| Message ID | 1563160264-131104-1-git-send-email-leozhang@qiyi.com |
|---|---|
| State | Superseded |
| Headers | show |
Let me add that, descriptor provides extensible syntax and semantics for describing Adaptation Set properties. In my scenario，I implemented one VR tiled video system using descriptor. leozhang <leozhang@qiyi.com> 于2019年7月15日周一 上午11:11写道： > > change history: > 1. remove unnecessary cast. > 2. add some braces. > > Please comment, Thanks > > Signed-off-by: leozhang <leozhang@qiyi.com> > --- > doc/muxers.texi | 3 +++ > libavformat/dashenc.c | 35 ++++++++++++++++++++++++++++++++--- > 2 files changed, 35 insertions(+), 3 deletions(-) > > diff --git a/doc/muxers.texi b/doc/muxers.texi > index b109297..ac06ad2 100644 > --- a/doc/muxers.texi > +++ b/doc/muxers.texi > @@ -275,6 +275,9 @@ of the adaptation sets and a,b,c,d and e are the indices of the mapped streams. > To map all video (or audio) streams to an AdaptationSet, "v" (or "a") can be used as stream identifier instead of IDs. > > When no assignment is defined, this defaults to an AdaptationSet for each stream. > + > +Optional syntax is "id=x,descriptor=descriptor_str,streams=a,b,c id=y,streams=d,e" and so on, descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015. > +And descriptor_str must be a properly formatted XML element, which is encoded by base64. > @item timeout @var{timeout} > Set timeout for socket I/O operations. Applicable only for HTTP output. > @item index_correction @var{index_correction} > diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c > index b25afb4..a48031c 100644 > --- a/libavformat/dashenc.c > +++ b/libavformat/dashenc.c > @@ -34,6 +34,7 @@ > #include "libavutil/rational.h" > #include "libavutil/time.h" > #include "libavutil/time_internal.h" > +#include "libavutil/base64.h" > > #include "avc.h" > #include "avformat.h" > @@ -68,6 +69,7 @@ typedef struct Segment { > > typedef struct AdaptationSet { > char id[10]; > + char descriptor[1024]; > enum AVMediaType media_type; > AVDictionary *metadata; > AVRational min_frame_rate, max_frame_rate; > @@ -748,7 +750,8 @@ static int write_adaptation_set(AVFormatContext *s, AVIOContext *out, int as_ind > role = av_dict_get(as->metadata, "role", NULL, 0); > if (role) > avio_printf(out, "\t\t\t<Role schemeIdUri=\"urn:mpeg:dash:role:2011\" value=\"%s\"/>\n", role->value); > - > + if (strlen(as->descriptor)) > + avio_printf(out, "\t\t\t%s\n", as->descriptor); > for (i = 0; i < s->nb_streams; i++) { > OutputStream *os = &c->streams[i]; > char bandwidth_str[64] = {'\0'}; > @@ -820,7 +823,7 @@ static int parse_adaptation_sets(AVFormatContext *s) > { > DASHContext *c = s->priv_data; > const char *p = c->adaptation_sets; > - enum { new_set, parse_id, parsing_streams } state; > + enum { new_set, parse_id, parsing_streams, parse_descriptor } state; > AdaptationSet *as; > int i, n, ret; > > @@ -837,6 +840,9 @@ static int parse_adaptation_sets(AVFormatContext *s) > } > > // syntax id=0,streams=0,1,2 id=1,streams=3,4 and so on > + // option id=0,descriptor=descriptor_str,streams=0,1,2 and so on > + // descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015 > + // descriptor_str must be a properly formatted XML element, encoded by base64. > state = new_set; > while (*p) { > if (*p == ' ') { > @@ -854,7 +860,30 @@ static int parse_adaptation_sets(AVFormatContext *s) > if (*p) > p++; > state = parse_id; > - } else if (state == parse_id && av_strstart(p, "streams=", &p)) { > + } else if (state == parse_id && av_strstart(p, "descriptor=", &p)) { > + char *encode_str, *decode_str; > + int decode_size, ret; > + > + n = strcspn(p, ","); > + encode_str = av_strndup(p, n); > + decode_size = AV_BASE64_DECODE_SIZE(n); > + decode_str = av_mallocz(decode_size); > + if (decode_str) { > + ret = av_base64_decode(decode_str, encode_str, decode_size); > + if (ret >= 0) > + snprintf(as->descriptor, sizeof(as->descriptor), "%.