1 const char encode_rcs[] = "$Id: encode.c,v 1.11 2006/12/28 18:25:53 fabiankeil 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 1.11 2006/12/28 18:25:53 fabiankeil
37 * Fixed gcc43 compiler warning.
39 * Revision 1.10 2006/07/18 14:48:45 david__schmidt
40 * Reorganizing the repository: swapping out what was HEAD (the old 3.1 branch)
41 * with what was really the latest development (the v_3_0_branch branch)
43 * Revision 1.8 2002/03/26 22:29:54 swa
44 * we have a new homepage!
46 * Revision 1.7 2002/03/24 13:25:43 swa
47 * name change related issues
49 * Revision 1.6 2002/03/13 00:27:04 jongfoster
52 * Revision 1.5 2002/03/07 03:46:53 oes
53 * Fixed compiler warnings etc
55 * Revision 1.4 2002/01/22 23:28:07 jongfoster
56 * Adding convenience function html_encode_and_free_original()
57 * Making all functions accept NULL paramaters - in this case, they
58 * simply return NULL. This allows error-checking to be deferred.
60 * Revision 1.3 2001/11/13 00:16:40 jongfoster
61 * Replacing references to malloc.h with the standard stdlib.h
62 * (See ANSI or K&R 2nd Ed)
64 * Revision 1.2 2001/05/17 22:52:35 oes
65 * - Cleaned CRLF's from the sources and related files
67 * Revision 1.1.1.1 2001/05/15 13:58:51 oes
68 * Initial import of version 2.9.3 source tree
71 *********************************************************************/
84 const char encode_h_rcs[] = ENCODE_H_VERSION;
86 /* Maps special characters in a URL to their equivalent % codes. */
87 static const char * const url_code_map[256] = {
88 NULL, "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
89 "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
90 "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
91 "%1E", "%1F", "+", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
92 "%28", "%29", NULL, "%2B", "%2C", NULL, NULL, "%2F", NULL, NULL,
93 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3A", "%3B",
94 "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, NULL, NULL, NULL,
95 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
96 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
97 NULL, "%5B", "%5C", "%5D", "%5E", NULL, "%60", NULL, NULL, NULL,
98 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
99 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
100 NULL, NULL, NULL, "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
101 "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
102 "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
103 "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
104 "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
105 "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
106 "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
107 "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
108 "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
109 "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
110 "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
111 "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
112 "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
113 "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
116 /* Maps special characters in HTML to their equivalent entites. */
117 static const char * const html_code_map[256] = {
118 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
119 NULL, NULL, 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,
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,
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, NULL, NULL, NULL, NULL,
139 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
140 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
141 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
142 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
143 NULL, NULL, NULL, NULL, NULL, NULL
146 /* Maps special characters in a cookie to their equivalent % codes. */
147 static const char * const cookie_code_map[256] = {
148 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
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,
152 NULL, NULL, NULL, NULL, "%2C",NULL, NULL, NULL, NULL, NULL,
153 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3B",
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, NULL, NULL, NULL, NULL,
169 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
170 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
171 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
172 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
173 NULL, NULL, NULL, NULL, NULL, NULL
177 /*********************************************************************
179 * Function : html_encode
181 * Description : Encodes a string so it's not interpreted as
182 * containing HTML tags or entities.
183 * Replaces <, >, &, and " with the appropriate HTML
187 * 1 : s = String to encode. Null-terminated.
189 * Returns : Encoded string, newly allocated on the heap.
190 * Caller is responsible for freeing it with free().
191 * If s is NULL, or on out-of memory, returns NULL.
193 *********************************************************************/
194 char * html_encode(const char *s)
204 /* each input char can expand to at most 6 chars */
205 buf_size = (strlen(s) * 6) + 1;
206 buf = (char *) malloc(buf_size);
212 while ( (c = *s++) != '\0')
214 const char * replace_with = html_code_map[(unsigned char) c];
215 if(replace_with != NULL)
217 const size_t bytes_written = (size_t)(p - buf);
218 assert(bytes_written < buf_size);
219 p += strlcpy(p, replace_with, buf_size - bytes_written);
230 assert(strlen(buf) < buf_size);
235 /*********************************************************************
237 * Function : html_encode_and_free_original
239 * Description : Encodes a string so it's not interpreted as
240 * containing HTML tags or entities.
