FFmpeg
realtextdec.c
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2012 Clément Bœsch
3  *
4  * This file is part of FFmpeg.
5  *
6  * FFmpeg is free software; you can redistribute it and/or
7  * modify it under the terms of the GNU Lesser General Public
8  * License as published by the Free Software Foundation; either
9  * version 2.1 of the License, or (at your option) any later version.
10  *
11  * FFmpeg is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14  * Lesser General Public License for more details.
15  *
16  * You should have received a copy of the GNU Lesser General Public
17  * License along with FFmpeg; if not, write to the Free Software
18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19  */
20 
21 /**
22  * @file
23  * RealText subtitle demuxer
24  * @see http://service.real.com/help/library/guides/ProductionGuide/prodguide/htmfiles/realtext.htm
25  */
26 
27 #include "avformat.h"
28 #include "demux.h"
29 #include "internal.h"
30 #include "subtitles.h"
31 #include "libavutil/avstring.h"
32 #include "libavutil/bprint.h"
33 #include "libavutil/mem.h"
34 
35 typedef struct {
38 
39 static int realtext_probe(const AVProbeData *p)
40 {
41  char buf[7];
42  FFTextReader tr;
43  ff_text_init_buf(&tr, p->buf, p->buf_size);
44  ff_text_read(&tr, buf, sizeof(buf));
45 
46  return !av_strncasecmp(buf, "<window", 7) ? AVPROBE_SCORE_EXTENSION : 0;
47 }
48 
49 static int64_t read_ts(const char *s)
50 {
51  int hh, mm, ss, ms;
52 
53  if (sscanf(s, "%u:%u:%u.%u", &hh, &mm, &ss, &ms) == 4) return (hh*3600LL + mm*60LL + ss) * 100LL + ms;
54  if (sscanf(s, "%u:%u:%u" , &hh, &mm, &ss ) == 3) return (hh*3600LL + mm*60LL + ss) * 100LL;
55  if (sscanf(s, "%u:%u.%u", &mm, &ss, &ms) == 3) return ( mm*60LL + ss) * 100LL + ms;
56  if (sscanf(s, "%u:%u" , &mm, &ss ) == 2) return ( mm*60LL + ss) * 100LL;
57  if (sscanf(s, "%u.%u", &ss, &ms) == 2) return ( ss) * 100LL + ms;
58  return strtoll(s, NULL, 10) * 100ULL;
59 }
60 
62 {
63  RealTextContext *rt = s->priv_data;
65  AVBPrint buf;
66  char c = 0;
67  int res = 0, duration = read_ts("60"); // default duration is 60 seconds
68  FFTextReader tr;
69  ff_text_init_avio(s, &tr, s->pb);
70 
71  if (!st)
72  return AVERROR(ENOMEM);
73  avpriv_set_pts_info(st, 64, 1, 100);
76 
78 
79  while (!ff_text_eof(&tr)) {
80  AVPacket *sub;
81  const int64_t pos = ff_text_pos(&tr) - (c != 0);
82  int n = ff_smil_extract_next_text_chunk(&tr, &buf, &c);
83 
84  if (n < 0) {
85  res = n;
86  goto end;
87  }
88  if (n == 0)
89  break;
90 
91  if (!av_strncasecmp(buf.str, "<window", 7)) {
92  /* save header to extradata */
93  const char *p = ff_smil_get_attr_ptr(buf.str, "duration");
94 
95  if (st->codecpar->extradata) {
96  res = AVERROR_INVALIDDATA;
97  goto end;
98  }
99  if (p)
100  duration = read_ts(p);
101  st->codecpar->extradata = av_strdup(buf.str);
102  if (!st->codecpar->extradata) {
103  res = AVERROR(ENOMEM);
104  goto end;
105  }
106  st->codecpar->extradata_size = buf.len + 1;
107  } else {
108  /* if we just read a <time> tag, introduce a new event, otherwise merge
109  * with the previous one */
110  int merge = !av_strncasecmp(buf.str, "<time", 5) ? 0 : 1;
111  sub = ff_subtitles_queue_insert_bprint(&rt->q, &buf, merge);
112  if (!sub) {
113  res = AVERROR(ENOMEM);
114  goto end;
115  }
116  if (!merge) {
117  const char *begin = ff_smil_get_attr_ptr(buf.str, "begin");
118  const char *end = ff_smil_get_attr_ptr(buf.str, "end");