*s", decode_size, decode_str); > + else > + av_log(s, AV_LOG_WARNING, "descriptor string is invalid base64 encode\n"); > + } else { > + av_log(s, AV_LOG_WARNING, "av_mallocz failed, will not parse descriptor\n"); > + } > + p += n; > + if (*p) > + p++; > + state = parse_descriptor; > + av_freep(&encode_str); > + av_freep(&decode_str); > + } else if ((state == parse_id || state == parse_descriptor) && av_strstart(p, "streams=", &p)) { //descriptor is optional > state = parsing_streams; > } else if (state == parsing_streams) { > AdaptationSet *as = &c->as[c->nb_as - 1]; > -- > 1.8.3.1 > > _______________________________________________ > ffmpeg-devel mailing list > ffmpeg-devel@ffmpeg.org > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel > > To unsubscribe, visit link above, or email > ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
On 7/15/19 8:41 AM, leozhang wrote: > change history: > 1. remove unnecessary cast. > 2. add some braces. > > Please comment, Thanks Thanks for sending the patch. Please find some of my comments inlined below. > > Signed-off-by: leozhang <leozhang@qiyi.com> > --- > doc/muxers.texi | 3 +++ > libavformat/dashenc.c | 35 ++++++++++++++++++++++++++++++++--- > 2 files changed, 35 insertions(+), 3 deletions(-) > > diff --git a/doc/muxers.texi b/doc/muxers.texi > index b109297..ac06ad2 100644 > --- a/doc/muxers.texi > +++ b/doc/muxers.texi > @@ -275,6 +275,9 @@ of the adaptation sets and a,b,c,d and e are the indices of the mapped streams. > To map all video (or audio) streams to an AdaptationSet, "v" (or "a") can be used as stream identifier instead of IDs. > > When no assignment is defined, this defaults to an AdaptationSet for each stream. > + > +Optional syntax is "id=x,descriptor=descriptor_str,streams=a,b,c id=y,streams=d,e" and so on, descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015. > +And descriptor_str must be a properly formatted XML element, which is encoded by base64. Two comments: 1. Please provide an example here. So that it is easier for people to understand 2. Why do we need this to be base64 encoded? What is the use-case where a normal string doesn't work? > @item timeout @var{timeout} > Set timeout for socket I/O operations. Applicable only for HTTP output. > @item index_correction @var{index_correction} > diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c > index b25afb4..a48031c 100644 > --- a/libavformat/dashenc.c > +++ b/libavformat/dashenc.c > @@ -34,6 +34,7 @@ > #include "libavutil/rational.h" > #include "libavutil/time.h" > #include "libavutil/time_internal.h" > +#include "libavutil/base64.h" > > #include "avc.h" > #include "avformat.h" > @@ -68,6 +69,7 @@ typedef struct Segment { > > typedef struct AdaptationSet { > char id[10]; > + char descriptor[1024]; Please change this char * and allocate it dynamically. I understand there are some legacy code in dashenc using this 1024 length. But at least new code should follow dynamic allocation. > enum AVMediaType media_type; > AVDictionary *metadata; > AVRational min_frame_rate, max_frame_rate; > @@ -748,7 +750,8 @@ static int write_adaptation_set(AVFormatContext *s, AVIOContext *out, int as_ind > role = av_dict_get(as->metadata, "role", NULL, 0); > if (role) > avio_printf(out, "\t\t\t<Role