ffmpeg/libavcodec/ass.c

223 lines
7.5 KiB
C
Raw Normal View History

/*
* SSA/ASS common functions
* Copyright (c) 2010 Aurelien Jacobs <aurel@gnuage.org>
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "avcodec.h"
#include "ass.h"
#include "libavutil/avassert.h"
2011-05-03 20:19:31 +02:00
#include "libavutil/avstring.h"
#include "libavutil/bprint.h"
#include "libavutil/common.h"
int ff_ass_subtitle_header(AVCodecContext *avctx,
const char *font, int font_size,
int color, int back_color,
int bold, int italic, int underline,
int alignment)
{
avctx->subtitle_header = av_asprintf(
"[Script Info]\r\n"
2014-10-11 18:37:43 +02:00
"; Script generated by FFmpeg/Lavc%s\r\n"
"ScriptType: v4.00+\r\n"
"PlayResX: 384\r\n"
"PlayResY: 288\r\n"
"\r\n"
"[V4+ Styles]\r\n"
/* ASSv4 header */
"Format: Name, "
"Fontname, Fontsize, "
"PrimaryColour, SecondaryColour, OutlineColour, BackColour, "
"Bold, Italic, Underline, StrikeOut, "
"ScaleX, ScaleY, "
"Spacing, Angle, "
"BorderStyle, Outline, Shadow, "
"Alignment, MarginL, MarginR, MarginV, "
"Encoding\r\n"
"Style: "
"Default," /* Name */
"%s,%d," /* Font{name,size} */
"&H%x,&H%x,&H%x,&H%x," /* {Primary,Secondary,Outline,Back}Colour */
"%d,%d,%d,0," /* Bold, Italic, Underline, StrikeOut */
"100,100," /* Scale{X,Y} */
"0,0," /* Spacing, Angle */
"1,1,0," /* BorderStyle, Outline, Shadow */
"%d,10,10,10," /* Alignment, Margin[LRV] */
"0\r\n" /* Encoding */
"\r\n"
"[Events]\r\n"
"Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text\r\n",
2014-10-11 18:37:43 +02:00
!(avctx->flags & CODEC_FLAG_BITEXACT) ? AV_STRINGIFY(LIBAVCODEC_VERSION) : "",
font, font_size, color, color, back_color, back_color,
-bold, -italic, -underline, alignment);
if (!avctx->subtitle_header)
return AVERROR(ENOMEM);
avctx->subtitle_header_size = strlen(avctx->subtitle_header);
return 0;
}
int ff_ass_subtitle_header_default(AVCodecContext *avctx)
{
return ff_ass_subtitle_header(avctx, ASS_DEFAULT_FONT,
ASS_DEFAULT_FONT_SIZE,
ASS_DEFAULT_COLOR,
ASS_DEFAULT_BACK_COLOR,
ASS_DEFAULT_BOLD,
ASS_DEFAULT_ITALIC,
ASS_DEFAULT_UNDERLINE,
ASS_DEFAULT_ALIGNMENT);
}
static void insert_ts(AVBPrint *buf, int ts)
{
if (ts == -1) {
av_bprintf(buf, "9:59:59.99,");
} else {
int h, m, s;
h = ts/360000; ts -= 360000*h;
m = ts/ 6000; ts -= 6000*m;
s = ts/ 100; ts -= 100*s;
av_bprintf(buf, "%d:%02d:%02d.%02d,", h, m, s, ts);
}
}
int ff_ass_bprint_dialog(AVBPrint *buf, const char *dialog,
int ts_start, int duration, int raw)
{
int dlen;
subtitles: introduce ASS codec id and use it. Currently, we have a AV_CODEC_ID_SSA, which matches the way the ASS/SSA markup is muxed in a standalone .ass/.ssa file. This means the AVPacket data starts with a "Dialogue:" string, followed by a timing information (start and end of the event as string) and a trailing CRLF after each line. One packet can contain several lines. We'll refer to this layout as "SSA" or "SSA lines". In matroska, this markup is not stored as such: it has no "Dialogue:" prefix, it contains a ReadOrder field, the timing information is not in the payload, and it doesn't contain the trailing CRLF. See [1] for more info. We'll refer to this layout as "ASS". Since we have only one common codec for both formats, the matroska demuxer is constructing an AVPacket following the "SSA lines" format. This causes several problems, so it was decided to change this into clean ASS packets. Some insight about what is changed or unchanged in this commit: CODECS ------ - the decoding process still writes "SSA lines" markup inside the ass fields of the subtitles rectangles (sub->rects[n]->ass), which is still the current common way of representing decoded subtitles markup. It is meant to change later. - new ASS codec id: AV_CODEC_ID_ASS (which is different from the legacy AV_CODEC_ID_SSA) - lavc/assdec: the "ass" decoder is renamed into "ssa" (instead of "ass") for consistency with the codec id and allows to add