1 const char encode_rcs[] = "$Id: encode.c,v 1.4 2002/01/22 23:28:07 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 * 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 1.4 2002/01/22 23:28:07 jongfoster
37 * Adding convenience function html_encode_and_free_original()
38 * Making all functions accept NULL paramaters - in this case, they
39 * simply return NULL. This allows error-checking to be deferred.
41 * Revision 1.3 2001/11/13 00:16:40 jongfoster
42 * Replacing references to malloc.h with the standard stdlib.h
43 * (See ANSI or K&R 2nd Ed)
45 * Revision 1.2 2001/05/17 22:52:35 oes
46 * - Cleaned CRLF's from the sources and related files
48 * Revision 1.1.1.1 2001/05/15 13:58:51 oes
49 * Initial import of version 2.9.3 source tree
52 *********************************************************************/
63 const char encode_h_rcs[] = ENCODE_H_VERSION;
65 /* Maps special characters in a URL to their equivalent % codes. */
66 static const char * const url_code_map[256] = {
67 NULL, "%01", "%02", "%03", "%04", "%05", "%06", "%07", "%08", "%09",
68 "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", "%10", "%11", "%12", "%13",
69 "%14", "%15", "%16", "%17", "%18", "%19", "%1A", "%1B", "%1C", "%1D",
70 "%1E", "%1F", "+", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
71 "%28", "%29", NULL, "%2B", "%2C", NULL, NULL, "%2F", NULL, NULL,
72 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3A", "%3B",
73 "%3C", "%3D", "%3E", "%3F", NULL, NULL, NULL, NULL, NULL, NULL,
74 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
75 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
76 NULL, "%5B", "%5C", "%5D", "%5E", NULL, "%60", 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, NULL, NULL, "%7B", "%7C", "%7D", "%7E", "%7F", "%80", "%81",
80 "%82", "%83", "%84", "%85", "%86", "%87", "%88", "%89", "%8A", "%8B",
81 "%8C", "%8D", "%8E", "%8F", "%90", "%91", "%92", "%93", "%94", "%95",
82 "%96", "%97", "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
83 "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", "%A8", "%A9",
84 "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", "%B0", "%B1", "%B2", "%B3",
85 "%B4", "%B5", "%B6", "%B7", "%B8", "%B9", "%BA", "%BB", "%BC", "%BD",
86 "%BE", "%BF", "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
87 "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", "%D0", "%D1",
88 "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", "%D8", "%D9", "%DA", "%DB",
89 "%DC", "%DD", "%DE", "%DF", "%E0", "%E1", "%E2", "%E3", "%E4", "%E5",
90 "%E6", "%E7", "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
91 "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", "%F8", "%F9",
92 "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
95 /* Maps special characters in HTML to their equivalent entites. */
96 static const char * const html_code_map[256] = {
97 NULL, NULL, NULL, NULL, NULL, NULL, NULL, 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, 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, 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
125 /* Maps special characters in a cookie to their equivalent % codes. */
126 static const char * const cookie_code_map[256] = {
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,
131 NULL, NULL, NULL, NULL, "%2C",NULL, NULL, NULL, NULL, NULL,
132 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, "%3B",
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, 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
156 /*********************************************************************
158 * Function : html_encode
160 * Description : Encodes a string so it's not interpreted as
161 * containing HTML tags or entities.
162 * Replaces <, >, &, and " with the appropriate HTML
166 * 1 : s = String to encode. Null-terminated.
168 * Returns : Encoded string, newly allocated on the heap.
169 * Caller is responsible for freeing it with free().
170 * If s is NULL, or on out-of memory, returns NULL.
172 *********************************************************************/
173 char * html_encode(const char *s)
182 /* each input char can expand to at most 6 chars */
183 buf = (char *) malloc((strlen(s) * 6) + 1);
189 while ( (c = *s++) != '\0')
191 const char * replace_with = html_code_map[(unsigned char) c];
192 if(replace_with != NULL)
194 strcpy(p, replace_with);
195 p += strlen(replace_with);
210 /*********************************************************************
212 * Function : html_encode_and_free_original
214 * Description : Encodes a string so it's not interpreted as
215 * containing HTML tags or entities.
216 * Replaces <, >, &, and " with the appropriate HTML
217 * entities. Free()s original string.
218 * If original string is NULL, simply returns NULL.
221 * 1 : s = String to encode. Null-terminated.
223 * Returns : Encoded string, newly allocated on the heap.
224 * Caller is responsible for freeing it with free().
225 * If s is NULL, or on out-of memory, returns NULL.
227 *********************************************************************/
228 char * html_encode_and_free_original(char *s)
237 result = html_encode(s);
244 /*********************************************************************
246 * Function : cookie_encode
248 * Description : Encodes a string so it can be used in a cookie.
249 * Replaces " ", ",", and ";" with the appropriate
253 * 1 : s = String to encode. Null-terminated.
255 * Returns : Encoded string, newly allocated on the heap.
256 * Caller is responsible for freeing it with free().
257 * If s is NULL, or on out-of memory, returns NULL.
259 *********************************************************************/
260 char * cookie_encode(const char *s)
269 /* each input char can expand to at most 3 chars */
270 buf = (char *) malloc((strlen(s) * 3) + 1);
276 while ( (c = *s++) != '\0')
278 const char * replace_with = cookie_code_map[(unsigned char) c];
279 if (replace_with != NULL)
281 strcpy(p, replace_with);
282 p += strlen(replace_with);
296 /*********************************************************************
298 * Function : url_encode
300 * Description : Encodes a string so it can be used in a URL
301 * query string. Replaces special characters with
302 * the appropriate %xx codes.
305 * 1 : s = String to encode. Null-terminated.
307 * Returns : Encoded string, newly allocated on the heap.
308 * Caller is responsible for freeing it with free().
309 * If s is NULL, or on out-of memory, returns NULL.
311 *********************************************************************/
312 char * url_encode(const char *s)
321 /* each input char can expand to at most 3 chars */
322 buf = (char *) malloc((strlen(s) * 3) + 1);
328 while( (c = *s++) != '\0')
330 const char * replace_with = url_code_map[(unsigned char) c];
331 if (replace_with != NULL)
333 strcpy(p, replace_with);
334 p += strlen(replace_with);
350 /*********************************************************************
354 * Description : Converts a single hex digit to an integer.
357 * 1 : d = in the range of ['0'..'9', 'A'..'F', 'a'..'f']
359 * Returns : The integer value, or -1 for non-hex characters.
361 *********************************************************************/
362 static int xdtoi(const int d)
364 if ((d >= '0') && (d <= '9'))
368 else if ((d >= 'a') && (d <= 'f'))
370 return(d - 'a' + 10);
372 else if ((d >= 'A') && (d <= 'F'))
374 return(d - 'A' + 10);
383 /*********************************************************************
387 * Description : Hex string to integer conversion.
390 * 1 : s = a 2 digit hex string (e.g. "1f"). Only the
391 * first two characters will be looked at.
393 * Returns : The integer value, or 0 for non-hex strings.
395 *********************************************************************/
396 static int xtoi(const char *s)
406 return (d1 << 4) + d2;
414 /*********************************************************************
416 * Function : url_decode
418 * Description : Decodes a URL query string, replacing %xx codes
419 * with their decoded form.
422 * 1 : s = String to decode. Null-terminated.
424 * Returns : Decoded string, newly allocated on the heap.
425 * Caller is responsible for freeing it with free().
427 *********************************************************************/
428 char *url_decode(const char * s)
430 char *buf = malloc(strlen(s) + 1);
445 if ((*q = xtoi(s + 1)))
452 /* malformed, just use it */