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
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
|
#include "frame_utils.h"
#include "foundation/error.h"
#include "nsid3v2/nsid3v2.h"
#if defined(_WIN32) && !defined(strcasecmp)
#define strcasecmp _stricmp
#else
#include <string.h>
#endif
int ParseDescription(const char *&str, size_t &data_len, size_t &str_cch)
{
str_cch=0;
while (data_len && str[str_cch])
{
data_len--;
str_cch++;
}
if (!data_len)
return NErr_Error;
data_len--;
return NErr_Success;
}
int ParseDescription(const wchar_t *&str, size_t &data_len, size_t &str_cch, uint8_t &str_encoding)
{
str_cch=0;
if (data_len > 2 && str[0] == 0xFFFE)
{
str_encoding=2;
str++;
str-=3;
}
else if (data_len > 2 && str[0] == 0xFEFF)
{
str_encoding=1;
str++;
data_len-=3;
}
else
{
data_len--;
}
while (data_len > 1 && str[str_cch])
{
data_len-=2;
str_cch++;
}
if (!data_len)
return NErr_Error;
data_len-=2;
return NErr_Success;
}
static void ParseBOM(bytereader_t reader, uint8_t *encoding, const uint8_t default_encoding)
{
if (bytereader_size(reader) >= 2)
{
uint16_t bom = bytereader_show_u16_le(reader);
if (bom == 0xFFFE)
{
bytereader_advance(reader, 2);
*encoding=2;
}
else if (bom == 0xFEFF)
{
bytereader_advance(reader, 2);
*encoding=1;
}
else
{
*encoding=default_encoding;
}
}
else
{
*encoding=default_encoding;
}
}
int ParseNullTerminatedString(bytereader_t reader, uint8_t encoding, ParsedString &parsed)
{
switch(encoding)
{
case 0: // ISO-8859-1
if (bytereader_size(reader) == 0)
return NErr_Insufficient;
parsed.encoding = 0;
parsed.data = bytereader_pointer(reader);
parsed.byte_length = 0;
while (bytereader_size(reader) && bytereader_read_u8(reader))
parsed.byte_length++;
return NErr_Success;
case 1: // UTF-16
if (bytereader_size(reader) < 2)
return NErr_Insufficient;
parsed.byte_length = 0;
ParseBOM(reader, &parsed.encoding, 1);
parsed.data = bytereader_pointer(reader);
while (bytereader_size(reader) && bytereader_read_u16_le(reader))
parsed.byte_length+=2;
return NErr_Success;
case 2: // UTF-16BE
if (bytereader_size(reader) < 2)
return NErr_Insufficient;
parsed.byte_length = 0;
ParseBOM(reader, &parsed.encoding, 2);
parsed.data = bytereader_pointer(reader);
while (bytereader_size(reader) && bytereader_read_u16_le(reader))
parsed.byte_length+=2;
return NErr_Success;
case 3: // UTF-8
if (bytereader_size(reader) == 0)
return NErr_Insufficient;
parsed.encoding = 3;
parsed.data = bytereader_pointer(reader);
parsed.byte_length = 0;
size_t start = bytereader_size(reader);
#if 0 // TODO
/* check for UTF-8 BOM and skip it */
if (bytereader_size(reader) > 3 && bytereader_read_u8(reader) == 0xEF && bytereader_read_u8(reader) == 0xBB && bytereader_read_u8(reader) == 0xBF)
{
parsed.data = bytereader_pointer(reader);
parsed.byte_length = bytereader_size(reader);
}
else
{
/* no BOM but skip however far we read into the string */
size_t offset = start - bytereader_size(reader);
parsed.data = (const uint8_t *)parsed.data + offset;
parsed.byte_length -= offset;
}
#endif
/* finish it up */
while (bytereader_size(reader) && bytereader_read_u8(reader))
parsed.byte_length++;
return NErr_Success;
}
return NErr_Unknown;
}
int ParseFrameTerminatedString(bytereader_t reader, uint8_t encoding, ParsedString &parsed)
{
switch(encoding)
{
case 0: // ISO-8859-1
parsed.encoding = 0;
parsed.data = bytereader_pointer(reader);
parsed.byte_length = bytereader_size(reader);
return NErr_Success;
case 1: // UTF-16
if ((bytereader_size(reader) & 1) == 1)
return NErr_Error;
ParseBOM(reader, &parsed.encoding, 1);
parsed.data = bytereader_pointer(reader);
parsed.byte_length = bytereader_size(reader);
return NErr_Success;
case 2: // UTF-16BE
if ((bytereader_size(reader) & 1) == 1)
return NErr_Error;
ParseBOM(reader, &parsed.encoding, 2);
parsed.data = bytereader_pointer(reader);
parsed.byte_length = bytereader_size(reader);
return NErr_Success;
case 3: // UTF-8
parsed.encoding = 3;
parsed.data = bytereader_pointer(reader);
parsed.byte_length = bytereader_size(reader);
if (bytereader_size(reader) > 3 && bytereader_read_u8(reader) == 0xEF && bytereader_read_u8(reader) == 0xBB && bytereader_read_u8(reader) == 0xBF)
{
parsed.data = bytereader_pointer(reader);
parsed.byte_length = bytereader_size(reader);
}
return NErr_Success;
}
return NErr_Error;
}
int NXStringCreateFromParsedString(nx_string_t *value, ParsedString &parsed, int text_flags)
{
switch(parsed.encoding)
{
case 0: // ISO-8859-1
if (parsed.byte_length == 0)
return NXStringCreateEmpty(value);
if (text_flags & NSID3V2_TEXT_SYSTEM)
return NXStringCreateWithBytes(value, parsed.data, parsed.byte_length, nx_charset_system);
else
return NXStringCreateWithBytes(value, parsed.data, parsed.byte_length, nx_charset_latin1);
case 1: // UTF-16
if (parsed.byte_length < 2)
return NXStringCreateEmpty(value);
return NXStringCreateWithBytes(value, parsed.data, parsed.byte_length, nx_charset_utf16le);
case 2: // UTF-16BE
if (parsed.byte_length < 2)
return NXStringCreateEmpty(value);
return NXStringCreateWithBytes(value, parsed.data, parsed.byte_length, nx_charset_utf16be);
case 3: // UTF-8
if (parsed.byte_length == 0)
return NXStringCreateEmpty(value);
return NXStringCreateWithBytes(value, parsed.data, parsed.byte_length, nx_charset_utf8);
default:
return NErr_Unknown;
}
}
bool DescriptionMatches(const ParsedString &parsed, const char *description, int text_flags)
{
// see if our description matches
switch(parsed.encoding)
{
case 0: // ISO-8859-1
return !strcasecmp(description, (const char *)parsed.data);
case 1:
{
bytereader_value_t utf16;
bytereader_init(&utf16, parsed.data, parsed.byte_length);
while (*description && bytereader_size(&utf16))
{
if ((*description++ & ~0x20) != (bytereader_read_u16_le(&utf16) & ~0x20))
return false;
}
if (*description == 0 && bytereader_size(&utf16) == 0)
return true;
else
return false;
}
case 2:
{
bytereader_value_t utf16;
bytereader_init(&utf16, parsed.data, parsed.byte_length);
while (*description && bytereader_size(&utf16))
{
if ((*description++ & ~0x20) != (bytereader_read_u16_be(&utf16) & ~0x20))
return false;
}
if (*description == 0 && bytereader_size(&utf16) == 0)
return true;
else
return false;
}
case 3:
return !strcasecmp(description, (const char *)parsed.data);
}
return false;
}
|