a real ass decoder. This ass decoder receives clean ASS lines (so it starts with a ReadOrder, is followed by the Layer, etc). We make sure this is decoded properly in a new ass-line rectangle of the decoded subtitles (the ssa decoder OTOH is doing a simple straightforward copy). Using the packet timing instead of data string makes sure the ass-line now contains the appropriate timing. - lavc/assenc: just like the ass decoder, the "ssa" encoder is renamed into "ssa" (instead of "ass") for consistency with the codec id, and allows to add a real "ass" encoder. One important thing about this encoder is that it only supports one ass rectangle: we could have put several dialogue events in the AVPacket (separated by a \0 for instance) but this would have cause trouble for the muxer which needs not only the start time, but also the duration: typically, you have merged events with the same start time (stored in the AVPacket->pts) but a different duration. At the moment, only the matroska do the merge with the SSA-line codec. We will need to make sure all the decoders in the future can't add more than one rectangle (and only one Dialogue line in it obviously). FORMATS ------- - lavf/assenc: the .ass/.ssa muxer can take both SSA and ASS packets. In the case of ASS packets as input, it adds the timing based on the AVPacket pts and duration, and mux it with "Dialogue:", trailing CRLF, etc. - lavf/assdec: unchanged; it currently still only outputs SSA-lines packets. - lavf/mkv: the demuxer can now output ASS packets without the need of any "SSA-lines" reconstruction hack. It will become the default at next libavformat bump, and the SSA support will be dropped from the demuxer. The muxer can take ASS packets since it's muxed normally, and still supports the old SSA packets. All the SSA support and hacks in Matroska code will be dropped at next lavf bump. [1]: http://www.matroska.org/technical/specs/subtitles/ssa.html
2013-01-03 03:06:43 +01:00
if (!raw || raw == 2) {
long int layer = 0;
if (raw == 2) {
/* skip ReadOrder */
dialog = strchr(dialog, ',');
if (!dialog)
return AVERROR_INVALIDDATA;
dialog++;
/* extract Layer or Marked */
layer = strtol(dialog, (char**)&dialog, 10);
if (*dialog != ',')
return AVERROR_INVALIDDATA;
dialog++;
}
av_bprintf(buf, "Dialogue: %ld,", layer);
insert_ts(buf, ts_start);
insert_ts(buf, duration == -1 ? -1 : ts_start + duration);
subtitles: introduce ASS codec id and use it. Currently, we have a AV_CODEC_ID_SSA, which matches the way the ASS/SSA markup is muxed in a standalone .ass/.ssa file. This means the AVPacket data starts with a "Dialogue:" string, followed by a timing information (start and end of the event as string) and a trailing CRLF after each line. One packet can contain several lines. We'll refer to this layout as "SSA" or "SSA lines". In matroska, this markup is not stored as such: it has no "Dialogue:" prefix, it contains a ReadOrder field, the timing information is not in the payload, and it doesn't contain the trailing CRLF. See [1] for more info. We'll refer to this layout as "ASS". Since we have only one common codec for both formats, the matroska demuxer is constructing an AVPacket following the "SSA lines" format. This causes several problems, so it was decided to change this into clean ASS packets. Some insight about what is changed or unchanged in this commit: CODECS ------ - the decoding process still writes "SSA lines" markup inside the ass fields of the subtitles rectangles (sub->rects[n]->ass), which is still the current common way of representing decoded subtitles markup. It is meant to change later. - new ASS codec id: AV_CODEC_ID_ASS (which is different from the legacy AV_CODEC_ID_SSA) - lavc/assdec: the "ass" decoder is renamed into "ssa" (instead of "ass") for consistency with the codec id and allows to add a real ass decoder. This ass decoder receives clean ASS lines (so it starts