File: gurifuncs.c

package info (click to toggle)
glib2.0 2.58.3-2+deb10u2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, buster, buster-backports, sid
  • size: 48,956 kB
  • sloc: ansic: 452,656; xml: 16,781; python: 6,149; makefile: 3,776; sh: 1,499; perl: 1,140; cpp: 9
file content (252 lines) | stat: -rw-r--r-- 6,836 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
/* GIO - GLib Input, Output and Streaming Library
 * 
 * Copyright (C) 2006-2007 Red Hat, Inc.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General
 * Public License along with this library; if not, see <http://www.gnu.org/licenses/>.
 *
 * Author: Alexander Larsson <alexl@redhat.com>
 */

#include "config.h"

#include "gurifuncs.h"

#include <glib/gstrfuncs.h>
#include <glib/gmessages.h>
#include <glib/gstring.h>
#include <glib/gmem.h>

#include <string.h>

#include "config.h"

/**
 * SECTION:gurifuncs
 * @title: URI Functions
 * @short_description: manipulating URIs
 *
 * Functions for manipulating Universal Resource Identifiers (URIs) as
 * defined by
 * [RFC 3986](http://www.ietf.org/rfc/rfc3986.txt).
 * It is highly recommended that you have read and
 * understand RFC 3986 for understanding this API.
 */

static int
unescape_character (const char *scanner)
{
  int first_digit;
  int second_digit;
  
  first_digit = g_ascii_xdigit_value (*scanner++);
  if (first_digit < 0)
    return -1;

  second_digit = g_ascii_xdigit_value (*scanner++);
  if (second_digit < 0)
    return -1;

  return (first_digit << 4) | second_digit;
}

/**
 * g_uri_unescape_segment:
 * @escaped_string: (nullable): A string, may be %NULL
 * @escaped_string_end: (nullable): Pointer to end of @escaped_string, may be %NULL
 * @illegal_characters: (nullable): An optional string of illegal characters not to be allowed, may be %NULL
 * 
 * Unescapes a segment of an escaped string.
 *
 * If any of the characters in @illegal_characters or the character zero appears
 * as an escaped character in @escaped_string then that is an error and %NULL
 * will be returned. This is useful it you want to avoid for instance having a
 * slash being expanded in an escaped path element, which might confuse pathname
 * handling.
 *
 * Returns: an unescaped version of @escaped_string or %NULL on error.
 * The returned string should be freed when no longer needed.  As a
 * special case if %NULL is given for @escaped_string, this function
 * will return %NULL.
 *
 * Since: 2.16
 **/
char *
g_uri_unescape_segment (const char *escaped_string,
			const char *escaped_string_end,
			const char *illegal_characters)
{
  const char *in;
  char *out, *result;
  gint character;
  
  if (escaped_string == NULL)
    return NULL;
  
  if (escaped_string_end == NULL)
    escaped_string_end = escaped_string + strlen (escaped_string);
  
  result = g_malloc (escaped_string_end - escaped_string + 1);
  
  out = result;
  for (in = escaped_string; in < escaped_string_end; in++)
    {
      character = *in;
      
      if (*in == '%')
	{
	  in++;
	  
	  if (escaped_string_end - in < 2)
	    {
	      /* Invalid escaped char (to short) */
	      g_free (result);
	      return NULL;
	    }
	  
	  character = unescape_character (in);
	  
	  /* Check for an illegal character. We consider '\0' illegal here. */
	  if (character <= 0 ||
	      (illegal_characters != NULL &&
	       strchr (illegal_characters, (char)character) != NULL))
	    {
	      g_free (result);
	      return NULL;
	    }
	  
	  in++; /* The other char will be eaten in the loop header */
	}
      *out++ = (char)character;
    }
  
  *out = '\0';
  
  return result;
}

/**
 * g_uri_unescape_string:
 * @escaped_string: an escaped string to be unescaped.
 * @illegal_characters: (nullable): a string of illegal characters not to be
 *      allowed, or %NULL.
 * 
 * Unescapes a whole escaped string.
 * 
 * If any of the characters in @illegal_characters or the character zero appears
 * as an escaped character in @escaped_string then that is an error and %NULL
 * will be returned. This is useful it you want to avoid for instance having a
 * slash being expanded in an escaped path element, which might confuse pathname
 * handling.
 *
 * Returns: an unescaped version of @escaped_string. The returned string 
 * should be freed when no longer needed.
 *
 * Since: 2.16
 **/
char *
g_uri_unescape_string (const char *escaped_string,
		       const char *illegal_characters)
{
  return g_uri_unescape_segment (escaped_string, NULL, illegal_characters);
}

/**
 * g_uri_parse_scheme:
 * @uri: a valid URI.
 * 
 * Gets the scheme portion of a URI string. RFC 3986 decodes the scheme as:
 * |[
 * URI = scheme ":" hier-part [ "?" query ] [ "#" fragment ] 
 * ]|
 * Common schemes include "file", "http", "svn+ssh", etc.
 * 
 * Returns: The "Scheme" component of the URI, or %NULL on error. 
 * The returned string should be freed when no longer needed.
 *
 * Since: 2.16
 **/
char *
g_uri_parse_scheme (const char  *uri)
{
  const char *p;
  char c;

  g_return_val_if_fail (uri != NULL, NULL);

  /* From RFC 3986 Decodes:
   * URI         = scheme ":" hier-part [ "?" query ] [ "#" fragment ]
   */ 

  p = uri;
  
  /* Decode scheme:
     scheme      = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
  */

  if (!g_ascii_isalpha (*p))
    return NULL;
  
  while (1)
    {
      c = *p++;
      
      if (c == ':')
	break;
      
      if (!(g_ascii_isalnum(c) ||
	    c == '+' ||
	    c == '-' ||
	    c == '.'))
	return NULL;
    }
  
  return g_strndup (uri, p - uri - 1);
}

/**
 * g_uri_escape_string:
 * @unescaped: the unescaped input string.
 * @reserved_chars_allowed: (nullable): a string of reserved characters that
 *      are allowed to be used, or %NULL.
 * @allow_utf8: %TRUE if the result can include UTF-8 characters.
 * 
 * Escapes a string for use in a URI.
 *
 * Normally all characters that are not "unreserved" (i.e. ASCII alphanumerical
 * characters plus dash, dot, underscore and tilde) are escaped.
 * But if you specify characters in @reserved_chars_allowed they are not
 * escaped. This is useful for the "reserved" characters in the URI
 * specification, since those are allowed unescaped in some portions of
 * a URI. 
 * 
 * Returns: an escaped version of @unescaped. The returned string should be 
 * freed when no longer needed.
 *
 * Since: 2.16
 **/
char *
g_uri_escape_string (const char *unescaped,
		     const char  *reserved_chars_allowed,
		     gboolean     allow_utf8)
{
  GString *s;

  g_return_val_if_fail (unescaped != NULL, NULL);

  s = g_string_sized_new (strlen (unescaped) + 10);
  
  g_string_append_uri_escaped (s, unescaped, reserved_chars_allowed, allow_utf8);
  
  return g_string_free (s, FALSE);
}