
74 #define isoctal(c) (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
75 #define xtod(c) (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10))
76 #define XTOD(c) (isdigit(c) ? (c - '0') : ((c - 'A') + 10))
81 static const struct nv {
85 { "AElig", 198 }, /* capital AE diphthong (ligature) */
86 { "Aacute", 193 }, /* capital A, acute accent */
87 { "Acirc", 194 }, /* capital A, circumflex accent */
88 { "Agrave", 192 }, /* capital A, grave accent */
89 { "Aring", 197 }, /* capital A, ring */
90 { "Atilde", 195 }, /* capital A, tilde */
91 { "Auml", 196 }, /* capital A, dieresis or umlaut mark */
92 { "Ccedil", 199 }, /* capital C, cedilla */
93 { "ETH", 208 }, /* capital Eth, Icelandic */
94 { "Eacute", 201 }, /* capital E, acute accent */
95 { "Ecirc", 202 }, /* capital E, circumflex accent */
96 { "Egrave", 200 }, /* capital E, grave accent */
97 { "Euml", 203 }, /* capital E, dieresis or umlaut mark */
98 { "Iacute", 205 }, /* capital I, acute accent */
99 { "Icirc", 206 }, /* capital I, circumflex accent */
100 { "Igrave", 204 }, /* capital I, grave accent */
101 { "Iuml", 207 }, /* capital I, dieresis or umlaut mark */
102 { "Ntilde", 209 }, /* capital N, tilde */
103 { "Oacute", 211 }, /* capital O, acute accent */
104 { "Ocirc", 212 }, /* capital O, circumflex accent */
105 { "Ograve", 210 }, /* capital O, grave accent */
106 { "Oslash", 216 }, /* capital O, slash */
107 { "Otilde", 213 }, /* capital O, tilde */
108 { "Ouml", 214 }, /* capital O, dieresis or umlaut mark */
109 { "THORN", 222 }, /* capital THORN, Icelandic */
110 { "Uacute", 218 }, /* capital U, acute accent */
111 { "Ucirc", 219 }, /* capital U, circumflex accent */
112 { "Ugrave", 217 }, /* capital U, grave accent */
113 { "Uuml", 220 }, /* capital U, dieresis or umlaut mark */
114 { "Yacute", 221 }, /* capital Y, acute accent */
115 { "aacute", 225 }, /* small a, acute accent */
116 { "acirc", 226 }, /* small a, circumflex accent */
117 { "acute", 180 }, /* acute accent */
118 { "aelig", 230 }, /* small ae diphthong (ligature) */
119 { "agrave", 224 }, /* small a, grave accent */
120 { "amp", 38 }, /* ampersand */
121 { "aring", 229 }, /* small a, ring */
122 { "atilde", 227 }, /* small a, tilde */
123 { "auml", 228 }, /* small a, dieresis or umlaut mark */
124 { "brvbar", 166 }, /* broken (vertical) bar */
125 { "ccedil", 231 }, /* small c, cedilla */
126 { "cedil", 184 }, /* cedilla */
127 { "cent", 162 }, /* cent sign */
128 { "copy", 169 }, /* copyright sign */
129 { "curren", 164 }, /* general currency sign */
130 { "deg", 176 }, /* degree sign */
131 { "divide", 247 }, /* divide sign */
132 { "eacute", 233 }, /* small e, acute accent */
133 { "ecirc", 234 }, /* small e, circumflex accent */
