gurifuncs.c 6.61 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
/* 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 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, write to the
 * Free Software Foundation, Inc., 59 Temple Place, Suite 330,
 * Boston, MA 02111-1307, USA.
 *
 * Author: Alexander Larsson <alexl@redhat.com>
 */

23 24
#include "config.h"

25
#include "gurifuncs.h"
26 27 28 29 30 31

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

32
#include <string.h>
33

34
#include "config.h"
Alexander Larsson's avatar
Alexander Larsson committed
35 36
#include "galias.h"

37 38 39 40 41
/**
 * SECTION:gurifuncs
 * @short_description: URI Functions
 * 
 * Functions for manipulating Universal Resource Identifiers (URIs) as 
Stefan Kost's avatar
Stefan Kost committed
42 43 44 45
 * defined by <ulink url="http://www.ietf.org/rfc/rfc3986.txt">
 * RFC 3986</ulink>. It is highly recommended that you have read and
 * understand RFC 3986 for understanding this API.
 */
46

47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67
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: a string.
 * @escaped_string_end: a string.
68
 * @illegal_characters: an optional string of illegal characters not to be allowed.
69
 * 
70
 * Unescapes a segment of an escaped string.
71 72 73 74 75 76 77
 *
 * 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.
 *
78 79
 * Returns: an unescaped version of @escaped_string or %NULL on error.
 * The returned string should be freed when no longer needed.
80 81
 *
 * Since: 2.16
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
 **/
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.
140
 * @illegal_characters: an optional string of illegal characters not to be allowed.
141
 * 
142 143
 * Unescapes a whole escaped string.
 * 
144 145 146 147 148 149
 * 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.
 *
150 151
 * Returns: an unescaped version of @escaped_string. The returned string 
 * should be freed when no longer needed.
152 153
 *
 * Since: 2.16
154 155 156 157 158 159 160 161 162
 **/
char *
g_uri_unescape_string (const char *escaped_string,
		       const char *illegal_characters)
{
  return g_uri_unescape_segment (escaped_string, NULL, illegal_characters);
}

/**
163
 * g_uri_parse_scheme:
164 165
 * @uri: a valid URI.
 * 
166
 * Gets the scheme portion of a URI string. RFC 3986 decodes the scheme as:
Matthias Clasen's avatar
Matthias Clasen committed
167
 * <programlisting>
168
 * URI = scheme ":" hier-part [ "?" query ] [ "#" fragment ] 
Matthias Clasen's avatar
Matthias Clasen committed
169
 * </programlisting>
170 171 172
 * Common schemes include "file", "http", "svn+ssh", etc.
 * 
 * Returns: The "Scheme" component of the URI, or %NULL on error. 
173
 * The returned string should be freed when no longer needed.
174 175
 *
 * Since: 2.16
176 177
 **/
char *
178
g_uri_parse_scheme (const char  *uri)
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
{
  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.
Matthias Clasen's avatar
Matthias Clasen committed
218
 * @reserved_chars_allowed: a string of reserved characters that are
Behdad Esfahbod's avatar
Behdad Esfahbod committed
219
 *      allowed to be used, or %NULL.
Matthias Clasen's avatar
Matthias Clasen committed
220
 * @allow_utf8: %TRUE if the result can include UTF-8 characters.
221
 * 
222
 * Escapes a string for use in a URI.
223 224 225 226 227 228 229
 *
 * 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. 
230
 * 
231 232
 * Returns: an escaped version of @unescaped. The returned string should be 
 * freed when no longer needed.
233 234
 *
 * Since: 2.16
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
 **/
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);
}
Alexander Larsson's avatar
Alexander Larsson committed
251 252 253

#define __G_URI_FUNCS_C__
#include "galiasdef.c"