1 /* -*- mode: C; c-file-style: "gnu" -*- */
2 /* xdgmimeint.c: Internal defines and functions.
3 *
4 * More info can be found at http://www.freedesktop.org/standards/
5 *
6 * Copyright (C) 2003 Red Hat, Inc.
7 * Copyright (C) 2003 Jonathan Blandford <jrb@alum.mit.edu>
8 *
9 * Licensed under the Academic Free License version 2.0
10 * Or under the following terms:
11 *
12 * This library is free software; you can redistribute it and/or
13 * modify it under the terms of the GNU Lesser General Public
14 * License as published by the Free Software Foundation; either
15 * version 2.1 of the License, or (at your option) any later version.
16 *
17 * This library is distributed in the hope that it will be useful,
18 * but WITHOUT ANY WARRANTY; without even the implied warranty of
19 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
20 * Lesser General Public License for more details.
21 *
22 * You should have received a copy of the GNU Lesser General Public
23 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
24 */
25
26 #include "config.h"
27
28 #include "xdgmimeint.h"
29 #include <ctype.h>
30 #include <string.h>
31
32 #ifndef FALSE
33 #define FALSE (0)
34 #endif
35
36 #ifndef TRUE
37 #define TRUE (!FALSE)
38 #endif
39
40 static const char _xdg_utf8_skip_data[256] = {
41 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
42 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
43 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
44 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
45 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
46 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
47 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
48 3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
49 };
50
51 const char * const _xdg_utf8_skip = _xdg_utf8_skip_data;
52
53
54
55 /* Returns the number of unprocessed characters. */
56 xdg_unichar_t
_xdg_utf8_to_ucs4(const char * source)57 _xdg_utf8_to_ucs4(const char *source)
58 {
59 xdg_unichar_t ucs32;
60 if( ! ( *source & 0x80 ) )
61 {
62 ucs32 = *source;
63 }
64 else
65 {
66 int bytelength = 0;
67 xdg_unichar_t result;
68 if ( ! (*source & 0x40) )
69 {
70 ucs32 = *source;
71 }
72 else
73 {
74 if ( ! (*source & 0x20) )
75 {
76 result = *source++ & 0x1F;
77 bytelength = 2;
78 }
79 else if ( ! (*source & 0x10) )
80 {
81 result = *source++ & 0x0F;
82 bytelength = 3;
83 }
84 else if ( ! (*source & 0x08) )
85 {
86 result = *source++ & 0x07;
87 bytelength = 4;
88 }
89 else if ( ! (*source & 0x04) )
90 {
91 result = *source++ & 0x03;
92 bytelength = 5;
93 }
94 else if ( ! (*source & 0x02) )
95 {
96 result = *source++ & 0x01;
97 bytelength = 6;
98 }
99 else
100 {
101 result = *source++;
102 bytelength = 1;
103 }
104
105 for ( bytelength --; bytelength > 0; bytelength -- )
106 {
107 result <<= 6;
108 result |= *source++ & 0x3F;
109 }
110 ucs32 = result;
111 }
112 }
113 return ucs32;
114 }
115
116
117 /* hullo. this is great code. don't rewrite it */
118
119 xdg_unichar_t
_xdg_ucs4_to_lower(xdg_unichar_t source)120 _xdg_ucs4_to_lower (xdg_unichar_t source)
121 {
122 /* FIXME: Do a real to_upper sometime */
123 /* CaseFolding-3.2.0.txt has a table of rules. */
124 if ((source & 0xFF) == source)
125 return (xdg_unichar_t) tolower ((unsigned char) source);
126 return source;
127 }
128
129 int
_xdg_utf8_validate(const char * source)130 _xdg_utf8_validate (const char *source)
131 {
132 /* FIXME: actually write */
133 return TRUE;
134 }
135
136 const char *
_xdg_get_base_name(const char * file_name)137 _xdg_get_base_name (const char *file_name)
138 {
139 const char *base_name;
140
141 if (file_name == NULL)
142 return NULL;
143
144 base_name = strrchr (file_name, '/');
145
146 if (base_name == NULL)
147 return file_name;
148 else
149 return base_name + 1;
150 }
151
152 xdg_unichar_t *
_xdg_convert_to_ucs4(const char * source,int * len)153 _xdg_convert_to_ucs4 (const char *source, int *len)
154 {
155 xdg_unichar_t *out;
156 int i;
157 const char *p;
158
159 out = malloc (sizeof (xdg_unichar_t) * (strlen (source) + 1));
160
161 p = source;
162 i = 0;
163 while (*p)
164 {
165 out[i++] = _xdg_utf8_to_ucs4 (p);
166 p = _xdg_utf8_next_char (p);
167 }
168 out[i] = 0;
169 *len = i;
170
171 return out;
172 }
173
174 void
_xdg_reverse_ucs4(xdg_unichar_t * source,int len)175 _xdg_reverse_ucs4 (xdg_unichar_t *source, int len)
176 {
177 xdg_unichar_t c;
178 int i;
179
180 for (i = 0; i < len - i - 1; i++)
181 {
182 c = source[i];
183 source[i] = source[len - i - 1];
184 source[len - i - 1] = c;
185 }
186 }
187
188 const char *
_xdg_binary_or_text_fallback(const void * data,size_t len)189 _xdg_binary_or_text_fallback(const void *data, size_t len)
190 {
191 unsigned char *chardata;
192 int i;
193
194 chardata = (unsigned char *) data;
195 for (i = 0; i < 128 && i < len; ++i)
196 {
197 if (chardata[i] < 32 && chardata[i] != 9 && chardata[i] != 10 && chardata[i] != 13)
198 return XDG_MIME_TYPE_UNKNOWN; /* binary data */
199 }
200
201 return XDG_MIME_TYPE_TEXTPLAIN;
202 }
203