schemeIdUri=\"urn:mpeg:dash:role:2011\" value=\"%s\"/>\n", role->value); > - > + if (strlen(as->descriptor)) > + avio_printf(out, "\t\t\t%s\n", as->descriptor); > for (i = 0; i < s->nb_streams; i++) { > OutputStream *os = &c->streams[i]; > char bandwidth_str[64] = {'\0'}; > @@ -820,7 +823,7 @@ static int parse_adaptation_sets(AVFormatContext *s) > { > DASHContext *c = s->priv_data; > const char *p = c->adaptation_sets; > - enum { new_set, parse_id, parsing_streams } state; > + enum { new_set, parse_id, parsing_streams, parse_descriptor } state; > AdaptationSet *as; > int i, n, ret; > > @@ -837,6 +840,9 @@ static int parse_adaptation_sets(AVFormatContext *s) > } > > // syntax id=0,streams=0,1,2 id=1,streams=3,4 and so on > + // option id=0,descriptor=descriptor_str,streams=0,1,2 and so on > + // descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015 > + // descriptor_str must be a properly formatted XML element, encoded by base64. > state = new_set; > while (*p) { > if (*p == ' ') { > @@ -854,7 +860,30 @@ static int parse_adaptation_sets(AVFormatContext *s) > if (*p) > p++; > state = parse_id; > - } else if (state == parse_id && av_strstart(p, "streams=", &p)) { > + } else if (state == parse_id && av_strstart(p, "descriptor=", &p)) { > + char *encode_str, *decode_str; > + int decode_size, ret; > + > + n = strcspn(p, ","); > + encode_str = av_strndup(p, n); > + decode_size = AV_BASE64_DECODE_SIZE(n); > + decode_str = av_mallocz(decode_size); > + if (decode_str) { > + ret = av_base64_decode(decode_str, encode_str, decode_size); > + if (ret >= 0) > + snprintf(as->descriptor, sizeof(as->descriptor), "%.*s", decode_size, decode_str); > + else > + av_log(s, AV_LOG_WARNING, "descriptor string is invalid base64 encode\n"); > + } else { > + av_log(s, AV_LOG_WARNING, "av_mallocz failed, will not parse descriptor\n"); > + } > + p += n; > + if (*p) > + p++; > + state = parse_descriptor; > + av_freep(&encode_str); > + av_freep(&decode_str); > + } else if ((state == parse_id || state == parse_descriptor) && av_strstart(p, "streams=", &p)) { //descriptor is optional > state = parsing_streams; > } else if (state == parsing_streams) { > AdaptationSet *as = &c->as[c->nb_as - 1]; Regards, Karthick
Jeyapal, Karthick <kjeyapal@akamai.com> 于2019年7月17日周三 上午10:46写道： > > > On 7/15/19 8:41 AM, leozhang wrote: > > change history: > > 1. remove unnecessary cast. > > 2. add some braces. > > > > Please comment, Thanks > Thanks for sending the patch. Please find some of my comments inlined below. Thanks for your comments. I made some changes below. Please review it, thanks. > > > > Signed-off-by: leozhang <leozhang@qiyi.com> > > --- > > doc/muxers.texi | 3 +++ > > libavformat/dashenc.c | 35 ++++++++++++++++++++++++++++++++--- > > 2 files changed, 35 insertions(+), 3 deletions(-) > > > > diff --git a/doc/muxers.texi b/doc/muxers.texi > > index b109297..ac06ad2 100644 > > --- a/doc/muxers.texi > > +++ b/doc/muxers.texi > > @@ -275,6 +275,9 @@ of the adaptation sets and a,b,c,d and e are the indices of the mapped streams. > > To map all video (or audio) streams to an AdaptationSet, "v" (or "a") can be used as stream identifier instead of IDs. > > > > When no assignment is defined, this defaults to an AdaptationSet for each stream. > > + > > +Optional syntax is "id=x,descriptor=descriptor_str,streams=a,b,c id=y,streams=d,e" and so on, descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015. > > +And descriptor_str must be a properly formatted XML element, which is encoded by base64. > Two comments: > 1. Please provide an example here. So that it is easier for people to understand For the instance using