134 { "egrave", 232 }, /* small e, grave accent */
135 { "eth", 240 }, /* small eth, Icelandic */
136 { "euml", 235 }, /* small e, dieresis or umlaut mark */
137 { "frac12", 189 }, /* fraction one-half */
138 { "frac14", 188 }, /* fraction one-quarter */
139 { "frac34", 190 }, /* fraction three-quarters */
140 { "gt", 62 }, /* greater than */
141 { "iacute", 237 }, /* small i, acute accent */
142 { "icirc", 238 }, /* small i, circumflex accent */
143 { "iexcl", 161 }, /* inverted exclamation mark */
144 { "igrave", 236 }, /* small i, grave accent */
145 { "iquest", 191 }, /* inverted question mark */
146 { "iuml", 239 }, /* small i, dieresis or umlaut mark */
147 { "laquo", 171 }, /* angle quotation mark, left */
148 { "lt", 60 }, /* less than */
149 { "macr", 175 }, /* macron */
150 { "micro", 181 }, /* micro sign */
151 { "middot", 183 }, /* middle dot */
152 { "nbsp", 160 }, /* no-break space */
153 { "not", 172 }, /* not sign */
154 { "ntilde", 241 }, /* small n, tilde */
155 { "oacute", 243 }, /* small o, acute accent */
156 { "ocirc", 244 }, /* small o, circumflex accent */
157 { "ograve", 242 }, /* small o, grave accent */
158 { "ordf", 170 }, /* ordinal indicator, feminine */
159 { "ordm", 186 }, /* ordinal indicator, masculine */
160 { "oslash", 248 }, /* small o, slash */
161 { "otilde", 245 }, /* small o, tilde */
162 { "ouml", 246 }, /* small o, dieresis or umlaut mark */
163 { "para", 182 }, /* pilcrow (paragraph sign) */
164 { "plusmn", 177 }, /* plus-or-minus sign */
165 { "pound", 163 }, /* pound sterling sign */
166 { "quot", 34 }, /* double quote */
167 { "raquo", 187 }, /* angle quotation mark, right */
168 { "reg", 174 }, /* registered sign */
169 { "sect", 167 }, /* section sign */
170 { "shy", 173 }, /* soft hyphen */
171 { "sup1", 185 }, /* superscript one */
172 { "sup2", 178 }, /* superscript two */
173 { "sup3", 179 }, /* superscript three */
174 { "szlig", 223 }, /* small sharp s, German (sz ligature) */
175 { "thorn", 254 }, /* small thorn, Icelandic */
176 { "times", 215 }, /* multiply sign */
177 { "uacute", 250 }, /* small u, acute accent */
178 { "ucirc", 251 }, /* small u, circumflex accent */
179 { "ugrave", 249 }, /* small u, grave accent */
180 { "uml", 168 }, /* umlaut (dieresis) */
181 { "uuml", 252 }, /* small u, dieresis or umlaut mark */
182 { "yacute", 253 }, /* small y, acute accent */
183 { "yen", 165 }, /* yen sign */
184 { "yuml", 255 }, /* small y, dieresis or umlaut mark */
188 * unvis - decode characters previously encoded by vis
191 unvis(char *cp, int c, int *astate, int flag)
193 unsigned char uc = (unsigned char)c;
194 unsigned char st, ia, is, lc;
197 * Bottom 8 bits of astate hold the state machine state.
