3 * Copyright (c) 2003 Fabrice Bellard
5 * This file is part of FFmpeg.
7 * FFmpeg is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
12 * FFmpeg is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15 * Lesser General Public License for more details.
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with FFmpeg; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
24 #include "libavutil/avstring.h"
25 #include "libavutil/intreadwrite.h"
27 #include "avio_internal.h"
29 int ff_id3v2_match(const uint8_t *buf, const char * magic)
31 return buf[0] == magic[0] &&
36 (buf[6] & 0x80) == 0 &&
37 (buf[7] & 0x80) == 0 &&
38 (buf[8] & 0x80) == 0 &&
42 int ff_id3v2_tag_len(const uint8_t * buf)
44 int len = ((buf[6] & 0x7f) << 21) +
45 ((buf[7] & 0x7f) << 14) +
46 ((buf[8] & 0x7f) << 7) +
50 len += ID3v2_HEADER_SIZE;
54 static unsigned int get_size(AVIOContext *s, int len)
58 v = (v << 7) + (avio_r8(s) & 0x7F);
62 static void read_ttag(AVFormatContext *s, AVIOContext *pb, int taglen, const char *key)
65 const char *val = NULL;
66 int len, dstlen = sizeof(dst) - 1;
68 unsigned int (*get)(AVIOContext*) = avio_rb16;
74 taglen--; /* account for encoding type byte */
76 switch (avio_r8(pb)) { /* encoding type */
78 case ID3v2_ENCODING_ISO8859:
80 while (taglen-- && q - dst < dstlen - 7) {
82 PUT_UTF8(avio_r8(pb), tmp, *q++ = tmp;)
87 case ID3v2_ENCODING_UTF16BOM:
89 switch (avio_rb16(pb)) {
95 av_log(s, AV_LOG_ERROR, "Incorrect BOM value in tag %s.\n", key);
100 case ID3v2_ENCODING_UTF16BE:
102 while (taglen > 1 && q - dst < dstlen - 7) {
106 GET_UTF16(ch, ((taglen -= 2) >= 0 ? get(pb) : 0), break;)
107 PUT_UTF8(ch, tmp, *q++ = tmp;)
112 case ID3v2_ENCODING_UTF8:
113 len = FFMIN(taglen, dstlen);
114 avio_read(pb, dst, len);
118 av_log(s, AV_LOG_WARNING, "Unknown encoding in tag %s.\n", key);
121 if (!(strcmp(key, "TCON") && strcmp(key, "TCO"))
122 && (sscanf(dst, "(%d)", &genre) == 1 || sscanf(dst, "%d", &genre) == 1)
123 && genre <= ID3v1_GENRE_MAX)
124 val = ff_id3v1_genre_str[genre];
125 else if (!(strcmp(key, "TXXX") && strcmp(key, "TXX"))) {
126 /* dst now contains two 0-terminated strings */
130 val = dst + FFMIN(len + 1, dstlen);
136 av_metadata_set2(&s->metadata, key, val, AV_METADATA_DONT_OVERWRITE);
139 static int is_number(const char *str)
141 while (*str >= '0' && *str <= '9') str++;
145 static AVMetadataTag* get_date_tag(AVMetadata *m, const char *tag)
148 if ((t = av_metadata_get(m, tag, NULL, AV_METADATA_MATCH_CASE)) &&
149 strlen(t->value) == 4 && is_number(t->value))
154 static void merge_date(AVMetadata **m)
157 char date[17] = {0}; // YYYY-MM-DD hh:mm
159 if (!(t = get_date_tag(*m, "TYER")) &&
160 !(t = get_date_tag(*m, "TYE")))
162 av_strlcpy(date, t->value, 5);
163 av_metadata_set2(m, "TYER", NULL, 0);
164 av_metadata_set2(m, "TYE", NULL, 0);
166 if (!(t = get_date_tag(*m, "TDAT")) &&
167 !(t = get_date_tag(*m, "TDA")))
169 snprintf(date + 4, sizeof(date) - 4, "-%.2s-%.2s", t->value + 2, t->value);
170 av_metadata_set2(m, "TDAT", NULL, 0);
171 av_metadata_set2(m, "TDA", NULL, 0);
173 if (!(t = get_date_tag(*m, "TIME")) &&
174 !(t = get_date_tag(*m, "TIM")))
176 snprintf(date + 10, sizeof(date) - 10, " %.2s:%.2s", t->value, t->value + 2);
177 av_metadata_set2(m, "TIME", NULL, 0);
178 av_metadata_set2(m, "TIM", NULL, 0);
182 av_metadata_set2(m, "date", date, 0);
185 static void ff_id3v2_parse(AVFormatContext *s, int len, uint8_t version, uint8_t flags)
190 int64_t next, end = avio_tell(s->pb) + len;
192 const char *reason = NULL;