descriptor in VR tiled video application， this short interesting video https://www.hhi.fraunhofer.de/en/departments/vca/research-groups/multimedia-communications/research-topics/mpeg-omaf.html is more intuitive than a textual description. Then, how DASH pack media data in tile based streaming? Refer ISO/IEC 23009-1:2014/Amd.2:2015, for example, the descriptor string <SupplementalProperty schemeIdUri="urn:mpeg:dash:srd:2014" value="0,0,0,1,1,2,2"/> indicates that AdaptationSet is the top-left corner tile of full video divided into 2x2 tiles. Finally, how to use FFmpeg DASH muxer to generate the tile based streaming? We split the video by NxN tiles, insert descriptor syntax together with AdaptationSet in MPD. For example, the pseudo ffmpeg command {-adaptation_sets "id=0,descriptor=PFN1cHBsZW1lbnRhbFByb3BlcnR5IHNjaGVtZUlkVXJpPSJ1cm46bXBlZzpkYXNoOnNyZDoyMDE0IiB2YWx1ZT0iMCwwLDAsMSwxLDIsMiIvPg==,streams=v"} will insert descriptor string <SupplementalProperty schemeIdUri="urn:mpeg:dash:srd:2014" value="0,0,0,1,1,2,2"/> like below <!-- top-left tile of the full video divided into 2x2 tiles --> <AdaptationSet segmentAlignment="true" subsegmentAlignment="true" subsegmentStartsWithSAP="1"> <SupplementalProperty schemeIdUri="urn:mpeg:dash:srd:2014" value="0,0,0,1,1,2,2"/> <Representation mimeType="video/mp4" codecs="avc1.42c00d" width="640" height="360" bandwidth="218284" startWithSAP="1"> ... </Representation> </AdaptationSet> In addition to VR applications, zoomed video part can also be indicated by descriptor. > 2. Why do we need this to be base64 encoded? What is the use-case where a normal string doesn't work? The parser code used comma and space as separator. The unencrypted descriptor string like <SupplementalProperty schemeIdUri="urn:mpeg:dash:srd:2014" value="0,0,0,1,1,2,2"/> contains comma and space, which disturbs the normal parse result. > > @item timeout @var{timeout} > > Set timeout for socket I/O operations. Applicable only for HTTP output. > > @item index_correction @var{index_correction} > > diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c > > index b25afb4..a48031c 100644 > > --- a/libavformat/dashenc.c > > +++ b/libavformat/dashenc.c > > @@ -34,6 +34,7 @@ > > #include "libavutil/rational.h" > > #include "libavutil/time.h" > > #include "libavutil/time_internal.h" > > +#include "libavutil/base64.h" > > > > #include "avc.h" > > #include "avformat.h" > > @@ -68,6 +69,7 @@ typedef struct Segment { > > > > typedef struct AdaptationSet { > > char id[10]; > > + char descriptor[1024]; > Please change this char * and allocate it dynamically. I understand there are some legacy code in dashenc using this 1024 length. > But at least new code should follow dynamic allocation. Agree, will fix it > > enum AVMediaType media_type; > > AVDictionary *metadata; > > AVRational min_frame_rate, max_frame_rate; > > @@ -748,7 +750,8 @@ static int write_adaptation_set(AVFormatContext *s, AVIOContext *out, int as_ind > > role = av_dict_get(as->metadata, "role", NULL, 0); > > if (role) > > avio_printf(out, "\t\t\t<Role schemeIdUri=\"urn:mpeg:dash:role:2011\" value=\"%s\"/>\n", role->value); > > - > > + if (strlen(as->descriptor)) > > + avio_printf(out, "\t\t\t%s\n", as->descriptor); > > for (i = 0; i < s->nb_streams; i++) { > > OutputStream *os = &c->streams[i]; > > char bandwidth_str[64] = {'\0'}; > > @@ -820,7 +823,7 @@ static int parse_adaptation_sets(AVFormatContext *s) > > { > > DASHContext *c = s->priv_data; > > const char *p = c->adaptation_sets; > > - enum { new_set, parse_id, parsing_streams } state; > > + enum { new_set, parse_id, parsing_streams, parse_descriptor } state; > > AdaptationSet *as; > > int i, n, ret; > > > > @@ -837,6 +840,9 @@ static int parse_adaptation_sets(AVFormatContext *s) > > } > > > > // syntax id=0,streams=0,1,2 id=1,streams=3,4 and so on > > + // option id=0,descriptor=descriptor_str,streams=0,1,2 and so on > > + // descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015 > > + // descriptor_str must be a properly formatted XML element, encoded by base64. > > state = new_set; > > while (*p) { > > if (*p == ' ') { > > @@ -854,7 +860,30 @@ static int parse_adaptation_sets(AVFormatContext *s) > > if (*p) > > p++; > > state = parse_id; > > - } else if (state == parse_id && av_strstart(p, "streams=", &p)) { > > + } else if (state == parse_id && av_strstart(p, "descriptor=", &p)) { > > + char *encode_str, *decode_str; > > + int decode_size, ret; > > + > > + n = strcspn(p, ","); > > + encode_str = av_strndup(p, n); > > + decode_size = AV_BASE64_DECODE_SIZE(n); > > + decode_str = av_mallocz(decode_size); > > + if (decode_str) { > > + ret = av_base64_decode(decode_str, encode_str, decode_size); > > + if (ret >= 0) > > + snprintf(as->descriptor, sizeof(as->descriptor), "%.*s", decode_size, decode_str); > > + else > > + av_log(s, AV_LOG_WARNING, "descriptor string is invalid base64 encode\n"); > > + } else { > > + av_log(s, AV_LOG_WARNING, "av_mallocz failed, will not parse descriptor\n"); > > + } > > + p += n; > > + if (*p) > > + p++; > > + state = parse_descriptor; > > + av_freep(&encode_str); > > + av_freep(&decode_str); > > + } else if ((state == parse_id || state == parse_descriptor) && av_strstart(p, "streams=", &p)) { //descriptor is optional > > state = parsing_streams; > > } else if (state == parsing_streams) { > > AdaptationSet *as = &c->as[c->nb_as - 1]; > Regards, > Karthick > > _______________________________________________ > ffmpeg-devel mailing list > ffmpeg-devel@ffmpeg.org > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel > > To unsubscribe, visit link above, or email > ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
On 7/17/19 10:21 AM, Tao Zhang wrote: > Jeyapal, Karthick <kjeyapal@akamai.com> 于2019年7月17日周三 上午10:46写道： >> >> >> On 7/15/19 8:41 AM, leozhang wrote: >>> change history: >>> 1. remove unnecessary cast. >>> 2. add some braces. >>> >>> Please comment, Thanks >> Thanks for sending the patch. Please find some of my comments inlined below. > Thanks for your comments. I made some changes below. Please review it, thanks. >>> >>> Signed-off-by: leozhang <leozhang@qiyi.com> >>> --- >>> doc/muxers.texi | 3 +++ >>> libavformat/dashenc.c | 35 ++++++++++++++++++++++++++++++++--- >>> 2 files changed, 35 insertions(+), 3 deletions(-) >>> >>> diff --git a/doc/muxers.texi b/doc/muxers.texi >>> index b109297..ac06ad2 100644 >>> --- a/doc/muxers.texi >>> +++ b/doc/muxers.texi >>> @@ -275,6 +275,9 @@ of the adaptation sets and a,b,c,d and e are the indices of the mapped streams. >>> To map all video (or audio) streams to an AdaptationSet, "v" (or "a") can be used as stream identifier instead of IDs. >>> >>> When no assignment is defined, this defaults to an AdaptationSet for each stream. >>> + >>> +Optional syntax is "id=x,descriptor=descriptor_str,streams=a,b,c id=y,streams=d,e" and so on, descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015. >>> +And descriptor_str must be a properly formatted XML element, which is encoded by base64. >> Two comments: >> 1. Please provide an example here. So that it is easier for people to understand > For the instance using descriptor in VR tiled video application， > this short interesting video > https://www.hhi.fraunhofer.de/en/departments/vca/research-groups/multimedia-communications/research-topics/mpeg-omaf.html > is more intuitive than a textual description. > Then, how DASH pack media data in tile based streaming? > Refer ISO/IEC 23009-1:2014/Amd.2:2015, for example, the descriptor > string <SupplementalProperty schemeIdUri="urn:mpeg:dash:srd:2014" > value="0,0,0,1,1,2,2"/> indicates that AdaptationSet is > the top-left corner tile of full video divided into 2x2 tiles. > Finally, how to use FFmpeg DASH muxer to generate the tile based streaming? > We split the video by NxN tiles, insert descriptor syntax together > with AdaptationSet in MPD. > For example, the pseudo ffmpeg command {-adaptation_sets > "id=0,descriptor=PFN1cHBsZW1lbnRhbFByb3BlcnR5IHNjaGVtZUlkVXJpPSJ1cm46bXBlZzpkYXNoOnNyZDoyMDE0IiB2YWx1ZT0iMCwwLDAsMSwxLDIsMiIvPg==,streams=v"} > will > insert descriptor string <SupplementalProperty > schemeIdUri="urn:mpeg:dash:srd:2014" value="0,0,0,1,1,2,2"/> like > below > <!-- top-left tile of the full video divided into 2x2 tiles --> > <AdaptationSet segmentAlignment="true" subsegmentAlignment="true" > subsegmentStartsWithSAP="1"> > <SupplementalProperty schemeIdUri="urn:mpeg:dash:srd:2014" > value="0,0,0,1,1,2,2"/> > <Representation mimeType="video/mp4" codecs="avc1.42c00d" > width="640" height="360" bandwidth="218284" startWithSAP="1"> > ... > </Representation> > </AdaptationSet> > > In addition to VR applications, zoomed video part can also be > indicated by descriptor. Thanks for the detailed explanation. Please add the following/similar line to muxers.texi For example, -adaptation_sets "id=0,descriptor=<SupplementalProperty schemeIdUri="urn:mpeg:dash:srd:2014" value="0,0,0,1,1,2,2"/>,streams=v" >> 2. Why do we need this to be base64 encoded? What is the use-case where a normal string doesn't work? > The parser code used comma and space as separator. The unencrypted > descriptor string like <SupplementalProperty > schemeIdUri="urn:mpeg:dash:srd:2014" value="0,0,0,1,1,2,2"/> contains > comma and space, which disturbs the normal parse result. Space is used as separator, only outside the if..else.. conditions. So, it won't count for spaces inside the descriptor string. Regarding comma separator you can change the logic for descriptor alone, as the relevant code is anyways inside an "else if" for descriptor. You can look for ''>" symbol as the terminating char, instead of looking for a separator. Also add a note in muxers.texi mentioning that descriptor string should be a self-closing xml tag. It is easier for users to send a self-closing xml tag as a command line input, rather than a base64 encoded string. >>> @item timeout @var{timeout} >>> Set timeout for socket I/O operations. Applicable only for HTTP output. >>> @item index_correction @var{index_correction} >>> diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c >>> index b25afb4..a48031c 100644 >>> --- a/libavformat/dashenc.c >>> +++ b/libavformat/dashenc.c >>> @@ -34,6 +34,7 @@ >>> #include "libavutil/rational.h" >>> #include "libavutil/time.h" >>> #include "libavutil/time_internal.h" >>> +#include "libavutil/base64.h" >>> >>> #include "avc.h" >>> #include "avformat.h" >>> @@ -68,6 +69,7 @@ typedef struct Segment { >>> >>> typedef struct AdaptationSet { >>> char id[10]; >>> + char descriptor[1024]; >> Please change this char * and allocate it dynamically. I understand there are some legacy code in dashenc using this 1024 length. >> But at least new code should follow dynamic allocation. > Agree, will fix it >>> enum AVMediaType media_type; >>> AVDictionary *metadata; >>> AVRational