1 /* $NetBSD: unvis.c,v 1.45 2022/04/19 20:32:15 rillig Exp $ */
4 * Copyright (c) 1989, 1993
5 * The Regents of the University of California. All rights reserved.
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
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.
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
32 #include <sys/cdefs.h>
33 #if defined(LIBC_SCCS) && !defined(lint)
35 static char sccsid[] = "@(#)unvis.c 8.1 (Berkeley) 6/4/93";
37 __RCSID("$NetBSD: unvis.c,v 1.45 2022/04/19 20:32:15 rillig Exp $");
39 #endif /* LIBC_SCCS and not lint */
41 #include "namespace.h"
42 #include <sys/types.h>
51 #define _DIAGASSERT(x) assert(x)
54 * Return the number of elements in a statically-allocated array,
57 #define __arraycount(__x) (sizeof(__x) / sizeof(__x[0]))
60 __weak_alias(strnunvisx,_strnunvisx)
65 * decode driven by state machine
67 #define S_GROUND 0 /* haven't seen escape char */
68 #define S_START 1 /* start decoding special sequence */
69 #define S_META 2 /* metachar started (M) */
70 #define S_META1 3 /* metachar more, regular char (-) */
71 #define S_CTRL 4 /* control char started (^) */
72 #define S_OCTAL2 5 /* octal digit 2 */
73 #define S_OCTAL3 6 /* octal digit 3 */
74 #define S_HEX 7 /* mandatory hex digit */
75 #define S_HEX1 8 /* http hex digit */
76 #define S_HEX2 9 /* http hex digit 2 */
77 #define S_MIME1 10 /* mime hex digit 1 */
78 #define S_MIME2 11 /* mime hex digit 2 */
79 #define S_EATCRNL 12 /* mime eating CRNL */
80 #define S_AMP 13 /* seen & */
81 #define S_NUMBER 14 /* collecting number */
82 #define S_STRING 15 /* collecting string */
84 #define isoctal(c) (((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
85 #define xtod(c) (isdigit(c) ? (c - '0') : ((tolower(c) - 'a') + 10))
86 #define XTOD(c) (isdigit(c) ? (c - '0') : ((c - 'A') + 10))
91 static const struct nv {
95 { "AElig", 198 }, /* capital AE diphthong (ligature) */
96 { "Aacute", 193 }, /* capital A, acute accent */
97 { "Acirc", 194 }, /* capital A, circumflex accent */
98 { "Agrave", 192 }, /* capital A, grave accent */
99 { "Aring", 197 }, /* capital A, ring */
100 { "Atilde", 195 }, /* capital A, tilde */
101 { "Auml", 196 }, /* capital A, dieresis or umlaut mark */
102 { "Ccedil", 199 }, /* capital C, cedilla */
103 { "ETH", 208 }, /* capital Eth, Icelandic */
104 { "Eacute", 201 }, /* capital E, acute accent */
105 { "Ecirc", 202 }, /* capital E, circumflex accent */
106 { "Egrave", 200 }, /* capital E, grave accent */
107 { "Euml", 203 }, /* capital E, dieresis or umlaut mark */
108 { "Iacute", 205 }, /* capital I, acute accent */
109 { "Icirc", 206 }, /* capital I, circumflex accent */
110 { "Igrave", 204 }, /* capital I, grave accent */
111 { "Iuml", 207 }, /* capital I, dieresis or umlaut mark */
112 { "Ntilde", 209 }, /* capital N, tilde */
113 { "Oacute", 211 }, /* capital O, acute accent */
114 { "Ocirc", 212 }, /* capital O, circumflex accent */
115 { "Ograve", 210 }, /* capital O, grave accent */
116 { "Oslash", 216 }, /* capital O, slash */
117 { "Otilde", 213 }, /* capital O, tilde */
118 { "Ouml", 214 }, /* capital O, dieresis or umlaut mark */
119 { "THORN", 222 }, /* capital THORN, Icelandic */
120 { "Uacute", 218 }, /* capital U, acute accent */
121 { "Ucirc", 219 }, /* capital U, circumflex accent */
122 { "Ugrave", 217 }, /* capital U, grave accent */
123 { "Uuml", 220 }, /* capital U, dieresis or umlaut mark */
124 { "Yacute", 221 }, /* capital Y, acute accent */
125 { "aacute", 225 }, /* small a, acute accent */