119  int64_t endi = end ? read_ts(end) : 0;
120 
121  sub->pos = pos;
122  sub->pts = begin ? read_ts(begin) : 0;
123  sub->duration = (end && endi > sub->pts && endi - (uint64_t)sub->pts <= INT64_MAX) ? endi - sub->pts : duration;
124  }
125  }
126  av_bprint_clear(&buf);
127  }
129 
130 end:
131  av_bprint_finalize(&buf, NULL);
132  return res;
133 }
134 
136  .p.name = "realtext",
137  .p.long_name = NULL_IF_CONFIG_SMALL("RealText subtitle format"),
138  .p.extensions = "rt",
139  .priv_data_size = sizeof(RealTextContext),
140  .flags_internal = FF_INFMT_FLAG_INIT_CLEANUP,
144  .read_seek2 = ff_subtitles_read_seek,
146 };
AVMEDIA_TYPE_SUBTITLE
@ AVMEDIA_TYPE_SUBTITLE
Definition: avutil.h:204
ff_subtitles_read_close
int ff_subtitles_read_close(AVFormatContext *s)
Definition: subtitles.c:345
AV_BPRINT_SIZE_UNLIMITED
#define AV_BPRINT_SIZE_UNLIMITED
AVCodecParameters::extradata
uint8_t * extradata
Extra binary data needed for initializing the decoder, codec-dependent.
Definition: codec_par.h:69
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
AVCodecParameters::codec_type
enum AVMediaType codec_type
General type of the encoded data.
Definition: codec_par.h:51
ff_smil_extract_next_text_chunk
int ff_smil_extract_next_text_chunk(FFTextReader *tr, AVBPrint *buf, char *c)
SMIL helper to load next chunk ("<...>" or untagged content) in buf.
Definition: subtitles.c:352
av_bprint_init
void av_bprint_init(AVBPrint *buf, unsigned size_init, unsigned size_max)
Definition: bprint.c:69
avformat_new_stream
AVStream * avformat_new_stream(AVFormatContext *s, const struct AVCodec *c)
Add a new stream to a media file.
merge
static void merge(GetBitContext *gb, uint8_t *dst, uint8_t *src, int size)
Merge two consequent lists of equal size depending on bits read.
Definition: bink.c:221
realtext_probe
static int realtext_probe(const AVProbeData *p)
Definition: realtextdec.c:39
read_ts
static int64_t read_ts(const char *s)
Definition: realtextdec.c:49
AVPacket::duration
int64_t duration
Duration of this packet in AVStream->time_base units, 0 if unknown.
Definition: packet.h:542
FFTextReader
Definition: subtitles.h:41
AVProbeData::buf_size
int buf_size
Size of buf except extra allocated bytes.
Definition: avformat.h:454
avpriv_set_pts_info
void avpriv_set_pts_info(AVStream *st, int pts_wrap_bits, unsigned int pts_num, unsigned int pts_den)
Set the time base and wrapping info for a given stream.
Definition: avformat.c:853
read_close
static av_cold int read_close(AVFormatContext *ctx)
Definition: libcdio.c:143
ss
#define ss(width, name, subs,...)
Definition: cbs_vp9.c:202
ff_subtitles_read_packet
int ff_subtitles_read_packet(AVFormatContext *s, AVPacket *pkt)
Definition: subtitles.c:331
duration
int64_t duration
Definition: movenc.c:65
read_packet
static int read_packet(void *opaque, uint8_t *buf, int buf_size)
Definition: avio_read_callback.c:42
s
#define s(width, name)
Definition: cbs_vp9.c:198
AVInputFormat::name
const char * name
A comma separated list of short names for the format.
Definition: avformat.h:553
AVProbeData::buf
unsigned char * buf
Buffer must have AVPROBE_PADDING_SIZE of extra allocated bytes filled with zero.
Definition: avformat.h:453
RealTextContext
Definition: realtextdec.c:35
FF_INFMT_FLAG_INIT_CLEANUP
#define FF_INFMT_FLAG_INIT_CLEANUP
For an FFInputFormat with this flag set read_close() needs to be called by the caller upon read_heade...
Definition: demux.h:35
AVFormatContext
Format I/O context.