198 * Top 8 bits hold the current character in the http 1866 nv string decoding
200 #define GS(a) ((a) & 0xff)
201 #define SS(a, b) (((uint32_t)(a) << 24) | (b))
202 #define GI(a) ((uint32_t)(a) >> 24)
204 _DIAGASSERT(cp != NULL);
205 _DIAGASSERT(astate != NULL);
208 if (flag & UNVIS_END) {
213 *astate = SS(0, S_GROUND);
226 if ((flag & VIS_NOESCAPE) == 0 && c == '\\') {
227 *astate = SS(0, S_START);
230 if ((flag & VIS_HTTP1808) && c == '%') {
231 *astate = SS(0, S_HEX1);
234 if ((flag & VIS_HTTP1866) && c == '&') {
235 *astate = SS(0, S_AMP);
238 if ((flag & VIS_MIMESTYLE) && c == '=') {
239 *astate = SS(0, S_MIME1);
249 *astate = SS(0, S_GROUND);
253 *astate = SS(0, S_GROUND);
255 case '0': case '1': case '2': case '3':
256 case '4': case '5': case '6': case '7':
258 *astate = SS(0, S_OCTAL2);
262 *astate = SS(0, S_META);
265 *astate = SS(0, S_CTRL);
269 *astate = SS(0, S_GROUND);
273 *astate = SS(0, S_GROUND);
277 *astate = SS(0, S_GROUND);
281 *astate = SS(0, S_GROUND);
285 *astate = SS(0, S_GROUND);
289 *astate = SS(0, S_GROUND);
293 *astate = SS(0, S_GROUND);
297 *astate = SS(0, S_GROUND);
301 *astate = SS(0, S_GROUND);
304 *astate = SS(0, S_HEX);
310 *astate = SS(0, S_GROUND);
316 *astate = SS(0, S_GROUND);
321 *astate = SS(0, S_GROUND);
329 *astate = SS(0, S_META1);
331 *astate = SS(0, S_CTRL);
337 *astate = SS(0, S_GROUND);
346 *astate = SS(0, S_GROUND);
349 case S_OCTAL2: /* second possible octal digit */
352 * yes - and maybe a third
354 *cp = (*cp << 3) + (c - '0');
355 *astate = SS(0, S_OCTAL3);
359 * no - done with current sequence, push back passed char
361 *astate = SS(0, S_GROUND);
362 return UNVIS_VALIDPUSH;
364 case S_OCTAL3: /* third possible octal digit */
365 *astate = SS(0, S_GROUND);
367 *cp = (*cp << 3) + (c - '0');
371 * we were done, push back passed char
373 return UNVIS_VALIDPUSH;
382 *astate = SS(0, S_HEX2);
386 * no - done with current sequence, push back passed char
388 *astate = SS(0, S_GROUND);
389 return UNVIS_VALIDPUSH;
394 *cp = xtod(uc) | (*cp << 4);
397 return UNVIS_VALIDPUSH;
400 if (uc == '\n' || uc == '\r') {
401 *astate = SS(0, S_EATCRNL);
404 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
406 *astate = SS(0, S_MIME2);
412 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
413 *astate = SS(0, S_GROUND);
414 *cp = XTOD(uc) | (*cp << 4);
425 *astate = SS(0, S_MIME1);
429 *astate = SS(0, S_GROUND);
436 *astate = SS(0, S_NUMBER);
439 *astate = SS(0, S_STRING);
443 ia = *cp; /* index in the array */
444 is = GI(*astate); /* index in the string */
445 lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */
450 for (; ia < __arraycount(nv); ia++) {
451 if (is != 0 && nv[ia].name[is - 1] != lc)
453 if (nv[ia].name[is] == uc)
457 if (ia == __arraycount(nv))
462 *astate = SS(is + 1, S_STRING);
467 *astate = SS(0, S_GROUND);
475 *cp += (*cp * 10) + uc - '0';
481 * decoder in unknown state - (probably uninitialized)
483 *astate = SS(0, S_GROUND);
489 * strnunvisx - decode src into dst
491 * Number of chars decoded into dst is returned, -1 on error.
492 * Dst is null terminated.
496 strnunvisx(char *dst, size_t dlen, const char *src, int flag)
499 char t = '\0', *start = dst;
502 _DIAGASSERT(src != NULL);
503 _DIAGASSERT(dst != NULL);
504 #define CHECKSPACE() \
510 } while (/*CONSTCOND*/0)
512 while ((c = *src++) != '\0') {
514 switch (unvis(&t, c, &state, flag)) {
519 case UNVIS_VALIDPUSH:
530 _DIAGASSERT(/*CONSTCOND*/0);
535 if (unvis(&t, c, &state, UNVIS_END) == UNVIS_VALID) {
541 return (int)(dst - start);
545 strunvisx(char *dst, const char *src, int flag)
547 return strnunvisx(dst, (size_t)~0, src, flag);
551 strunvis(char *dst, const char *src)
553 return strnunvisx(dst, (size_t)~0, src, 0);
557 strnunvis(char *dst, size_t dlen, const char *src)
559 return strnunvisx(dst, dlen, src, 0);