126 { "acirc", 226 }, /* small a, circumflex accent */
127 { "acute", 180 }, /* acute accent */
128 { "aelig", 230 }, /* small ae diphthong (ligature) */
129 { "agrave", 224 }, /* small a, grave accent */
130 { "amp", 38 }, /* ampersand */
131 { "aring", 229 }, /* small a, ring */
132 { "atilde", 227 }, /* small a, tilde */
133 { "auml", 228 }, /* small a, dieresis or umlaut mark */
134 { "brvbar", 166 }, /* broken (vertical) bar */
135 { "ccedil", 231 }, /* small c, cedilla */
136 { "cedil", 184 }, /* cedilla */
137 { "cent", 162 }, /* cent sign */
138 { "copy", 169 }, /* copyright sign */
139 { "curren", 164 }, /* general currency sign */
140 { "deg", 176 }, /* degree sign */
141 { "divide", 247 }, /* divide sign */
142 { "eacute", 233 }, /* small e, acute accent */
143 { "ecirc", 234 }, /* small e, circumflex accent */
144 { "egrave", 232 }, /* small e, grave accent */
145 { "eth", 240 }, /* small eth, Icelandic */
146 { "euml", 235 }, /* small e, dieresis or umlaut mark */
147 { "frac12", 189 }, /* fraction one-half */
148 { "frac14", 188 }, /* fraction one-quarter */
149 { "frac34", 190 }, /* fraction three-quarters */
150 { "gt", 62 }, /* greater than */
151 { "iacute", 237 }, /* small i, acute accent */
152 { "icirc", 238 }, /* small i, circumflex accent */
153 { "iexcl", 161 }, /* inverted exclamation mark */
154 { "igrave", 236 }, /* small i, grave accent */
155 { "iquest", 191 }, /* inverted question mark */
156 { "iuml", 239 }, /* small i, dieresis or umlaut mark */
157 { "laquo", 171 }, /* angle quotation mark, left */
158 { "lt", 60 }, /* less than */
159 { "macr", 175 }, /* macron */
160 { "micro", 181 }, /* micro sign */
161 { "middot", 183 }, /* middle dot */
162 { "nbsp", 160 }, /* no-break space */
163 { "not", 172 }, /* not sign */
164 { "ntilde", 241 }, /* small n, tilde */
165 { "oacute", 243 }, /* small o, acute accent */
166 { "ocirc", 244 }, /* small o, circumflex accent */
167 { "ograve", 242 }, /* small o, grave accent */
168 { "ordf", 170 }, /* ordinal indicator, feminine */
169 { "ordm", 186 }, /* ordinal indicator, masculine */
170 { "oslash", 248 }, /* small o, slash */
171 { "otilde", 245 }, /* small o, tilde */
172 { "ouml", 246 }, /* small o, dieresis or umlaut mark */
173 { "para", 182 }, /* pilcrow (paragraph sign) */
174 { "plusmn", 177 }, /* plus-or-minus sign */
175 { "pound", 163 }, /* pound sterling sign */
176 { "quot", 34 }, /* double quote */
177 { "raquo", 187 }, /* angle quotation mark, right */
178 { "reg", 174 }, /* registered sign */
179 { "sect", 167 }, /* section sign */
180 { "shy", 173 }, /* soft hyphen */
181 { "sup1", 185 }, /* superscript one */
182 { "sup2", 178 }, /* superscript two */
183 { "sup3", 179 }, /* superscript three */
184 { "szlig", 223 }, /* small sharp s, German (sz ligature) */
185 { "thorn", 254 }, /* small thorn, Icelandic */
186 { "times", 215 }, /* multiply sign */
187 { "uacute", 250 }, /* small u, acute accent */
188 { "ucirc", 251 }, /* small u, circumflex accent */
189 { "ugrave", 249 }, /* small u, grave accent */
190 { "uml", 168 }, /* umlaut (dieresis) */
191 { "uuml", 252 }, /* small u, dieresis or umlaut mark */
192 { "yacute", 253 }, /* small y, acute accent */
193 { "yen", 165 }, /* yen sign */
194 { "yuml", 255 }, /* small y, dieresis or umlaut mark */
198 * unvis - decode characters previously encoded by vis
201 unvis(char *cp, int c, int *astate, int flag)
203 unsigned char uc = (unsigned char)c;
204 unsigned char st, ia, is, lc;
207 * Bottom 8 bits of astate hold the state machine state.
