1 const char encode_rcs[] = "$Id: encode.c,v 1.10 2006/07/18 14:48:45 david__schmidt Exp $";
2 /*********************************************************************
4 * File : $Source: /cvsroot/ijbswa/current/encode.c,v $
6 * Purpose : Functions to encode and decode URLs, and also to
7 * encode cookies and HTML text.
9 * Copyright : Written by and Copyright (C) 2001 the SourceForge
10 * Privoxy team. http://www.privoxy.org/
12 * Based on the Internet Junkbuster originally written
13 * by and Copyright (C) 1997 Anonymous Coders and
14 * Junkbusters Corporation. http://www.junkbusters.com
16 * This program is free software; you can redistribute it
17 * and/or modify it under the terms of the GNU General
18 * Public License as published by the Free Software
19 * Foundation; either version 2 of the License, or (at
20 * your option) any later version.
22 * This program is distributed in the hope that it will
23 * be useful, but WITHOUT ANY WARRANTY; without even the
24 * implied warranty of MERCHANTABILITY or FITNESS FOR A
25 * PARTICULAR PURPOSE. See the GNU General Public
26 * License for more details.
28 * The GNU General Public License should be included with
29 * this file. If not, you can view it at
30 * http://www.gnu.org/copyleft/gpl.html
31 * or write to the Free Software Foundation, Inc., 59
32 * Temple Place - Suite 330, Boston, MA 02111-1307, USA.
36 * Revision 1.10 2006/07/18 14:48:45 david__schmidt
37 * Reorganizing the repository: swapping out what was HEAD (the old 3.1 branch)
38 * with what was really the latest development (the v_3_0_branch branch)
40 * Revision 1.8 2002/03/26 22:29:54 swa
41 * we have a new homepage!
43 * Revision 1.7 2002/03/24 13:25:43 swa
44 * name change related issues
46 * Revision 1.6 2002/03/13 00:27:04 jongfoster
49 * Revision 1.5 2002/03/07 03:46:53 oes
50 * Fixed compiler warnings etc
52 * Revision 1.4 2002/01/22 23:28:07 jongfoster
53 * Adding convenience function html_encode_and_free_original()
54 * Making all functions accept NULL paramaters - in this case, they
55 * simply return NULL. This allows error-checking to be deferred.
57 * Revision 1.3 2001/11/13 00:16:40 jongfoster
58 * Replacing references to malloc.h with the standard stdlib.h
59 * (See ANSI or K&R 2nd Ed)
61 * Revision 1.2 2001/05/17 22:52:35 oes
62 * - Cleaned CRLF's from the sources and related files
64 * Revision 1.1.1.1 2001/05/15 13:58:51 oes
65 * Initial import of version 2.9.3 source tree
68 *********************************************************************/
79 const char encode_h_rcs[] = ENCODE_H_VERSION;
81 /* Maps special characters in a URL to their equivalent % codes. */
82 static const char * const url_code_map[256] = {
83 NULL, "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
84 "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
85 "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
86 "%1E", "%1F", "+", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
87 "%28", "%29", NULL, "%2B", "%2C", NULL, NULL, "%2F", NULL, NULL,
88 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3A", "%3B",
89 "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, NULL, NULL, NULL,
90 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
91 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
92 NULL, "%5B", "%5C", "%5D", "%5E", NULL, "%60", NULL, NULL, NULL,
93 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
94 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
95 NULL, NULL, NULL, "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
96 "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
97 "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
98 "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
99 "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
100 "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
101 "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
102 "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
103 "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
104 "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
105 "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
106 "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
107 "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
108 "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
111 /* Maps special characters in HTML to their equivalent entites. */
112 static const char * const html_code_map[256] = {
113 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
114 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
115 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
116 NULL, NULL, NULL, NULL,""",NULL,NULL,NULL,"&",NULL,
117 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
118 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
119 "<",NULL,">",NULL,NULL, NULL, NULL, NULL, NULL, NULL,
120 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
121 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
122 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
123 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
124 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
125 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
126 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
127 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
128 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
129 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
130 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
131 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
132 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
133 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
134 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
135 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
136 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
137 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
138 NULL, NULL, NULL, NULL, NULL, NULL
141 /* Maps special characters in a cookie to their equivalent % codes. */
142 static const char * const cookie_code_map[256] = {
143 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
144 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
145 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
146 NULL, NULL, "+", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
147 NULL, NULL, NULL, NULL, "%2C",NULL, NULL, NULL, NULL, NULL,
148 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3B",
149 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
150 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
151 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
152 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
153 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
154 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
155 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
156 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
157 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
158 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
159 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
160 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
161 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
162 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
163 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
164 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
165 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
166 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
167 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
168 NULL, NULL, NULL, NULL, NULL, NULL
172 /*********************************************************************
174 * Function : html_encode
176 * Description : Encodes a string so it's not interpreted as
177 * containing HTML tags or entities.
