FFmpeg
lrcdec.c
Go to the documentation of this file.
1 /*
2  * LRC lyrics file format decoder
3  * Copyright (c) 2014 StarBrilliant <m13253@hotmail.com>
4  *
5  * This file is part of FFmpeg.
6  *
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.
11  *
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.
16  *
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
20  */
21 
22 #include <inttypes.h>
23 #include <stdint.h>
24 #include <string.h>
25 
26 #include "avformat.h"
27 #include "internal.h"
28 #include "lrc.h"
29 #include "metadata.h"
30 #include "subtitles.h"
31 #include "libavutil/bprint.h"
32 #include "libavutil/dict.h"
33 
34 typedef struct LRCContext {
36  int64_t ts_offset; // offset metadata item
37 } LRCContext;
38 
39 static int64_t find_header(const char *p)
40 {
41  int64_t offset = 0;
42  while(p[offset] == ' ' || p[offset] == '\t') {
43  offset++;
44  }
45  if(p[offset] == '[' && p[offset + 1] >= 'a' && p[offset + 1] <= 'z') {
46  return offset;
47  } else {
48  return -1;
49  }
50 }
51 
52 static int64_t count_ts(const char *p)
53 {
54  int64_t offset = 0;
55  int in_brackets = 0;
56 
57  for(;;) {
58  if(p[offset] == ' ' || p[offset] == '\t') {
59  offset++;
60  } else if(p[offset] == '[') {
61  offset++;
62  in_brackets++;
63  } else if (p[offset] == ']' && in_brackets) {
64  offset++;
65  in_brackets--;
66  } else if(in_brackets &&
67  (p[offset] == ':' || p[offset] == '.' || p[offset] == '-' ||
68  (p[offset] >= '0' && p[offset] <= '9'))) {
69  offset++;
70  } else {
71  break;
72  }
73  }
74  return offset;
75 }
76 
77 static int64_t read_ts(const char *p, int64_t *start)
78 {
79  int64_t offset = 0;
80  uint64_t mm, ss, cs;
81 
82  while(p[offset] == ' ' || p[offset] == '\t') {
83  offset++;
84  }
85  if(p[offset] != '[') {
86  return 0;
87  }
88  if(sscanf(p, "[-%"SCNu64":%"SCNu64".%"SCNu64"]", &mm, &ss, &cs) == 3) {
89  /* Just in case negative pts, players may drop it but we won't. */
90  *start = -(int64_t) (mm*60000 + ss*1000 + cs*10);
91  } else if(sscanf(p, "[%"SCNu64":%"SCNu64".%"SCNu64"]", &mm, &ss, &cs) == 3) {
92  *start = mm*60000 + ss*1000 + cs*10;
93  } else {
94  return 0;
95  }
96  do {
97  offset++;
98  } while(p[offset] && p[offset-1] != ']');
99  return offset;
100 }
101 
102 static int64_t read_line(AVBPrint *buf, AVIOContext *pb)
103 {
104  int64_t pos = avio_tell(pb);
105 
107  while(!avio_feof(pb)) {
108  int c = avio_r8(pb);
109  if(c != '\r') {
110  av_bprint_chars(buf, c, 1);
111  }
112  if(c == '\n') {
113  break;
114  }
115  }
116  return pos;
117 }
118 
119 static int lrc_probe(const AVProbeData *p)
120 {
121  int64_t offset = 0;
122  int64_t mm;
123  uint64_t ss, cs;
124  const AVMetadataConv *metadata_item;
125 
126  if(!memcmp(p->buf, "\xef\xbb\xbf", 3)) { // Skip UTF-8 BOM header
127  offset += 3;
128  }
129  while(p->buf[offset] == '\n' || p->buf[offset] == '\r') {
130  offset++;
131  }
132  if(p->buf[offset] != '[') {
133  return 0;
134  }
135  offset++;
136  // Common metadata item but not exist in ff_lrc_metadata_conv
137  if(!memcmp(p->buf + offset, "offset:", 7)) {
138  return 40;
139  }
140  if(sscanf(p->buf + offset, "%"SCNd64":%"SCNu64".%"SCNu64"]",