194 unsigned char *buffer = NULL;
200 reason = "compression";
218 unsync = flags & 0x80;
220 if (isv34 && flags & 0x40) /* Extended header present, just skip over it */
221 avio_skip(s->pb, get_size(s->pb, 4));
223 while (len >= taghdrlen) {
228 avio_read(s->pb, tag, 4);
231 tlen = avio_rb32(s->pb);
233 tlen = get_size(s->pb, 4);
234 tflags = avio_rb16(s->pb);
235 tunsync = tflags & ID3v2_FLAG_UNSYNCH;
237 avio_read(s->pb, tag, 3);
239 tlen = avio_rb24(s->pb);
243 len -= taghdrlen + tlen;
248 next = avio_tell(s->pb) + tlen;
250 if (tflags & ID3v2_FLAG_DATALEN) {
255 if (tflags & (ID3v2_FLAG_ENCRYPTION | ID3v2_FLAG_COMPRESSION)) {
256 av_log(s, AV_LOG_WARNING, "Skipping encrypted/compressed ID3v2 frame %s.\n", tag);
257 avio_skip(s->pb, tlen);
258 } else if (tag[0] == 'T') {
259 if (unsync || tunsync) {
261 av_fast_malloc(&buffer, &buffer_size, tlen);
262 for (i = 0, j = 0; i < tlen; i++, j++) {
263 buffer[j] = avio_r8(s->pb);
264 if (j > 0 && !buffer[j] && buffer[j - 1] == 0xff) {
265 /* Unsynchronised byte, skip it */
269 ffio_init_context(&pb, buffer, j, 0, NULL, NULL, NULL, NULL);
270 read_ttag(s, &pb, j, tag);
272 read_ttag(s, s->pb, tlen, tag);
277 av_log(s, AV_LOG_WARNING, "invalid frame id, assuming padding");
278 avio_skip(s->pb, tlen);
281 /* Skip to end of tag */
282 avio_seek(s->pb, next, SEEK_SET);
285 if (version == 4 && flags & 0x10) /* Footer preset, always 10 bytes, skip over it */
290 av_log(s, AV_LOG_INFO, "ID3v2.%d tag skipped, cannot handle %s\n", version, reason);
291 avio_seek(s->pb, end, SEEK_SET);
296 void ff_id3v2_read(AVFormatContext *s, const char *magic)
299 uint8_t buf[ID3v2_HEADER_SIZE];
304 /* save the current offset in case there's nothing to read/skip */
305 off = avio_tell(s->pb);
306 ret = avio_read(s->pb, buf, ID3v2_HEADER_SIZE);
307 if (ret != ID3v2_HEADER_SIZE)
309 found_header = ff_id3v2_match(buf, magic);
311 /* parse ID3v2 header */
312 len = ((buf[6] & 0x7f) << 21) |
313 ((buf[7] & 0x7f) << 14) |
314 ((buf[8] & 0x7f) << 7) |
316 ff_id3v2_parse(s, len, buf[3], buf[5]);
318 avio_seek(s->pb, off, SEEK_SET);
320 } while (found_header);
321 ff_metadata_conv(&s->metadata, NULL, ff_id3v2_34_metadata_conv);
322 ff_metadata_conv(&s->metadata, NULL, ff_id3v2_2_metadata_conv);
323 ff_metadata_conv(&s->metadata, NULL, ff_id3v2_4_metadata_conv);
324 merge_date(&s->metadata);
327 const AVMetadataConv ff_id3v2_34_metadata_conv[] = {
329 { "TCOM", "composer"},
331 { "TCOP", "copyright"},
332 { "TENC", "encoded_by"},
334 { "TLAN", "language"},
336 { "TPE2", "album_artist"},
337 { "TPE3", "performer"},
339 { "TPUB", "publisher"},
341 { "TSSE", "encoder"},
345 const AVMetadataConv ff_id3v2_4_metadata_conv[] = {
348 { "TDEN", "creation_time"},
349 { "TSOA", "album-sort"},
350 { "TSOP", "artist-sort"},
351 { "TSOT", "title-sort"},
355 const AVMetadataConv ff_id3v2_2_metadata_conv[] = {
359 { "TEN", "encoded_by"},
361 { "TP2", "album_artist"},
362 { "TP3", "performer"},
368 const char ff_id3v2_tags[][4] = {
369 "TALB", "TBPM", "TCOM", "TCON", "TCOP", "TDLY", "TENC", "TEXT",
370 "TFLT", "TIT1", "TIT2", "TIT3", "TKEY", "TLAN", "TLEN", "TMED",
371 "TOAL", "TOFN", "TOLY", "TOPE", "TOWN", "TPE1", "TPE2", "TPE3",
372 "TPE4", "TPOS", "TPUB", "TRCK", "TRSN", "TRSO", "TSRC", "TSSE",
376 const char ff_id3v2_4_tags[][4] = {
377 "TDEN", "TDOR", "TDRC", "TDRL", "TDTG", "TIPL", "TMCL", "TMOO",
378 "TPRO", "TSOA", "TSOP", "TSOT", "TSST",
382 const char ff_id3v2_3_tags[][4] = {
383 "TDAT", "TIME", "TORY", "TRDA", "TSIZ", "TYER",