[FFmpeg-devel,v2,1/2] avformat/dashenc: Added option for Segment file format

Submitted by kjeyapal@akamai.com on May 14, 2018, 6:11 a.m.

Details

Message ID 1526278285-32733-1-git-send-email-kjeyapal@akamai.com
State New
Headers show

Commit Message

kjeyapal@akamai.com May 14, 2018, 6:11 a.m.
From: Karthick Jeyapal <kjeyapal@akamai.com>

Right now segment file format is chosen to be either mp4 or webm based on the codec format.
This patch makes that choice configurable by the user, instead of being decided by the muxer.

Also with this change per-stream choice segment file format(based on codec type) is not possible.
All the output audio and video streams should be in the same file format.
---
 doc/muxers.texi       |  8 +++++++
 libavformat/dashenc.c | 66 +++++++++++++++++++++++++++++----------------------
 2 files changed, 46 insertions(+), 28 deletions(-)

Comments

Gyan May 14, 2018, 6:25 a.m.
On 5/14/2018 11:41 AM, Karthick J wrote:

> Right now segment file format is chosen to be either mp4 or webm based on the codec format.
> This patch makes that choice configurable by the user, instead of being decided by the muxer.

Can you update the docs to reflect on the differences between using the 
dash muxer for WebM and the webm_dash_manifest + webm_chunk muxers?

Thanks,
Gyan
kjeyapal@akamai.com May 14, 2018, 8:27 a.m.
On 5/14/18 11:55 AM, Gyan Doshi wrote:
>

>

> On 5/14/2018 11:41 AM, Karthick J wrote:

>

>> Right now segment file format is chosen to be either mp4 or webm based on the codec format.

>> This patch makes that choice configurable by the user, instead of being decided by the muxer.

>

> Can you update the docs to reflect on the differences between using the

> dash muxer for WebM and the webm_dash_manifest + webm_chunk muxers?

That's a good question. 
I have never worked/used webm_dash_manifest + webm_chunk muxer, and hence I don't know the difference.
If somebody knows the difference, then patches welcome (
>

> Thanks,

> Gyan

> _______________________________________________

> ffmpeg-devel mailing list

> ffmpeg-devel@ffmpeg.org

> http://ffmpeg.org/mailman/listinfo/ffmpeg-devel

Patch hide | download patch | download mbox

diff --git a/doc/muxers.texi b/doc/muxers.texi
index 57948cf..ea80296 100644
--- a/doc/muxers.texi
+++ b/doc/muxers.texi
@@ -284,6 +284,14 @@  corrects that index value.
 Typically this logic is needed in live streaming use cases. The network bandwidth
 fluctuations are common during long run streaming. Each fluctuation can cause
 the segment indexes fall behind the expected real time position.
+
+@item dash_segment_type @var{dash_segment_type}
+Possible values:
+@item mp4
+If this flag is set, the dash segment files will be in in ISOBMFF format. This is the default format.
+
+@item webm
+If this flag is set, the dash segment files will be in in WebM format.
 @end table
 
 @anchor{framecrc}
diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c
index 1dd6333..9a57ad1 100644
--- a/libavformat/dashenc.c
+++ b/libavformat/dashenc.c
@@ -48,6 +48,12 @@ 
 #include "vpcc.h"
 #include "dash.h"
 
+typedef enum {
+    SEGMENT_TYPE_MP4 = 0,
+    SEGMENT_TYPE_WEBM,
+    SEGMENT_TYPE_NB
+} SegmentType;
+
 typedef struct Segment {
     char file[1024];
     int64_t start_pos;
@@ -69,7 +75,6 @@  typedef struct OutputStream {
     AVFormatContext *ctx;
     int ctx_inited, as_idx;
     AVIOContext *out;
-    char format_name[8];
     int packets_written;
     char initfile[1024];
     int64_t init_start_pos, pos;
@@ -125,6 +130,8 @@  typedef struct DASHContext {
     int streaming;
     int64_t timeout;
     int index_correction;
+    SegmentType segment_type;
+    const char *format_name;
 } DASHContext;
 
 static struct codec_string {
@@ -138,6 +145,15 @@  static struct codec_string {
     { 0, NULL }
 };
 