141  &mm, &ss, &cs) == 3) {
142  return 50;
143  }
144  // Metadata items exist in ff_lrc_metadata_conv
145  for(metadata_item = ff_lrc_metadata_conv;
146  metadata_item->native; metadata_item++) {
147  size_t metadata_item_len = strlen(metadata_item->native);
148  if(p->buf[offset + metadata_item_len] == ':' &&
149  !memcmp(p->buf + offset, metadata_item->native, metadata_item_len)) {
150  return 40;
151  }
152  }
153  return 5; // Give it 5 scores since it starts with a bracket
154 }
155 
157 {
158  LRCContext *lrc = s->priv_data;
159  AVBPrint line;
160  AVStream *st;
161 
162  st = avformat_new_stream(s, NULL);
163  if(!st) {
164  return AVERROR(ENOMEM);
165  }
166  avpriv_set_pts_info(st, 64, 1, 1000);
167  lrc->ts_offset = 0;
171 
172  while(!avio_feof(s->pb)) {
173  int64_t pos = read_line(&line, s->pb);
174  int64_t header_offset = find_header(line.str);
175  if(header_offset >= 0) {
176  char *comma_offset = strchr(line.str, ':');
177  if(comma_offset) {
178  char *right_bracket_offset = strchr(line.str, ']');
179  if(!right_bracket_offset) {
180  continue;
181  }
182 
183  *right_bracket_offset = *comma_offset = '\0';
184  if(strcmp(line.str + 1, "offset") ||
185  sscanf(comma_offset + 1, "%"SCNd64, &lrc->ts_offset) != 1) {
186  av_dict_set(&s->metadata, line.str + 1, comma_offset + 1, 0);
187  }
188  lrc->ts_offset = av_clip64(lrc->ts_offset, INT64_MIN/4, INT64_MAX/4);
189 
190  *comma_offset = ':';
191  *right_bracket_offset = ']';
192  }
193 
194  } else {
195  AVPacket *sub;
196  int64_t ts_start = AV_NOPTS_VALUE;
197  int64_t ts_stroffset = 0;
198  int64_t ts_stroffset_incr = 0;
199  int64_t ts_strlength = count_ts(line.str);
200 
201  while((ts_stroffset_incr = read_ts(line.str + ts_stroffset,
202  &ts_start)) != 0) {
203  ts_start = av_clip64(ts_start, INT64_MIN/4, INT64_MAX/4);
204  ts_stroffset += ts_stroffset_incr;
205  sub = ff_subtitles_queue_insert(&lrc->q, line.str + ts_strlength,
206  line.len - ts_strlength, 0);
207  if(!sub) {
209  return AVERROR(ENOMEM);
210  }
211  sub->pos = pos;
212  sub->pts = ts_start - lrc->ts_offset;
213  sub->duration = -1;
214  }
215  }
216  }
220  return 0;
221 }
222 
224 {
225  LRCContext *lrc = s->priv_data;
226  return ff_subtitles_queue_read_packet(&lrc->q, pkt);
227 }
228 
229 static int lrc_read_seek(AVFormatContext *s, int stream_index,
230  int64_t min_ts, int64_t ts, int64_t max_ts, int flags)
231 {
232  LRCContext *lrc = s->priv_data;
233  return ff_subtitles_queue_seek(&lrc->q, s, stream_index,
234  min_ts, ts, max_ts, flags);
235 }
236 
238 {
239  LRCContext *lrc = s->priv_data;
241  return 0;
242 }
243 
245  .name = "lrc",
246  .long_name = NULL_IF_CONFIG_SMALL("LRC lyrics"),
247  .priv_data_size = sizeof (LRCContext),
252  .read_seek2 = lrc_read_seek
253 };
AVMEDIA_TYPE_SUBTITLE
@ AVMEDIA_TYPE_SUBTITLE
Definition: avutil.h:204
AV_BPRINT_SIZE_UNLIMITED
#define AV_BPRINT_SIZE_UNLIMITED
LRCContext::ts_offset
int64_t ts_offset
Definition: lrcdec.c:36
AVERROR
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
avformat_new_stream
AVStream * avformat_new_stream(AVFormatContext *s, const AVCodec *c)
Add a new stream to a media file.
