path: root/libavcodec/webvttdec.c (plain)
blob: 7b2d1750deb9959417cb8620f24b9a8cf2e5bfa2

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
82	static int webvtt_decode_frame(AVCodecContext *avctx,
83	void *data, int *got_sub_ptr, AVPacket *avpkt)
84	{
85	int ret = 0;
86	AVSubtitle *sub = data;
87	const char *ptr = avpkt->data;
88	FFASSDecoderContext *s = avctx->priv_data;
89	AVBPrint buf;
90
91	av_bprint_init(&buf, 0, AV_BPRINT_SIZE_UNLIMITED);
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
101	AVCodec ff_webvtt_decoder = {
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,
107	.init = ff_ass_subtitle_header_default,
108	.flush = ff_ass_decoder_flush,
109	.priv_data_size = sizeof(FFASSDecoderContext),
110	};
111