241 * Replaces <, >, &, and " with the appropriate HTML
242 * entities. Free()s original string.
243 * If original string is NULL, simply returns NULL.
246 * 1 : s = String to encode. Null-terminated.
248 * Returns : Encoded string, newly allocated on the heap.
249 * Caller is responsible for freeing it with free().
250 * If s is NULL, or on out-of memory, returns NULL.
252 *********************************************************************/
253 char * html_encode_and_free_original(char *s)
262 result = html_encode(s);
269 /*********************************************************************
271 * Function : cookie_encode
273 * Description : Encodes a string so it can be used in a cookie.
274 * Replaces " ", ",", and ";" with the appropriate
278 * 1 : s = String to encode. Null-terminated.
280 * Returns : Encoded string, newly allocated on the heap.
281 * Caller is responsible for freeing it with free().
282 * If s is NULL, or on out-of memory, returns NULL.
284 *********************************************************************/
285 char * cookie_encode(const char *s)
295 /* each input char can expand to at most 3 chars */
296 buf_size = (strlen(s) * 3) + 1;
297 buf = (char *) malloc(buf_size);
303 while ( (c = *s++) != '\0')
305 const char * replace_with = cookie_code_map[(unsigned char) c];
306 if (replace_with != NULL)
308 const size_t bytes_written = (size_t)(p - buf);
309 assert(bytes_written < buf_size);
310 p += strlcpy(p, replace_with, buf_size - bytes_written);
321 assert(strlen(buf) < buf_size);
325 /*********************************************************************
327 * Function : url_encode
329 * Description : Encodes a string so it can be used in a URL
330 * query string. Replaces special characters with
331 * the appropriate %xx codes.
334 * 1 : s = String to encode. Null-terminated.
336 * Returns : Encoded string, newly allocated on the heap.
337 * Caller is responsible for freeing it with free().
338 * If s is NULL, or on out-of memory, returns NULL.
340 *********************************************************************/
341 char * url_encode(const char *s)
351 /* each input char can expand to at most 3 chars */
352 buf_size = (strlen(s) * 3) + 1;
353 buf = (char *) malloc(buf_size);
359 while( (c = *s++) != '\0')
361 const char * replace_with = url_code_map[(unsigned char) c];
362 if (replace_with != NULL)
364 const size_t bytes_written = (size_t)(p - buf);
365 assert(bytes_written < buf_size);
366 p += strlcpy(p, replace_with, buf_size - bytes_written);
378 assert(strlen(buf) < buf_size);
383 /*********************************************************************
387 * Description : Converts a single hex digit to an integer.
390 * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
392 * Returns : The integer value, or -1 for non-hex characters.
394 *********************************************************************/
395 static int xdtoi(const int d)
397 if ((d >= '0') && (d <= '9'))
401 else if ((d >= 'a') && (d <= 'f'))
403 return(d - 'a' + 10);
405 else if ((d >= 'A') && (d <= 'F'))
407 return(d - 'A' + 10);
416 /*********************************************************************
420 * Description : Hex string to integer conversion.
423 * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
424 * first two characters will be looked at.
426 * Returns : The integer value, or 0 for non-hex strings.
428 *********************************************************************/
429 static int xtoi(const char *s)
439 return (d1 << 4) + d2;
447 /*********************************************************************
449 * Function : url_decode
451 * Description : Decodes a URL query string, replacing %xx codes
452 * with their decoded form.
455 * 1 : s = String to decode. Null-terminated.
457 * Returns : Decoded string, newly allocated on the heap.
458 * Caller is responsible for freeing it with free().
460 *********************************************************************/
461 char *url_decode(const char * s)
463 char *buf = malloc(strlen(s) + 1);
478 if ((*q = (char)xtoi(s + 1)) != '\0')
485 /* malformed, just use it */