Definition: utils.c:4480
AVCodecParameters::codec_type
enum AVMediaType codec_type
General type of the encoded data.
Definition: avcodec.h:3953
av_bprint_finalize
int av_bprint_finalize(AVBPrint *buf, char **ret_str)
Finalize a print buffer.
Definition: bprint.c:235
av_bprint_init
void av_bprint_init(AVBPrint *buf, unsigned size_init, unsigned size_max)
Definition: bprint.c:69
AVMetadataConv::native
const char * native
Definition: metadata.h:35
AVMetadataConv
Definition: metadata.h:34
AVPacket::duration
int64_t duration
Duration of this packet in AVStream->time_base units, 0 if unknown.
Definition: avcodec.h:1495
lrc_read_header
static int lrc_read_header(AVFormatContext *s)
Definition: lrcdec.c:156
LRCContext
Definition: lrcdec.c:34
start
void INT64 start
Definition: avisynth_c.h:767
read_close
static av_cold int read_close(AVFormatContext *ctx)
Definition: libcdio.c:145
avio_tell
static av_always_inline int64_t avio_tell(AVIOContext *s)
ftell() equivalent for AVIOContext.
Definition: avio.h:557
ss
#define ss(width, name, subs,...)
Definition: cbs_vp9.c:261
ff_subtitles_queue_seek
int ff_subtitles_queue_seek(FFDemuxSubtitlesQueue *q, AVFormatContext *s, int stream_index, int64_t min_ts, int64_t ts, int64_t max_ts, int flags)
Update current_sub_idx to emulate a seek.
Definition: subtitles.c:249
buf
void * buf
Definition: avisynth_c.h:766
AVInputFormat
Definition: avformat.h:640
s
#define s(width, name)
Definition: cbs_vp9.c:257
lrc.h
AVInputFormat::name
const char * name
A comma separated list of short names for the format.
Definition: avformat.h:645
AVProbeData::buf
unsigned char * buf
Buffer must have AVPROBE_PADDING_SIZE of extra allocated bytes filled with zero.
Definition: avformat.h:448
ff_lrc_metadata_conv
const AVMetadataConv ff_lrc_metadata_conv[]
Definition: lrc.c:25
ff_subtitles_queue_read_packet
int ff_subtitles_queue_read_packet(FFDemuxSubtitlesQueue *q, AVPacket *pkt)
Generic read_packet() callback for subtitles demuxers using this queue system.
Definition: subtitles.c:212
find_header
static int64_t find_header(const char *p)
Definition: lrcdec.c:39
AVFormatContext
Format I/O context.
Definition: avformat.h:1342
internal.h
ff_metadata_conv_ctx
void ff_metadata_conv_ctx(AVFormatContext *ctx, const AVMetadataConv *d_conv, const AVMetadataConv *s_conv)
Definition: metadata.c:59
AVStream::codecpar
AVCodecParameters * codecpar
Codec parameters associated with this stream.
Definition: avformat.h:1017
read_header
static int read_header(FFV1Context *f)
Definition: ffv1dec.c:530
NULL
#define NULL
Definition: coverity.c:32
read_probe
static int read_probe(const AVProbeData *pd)
Definition: jvdec.c:55
AVProbeData
This structure contains the data a format has to probe a file.
Definition: avformat.h:446
ff_subtitles_queue_insert
AVPacket * ff_subtitles_queue_insert(FFDemuxSubtitlesQueue *q, const uint8_t *event, size_t len, int merge)
Insert a new subtitle event.
Definition: subtitles.c:111
ff_lrc_demuxer
AVInputFormat ff_lrc_demuxer
Definition: lrcdec.c:244
c
Undefined Behavior In the C some operations are like signed integer dereferencing freed accessing outside allocated Undefined Behavior must not occur in a C it is not safe even if the output of undefined operations is unused The unsafety may seem nit picking but Optimizing compilers have in fact optimized code on the assumption that no undefined Behavior occurs Optimizing code based on wrong assumptions can and has in some cases lead to effects beyond the output of computations The signed integer overflow problem in speed critical code Code which is highly optimized and works with signed integers sometimes has the problem that often the output of the computation does not c
Definition: undefined.txt:32
lrc_read_seek
static int lrc_read_seek(AVFormatContext *s, int stream_index, int64_t min_ts, int64_t ts, int64_t max_ts, int flags)
Definition: lrcdec.c:229
AVIOContext
Bytestream IO Context.
