1 const char encode_rcs[] = "$Id: encode.c,v 1.5 2002/03/07 03:46:53 oes 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 * IJBSWA 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 1.5 2002/03/07 03:46:53 oes
37 * Fixed compiler warnings etc
39 * Revision 1.4 2002/01/22 23:28:07 jongfoster
40 * Adding convenience function html_encode_and_free_original()
41 * Making all functions accept NULL paramaters - in this case, they
42 * simply return NULL. This allows error-checking to be deferred.
44 * Revision 1.3 2001/11/13 00:16:40 jongfoster
45 * Replacing references to malloc.h with the standard stdlib.h
46 * (See ANSI or K&R 2nd Ed)
48 * Revision 1.2 2001/05/17 22:52:35 oes
49 * - Cleaned CRLF's from the sources and related files
51 * Revision 1.1.1.1 2001/05/15 13:58:51 oes
52 * Initial import of version 2.9.3 source tree
55 *********************************************************************/
66 const char encode_h_rcs[] = ENCODE_H_VERSION;
68 /* Maps special characters in a URL to their equivalent % codes. */
69 static const char * const url_code_map[256] = {
70 NULL, "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
71 "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
72 "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
73 "%1E", "%1F", "+", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
74 "%28", "%29", NULL, "%2B", "%2C", NULL, NULL, "%2F", NULL, NULL,
75 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3A", "%3B",
76 "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, NULL, NULL, NULL,
77 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
78 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
79 NULL, "%5B", "%5C", "%5D", "%5E", NULL, "%60", 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, NULL, NULL, "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
83 "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
84 "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
85 "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
86 "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
87 "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
88 "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
89 "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
90 "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
91 "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
92 "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
93 "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
94 "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
95 "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
98 /* Maps special characters in HTML to their equivalent entites. */
99 static const char * const html_code_map[256] = {
100 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
101 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
102 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
103 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, 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
128 /* Maps special characters in a cookie to their equivalent % codes. */
129 static const char * const cookie_code_map[256] = {
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,
134 NULL, NULL, NULL, NULL, "%2C",NULL, NULL, NULL, NULL, NULL,
135 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3B",
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, 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
159 /*********************************************************************
161 * Function : html_encode
163 * Description : Encodes a string so it's not interpreted as
164 * containing HTML tags or entities.
165 * Replaces <, >, &, and " with the appropriate HTML
169 * 1 : s = String to encode. Null-terminated.
171 * Returns : Encoded string, newly allocated on the heap.
172 * Caller is responsible for freeing it with free().
173 * If s is NULL, or on out-of memory, returns NULL.
175 *********************************************************************/
176 char * html_encode(const char *s)
185 /* each input char can expand to at most 6 chars */
186 buf = (char *) malloc((strlen(s) * 6) + 1);
192 while ( (c = *s++) != '\0')
194 const char * replace_with = html_code_map[(unsigned char) c];
195 if(replace_with != NULL)
197 strcpy(p, replace_with);
198 p += strlen(replace_with);
213 /*********************************************************************
215 * Function : html_encode_and_free_original
217 * Description : Encodes a string so it's not interpreted as
218 * containing HTML tags or entities.
219 * Replaces <, >, &, and " with the appropriate HTML
220 * entities. Free()s original string.
221 * If original string is NULL, simply returns NULL.
224 * 1 : s = String to encode. Null-terminated.
226 * Returns : Encoded string, newly allocated on the heap.
227 * Caller is responsible for freeing it with free().
228 * If s is NULL, or on out-of memory, returns NULL.
230 *********************************************************************/
231 char * html_encode_and_free_original(char *s)
240 result = html_encode(s);
247 /*********************************************************************
249 * Function : cookie_encode
251 * Description : Encodes a string so it can be used in a cookie.
252 * Replaces " ", ",", and ";" with the appropriate
256 * 1 : s = String to encode. Null-terminated.
258 * Returns : Encoded string, newly allocated on the heap.
259 * Caller is responsible for freeing it with free().
260 * If s is NULL, or on out-of memory, returns NULL.
262 *********************************************************************/
263 char * cookie_encode(const char *s)
272 /* each input char can expand to at most 3 chars */
273 buf = (char *) malloc((strlen(s) * 3) + 1);
279 while ( (c = *s++) != '\0')
281 const char * replace_with = cookie_code_map[(unsigned char) c];
282 if (replace_with != NULL)
284 strcpy(p, replace_with);
285 p += strlen(replace_with);
299 /*********************************************************************
301 * Function : url_encode
303 * Description : Encodes a string so it can be used in a URL
304 * query string. Replaces special characters with
305 * the appropriate %xx codes.
308 * 1 : s = String to encode. Null-terminated.
310 * Returns : Encoded string, newly allocated on the heap.
311 * Caller is responsible for freeing it with free().
312 * If s is NULL, or on out-of memory, returns NULL.
314 *********************************************************************/
315 char * url_encode(const char *s)
324 /* each input char can expand to at most 3 chars */
325 buf = (char *) malloc((strlen(s) * 3) + 1);
331 while( (c = *s++) != '\0')
333 const char * replace_with = url_code_map[(unsigned char) c];
334 if (replace_with != NULL)
336 strcpy(p, replace_with);
337 p += strlen(replace_with);
353 /*********************************************************************
357 * Description : Converts a single hex digit to an integer.
360 * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
362 * Returns : The integer value, or -1 for non-hex characters.
364 *********************************************************************/
365 static int xdtoi(const int d)
367 if ((d >= '0') && (d <= '9'))
371 else if ((d >= 'a') && (d <= 'f'))
373 return(d - 'a' + 10);
375 else if ((d >= 'A') && (d <= 'F'))
377 return(d - 'A' + 10);
386 /*********************************************************************
390 * Description : Hex string to integer conversion.
393 * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
394 * first two characters will be looked at.
396 * Returns : The integer value, or 0 for non-hex strings.
398 *********************************************************************/
399 static int xtoi(const char *s)
409 return (d1 << 4) + d2;
417 /*********************************************************************
419 * Function : url_decode
421 * Description : Decodes a URL query string, replacing %xx codes
422 * with their decoded form.
425 * 1 : s = String to decode. Null-terminated.
427 * Returns : Decoded string, newly allocated on the heap.
428 * Caller is responsible for freeing it with free().
430 *********************************************************************/
431 char *url_decode(const char * s)
433 char *buf = malloc(strlen(s) + 1);
448 if ((*q = xtoi(s + 1)) != '\0')
455 /* malformed, just use it */