with a ReadOrder, is followed by the Layer, etc). We make sure this is decoded properly in a new ass-line rectangle of the decoded subtitles (the ssa decoder OTOH is doing a simple straightforward copy). Using the packet timing instead of data string makes sure the ass-line now contains the appropriate timing. - lavc/assenc: just like the ass decoder, the "ssa" encoder is renamed into "ssa" (instead of "ass") for consistency with the codec id, and allows to add a real "ass" encoder. One important thing about this encoder is that it only supports one ass rectangle: we could have put several dialogue events in the AVPacket (separated by a \0 for instance) but this would have cause trouble for the muxer which needs not only the start time, but also the duration: typically, you have merged events with the same start time (stored in the AVPacket->pts) but a different duration. At the moment, only the matroska do the merge with the SSA-line codec. We will need to make sure all the decoders in the future can't add more than one rectangle (and only one Dialogue line in it obviously). FORMATS ------- - lavf/assenc: the .ass/.ssa muxer can take both SSA and ASS packets. In the case of ASS packets as input, it adds the timing based on the AVPacket pts and duration, and mux it with "Dialogue:", trailing CRLF, etc. - lavf/assdec: unchanged; it currently still only outputs SSA-lines packets. - lavf/mkv: the demuxer can now output ASS packets without the need of any "SSA-lines" reconstruction hack. It will become the default at next libavformat bump, and the SSA support will be dropped from the demuxer. The muxer can take ASS packets since it's muxed normally, and still supports the old SSA packets. All the SSA support and hacks in Matroska code will be dropped at next lavf bump. [1]: http://www.matroska.org/technical/specs/subtitles/ssa.html
2013-01-03 03:06:43 +01:00
if (raw != 2)
av_bprintf(buf, "Default,,0,0,0,,");
}
dlen = strcspn(dialog, "\n");
dlen += dialog[dlen] == '\n';
av_bprintf(buf, "%.*s", dlen, dialog);
subtitles: introduce ASS codec id and use it. Currently, we have a AV_CODEC_ID_SSA, which matches the way the ASS/SSA markup is muxed in a standalone .ass/.ssa file. This means the AVPacket data starts with a "Dialogue:" string, followed by a timing information (start and end of the event as string) and a trailing CRLF after each line. One packet can contain several lines. We'll refer to this layout as "SSA" or "SSA lines". In matroska, this markup is not stored as such: it has no "Dialogue:" prefix, it contains a ReadOrder field, the timing information is not in the payload, and it doesn't contain the trailing CRLF. See [1] for more info. We'll refer to this layout as "ASS". Since we have only one common codec for both formats, the matroska demuxer is constructing an AVPacket following the "SSA lines" format. This causes several problems, so it was decided to change this into clean ASS packets. Some insight about what is changed or unchanged in this commit: CODECS ------ - the decoding process still writes "SSA lines" markup inside the ass fields of the subtitles rectangles (sub->rects[n]->ass), which is still the current common way of representing decoded subtitles markup. It is meant to change later. - new ASS codec id: AV_CODEC_ID_ASS (which is different from the legacy AV_CODEC_ID_SSA) - lavc/assdec: the "ass" decoder is renamed into "ssa" (instead of "ass") for consistency with the codec id and allows to add a real ass decoder. This ass decoder receives clean ASS lines (so it starts with a ReadOrder, is followed by the Layer, etc). We make sure this is decoded properly in a new ass-line rectangle of the decoded subtitles (the ssa decoder OTOH is doing a simple straightforward copy). Using the packet timing instead of data string makes sure the ass-line now contains the appropriate timing. - lavc/assenc: just like the ass