Definition: avio.h:161
NULL_IF_CONFIG_SMALL
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification.
Definition: internal.h:188
lrc_probe
static int lrc_probe(const AVProbeData *p)
Definition: lrcdec.c:119
count_ts
static int64_t count_ts(const char *p)
Definition: lrcdec.c:52
avpriv_set_pts_info
void avpriv_set_pts_info(AVStream *s, int pts_wrap_bits, unsigned int pts_num, unsigned int pts_den)
Set the time base and wrapping info for a given stream.
Definition: utils.c:4910
AV_NOPTS_VALUE
#define AV_NOPTS_VALUE
Undefined timestamp value.
Definition: avutil.h:248
ff_subtitles_queue_finalize
void ff_subtitles_queue_finalize(void *log_ctx, FFDemuxSubtitlesQueue *q)
Set missing durations, sort subtitles by PTS (and then byte position), and drop duplicated events.
Definition: subtitles.c:194
LRCContext::q
FFDemuxSubtitlesQueue q
Definition: lrcdec.c:35
FFDemuxSubtitlesQueue
Definition: subtitles.h:102
avio_r8
int avio_r8(AVIOContext *s)
Definition: aviobuf.c:638
lrc_read_packet
static int lrc_read_packet(AVFormatContext *s, AVPacket *pkt)
Definition: lrcdec.c:223
ff_subtitles_queue_clean
void ff_subtitles_queue_clean(FFDemuxSubtitlesQueue *q)
Remove and destroy all the subtitles packets.
Definition: subtitles.c:301
offset
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf offset
Definition: writing_filters.txt:86
line
Definition: graph2dot.c:48
bprint.h
AVPacket::pts
int64_t pts
Presentation timestamp in AVStream->time_base units; the time at which the decompressed packet will b...
Definition: avcodec.h:1470
read_packet
static int read_packet(void *opaque, uint8_t *buf, int buf_size)
Definition: avio_reading.c:42
AVStream
Stream structure.
Definition: avformat.h:870
metadata.h
avformat.h
dict.h
AV_CODEC_ID_TEXT
@ AV_CODEC_ID_TEXT
raw UTF-8 text
Definition: avcodec.h:660
av_bprint_clear
void av_bprint_clear(AVBPrint *buf)
Reset the string to "" but keep internal allocated data.
Definition: bprint.c:227
subtitles.h
pkt
static AVPacket pkt
Definition: demuxing_decoding.c:54
lrc_read_close
static int lrc_read_close(AVFormatContext *s)
Definition: lrcdec.c:237
read_line
static int64_t read_line(AVBPrint *buf, AVIOContext *pb)
Definition: lrcdec.c:102
read_ts
static int64_t read_ts(const char *p, int64_t *start)
Definition: lrcdec.c:77
AVCodecParameters::codec_id
enum AVCodecID codec_id
Specific type of the encoded data (the codec used).
Definition: avcodec.h:3957
AVPacket
This structure stores compressed data.
Definition: avcodec.h:1454
av_dict_set
int av_dict_set(AVDictionary **pm, const char *key, const char *value, int flags)
Set the given entry in *pm, overwriting an existing entry.
Definition: dict.c:70
AVPacket::pos
int64_t pos
byte position in stream, -1 if unknown
Definition: avcodec.h:1497
flags
#define flags(name, subs,...)
Definition: cbs_av1.c:565
av_bprint_chars
void av_bprint_chars(AVBPrint *buf, char c, unsigned n)
Append char c n times to a print buffer.
Definition: bprint.c:140
line
The official guide to swscale for confused that consecutive non overlapping rectangles of slice_bottom special converter These generally are unscaled converters of common like for each output line the vertical scaler pulls lines from a ring buffer When the ring buffer does not contain the wanted line
Definition: swscale.txt:40
avio_feof
int avio_feof(AVIOContext *s)
Similar to feof() but also returns nonzero on read errors.
Definition: aviobuf.c:358