208 * Top 8 bits hold the current character in the http 1866 nv string decoding
210 #define GS(a) ((a) & 0xff)
211 #define SS(a, b) (((uint32_t)(a) << 24) | (b))
212 #define GI(a) ((uint32_t)(a) >> 24)
214 _DIAGASSERT(cp != NULL);
215 _DIAGASSERT(astate != NULL);
218 if (flag & UNVIS_END) {
223 *astate = SS(0, S_GROUND);
236 if ((flag & VIS_NOESCAPE) == 0 && c == '\\') {
237 *astate = SS(0, S_START);
240 if ((flag & VIS_HTTP1808) && c == '%') {
241 *astate = SS(0, S_HEX1);
244 if ((flag & VIS_HTTP1866) && c == '&') {
245 *astate = SS(0, S_AMP);
248 if ((flag & VIS_MIMESTYLE) && c == '=') {
249 *astate = SS(0, S_MIME1);
259 *astate = SS(0, S_GROUND);
261 case '0': case '1': case '2': case '3':
262 case '4': case '5': case '6': case '7':
264 *astate = SS(0, S_OCTAL2);
268 *astate = SS(0, S_META);
271 *astate = SS(0, S_CTRL);
275 *astate = SS(0, S_GROUND);
279 *astate = SS(0, S_GROUND);
283 *astate = SS(0, S_GROUND);
287 *astate = SS(0, S_GROUND);
291 *astate = SS(0, S_GROUND);
295 *astate = SS(0, S_GROUND);
299 *astate = SS(0, S_GROUND);
303 *astate = SS(0, S_GROUND);
307 *astate = SS(0, S_GROUND);
310 *astate = SS(0, S_HEX);
316 *astate = SS(0, S_GROUND);
322 *astate = SS(0, S_GROUND);
327 *astate = SS(0, S_GROUND);
335 *astate = SS(0, S_META1);
337 *astate = SS(0, S_CTRL);
343 *astate = SS(0, S_GROUND);
352 *astate = SS(0, S_GROUND);
355 case S_OCTAL2: /* second possible octal digit */
358 * yes - and maybe a third
360 *cp = (*cp << 3) + (c - '0');
361 *astate = SS(0, S_OCTAL3);
365 * no - done with current sequence, push back passed char
367 *astate = SS(0, S_GROUND);
368 return UNVIS_VALIDPUSH;
370 case S_OCTAL3: /* third possible octal digit */
371 *astate = SS(0, S_GROUND);
373 *cp = (*cp << 3) + (c - '0');
377 * we were done, push back passed char
379 return UNVIS_VALIDPUSH;
388 *astate = SS(0, S_HEX2);
392 * no - done with current sequence, push back passed char
394 *astate = SS(0, S_GROUND);
395 return UNVIS_VALIDPUSH;
400 *cp = xtod(uc) | (*cp << 4);
403 return UNVIS_VALIDPUSH;
406 if (uc == '\n' || uc == '\r') {
407 *astate = SS(0, S_EATCRNL);
410 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
412 *astate = SS(0, S_MIME2);
418 if (isxdigit(uc) && (isdigit(uc) || isupper(uc))) {
419 *astate = SS(0, S_GROUND);
420 *cp = XTOD(uc) | (*cp << 4);
431 *astate = SS(0, S_MIME1);
435 *astate = SS(0, S_GROUND);
442 *astate = SS(0, S_NUMBER);
445 *astate = SS(0, S_STRING);
449 ia = *cp; /* index in the array */
450 is = GI(*astate); /* index in the string */
451 lc = is == 0 ? 0 : nv[ia].name[is - 1]; /* last character */
456 for (; ia < __arraycount(nv); ia++) {
457 if (is != 0 && nv[ia].name[is - 1] != lc)
459 if (nv[ia].name[is] == uc)
463 if (ia == __arraycount(nv))
468 *astate = SS(is + 1, S_STRING);
473 *astate = SS(0, S_GROUND);
481 *cp += (*cp * 10) + uc - '0';
487 * decoder in unknown state - (probably uninitialized)
489 *astate = SS(0, S_GROUND);
495 * strnunvisx - decode src into dst
497 * Number of chars decoded into dst is returned, -1 on error.
498 * Dst is null terminated.
502 strnunvisx(char *dst, size_t dlen, const char *src, int flag)
505 char t = '\0', *start = dst;
508 _DIAGASSERT(src != NULL);
509 _DIAGASSERT(dst != NULL);
510 #define CHECKSPACE() \
518 while ((c = *src++) != '\0') {
520 switch (unvis(&t, c, &state, flag)) {
525 case UNVIS_VALIDPUSH:
536 _DIAGASSERT(/*CONSTCOND*/0);
541 if (unvis(&t, c, &state, UNVIS_END) == UNVIS_VALID) {
547 return (int)(dst - start);
551 strunvisx(char *dst, const char *src, int flag)
553 return strnunvisx(dst, (size_t)~0, src, flag);
557 strunvis(char *dst, const char *src)
559 return strnunvisx(dst, (size_t)~0, src, 0);
563 strnunvis(char *dst, size_t dlen, const char *src)
565 return strnunvisx(dst, dlen, src, 0);