1 /* GIO - GLib Input, Output and Streaming Library
3 * Copyright (C) 2006-2007 Red Hat, Inc.
5 * This library is free software; you can redistribute it and/or
6 * modify it under the terms of the GNU Lesser General Public
7 * License as published by the Free Software Foundation; either
8 * version 2 of the License, or (at your option) any later version.
10 * This library is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 * Lesser General Public License for more details.
15 * You should have received a copy of the GNU Lesser General
16 * Public License along with this library; if not, write to the
17 * Free Software Foundation, Inc., 59 Temple Place, Suite 330,
18 * Boston, MA 02111-1307, USA.
20 * Author: Alexander Larsson <alexl@redhat.com>
25 #include "gurifuncs.h"
27 #include <glib/gstrfuncs.h>
28 #include <glib/gmessages.h>
29 #include <glib/gstring.h>
30 #include <glib/gmem.h>
38 * @short_description: URI Functions
40 * Functions for manipulating Universal Resource Identifiers (URIs) as
41 * defined by <ulink url="http://www.ietf.org/rfc/rfc3986.txt">
42 * RFC 3986</ulink>. It is highly recommended that you have read and
43 * understand RFC 3986 for understanding this API.
47 unescape_character (const char *scanner)
52 first_digit = g_ascii_xdigit_value (*scanner++);
56 second_digit = g_ascii_xdigit_value (*scanner++);
60 return (first_digit << 4) | second_digit;
64 * g_uri_unescape_segment:
65 * @escaped_string: a string.
66 * @escaped_string_end: a string.
67 * @illegal_characters: an optional string of illegal characters not to be allowed.
69 * Unescapes a segment of an escaped string.
71 * If any of the characters in @illegal_characters or the character zero appears
72 * as an escaped character in @escaped_string then that is an error and %NULL
73 * will be returned. This is useful it you want to avoid for instance having a
74 * slash being expanded in an escaped path element, which might confuse pathname
77 * Returns: an unescaped version of @escaped_string or %NULL on error.
78 * The returned string should be freed when no longer needed.
83 g_uri_unescape_segment (const char *escaped_string,
84 const char *escaped_string_end,
85 const char *illegal_characters)
91 if (escaped_string == NULL)
94 if (escaped_string_end == NULL)
95 escaped_string_end = escaped_string + strlen (escaped_string);
97 result = g_malloc (escaped_string_end - escaped_string + 1);
100 for (in = escaped_string; in < escaped_string_end; in++)
108 if (escaped_string_end - in < 2)
110 /* Invalid escaped char (to short) */
115 character = unescape_character (in);
117 /* Check for an illegal character. We consider '\0' illegal here. */
118 if (character <= 0 ||
119 (illegal_characters != NULL &&
120 strchr (illegal_characters, (char)character) != NULL))
126 in++; /* The other char will be eaten in the loop header */
128 *out++ = (char)character;
137 * g_uri_unescape_string:
138 * @escaped_string: an escaped string to be unescaped.
139 * @illegal_characters: an optional string of illegal characters not to be allowed.
141 * Unescapes a whole escaped string.
143 * If any of the characters in @illegal_characters or the character zero appears
144 * as an escaped character in @escaped_string then that is an error and %NULL
145 * will be returned. This is useful it you want to avoid for instance having a
146 * slash being expanded in an escaped path element, which might confuse pathname
149 * Returns: an unescaped version of @escaped_string. The returned string
150 * should be freed when no longer needed.
155 g_uri_unescape_string (const char *escaped_string,
156 const char *illegal_characters)
158 return g_uri_unescape_segment (escaped_string, NULL, illegal_characters);
162 * g_uri_parse_scheme:
165 * Gets the scheme portion of a URI string. RFC 3986 decodes the scheme as:
167 * URI = scheme ":" hier-part [ "?" query ] [ "#" fragment ]
169 * Common schemes include "file", "http", "svn+ssh", etc.
171 * Returns: The "Scheme" component of the URI, or %NULL on error.
172 * The returned string should be freed when no longer needed.
177 g_uri_parse_scheme (const char *uri)
182 g_return_val_if_fail (uri != NULL, NULL);
184 /* From RFC 3986 Decodes:
185 * URI = scheme ":" hier-part [ "?" query ] [ "#" fragment ]
191 scheme = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
194 if (!g_ascii_isalpha (*p))
204 if (!(g_ascii_isalnum(c) ||
211 return g_strndup (uri, p - uri - 1);
215 * g_uri_escape_string:
216 * @unescaped: the unescaped input string.
217 * @reserved_chars_allowed: a string of reserved characters that are
218 * allowed to be used, or %NULL.
219 * @allow_utf8: %TRUE if the result can include UTF-8 characters.
221 * Escapes a string for use in a URI.
223 * Normally all characters that are not "unreserved" (i.e. ASCII alphanumerical
224 * characters plus dash, dot, underscore and tilde) are escaped.
225 * But if you specify characters in @reserved_chars_allowed they are not
226 * escaped. This is useful for the "reserved" characters in the URI
227 * specification, since those are allowed unescaped in some portions of
230 * Returns: an escaped version of @unescaped. The returned string should be
231 * freed when no longer needed.
236 g_uri_escape_string (const char *unescaped,
237 const char *reserved_chars_allowed,
242 g_return_val_if_fail (unescaped != NULL, NULL);
244 s = g_string_sized_new (strlen (unescaped) + 10);
246 g_string_append_uri_escaped (s, unescaped, reserved_chars_allowed, allow_utf8);
248 return g_string_free (s, FALSE);