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
|
/*
This file is part of libextractor.
(C) 2002, 2003, 2004, 2006 Vidyut Samanta and Christian Grothoff
libextractor is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published
by the Free Software Foundation; either version 2, or (at your
option) any later version.
libextractor 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
General Public License for more details.
You should have received a copy of the GNU General Public License
along with libextractor; see the file COPYING. If not, write to the
Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.
*/
#define DEBUG_EXTRACT_ID3v23 0
#include "platform.h"
#include "extractor.h"
#include <string.h>
#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <stdlib.h>
#include <fcntl.h>
#ifndef MINGW
#include <sys/mman.h>
#endif
#include "convert.h"
static struct EXTRACTOR_Keywords * addKeyword(EXTRACTOR_KeywordList *oldhead,
char *phrase,
EXTRACTOR_KeywordType type) {
EXTRACTOR_KeywordList * keyword;
keyword = (EXTRACTOR_KeywordList*) malloc(sizeof(EXTRACTOR_KeywordList));
keyword->next = oldhead;
keyword->keyword = phrase;
keyword->keywordType = type;
return keyword;
}
typedef struct {
char * text;
EXTRACTOR_KeywordType type;
} Matches;
static Matches tmap[] = {
{ "COMM", EXTRACTOR_COMMENT },
{ "IPLS", EXTRACTOR_CONTRIBUTOR },
{ "LINK", EXTRACTOR_LINK },
{ "MCDI", EXTRACTOR_MUSIC_CD_IDENTIFIER },
{ "PCNT", EXTRACTOR_PLAY_COUNTER },
{ "POPM", EXTRACTOR_POPULARITY_METER },
{ "TCOP", EXTRACTOR_COPYRIGHT },
{ "TDAT", EXTRACTOR_DATE },
{ "TCON", EXTRACTOR_CONTENT_TYPE },
{ "TIT1", EXTRACTOR_GENRE },
{ "TENC", EXTRACTOR_ENCODED_BY },
{ "TEXT", EXTRACTOR_LYRICS },
{ "TOLY", EXTRACTOR_CONTRIBUTOR },
{ "TOPE", EXTRACTOR_CONTRIBUTOR },
{ "TOWN", EXTRACTOR_OWNER },
{ "TPE1", EXTRACTOR_ARTIST },
{ "TPE2", EXTRACTOR_ARTIST },
{ "TPE3", EXTRACTOR_CONDUCTOR },
{ "TPE4", EXTRACTOR_INTERPRET },
{ "TMED", EXTRACTOR_MEDIA_TYPE },
{ "TCOM", EXTRACTOR_CREATOR },
{ "TIME", EXTRACTOR_TIME },
{ "TOFN", EXTRACTOR_FILENAME },
{ "TOPE", EXTRACTOR_ARTIST },
{ "TPUB", EXTRACTOR_PUBLISHER },
{ "TRSN", EXTRACTOR_SOURCE },
{ "TRSO", EXTRACTOR_CREATED_FOR },
{ "TSRC", EXTRACTOR_RESOURCE_IDENTIFIER },
{ "TOAL", EXTRACTOR_ALBUM },
{ "TALB", EXTRACTOR_ALBUM },
{ "TLAN", EXTRACTOR_LANGUAGE },
{ "TYER", EXTRACTOR_YEAR },
{ "TLEN", EXTRACTOR_DURATION },
{ "TIT2", EXTRACTOR_TITLE },
{ "TIT3", EXTRACTOR_DESCRIPTION },
{ "WCOM", EXTRACTOR_RELEASE },
{ "WCOP", EXTRACTOR_DISCLAIMER },
{ "", EXTRACTOR_KEYWORDS },
{ NULL, 0},
};
/* mimetype = audio/mpeg */
struct EXTRACTOR_Keywords *
libextractor_id3v23_extract(const char * filename,
const unsigned char * data,
const size_t size,
struct EXTRACTOR_Keywords * prev) {
int unsync;
int extendedHdr;
int experimental;
unsigned int tsize;
unsigned int pos;
unsigned int ehdrSize;
unsigned int padding;
if ( (size < 16) ||
(data[0] != 0x49) ||
(data[1] != 0x44) ||
(data[2] != 0x33) ||
(data[3] != 0x03) ||
(data[4] != 0x00) )
return prev;
unsync = (data[5] & 0x80) > 0;
extendedHdr = (data[5] & 0x40) > 0;
experimental = (data[5] & 0x20) > 0;
tsize = ( ( (data[6] & 0x7F) << 21 ) |
( (data[7] & 0x7F) << 14 ) |
( (data[8] & 0x7F) << 7 ) |
( (data[9] & 0x7F) << 0 ) );
if ( (tsize + 10 > size) || (experimental) )
return prev;
pos = 10;
padding = 0;
if (extendedHdr) {
ehdrSize = ( ( (data[10]) << 24 ) |
( (data[11]) << 16 ) |
( (data[12]) << 8 ) |
( (data[12]) << 0 ) );
padding = ( ( (data[15]) << 24 ) |
( (data[16]) << 16 ) |
( (data[17]) << 8 ) |
( (data[18]) << 0 ) );
pos += 4 + ehdrSize;
if (padding < tsize)
tsize -= padding;
else
return prev;
}
while (pos < tsize) {
size_t csize;
int i;
unsigned short flags;
if (pos + 10 > tsize)
return prev;
csize = (data[pos+4] << 24) + (data[pos+5] << 16) + (data[pos+6] << 8) + data[pos+7];
if ( (pos + 10 + csize > tsize) ||
(csize > tsize) ||
(csize == 0) )
break;
flags = (data[pos+8]<<8) + data[pos+9];
if ( ( (flags & 0x80) > 0) /* compressed, not yet supported */ ||
( (flags & 0x40) > 0) /* encrypted, not supported */ ) {
pos += 10 + csize;
continue;
}
i = 0;
while (tmap[i].text != NULL) {
if (0 == strncmp(tmap[i].text,
(const char*) &data[pos],
4)) {
char * word;
if ( (flags & 0x20) > 0) {
/* "group" identifier, skip a byte */
pos++;
csize--;
}
csize--;
/* this byte describes the encoding
try to convert strings to UTF-8
if it fails, then forget it */
switch (data[pos+10]) {
case 0x00 :
word = convertToUtf8((const char*) &data[pos+11],
csize,
"ISO-8859-1");
break;
case 0x01 :
word = convertToUtf8((const char*) &data[pos+11],
csize,
"UCS-2");
break;
default:
/* bad encoding byte,
try to convert from iso-8859-1 */
word = convertToUtf8((const char*) &data[pos+11],
csize,
"ISO-8859-1");
break;
}
pos++;
if ( (word != NULL) &&
(strlen(word) > 0) ) {
prev = addKeyword(prev,
word,
tmap[i].type);
} else {
free(word);
}
break;
}
i++;
}
pos += 10 + csize;
}
return prev;
}
/* end of id3v23extractor.c */
|
