1 const char encode_rcs[] = "$Id: encode.c,v 1.6 2002/03/13 00:27:04 jongfoster 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://ijbswa.sourceforge.net
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 1.6 2002/03/13 00:27:04 jongfoster
39 * Revision 1.5 2002/03/07 03:46:53 oes
40 * Fixed compiler warnings etc
42 * Revision 1.4 2002/01/22 23:28:07 jongfoster
43 * Adding convenience function html_encode_and_free_original()
44 * Making all functions accept NULL paramaters - in this case, they
45 * simply return NULL. This allows error-checking to be deferred.
47 * Revision 1.3 2001/11/13 00:16:40 jongfoster
48 * Replacing references to malloc.h with the standard stdlib.h
49 * (See ANSI or K&R 2nd Ed)
51 * Revision 1.2 2001/05/17 22:52:35 oes
52 * - Cleaned CRLF's from the sources and related files
54 * Revision 1.1.1.1 2001/05/15 13:58:51 oes
55 * Initial import of version 2.9.3 source tree
58 *********************************************************************/
69 const char encode_h_rcs[] = ENCODE_H_VERSION;
71 /* Maps special characters in a URL to their equivalent % codes. */
72 static const char * const url_code_map[256] = {
73 NULL, "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
74 "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
75 "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
76 "%1E", "%1F", "+", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
77 "%28", "%29", NULL, "%2B", "%2C", NULL, NULL, "%2F", NULL, NULL,
78 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3A", "%3B",
79 "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, NULL, NULL, NULL,
80 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
81 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
82 NULL, "%5B", "%5C", "%5D", "%5E", NULL, "%60", NULL, NULL, NULL,
83 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
84 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
85 NULL, NULL, NULL, "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
86 "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
87 "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
88 "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
89 "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
90 "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
91 "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
92 "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
93 "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
94 "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
95 "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
96 "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
97 "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
98 "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
101 /* Maps special characters in HTML to their equivalent entites. */
102 static const char * const html_code_map[256] = {
103 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
104 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
105 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
106 NULL, NULL, NULL, NULL,""",NULL,NULL,NULL,"&",NULL,
107 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
108 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
109 "<",NULL,">",NULL,NULL, NULL, NULL, NULL, NULL, NULL,
110 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
111 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
112 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
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, 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, 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
131 /* Maps special characters in a cookie to their equivalent % codes. */
132 static const char * const cookie_code_map[256] = {
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,
137 NULL, NULL, NULL, NULL, "%2C",NULL, NULL, NULL, NULL, NULL,
138 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3B",
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, 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, NULL,
147 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
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, 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
162 /*********************************************************************
164 * Function : html_encode
166 * Description : Encodes a string so it's not interpreted as
167 * containing HTML tags or entities.
168 * Replaces <, >, &, and " with the appropriate HTML
172 * 1 : s = String to encode. Null-terminated.
174 * Returns : Encoded string, newly allocated on the heap.
175 * Caller is responsible for freeing it with free().
176 * If s is NULL, or on out-of memory, returns NULL.
178 *********************************************************************/
179 char * html_encode(const char *s)
188 /* each input char can expand to at most 6 chars */
189 buf = (char *) malloc((strlen(s) * 6) + 1);
195 while ( (c = *s++) != '\0')
197 const char * replace_with = html_code_map[(unsigned char) c];
198 if(replace_with != NULL)
200 strcpy(p, replace_with);
201 p += strlen(replace_with);
216 /*********************************************************************
218 * Function : html_encode_and_free_original
220 * Description : Encodes a string so it's not interpreted as
221 * containing HTML tags or entities.
222 * Replaces <, >, &, and " with the appropriate HTML
223 * entities. Free()s original string.
224 * If original string is NULL, simply returns NULL.
227 * 1 : s = String to encode. Null-terminated.
229 * Returns : Encoded string, newly allocated on the heap.
230 * Caller is responsible for freeing it with free().
231 * If s is NULL, or on out-of memory, returns NULL.
233 *********************************************************************/
234 char * html_encode_and_free_original(char *s)
243 result = html_encode(s);
250 /*********************************************************************
252 * Function : cookie_encode
254 * Description : Encodes a string so it can be used in a cookie.
255 * Replaces " ", ",", and ";" with the appropriate
259 * 1 : s = String to encode. Null-terminated.
261 * Returns : Encoded string, newly allocated on the heap.
262 * Caller is responsible for freeing it with free().
263 * If s is NULL, or on out-of memory, returns NULL.
265 *********************************************************************/
266 char * cookie_encode(const char *s)
275 /* each input char can expand to at most 3 chars */
276 buf = (char *) malloc((strlen(s) * 3) + 1);
282 while ( (c = *s++) != '\0')
284 const char * replace_with = cookie_code_map[(unsigned char) c];
285 if (replace_with != NULL)
287 strcpy(p, replace_with);
288 p += strlen(replace_with);
302 /*********************************************************************
304 * Function : url_encode
306 * Description : Encodes a string so it can be used in a URL
307 * query string. Replaces special characters with
308 * the appropriate %xx codes.
311 * 1 : s = String to encode. Null-terminated.
313 * Returns : Encoded string, newly allocated on the heap.
314 * Caller is responsible for freeing it with free().
315 * If s is NULL, or on out-of memory, returns NULL.
317 *********************************************************************/
318 char * url_encode(const char *s)
327 /* each input char can expand to at most 3 chars */
328 buf = (char *) malloc((strlen(s) * 3) + 1);
334 while( (c = *s++) != '\0')
336 const char * replace_with = url_code_map[(unsigned char) c];
337 if (replace_with != NULL)
339 strcpy(p, replace_with);
340 p += strlen(replace_with);
356 /*********************************************************************
360 * Description : Converts a single hex digit to an integer.
363 * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
365 * Returns : The integer value, or -1 for non-hex characters.
367 *********************************************************************/
368 static int xdtoi(const int d)
370 if ((d >= '0') && (d <= '9'))
374 else if ((d >= 'a') && (d <= 'f'))
376 return(d - 'a' + 10);
378 else if ((d >= 'A') && (d <= 'F'))
380 return(d - 'A' + 10);
389 /*********************************************************************
393 * Description : Hex string to integer conversion.
396 * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
397 * first two characters will be looked at.
399 * Returns : The integer value, or 0 for non-hex strings.
401 *********************************************************************/
402 static int xtoi(const char *s)
412 return (d1 << 4) + d2;
420 /*********************************************************************
422 * Function : url_decode
424 * Description : Decodes a URL query string, replacing %xx codes
425 * with their decoded form.
428 * 1 : s = String to decode. Null-terminated.
430 * Returns : Decoded string, newly allocated on the heap.
431 * Caller is responsible for freeing it with free().
433 *********************************************************************/
434 char *url_decode(const char * s)
436 char *buf = malloc(strlen(s) + 1);
451 if ((*q = xtoi(s + 1)) != '\0')
458 /* malformed, just use it */