1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-23 12:43:46 +02:00
FFmpeg/libavformat/assenc.c

242 lines
7.5 KiB
C
Raw Normal View History

/*
* SSA/ASS muxer
* Copyright (c) 2008 Michael Niedermayer
*
* 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
*/
2014-09-13 22:06:16 +03:00
#include "libavutil/avstring.h"
#include "avformat.h"
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 05:06:43 +03:00
#include "internal.h"
#include "libavutil/opt.h"
2014-09-13 22:06:16 +03:00
typedef struct DialogueLine {
int readorder;
char *line;
struct DialogueLine *prev, *next;
} DialogueLine;
typedef struct ASSContext {
const AVClass *class;
2014-09-13 22:06:16 +03:00
int expected_readorder;
DialogueLine *dialogue_cache;
DialogueLine *last_added_dialogue;
int cache_size;
int ssa_mode;
int ignore_readorder;
uint8_t *trailer;
size_t trailer_size;
} ASSContext;
static int write_header(AVFormatContext *s)
{
ASSContext *ass = s->priv_data;
lavf: replace AVStream.codec with AVStream.codecpar Currently, AVStream contains an embedded AVCodecContext instance, which is used by demuxers to export stream parameters to the caller and by muxers to receive stream parameters from the caller. It is also used internally as the codec context that is passed to parsers. In addition, it is also widely used by the callers as the decoding (when demuxer) or encoding (when muxing) context, though this has been officially discouraged since Libav 11. There are multiple important problems with this approach: - the fields in AVCodecContext are in general one of * stream parameters * codec options * codec state However, it's not clear which ones are which. It is consequently unclear which fields are a demuxer allowed to set or a muxer allowed to read. This leads to erratic behaviour depending on whether decoding or encoding is being performed or not (and whether it uses the AVStream embedded codec context). - various synchronization issues arising from the fact that the same context is used by several different APIs (muxers/demuxers, parsers, bitstream filters and encoders/decoders) simultaneously, with there being no clear rules for who can modify what and the different processes being typically delayed with respect to each other. - avformat_find_stream_info() making it necessary to support opening and closing a single codec context multiple times, thus complicating the semantics of freeing various allocated objects in the codec context. Those problems are resolved by replacing the AVStream embedded codec context with a newly added AVCodecParameters instance, which stores only the stream parameters exported by the demuxers or read by the muxers.
2014-06-18 21:42:52 +03:00
AVCodecParameters *par = s->streams[0]->codecpar;
if (s->nb_streams != 1 || par->codec_id != AV_CODEC_ID_ASS) {
av_log(s, AV_LOG_ERROR, "Exactly one ASS/SSA stream is needed.\n");
return AVERROR(EINVAL);
}
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 05:06:43 +03:00
avpriv_set_pts_info(s->streams[0], 64, 1, 100);
if (par->extradata_size > 0) {
size_t header_size = par->extradata_size;
uint8_t *trailer = strstr(par->extradata, "\n[Events]");
if (trailer)
trailer = strstr(trailer, "Format:");
if (trailer)
trailer = strstr(trailer, "\n");
if (trailer++) {
header_size = (trailer - par->extradata);
ass->trailer_size = par->extradata_size - header_size;
if (ass->trailer_size)
ass->trailer = trailer;
}
avio_write(s->pb, par->extradata, header_size);
if (par->extradata[header_size - 1] != '\n')
avio_write(s->pb, "\r\n", 2);
ass->ssa_mode = !strstr(par->extradata, "\n[V4+ Styles]");
if (!strstr(par->extradata, "\n[Events]"))
avio_printf(s->pb, "[Events]\r\nFormat: %s, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text\r\n",
ass->ssa_mode ? "Marked" : "Layer");
}
return 0;
}
2014-09-13 22:06:16 +03:00
static void purge_dialogues(AVFormatContext *s, int force)
{
int n = 0;
ASSContext *ass = s->priv_data;
DialogueLine *dialogue = ass->dialogue_cache;
while (dialogue && (dialogue->readorder == ass->expected_readorder || force)) {