Definition: avformat.h:1255
internal.h
ff_text_read
void ff_text_read(FFTextReader *r, char *buf, size_t size)
Read the given number of bytes (in UTF-8).
Definition: subtitles.c:86
AVStream::codecpar
AVCodecParameters * codecpar
Codec parameters associated with this stream.
Definition: avformat.h:766
read_header
static int read_header(FFV1Context *f)
Definition: ffv1dec.c:550
NULL
#define NULL
Definition: coverity.c:32
RealTextContext::q
FFDemuxSubtitlesQueue q
Definition: realtextdec.c:36
AVProbeData
This structure contains the data a format has to probe a file.
Definition: avformat.h:451
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
AVPROBE_SCORE_EXTENSION
#define AVPROBE_SCORE_EXTENSION
score for file extension
Definition: avformat.h:461
AVCodecParameters::extradata_size
int extradata_size
Size of the extradata content in bytes.
Definition: codec_par.h:73
ff_text_init_avio
void ff_text_init_avio(void *s, FFTextReader *r, AVIOContext *pb)
Initialize the FFTextReader from the given AVIOContext.
Definition: subtitles.c:28
av_strncasecmp
int av_strncasecmp(const char *a, const char *b, size_t n)
Locale-independent case-insensitive compare.
Definition: avstring.c:217
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:94
av_bprint_finalize
int av_bprint_finalize(AVBPrint *buf, char **ret_str)
Finalize a print buffer.
Definition: bprint.c:240
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:212
FFDemuxSubtitlesQueue
Definition: subtitles.h:103
FFInputFormat::p
AVInputFormat p
The public AVInputFormat.
Definition: demux.h:41
ff_realtext_demuxer
const FFInputFormat ff_realtext_demuxer
Definition: realtextdec.c:135
ff_subtitles_queue_insert_bprint
AVPacket * ff_subtitles_queue_insert_bprint(FFDemuxSubtitlesQueue *q, const AVBPrint *event, int merge)
Same as ff_subtitles_queue_insert but takes an AVBPrint input.
Definition: subtitles.c:156
bprint.h
AVPacket::pts
int64_t pts
Presentation timestamp in AVStream->time_base units; the time at which the decompressed packet will b...
Definition: packet.h:517
ff_text_pos
int64_t ff_text_pos(FFTextReader *r)
Return the byte position of the next byte returned by ff_text_r8().
Definition: subtitles.c:60
ff_subtitles_read_seek
int ff_subtitles_read_seek(AVFormatContext *s, int stream_index, int64_t min_ts, int64_t ts, int64_t max_ts, int flags)
Definition: subtitles.c:337
demux.h
AVStream
Stream structure.
Definition: avformat.h:743
pos
unsigned int pos
Definition: spdifenc.c:414
avformat.h
subtitles.h
av_bprint_clear
void av_bprint_clear(AVBPrint *buf)
Reset the string to "" but keep internal allocated data.
Definition: bprint.c:232
ff_text_init_buf
void ff_text_init_buf(FFTextReader *r, const void *buf, size_t size)
Similar to ff_text_init_avio(), but sets it up to read from a bounded buffer.
Definition: subtitles.c:54
av_strdup
char * av_strdup(const char *s)
Duplicate a string.
Definition: mem.c:272
read_probe
static int read_probe(const AVProbeData *p)
Definition: cdg.c:30
mem.h
ff_text_eof
int ff_text_eof(FFTextReader *r)
Return non-zero if EOF was reached.
Definition: subtitles.c:92
realtext_read_header
static int realtext_read_header(AVFormatContext *s)
Definition: realtextdec.c:61
AVCodecParameters::codec_id
enum AVCodecID codec_id
Specific type of the encoded data (the codec used).
Definition: codec_par.h:55
AVPacket
This structure stores compressed data.
Definition: packet.h:501
AVPacket::pos
int64_t pos
byte position in stream, -1 if unknown
Definition: packet.h:544
FFInputFormat
Definition: demux.h:37
AVERROR_INVALIDDATA
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:61
avstring.h
AV_CODEC_ID_REALTEXT
@ AV_CODEC_ID_REALTEXT
Definition: codec_id.h:563
ff_smil_get_attr_ptr
const char * ff_smil_get_attr_ptr(const char *s, const char *attr)
SMIL helper to point on the value of an attribute in the given tag.
Definition: subtitles.c:377