| 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 | * SAMI subtitle decoder |
| 24 | * @see http://msdn.microsoft.com/en-us/library/ms971327.aspx |
| 25 | */ |
| 26 | |
| 27 | #include "ass.h" |
| 28 | #include "libavutil/avstring.h" |
| 29 | #include "libavutil/bprint.h" |
| 30 | |
| 31 | typedef struct { |
| 32 | AVBPrint source; |
| 33 | AVBPrint content; |
| 34 | AVBPrint full; |
| 35 | } SAMIContext; |
| 36 | |
| 37 | static int sami_paragraph_to_ass(AVCodecContext *avctx, const char *src) |
| 38 | { |
| 39 | SAMIContext *sami = avctx->priv_data; |
| 40 | int ret = 0; |
| 41 | char *tag = NULL; |
| 42 | char *dupsrc = av_strdup(src); |
| 43 | char *p = dupsrc; |
| 44 | |
| 45 | av_bprint_clear(&sami->content); |
| 46 | for (;;) { |
| 47 | char *saveptr = NULL; |
| 48 | int prev_chr_is_space = 0; |
| 49 | AVBPrint *dst = &sami->content; |
| 50 | |
| 51 | /* parse & extract paragraph tag */ |
| 52 | p = av_stristr(p, "<P"); |
| 53 | if (!p) |
| 54 | break; |
| 55 | if (p[2] != '>' && !av_isspace(p[2])) { // avoid confusion with tags such as <PRE> |
| 56 | p++; |
| 57 | continue; |
| 58 | } |
| 59 | if (dst->len) // add a separator with the previous paragraph if there was one |
| 60 | av_bprintf(dst, "\\N"); |
| 61 | tag = av_strtok(p, ">", &saveptr); |
| 62 | if (!tag || !saveptr) |
| 63 | break; |
| 64 | p = saveptr; |
| 65 | |
| 66 | /* check if the current paragraph is the "source" (speaker name) */ |
| 67 | if (av_stristr(tag, "ID=Source") || av_stristr(tag, "ID=\"Source\"")) { |
| 68 | dst = &sami->source; |
| 69 | av_bprint_clear(dst); |
| 70 | } |
| 71 | |
| 72 | /* if empty event -> skip subtitle */ |
| 73 | while (av_isspace(*p)) |
| 74 | p++; |
| 75 | if (!strncmp(p, " ", 6)) { |
| 76 | ret = -1; |
| 77 | goto end; |
| 78 | } |
| 79 | |
| 80 | /* extract the text, stripping most of the tags */ |
| 81 | while (*p) { |
| 82 | if (*p == '<') { |
| 83 | if (!av_strncasecmp(p, "<P", 2) && (p[2] == '>' || av_isspace(p[2]))) |
| 84 | break; |
| 85 | if (!av_strncasecmp(p, "<BR", 3)) |
| 86 | av_bprintf(dst, "\\N"); |
| 87 | p++; |
| 88 | while (*p && *p != '>') |
| 89 | p++; |
| 90 | if (!*p) |
| 91 | break; |
| 92 | if (*p == '>') |
| 93 | p++; |
| 94 | } |
| 95 | if (!av_isspace(*p)) |
| 96 | av_bprint_chars(dst, *p, 1); |
| 97 | else if (!prev_chr_is_space) |
| 98 | av_bprint_chars(dst, ' ', 1); |
| 99 | prev_chr_is_space = av_isspace(*p); |
| 100 | p++; |
| 101 | } |
| 102 | } |
| 103 | |
| 104 | av_bprint_clear(&sami->full); |
| 105 | if (sami->source.len) |
| 106 | av_bprintf(&sami->full, "{\\i1}%s{\\i0}\\N", sami->source.str); |
| 107 | av_bprintf(&sami->full, "%s\r\n", sami->content.str); |
| 108 | |
| 109 | end: |
| 110 | av_free(dupsrc); |
| 111 | return ret; |
| 112 | } |
| 113 | |
| 114 | static int sami_decode_frame(AVCodecContext *avctx, |
| 115 | void *data, int *got_sub_ptr, AVPacket *avpkt) |
| 116 | { |
| 117 | AVSubtitle *sub = data; |
| 118 | const char *ptr = avpkt->data; |
| 119 | SAMIContext *sami = avctx->priv_data; |
| 120 | |
| 121 | if (ptr && avpkt->size > 0 && !sami_paragraph_to_ass(avctx, ptr)) { |
| 122 | int ts_start = av_rescale_q(avpkt->pts, avctx->time_base, (AVRational){1,100}); |
| 123 | int ts_duration = avpkt->duration != -1 ? |
| 124 | av_rescale_q(avpkt->duration, avctx->time_base, (AVRational){1,100}) : -1; |
| 125 | ff_ass_add_rect(sub, sami->full.str, ts_start, ts_duration, 0); |
| 126 | } |
| 127 | *got_sub_ptr = sub->num_rects > 0; |
| 128 | return avpkt->size; |
| 129 | } |
| 130 | |
| 131 | static av_cold int sami_init(AVCodecContext *avctx) |
| 132 | { |
| 133 | SAMIContext *sami = avctx->priv_data; |
| 134 | av_bprint_init(&sami->source, 0, 2048); |
| 135 | av_bprint_init(&sami->content, 0, 2048); |
| 136 | av_bprint_init(&sami->full, 0, 2048); |
| 137 | return ff_ass_subtitle_header_default(avctx); |
| 138 | } |
| 139 | |
| 140 | static av_cold int sami_close(AVCodecContext *avctx) |
| 141 | { |
| 142 | SAMIContext *sami = avctx->priv_data; |
| 143 | av_bprint_finalize(&sami->source, NULL); |
| 144 | av_bprint_finalize(&sami->content, NULL); |
| 145 | av_bprint_finalize(&sami->full, NULL); |
| 146 | return 0; |
| 147 | } |
| 148 | |
| 149 | AVCodec ff_sami_decoder = { |
| 150 | .name = "sami", |
| 151 | .long_name = NULL_IF_CONFIG_SMALL("SAMI subtitle"), |
| 152 | .type = AVMEDIA_TYPE_SUBTITLE, |
| 153 | .id = AV_CODEC_ID_SAMI, |
| 154 | .priv_data_size = sizeof(SAMIContext), |
| 155 | .init = sami_init, |
| 156 | .close = sami_close, |
| 157 | .decode = sami_decode_frame, |
| 158 | }; |