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
|
/*
* chardet.c
* Copyright 2006-2010 Yoshiki Yazawa, Matti Hämäläinen, and John Lindgren
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice,
* this list of conditions, and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions, and the following disclaimer in the documentation
* provided with the distribution.
*
* This software is provided "as is" and without any warranty, express or
* implied. In no event shall the authors be liable for any damages arising from
* the use of this software.
*/
#include <glib.h>
#include <string.h>
#include <libaudcore/audstrings.h>
#include "debug.h"
#include "i18n.h"
#include "main.h"
#include "misc.h"
#ifdef USE_CHARDET
# include <libguess.h>
#endif
static char * cd_chardet_to_utf8 (const char * str, int len,
int * arg_bytes_read, int * arg_bytes_written);
static char * str_to_utf8_fallback (const char * str)
{
char * out = g_strconcat (str, _(" (invalid UTF-8)"), NULL);
for (char * c = out; * c; c ++)
{
if (* c & 0x80)
* c = '?';
}
return out;
}
static char * cd_str_to_utf8 (const char * str)
{
char *out_str;
if (str == NULL)
return NULL;
/* Note: Currently, playlist calls this function repeatedly, even
* if the string is already converted into utf-8.
* chardet_to_utf8() would convert a valid utf-8 string into a
* different utf-8 string, if fallback encodings were supplied and
* the given string could be treated as a string in one of
* fallback encodings. To avoid this, g_utf8_validate() had been
* used at the top of evaluation.
*/
/* Note 2: g_utf8_validate() has so called encapsulated utf-8
* problem, thus chardet_to_utf8() took the place of that.
*/
/* Note 3: As introducing madplug, the problem of conversion from
* ISO-8859-1 to UTF-8 arose. This may be coped with g_convert()
* located near the end of chardet_to_utf8(), but it requires utf8
* validation guard where g_utf8_validate() was. New
* dfa_validate_utf8() employs libguess' DFA engine to validate
* utf-8 and can properly distinguish examples of encapsulated
* utf-8. It is considered to be safe to use as a guard.
*/
/* Already UTF-8? */
#ifdef USE_CHARDET
if (libguess_validate_utf8(str, strlen(str)))
return g_strdup(str);
#else
if (g_utf8_validate(str, strlen(str), NULL))
return g_strdup(str);
#endif
/* chardet encoding detector */
if ((out_str = cd_chardet_to_utf8 (str, strlen (str), NULL, NULL)))
return out_str;
/* all else fails, we mask off character codes >= 128, replace with '?' */
return str_to_utf8_fallback(str);
}
static char * cd_chardet_to_utf8 (const char * str, int len,
int * arg_bytes_read, int * arg_bytes_write)
{
char *ret = NULL;
int * bytes_read, * bytes_write;
int my_bytes_read, my_bytes_write;
bytes_read = arg_bytes_read != NULL ? arg_bytes_read : &my_bytes_read;
bytes_write = arg_bytes_write != NULL ? arg_bytes_write : &my_bytes_write;
g_return_val_if_fail(str != NULL, NULL);
#ifdef USE_CHARDET
if (libguess_validate_utf8(str, len))
#else
if (g_utf8_validate(str, len, NULL))
#endif
{
if (len < 0)
len = strlen (str);
ret = g_malloc (len + 1);
memcpy (ret, str, len);
ret[len] = 0;
if (arg_bytes_read != NULL)
* arg_bytes_read = len;
if (arg_bytes_write != NULL)
* arg_bytes_write = len;
return ret;
}
#ifdef USE_CHARDET
char * det = get_string (NULL, "chardet_detector");
if (det[0])
{
AUDDBG("guess encoding (%s) %s\n", det, str);
const char * encoding = libguess_determine_encoding (str, len, det);
AUDDBG("encoding = %s\n", encoding);
if (encoding)
{
gsize read_gsize = 0, written_gsize = 0;
ret = g_convert (str, len, "UTF-8", encoding, & read_gsize, & written_gsize, NULL);
* bytes_read = read_gsize;
* bytes_write = written_gsize;
}
}
g_free (det);
#endif
/* If detection failed or was not enabled, try fallbacks (if there are any) */
if (! ret)
{
char * fallbacks = get_string (NULL, "chardet_fallback");
char * * split = g_strsplit_set (fallbacks, " ,:;|/", -1);
for (char * * enc = split; * enc; enc ++)
{
gsize read_gsize = 0, written_gsize = 0;
ret = g_convert (str, len, "UTF-8", * enc, & read_gsize, & written_gsize, NULL);
* bytes_read = read_gsize;
* bytes_write = written_gsize;
if (len == *bytes_read)
break;
else {
g_free(ret);
ret = NULL;
}
}
g_strfreev (split);
g_free (fallbacks);
}
/* First fallback: locale (duh!) */
if (ret == NULL)
{
gsize read_gsize = 0, written_gsize = 0;
ret = g_locale_to_utf8 (str, len, & read_gsize, & written_gsize, NULL);
* bytes_read = read_gsize;
* bytes_write = written_gsize;
}
/* The final fallback is ISO-8859-1, if no other is specified or conversions fail */
if (ret == NULL)
{
gsize read_gsize = 0, written_gsize = 0;
ret = g_convert (str, len, "UTF-8", "ISO-8859-1", & read_gsize, & written_gsize, NULL);
* bytes_read = read_gsize;
* bytes_write = written_gsize;
}
if (ret != NULL)
{
if (g_utf8_validate(ret, -1, NULL))
return ret;
else
{
g_warning("g_utf8_validate() failed for converted string in cd_chardet_to_utf8: '%s'", ret);
g_free(ret);
return NULL;
}
}
return NULL; /* If we have no idea, return NULL. */
}
void chardet_init (void)
{
#ifdef USE_CHARDET
libguess_determine_encoding(NULL, -1, "");
#endif
str_set_utf8_impl (cd_str_to_utf8, cd_chardet_to_utf8);
}
|