decoder, the "ssa" encoder is renamed into "ssa" (instead of "ass") for consistency with the codec id, and allows to add a real "ass" encoder. One important thing about this encoder is that it only supports one ass rectangle: we could have put several dialogue events in the AVPacket (separated by a \0 for instance) but this would have cause trouble for the muxer which needs not only the start time, but also the duration: typically, you have merged events with the same start time (stored in the AVPacket->pts) but a different duration. At the moment, only the matroska do the merge with the SSA-line codec. We will need to make sure all the decoders in the future can't add more than one rectangle (and only one Dialogue line in it obviously). FORMATS ------- - lavf/assenc: the .ass/.ssa muxer can take both SSA and ASS packets. In the case of ASS packets as input, it adds the timing based on the AVPacket pts and duration, and mux it with "Dialogue:", trailing CRLF, etc. - lavf/assdec: unchanged; it currently still only outputs SSA-lines packets. - lavf/mkv: the demuxer can now output ASS packets without the need of any "SSA-lines" reconstruction hack. It will become the default at next libavformat bump, and the SSA support will be dropped from the demuxer. The muxer can take ASS packets since it's muxed normally, and still supports the old SSA packets. All the SSA support and hacks in Matroska code will be dropped at next lavf bump. [1]: http://www.matroska.org/technical/specs/subtitles/ssa.html
2013-01-03 03:06:43 +01:00
if (raw == 2)
av_bprintf(buf, "\r\n");
return dlen;
}
int ff_ass_add_rect(AVSubtitle *sub, const char *dialog,
int ts_start, int duration, int raw)
{
AVBPrint buf;
int ret, dlen;
AVSubtitleRect **rects;
av_bprint_init(&buf, 0, AV_BPRINT_SIZE_UNLIMITED);
if ((ret = ff_ass_bprint_dialog(&buf, dialog, ts_start, duration, raw)) < 0)
goto err;
dlen = ret;
if (!av_bprint_is_complete(&buf))
goto errnomem;
rects = av_realloc_array(sub->rects, (sub->num_rects+1), sizeof(*sub->rects));
if (!rects)
goto errnomem;
sub->rects = rects;
sub->end_display_time = FFMAX(sub->end_display_time, 10 * duration);
rects[sub->num_rects] = av_mallocz(sizeof(*rects[0]));
rects[sub->num_rects]->type = SUBTITLE_ASS;
ret = av_bprint_finalize(&buf, &rects[sub->num_rects]->ass);
if (ret < 0)
goto err;
sub->num_rects++;
return dlen;
errnomem:
ret = AVERROR(ENOMEM);
err:
av_bprint_finalize(&buf, NULL);
return ret;
}
int ff_ass_add_rect_bprint(AVSubtitle *sub, AVBPrint *buf,
int ts_start, int duration)
{
av_bprintf(buf, "\r\n");
if (!av_bprint_is_complete(buf))
return AVERROR(ENOMEM);
return ff_ass_add_rect(sub, buf->str, ts_start, duration, 0);
}
void ff_ass_bprint_text_event(AVBPrint *buf, const char *p, int size,
const char *linebreaks, int keep_ass_markup)
{
const char *p_end = p + size;
for (; p < p_end && *p; p++) {
/* forced custom line breaks, not accounted as "normal" EOL */
if (linebreaks && strchr(linebreaks, *p)) {
av_bprintf(buf, "\\N");
/* standard ASS escaping so random characters don't get mis-interpreted
* as ASS */
} else if (!keep_ass_markup && strchr("{}\\", *p)) {
av_bprintf(buf, "\\%c", *p);
/* some packets might end abruptly (no \0 at the end, like for example
* in some cases of demuxing from a classic video container), some
* might be terminated with \n or \r\n which we have to remove (for
* consistency with those who haven't), and we also have to deal with
* evil cases such as \r at the end of the buffer (and no \0 terminated
* character) */
} else if (p[0] == '\n') {
/* some stuff left so we can insert a line break */
if (p < p_end - 1)
av_bprintf(buf, "\\N");
} else if (p[0] == '\r' && p < p_end - 1 && p[1] == '\n') {
/* \r followed by a \n, we can skip it. We don't insert the \N yet
* because we don't know if it is followed by more text */
continue;
/* finally, a sane character */
} else {
av_bprint_chars(buf, *p, 1);
}
}
}