+static struct format_string {
+    SegmentType segment_type;
+    const char *str;
+} formats[] = {
+    { SEGMENT_TYPE_MP4, "mp4" },
+    { SEGMENT_TYPE_WEBM, "webm" },
+    { 0, NULL }
+};
+
 static int dashenc_io_open(AVFormatContext *s, AVIOContext **pb, char *filename,
                            AVDictionary **options) {
     DASHContext *c = s->priv_data;
@@ -171,6 +187,14 @@  static void dashenc_io_close(AVFormatContext *s, AVIOContext **pb, char *filenam
     }
 }
 
+static const char *get_format_str(SegmentType segment_type) {
+    int i;
+    for (i = 0; i < SEGMENT_TYPE_NB; i++)
+        if (formats[i].segment_type == segment_type)
+            return formats[i].str;
+    return NULL;
+}
+
 static void set_vp9_codec_str(AVFormatContext *s, AVCodecParameters *par,
                               AVRational *frame_rate, char *str, int size) {
     VPCC vpcc;
@@ -581,13 +605,13 @@  static int write_adaptation_set(AVFormatContext *s, AVIOContext *out, int as_ind
         if (as->media_type == AVMEDIA_TYPE_VIDEO) {
             AVStream *st = s->streams[i];
             avio_printf(out, "\t\t\t<Representation id=\"%d\" mimeType=\"video/%s\" codecs=\"%s\"%s width=\"%d\" height=\"%d\"",
-                i, os->format_name, os->codec_str, bandwidth_str, s->streams[i]->codecpar->width, s->streams[i]->codecpar->height);
+                i, c->format_name, os->codec_str, bandwidth_str, s->streams[i]->codecpar->width, s->streams[i]->codecpar->height);
             if (st->avg_frame_rate.num)
                 avio_printf(out, " frameRate=\"%d/%d\"", st->avg_frame_rate.num, st->avg_frame_rate.den);
             avio_printf(out, ">\n");
         } else {
             avio_printf(out, "\t\t\t<Representation id=\"%d\" mimeType=\"audio/%s\" codecs=\"%s\"%s audioSamplingRate=\"%d\">\n",
-                i, os->format_name, os->codec_str, bandwidth_str, s->streams[i]->codecpar->sample_rate);
+                i, c->format_name, os->codec_str, bandwidth_str, s->streams[i]->codecpar->sample_rate);
             avio_printf(out, "\t\t\t\t<AudioChannelConfiguration schemeIdUri=\"urn:mpeg:dash:23003:3:audio_channel_configuration:2011\" value=\"%d\" />\n",
                 s->streams[i]->codecpar->channels);
         }
@@ -959,27 +983,10 @@  static int dash_init(AVFormatContext *s)
         if (!ctx)
             return AVERROR(ENOMEM);
 