178 * Replaces <, >, &, and " with the appropriate HTML
182 * 1 : s = String to encode. Null-terminated.
184 * Returns : Encoded string, newly allocated on the heap.
185 * Caller is responsible for freeing it with free().
186 * If s is NULL, or on out-of memory, returns NULL.
188 *********************************************************************/
189 char * html_encode(const char *s)
198 /* each input char can expand to at most 6 chars */
199 buf = (char *) malloc((strlen(s) * 6) + 1);
205 while ( (c = *s++) != '\0')
207 const char * replace_with = html_code_map[(unsigned char) c];
208 if(replace_with != NULL)
210 strcpy(p, replace_with);
211 p += strlen(replace_with);
226 /*********************************************************************
228 * Function : html_encode_and_free_original
230 * Description : Encodes a string so it's not interpreted as
231 * containing HTML tags or entities.
232 * Replaces <, >, &, and " with the appropriate HTML
233 * entities. Free()s original string.
234 * If original string is NULL, simply returns NULL.
237 * 1 : s = String to encode. Null-terminated.
239 * Returns : Encoded string, newly allocated on the heap.
240 * Caller is responsible for freeing it with free().
241 * If s is NULL, or on out-of memory, returns NULL.
243 *********************************************************************/
244 char * html_encode_and_free_original(char *s)
253 result = html_encode(s);
260 /*********************************************************************
262 * Function : cookie_encode
264 * Description : Encodes a string so it can be used in a cookie.
265 * Replaces " ", ",", and ";" with the appropriate
269 * 1 : s = String to encode. Null-terminated.
271 * Returns : Encoded string, newly allocated on the heap.
272 * Caller is responsible for freeing it with free().
273 * If s is NULL, or on out-of memory, returns NULL.
275 *********************************************************************/
276 char * cookie_encode(const char *s)
285 /* each input char can expand to at most 3 chars */
286 buf = (char *) malloc((strlen(s) * 3) + 1);
292 while ( (c = *s++) != '\0')
294 const char * replace_with = cookie_code_map[(unsigned char) c];
295 if (replace_with != NULL)
297 strcpy(p, replace_with);
298 p += strlen(replace_with);
312 /*********************************************************************
314 * Function : url_encode
316 * Description : Encodes a string so it can be used in a URL
317 * query string. Replaces special characters with
318 * the appropriate %xx codes.
321 * 1 : s = String to encode. Null-terminated.
323 * Returns : Encoded string, newly allocated on the heap.
324 * Caller is responsible for freeing it with free().
325 * If s is NULL, or on out-of memory, returns NULL.
327 *********************************************************************/
328 char * url_encode(const char *s)
337 /* each input char can expand to at most 3 chars */
338 buf = (char *) malloc((strlen(s) * 3) + 1);
344 while( (c = *s++) != '\0')
346 const char * replace_with = url_code_map[(unsigned char) c];
347 if (replace_with != NULL)
349 strcpy(p, replace_with);
350 p += strlen(replace_with);
366 /*********************************************************************
370 * Description : Converts a single hex digit to an integer.
373 * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
375 * Returns : The integer value, or -1 for non-hex characters.
377 *********************************************************************/
378 static int xdtoi(const int d)
380 if ((d >= '0') && (d <= '9'))
384 else if ((d >= 'a') && (d <= 'f'))
386 return(d - 'a' + 10);
388 else if ((d >= 'A') && (d <= 'F'))
390 return(d - 'A' + 10);
399 /*********************************************************************
403 * Description : Hex string to integer conversion.
406 * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
407 * first two characters will be looked at.
409 * Returns : The integer value, or 0 for non-hex strings.
411 *********************************************************************/
412 static int xtoi(const char *s)
422 return (d1 << 4) + d2;
430 /*********************************************************************
432 * Function : url_decode
434 * Description : Decodes a URL query string, replacing %xx codes
435 * with their decoded form.
438 * 1 : s = String to decode. Null-terminated.
440 * Returns : Decoded string, newly allocated on the heap.
441 * Caller is responsible for freeing it with free().
443 *********************************************************************/
444 char *url_decode(const char * s)
446 char *buf = malloc(strlen(s) + 1);
461 if ((*q = (char)xtoi(s + 1)) != '\0')
468 /* malformed, just use it */