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

5 files changed, 62 insertions, 4 deletions

diff --git a/libavformat/assenc.c b/libavformat/assenc.c
index e378dc0e6c..f2e904a59e 100644
--- a/libavformat/assenc.c
+++ b/libavformat/assenc.c
@@ -20,9 +20,11 @@
  */
 
 #include "avformat.h"
+#include "internal.h"
 
 typedef struct ASSContext{
     unsigned int extra_index;
+    int write_ts; // 0: ssa (timing in payload), 1: ass (matroska like)
 }ASSContext;
 
 static int write_header(AVFormatContext *s)
@@ -31,10 +33,13 @@ static int write_header(AVFormatContext *s)
     AVCodecContext *avctx= s->streams[0]->codec;
     uint8_t *last= NULL;
 
-    if(s->nb_streams != 1 || avctx->codec_id != AV_CODEC_ID_SSA){
+    if (s->nb_streams != 1 || (avctx->codec_id != AV_CODEC_ID_SSA &&
+                               avctx->codec_id != AV_CODEC_ID_ASS)) {
         av_log(s, AV_LOG_ERROR, "Exactly one ASS/SSA stream is needed.\n");
         return -1;
     }
+    ass->write_ts = avctx->codec_id == AV_CODEC_ID_ASS;
+    avpriv_set_pts_info(s->streams[0], 64, 1, 100);
 
     while(ass->extra_index < avctx->extradata_size){
         uint8_t *p  = avctx->extradata + ass->extra_index;
@@ -57,7 +62,31 @@ static int write_header(AVFormatContext *s)
 
 static int write_packet(AVFormatContext *s, AVPacket *pkt)
 {
-    avio_write(s->pb, pkt->data, pkt->size);
+    ASSContext *ass = s->priv_data;
+
+    if (ass->write_ts) {
+        long int layer;
+        char *p;
+        int64_t start = pkt->pts;
+        int64_t end   = start + pkt->duration;
+        int hh1, mm1, ss1, ms1;
+        int hh2, mm2, ss2, ms2;
+
+        p = pkt->data + strcspn(pkt->data, ",") + 1; // skip ReadOrder
+        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;
+        avio_printf(s->pb, "Dialogue: %ld,%d:%02d:%02d.%02d,%d:%02d:%02d.%02d,%s\r\n",
+                    layer, hh1, mm1, ss1, ms1, hh2, mm2, ss2, ms2, p);
+    } else {
+        avio_write(s->pb, pkt->data, pkt->size);
+    }
     return 0;
 }
 
diff --git a/libavformat/matroska.c b/libavformat/matroska.c
index 09eecf20f6..ee57c1820a 100644
--- a/libavformat/matroska.c
+++ b/libavformat/matroska.c
@@ -61,10 +61,16 @@ const CodecTags ff_mkv_codec_tags[]={
     {"S_TEXT/UTF8"      , AV_CODEC_ID_TEXT},
     {"S_TEXT/UTF8"      , AV_CODEC_ID_SRT},
     {"S_TEXT/ASCII"     , AV_CODEC_ID_TEXT},
+#if FF_API_ASS_SSA
     {"S_TEXT/ASS"       , AV_CODEC_ID_SSA},
     {"S_TEXT/SSA"       , AV_CODEC_ID_SSA},
     {"S_ASS"            , AV_CODEC_ID_SSA},
     {"S_SSA"            , AV_CODEC_ID_SSA},
+#endif
+    {"S_TEXT/ASS"       , AV_CODEC_ID_ASS},
+    {"S_TEXT/SSA"       , AV_CODEC_ID_ASS},
+    {"S_ASS"            , AV_CODEC_ID_ASS},
+    {"S_SSA"            , AV_CODEC_ID_ASS},
     {"S_VOBSUB"         , AV_CODEC_ID_DVD_SUBTITLE},
     {"S_DVBSUB"         , AV_CODEC_ID_DVB_SUBTITLE},
     {"S_HDMV/PGS"       , AV_CODEC_ID_HDMV_PGS_SUBTITLE},
diff --git a/libavformat/matroskadec.c b/libavformat/matroskadec.c
index ad0401a857..c103dcebf4 100644
--- a/libavformat/matroskadec.c
+++ b/libavformat/matroskadec.c
@@ -1213,6 +1213,7 @@ static int matroska_decode_buffer(uint8_t** buf, int* buf_size,
     return result;
 }
 