-        // choose muxer based on codec: webm for VP8 and opus, mp4 otherwise
-        // note: os->format_name is also used as part of the mimetype of the
-        //       representation, e.g. video/<format_name>
-        if (s->streams[i]->codecpar->codec_id == AV_CODEC_ID_VP8 ||
-            s->streams[i]->codecpar->codec_id == AV_CODEC_ID_OPUS ||
-            s->streams[i]->codecpar->codec_id == AV_CODEC_ID_VORBIS) {
-            snprintf(os->format_name, sizeof(os->format_name), "webm");
-
-            if (s->strict_std_compliance > FF_COMPLIANCE_EXPERIMENTAL) {
-                av_log(s, AV_LOG_ERROR,
-                       "WebM support in dashenc is experimental and has not "
-                       "been validated. For testing purposes, make sure "
-                       "to add -strict experimental and override "
-                       "-init_seg_name and -media_seg_name to end with "
-                       "the extension 'webm'.\n");
-                return AVERROR(EINVAL);
-            }
-        } else {
-            snprintf(os->format_name, sizeof(os->format_name), "mp4");
-        }
-        ctx->oformat = av_guess_format(os->format_name, NULL, NULL);
+        c->format_name = get_format_str(c->segment_type);
+        if (!c->format_name)
+            return AVERROR_MUXER_NOT_FOUND;
+        ctx->oformat = av_guess_format(c->format_name, NULL, NULL);
         if (!ctx->oformat)
             return AVERROR_MUXER_NOT_FOUND;
         os->ctx = ctx;
@@ -1017,7 +1024,7 @@  static int dash_init(AVFormatContext *s)
         av_dict_free(&opts);
         os->init_start_pos = 0;
 
-        if (!strcmp(os->format_name, "mp4")) {
+        if (c->segment_type == SEGMENT_TYPE_MP4) {
             if (c->streaming)
                 av_dict_set(&opts, "movflags", "frag_every_frame+dash+delay_moov", 0);
             else
@@ -1082,7 +1089,7 @@  static int dash_write_header(AVFormatContext *s)
         // Flush init segment
         // Only for WebM segment, since for mp4 delay_moov is set and
         // the init segment is thus flushed after the first packets.
-        if (strcmp(os->format_name, "mp4") &&
+        if (c->segment_type == SEGMENT_TYPE_WEBM &&
             (ret = flush_init_segment(s, os)) < 0)
             return ret;
     }
@@ -1253,7 +1260,7 @@  static int dash_flush(AVFormatContext *s, int final, int stream)
         }
 
         if (!c->single_file) {
-            if (!strcmp(os->format_name, "mp4") && !os->written_len)
+            if (c->segment_type == SEGMENT_TYPE_MP4 && !os->written_len)
                 write_styp(os->ctx->pb);
         } else {
             snprintf(os->full_path, sizeof(os->full_path), "%s%s", c->dirname, os->initfile);
@@ -1443,7 +1450,7 @@  static int dash_write_packet(AVFormatContext *s, AVPacket *pkt)
     }
 
     //write out the data immediately in streaming mode
-    if (c->streaming && !strcmp(os->format_name, "mp4")) {
+    if (c->streaming && c->segment_type == SEGMENT_TYPE_MP4) {
         int len = 0;
         uint8_t *buf = NULL;
         if (!os->written_len)
@@ -1538,6 +1545,9 @@  static const AVOption options[] = {
     { "streaming", "Enable/Disable streaming mode of output. Each frame will be moof fragment", OFFSET(streaming), AV_OPT_TYPE_BOOL, { .i64 = 0 }, 0, 1, E },
     { "timeout", "set timeout for socket I/O operations", OFFSET(timeout), AV_OPT_TYPE_DURATION, { .i64 = -1 }, -1, INT_MAX, .flags = E },
     { "index_correction", "Enable/Disable segment index correction logic", OFFSET(index_correction), AV_OPT_TYPE_BOOL, { .i64 = 0 }, 0, 1, E },
+    { "dash_segment_type", "set dash segment files type", OFFSET(segment_type), AV_OPT_TYPE_INT, {.i64 = SEGMENT_TYPE_MP4 }, 0, SEGMENT_TYPE_NB - 1, E, "segment_type"},
+    { "mp4", "make segment file in ISOBMFF format", 0, AV_OPT_TYPE_CONST, {.i64 = SEGMENT_TYPE_MP4 }, 0, UINT_MAX,   E, "segment_type"},
+    { "webm", "make segment file in WebM format", 0, AV_OPT_TYPE_CONST, {.i64 = SEGMENT_TYPE_WEBM }, 0, UINT_MAX,   E, "segment_type"},
     { NULL },
 };