DialogueLine *next = dialogue->next;
if (dialogue->readorder != ass->expected_readorder) {
av_log(s, AV_LOG_WARNING, "ReadOrder gap found between %d and %d\n",
ass->expected_readorder, dialogue->readorder);
ass->expected_readorder = dialogue->readorder;
}
avio_print(s->pb, "Dialogue: ", dialogue->line, "\r\n");
2014-09-13 22:06:16 +03:00
if (dialogue == ass->last_added_dialogue)
ass->last_added_dialogue = next;
av_freep(&dialogue->line);
2014-09-13 22:06:16 +03:00
av_free(dialogue);
if (next)
next->prev = NULL;
dialogue = ass->dialogue_cache = next;
ass->expected_readorder++;
n++;
}
ass->cache_size -= n;
if (n > 1)
av_log(s, AV_LOG_DEBUG, "wrote %d ASS lines, cached dialogues: %d, waiting for event id %d\n",
n, ass->cache_size, ass->expected_readorder);
}
static void insert_dialogue(ASSContext *ass, DialogueLine *dialogue)
{
DialogueLine *cur, *next = NULL, *prev = NULL;
/* from the last added to the end of the list */
if (ass->last_added_dialogue) {
for (cur = ass->last_added_dialogue; cur; cur = cur->next) {
if (cur->readorder > dialogue->readorder)
break;
prev = cur;
next = cur->next;
}
}
/* from the beginning to the last one added */
if (!prev) {
next = ass->dialogue_cache;
for (cur = next; cur != ass->last_added_dialogue; cur = cur->next) {
if (cur->readorder > dialogue->readorder)
break;
prev = cur;
next = cur->next;
}
}
if (prev) {
prev->next = dialogue;
dialogue->prev = prev;
} else {
dialogue->prev = ass->dialogue_cache;
ass->dialogue_cache = dialogue;
}
if (next) {
next->prev = dialogue;
dialogue->next = next;
}
ass->cache_size++;
ass->last_added_dialogue = dialogue;
}
static int write_packet(AVFormatContext *s, AVPacket *pkt)
{
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 05:06:43 +03:00
ASSContext *ass = s->priv_data;
long int layer;
char *p = pkt->data;
int64_t start = pkt->pts;
int64_t end = start + pkt->duration;
int hh1, mm1, ss1, ms1;
int hh2, mm2, ss2, ms2;
DialogueLine *dialogue = av_mallocz(sizeof(*dialogue));
if (!dialogue)
return AVERROR(ENOMEM);
dialogue->readorder = strtol(p, &p, 10);
if (dialogue->readorder < ass->expected_readorder)
av_log(s, AV_LOG_WARNING, "Unexpected ReadOrder %d\n",
dialogue->readorder);
if (*p == ',')
p++;
if (ass->ssa_mode && !strncmp(p, "Marked=", 7))
p += 7;
layer = strtol(p, &p, 10);
if (*p == ',')
p++;
hh1 = (int)(start / 360000); mm1 = (int)(start / 6000) % 60;
hh2 = (int)(end / 360000); mm2 = (int)(end / 6000) % 60;
ss1 = (int)(start / 100) % 60; ms1 = (int)(start % 100);
ss2 = (int)(end / 100) % 60; ms2 = (int)(end % 100);
if (hh1 > 9) hh1 = 9, mm1 = 59, ss1 = 59, ms1 = 99;
if (hh2 > 9) hh2 = 9, mm2 = 59, ss2 = 59, ms2 = 99;
dialogue->line = av_asprintf("%s%ld,%d:%02d:%02d.%02d,%d:%02d:%02d.%02d,%s",
ass->ssa_mode ? "Marked=" : "",
layer, hh1, mm1, ss1, ms1, hh2, mm2, ss2, ms2, p);
if (!dialogue->line) {
av_free(dialogue);
return AVERROR(ENOMEM);
}
insert_dialogue(ass, dialogue);
purge_dialogues(s, ass->ignore_readorder);
return 0;
}
static int write_trailer(AVFormatContext *s)
{
ASSContext *ass = s->priv_data;
2014-09-13 22:06:16 +03:00
purge_dialogues(s, 1);
if (ass->trailer) {
avio_write(s->pb, ass->trailer, ass->trailer_size);
}
return 0;
}
#define OFFSET(x) offsetof(ASSContext, x)
#define E AV_OPT_FLAG_ENCODING_PARAM
static const AVOption options[] = {
{ "ignore_readorder", "write events immediately, even if they're out-of-order", OFFSET(ignore_readorder), AV_OPT_TYPE_BOOL, {.i64 = 0}, 0, 1, E },
{ NULL },
};
static const AVClass ass_class = {
.class_name = "ass muxer",
.item_name = av_default_item_name,
.option = options,
.version = LIBAVUTIL_VERSION_INT,
};
AVOutputFormat ff_ass_muxer = {
.name = "ass",
.long_name = NULL_IF_CONFIG_SMALL("SSA (SubStation Alpha) subtitle"),
2014-09-14 21:55:36 +03:00
.mime_type = "text/x-ass",
.extensions = "ass,ssa",
.priv_data_size = sizeof(ASSContext),
2014-09-14 21:55:36 +03:00
.subtitle_codec = AV_CODEC_ID_ASS,
.write_header = write_header,
.write_packet = write_packet,
.write_trailer = write_trailer,
.flags = AVFMT_GLOBALHEADER | AVFMT_NOTIMESTAMPS | AVFMT_TS_NONSTRICT,
.priv_class = &ass_class,
};