+#if FF_API_ASS_SSA
 static void matroska_fix_ass_packet(MatroskaDemuxContext *matroska,
                                     AVPacket *pkt, uint64_t display_duration)
 {
@@ -1259,6 +1260,7 @@ static int matroska_merge_packets(AVPacket *out, AVPacket *in)
     av_free(in);
     return 0;
 }
+#endif
 
 static void matroska_convert_tag(AVFormatContext *s, EbmlList *list,
                                  AVDictionary **metadata, char *prefix)
@@ -1859,7 +1861,12 @@ static int matroska_read_header(AVFormatContext *s)
             st->need_parsing = AVSTREAM_PARSE_HEADERS;
         } else if (track->type == MATROSKA_TRACK_TYPE_SUBTITLE) {
             st->codec->codec_type = AVMEDIA_TYPE_SUBTITLE;
-            if (st->codec->codec_id == AV_CODEC_ID_SSA)
+#if FF_API_ASS_SSA
+            if (st->codec->codec_id == AV_CODEC_ID_SSA ||
+                st->codec->codec_id == AV_CODEC_ID_ASS)
+#else
+            if (st->codec->codec_id == AV_CODEC_ID_ASS)
+#endif
                 matroska->contains_ssa = 1;
         }
     }
@@ -2221,6 +2228,7 @@ static int matroska_parse_frame(MatroskaDemuxContext *matroska,
         pkt->duration = lace_duration;
     }
 
+#if FF_API_ASS_SSA
     if (st->codec->codec_id == AV_CODEC_ID_SSA)
         matroska_fix_ass_packet(matroska, pkt, lace_duration);
 
@@ -2234,6 +2242,10 @@ static int matroska_parse_frame(MatroskaDemuxContext *matroska,
         dynarray_add(&matroska->packets,&matroska->num_packets,pkt);
         matroska->prev_pkt = pkt;
     }
+#else
+    dynarray_add(&matroska->packets, &matroska->num_packets, pkt);
+    matroska->prev_pkt = pkt;
+#endif
 
     return 0;
 }
diff --git a/libavformat/matroskaenc.c b/libavformat/matroskaenc.c
index a151eef457..6726fd9812 100644
--- a/libavformat/matroskaenc.c
+++ b/libavformat/matroskaenc.c
@@ -1072,6 +1072,7 @@ static int ass_get_duration(const uint8_t *p)
     return end - start;
 }
 
+#if FF_API_ASS_SSA
 static int mkv_write_ass_blocks(AVFormatContext *s, AVIOContext *pb, AVPacket *pkt)
 {
     MatroskaMuxContext *mkv = s->priv_data;
@@ -1116,6 +1117,7 @@ static int mkv_write_ass_blocks(AVFormatContext *s, AVIOContext *pb, AVPacket *p
 
     return max_duration;
 }
+#endif
 
 static void mkv_write_block(AVFormatContext *s, AVIOContext *pb,
                             unsigned int blockid, AVPacket *pkt, int flags)
@@ -1236,8 +1238,10 @@ static int mkv_write_packet_internal(AVFormatContext *s, AVPacket *pkt)
 
     if (codec->codec_type != AVMEDIA_TYPE_SUBTITLE) {
         mkv_write_block(s, pb, MATROSKA_ID_SIMPLEBLOCK, pkt, keyframe << 7);
+#if FF_API_ASS_SSA
     } else if (codec->codec_id == AV_CODEC_ID_SSA) {
         duration = mkv_write_ass_blocks(s, pb, pkt);
+#endif
     } else if (codec->codec_id == AV_CODEC_ID_SRT) {
         duration = mkv_write_srt_blocks(s, pb, pkt);
     } else {
@@ -1418,7 +1422,11 @@ AVOutputFormat ff_matroska_muxer = {
          ff_codec_bmp_tags, ff_codec_wav_tags,
          additional_audio_tags, additional_video_tags, 0
     },
+#if FF_API_ASS_SSA
     .subtitle_codec    = AV_CODEC_ID_SSA,
+#else
+    .subtitle_codec    = AV_CODEC_ID_ASS,
+#endif
     .query_codec       = mkv_query_codec,
 };
 #endif
diff --git a/libavformat/version.h b/libavformat/version.h
index 8f9139ab71..8fd08cf032 100644
--- a/libavformat/version.h
+++ b/libavformat/version.h
@@ -30,7 +30,7 @@
 #include "libavutil/avutil.h"
 
 #define LIBAVFORMAT_VERSION_MAJOR 55
-#define LIBAVFORMAT_VERSION_MINOR  2
+#define LIBAVFORMAT_VERSION_MINOR  3
 #define LIBAVFORMAT_VERSION_MICRO 100
 
 #define LIBAVFORMAT_VERSION_INT AV_VERSION_INT(LIBAVFORMAT_VERSION_MAJOR, \
@@ -73,6 +73,9 @@
 #ifndef FF_API_READ_PACKET
 #define FF_API_READ_PACKET             (LIBAVFORMAT_VERSION_MAJOR < 56)
 #endif
+#ifndef FF_API_ASS_SSA
+#define FF_API_ASS_SSA                 (LIBAVFORMAT_VERSION_MAJOR < 56)
+#endif
 #ifndef FF_API_R_FRAME_RATE
 #define FF_API_R_FRAME_RATE            1
 #endif