FFmpeg
webvttdec.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  * WebVTT subtitle decoder
24  * @see http://dev.w3.org/html5/webvtt/
25  * @todo need to support extended markups and cue settings
26  */
27 
28 #include "avcodec.h"
29 #include "ass.h"
30 #include "libavutil/bprint.h"
31 
32 static const struct {
33  const char *from;
34  const char *to;
35 } webvtt_tag_replace[] = {
36  {"<i>", "{\\i1}"}, {"</i>", "{\\i0}"},
37  {"<b>", "{\\b1}"}, {"</b>", "{\\b0}"},
38  {"<u>", "{\\u1}"}, {"</u>", "{\\u0}"},
39  {"{", "\\{"}, {"}", "\\}"}, // escape to avoid ASS markup conflicts
40  {"&gt;", ">"}, {"&lt;", "<"},
41  {"&lrm;", ""}, {"&rlm;", ""}, // FIXME: properly honor bidi marks
42  {"&amp;", "&"}, {"&nbsp;", "\\h"},
43 };
44 
45 static int webvtt_event_to_ass(AVBPrint *buf, const char *p)
46 {
47  int i, again = 0, skip = 0;
48 
49  while (*p) {
50 
51  for (i = 0; i < FF_ARRAY_ELEMS(webvtt_tag_replace); i++) {
52  const char *from = webvtt_tag_replace[i].from;
53  const size_t len = strlen(from);
54  if (!strncmp(p, from, len)) {
55  av_bprintf(buf, "%s", webvtt_tag_replace[i].to);
56  p += len;
57  again = 1;
58  break;
59  }
60  }
61  if (!*p)
62  break;
63 
64  if (again) {
65  again = 0;
66  skip = 0;
67  continue;
68  }
69  if (*p == '<')
70  skip = 1;
71  else if (*p == '>')
72  skip = 0;
73  else if (p[0] == '\n' && p[1])
74  av_bprintf(buf, "\\N");
75  else if (!skip && *p != '\r')
76  av_bprint_chars(buf, *p, 1);
77  p++;
78  }
79  return 0;
80 }
81 
83  void *data, int *got_sub_ptr, AVPacket *avpkt)
84 {
85  int ret = 0;
86  AVSubtitle *sub = data;
87  const char *ptr = avpkt->data;
89  AVBPrint buf;
90 
92  if (ptr && avpkt->size > 0 && !webvtt_event_to_ass(&buf, ptr))
93  ret = ff_ass_add_rect(sub, buf.str, s->readorder++, 0, NULL, NULL);
94  av_bprint_finalize(&buf, NULL);
95  if (ret < 0)
96  return ret;
97  *got_sub_ptr = sub->num_rects > 0;
98  return avpkt->size;
99 }
100 
102  .name = "webvtt",
103  .long_name = NULL_IF_CONFIG_SMALL("WebVTT subtitle"),
104  .type = AVMEDIA_TYPE_SUBTITLE,
105  .id = AV_CODEC_ID_WEBVTT,
106  .decode = webvtt_decode_frame,
108  .flush = ff_ass_decoder_flush,
109  .priv_data_size = sizeof(FFASSDecoderContext),
110 };
#define NULL
Definition: coverity.c:32
void av_bprintf(AVBPrint *buf, const char *fmt,...)
Definition: bprint.c:94
ptrdiff_t const GLvoid * data
Definition: opengl_enc.c:100
int size
Definition: avcodec.h:1483
unsigned num_rects
Definition: avcodec.h:3950
int ff_ass_add_rect(AVSubtitle *sub, const char *dialog, int readorder, int layer, const char *style, const char *speaker)
Add an ASS dialog to a subtitle.
Definition: ass.c:101
AVCodec.
Definition: avcodec.h:3494
int av_bprint_finalize(AVBPrint *buf, char **ret_str)
Finalize a print buffer.
Definition: bprint.c:235
int ff_ass_subtitle_header_default(AVCodecContext *avctx)
Generate a suitable AVCodecContext.subtitle_header for SUBTITLE_ASS with default style.
Definition: ass.c:80
uint8_t * data
Definition: avcodec.h:1482
const char * to
Definition: webvttdec.c:34
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:259
#define AV_BPRINT_SIZE_UNLIMITED
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
Definition: internal.h:186
void av_bprint_init(AVBPrint *buf, unsigned size_init, unsigned size_max)
Definition: bprint.c:69
const char * name
Name of the codec implementation.
Definition: avcodec.h:3501
#define s(width, name)
Definition: cbs_vp9.c:257
static int webvtt_event_to_ass(AVBPrint *buf, const char *p)
Definition: webvttdec.c:45
#define FF_ARRAY_ELEMS(a)
Libavcodec external API header.
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 again
main external API structure.
Definition: avcodec.h:1570
void * buf
Definition: avisynth_c.h:766
void ff_ass_decoder_flush(AVCodecContext *avctx)
Helper to flush a text subtitles decoder making use of the FFASSDecoderContext.
Definition: ass.c:124
static int webvtt_decode_frame(AVCodecContext *avctx, void *data, int *got_sub_ptr, AVPacket *avpkt)
Definition: webvttdec.c:82
AVCodec ff_webvtt_decoder
Definition: webvttdec.c:101
const char * from
Definition: webvttdec.c:33
void * priv_data
Definition: avcodec.h:1597
static const struct @205 webvtt_tag_replace[]
int len
This structure stores compressed data.
Definition: avcodec.h:1459
void av_bprint_chars(AVBPrint *buf, char c, unsigned n)
Append char c n times to a print buffer.
Definition: bprint.c:140