libavcodec/webvttdec.c

   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 "codec_internal.h"
  31 #include "libavutil/bprint.h"
  32
  33 static const struct {
  34     const char *from;
  35     const char *to;
  36 } webvtt_tag_replace[] = {
  37     {"<i>", "{\\i1}"}, {"</i>", "{\\i0}"},
  38     {"<b>", "{\\b1}"}, {"</b>", "{\\b0}"},
  39     {"<u>", "{\\u1}"}, {"</u>", "{\\u0}"},
  40     {"{", "\\{{}"}, {"\\", "\\\xe2\x81\xa0"}, // escape to avoid ASS markup conflicts
  41     {"&gt;", ">"}, {"&lt;", "<"},
  42     {"&lrm;", "\xe2\x80\x8e"}, {"&rlm;", "\xe2\x80\x8f"},
  43     {"&amp;", "&"}, {"&nbsp;", "\\h"},
  44 };
  45
  46 static int webvtt_event_to_ass(AVBPrint *buf, const char *p)
  47 {
  48     int i, again = 0, skip = 0;
  49
  50     while (*p) {
  51
  52         for (i = 0; i < FF_ARRAY_ELEMS(webvtt_tag_replace); i++) {
  53             const char *from = webvtt_tag_replace[i].from;
  54             const size_t len = strlen(from);
  55             if (!strncmp(p, from, len)) {
  56                 av_bprintf(buf, "%s", webvtt_tag_replace[i].to);
  57                 p += len;
  58                 again = 1;
  59                 break;
  60             }
  61         }
  62         if (!*p)
  63             break;
  64
  65         if (again) {
  66             again = 0;
  67             skip = 0;
  68             continue;
  69         }
  70         if (*p == '<')
  71             skip = 1;
  72         else if (*p == '>')
  73             skip = 0;
  74         else if (p[0] == '\n' && p[1])
  75             av_bprintf(buf, "\\N");
  76         else if (!skip && *p != '\r')
  77             av_bprint_chars(buf, *p, 1);
  78         p++;
  79     }
  80     return 0;
  81 }
  82
  83 static int webvtt_decode_frame(AVCodecContext *avctx, AVSubtitle *sub,
  84                                int *got_sub_ptr, const AVPacket *avpkt)
  85 {
  86     int ret = 0;
  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 const FFCodec ff_webvtt_decoder = {
 102     .p.name         = "webvtt",
 103     CODEC_LONG_NAME("WebVTT subtitle"),
 104     .p.type         = AVMEDIA_TYPE_SUBTITLE,
 105     .p.id           = AV_CODEC_ID_WEBVTT,
 106     FF_CODEC_DECODE_SUB_CB(webvtt_decode_frame),
 107     .init           = ff_ass_subtitle_header_default,
 108     .flush          = ff_ass_decoder_flush,
 109     .priv_data_size = sizeof(FFASSDecoderContext),
 110 };