min_frame_rate, max_frame_rate; >>> @@ -748,7 +750,8 @@ static int write_adaptation_set(AVFormatContext *s, AVIOContext *out, int as_ind >>> role = av_dict_get(as->metadata, "role", NULL, 0); >>> if (role) >>> avio_printf(out, "\t\t\t<Role schemeIdUri=\"urn:mpeg:dash:role:2011\" value=\"%s\"/>\n", role->value); >>> - >>> + if (strlen(as->descriptor)) >>> + avio_printf(out, "\t\t\t%s\n", as->descriptor); >>> for (i = 0; i < s->nb_streams; i++) { >>> OutputStream *os = &c->streams[i]; >>> char bandwidth_str[64] = {'\0'}; >>> @@ -820,7 +823,7 @@ static int parse_adaptation_sets(AVFormatContext *s) >>> { >>> DASHContext *c = s->priv_data; >>> const char *p = c->adaptation_sets; >>> - enum { new_set, parse_id, parsing_streams } state; >>> + enum { new_set, parse_id, parsing_streams, parse_descriptor } state; >>> AdaptationSet *as; >>> int i, n, ret; >>> >>> @@ -837,6 +840,9 @@ static int parse_adaptation_sets(AVFormatContext *s) >>> } >>> >>> // syntax id=0,streams=0,1,2 id=1,streams=3,4 and so on >>> + // option id=0,descriptor=descriptor_str,streams=0,1,2 and so on >>> + // descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015 >>> + // descriptor_str must be a properly formatted XML element, encoded by base64. >>> state = new_set; >>> while (*p) { >>> if (*p == ' ') { >>> @@ -854,7 +860,30 @@ static int parse_adaptation_sets(AVFormatContext *s) >>> if (*p) >>> p++; >>> state = parse_id; >>> - } else if (state == parse_id && av_strstart(p, "streams=", &p)) { >>> + } else if (state == parse_id && av_strstart(p, "descriptor=", &p)) { >>> + char *encode_str, *decode_str; >>> + int decode_size, ret; >>> + >>> + n = strcspn(p, ","); >>> + encode_str = av_strndup(p, n); >>> + decode_size = AV_BASE64_DECODE_SIZE(n); >>> + decode_str = av_mallocz(decode_size); >>> + if (decode_str) { >>> + ret = av_base64_decode(decode_str, encode_str, decode_size); >>> + if (ret >= 0) >>> + snprintf(as->descriptor, sizeof(as->descriptor), "%.*s", decode_size, decode_str); >>> + else >>> + av_log(s, AV_LOG_WARNING, "descriptor string is invalid base64 encode\n"); >>> + } else { >>> + av_log(s, AV_LOG_WARNING, "av_mallocz failed, will not parse descriptor\n"); >>> + } >>> + p += n; >>> + if (*p) >>> + p++; >>> + state = parse_descriptor; >>> + av_freep(&encode_str); >>> + av_freep(&decode_str); >>> + } else if ((state == parse_id || state == parse_descriptor) && av_strstart(p, "streams=", &p)) { //descriptor is optional >>> state = parsing_streams; >>> } else if (state == parsing_streams) { >>> AdaptationSet *as = &c->as[c->nb_as - 1]; >> Regards, >> Karthick >> >> _______________________________________________ >> ffmpeg-devel mailing list >> ffmpeg-devel@ffmpeg.org >> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel >> >> To unsubscribe, visit link above, or email >> ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe". > _______________________________________________ > ffmpeg-devel mailing list > ffmpeg-devel@ffmpeg.org > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel > > To unsubscribe, visit link above, or email > ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
diff --git a/doc/muxers.texi b/doc/muxers.texi index b109297..ac06ad2 100644 --- a/doc/muxers.texi +++ b/doc/muxers.texi @@ -275,6 +275,9 @@ of the adaptation sets and a,b,c,d and e are the indices of the mapped streams. To map all video (or audio) streams to an AdaptationSet, "v" (or "a") can be used as stream identifier instead of IDs. When no assignment is defined, this defaults to an AdaptationSet for each stream. + +Optional syntax is "id=x,descriptor=descriptor_str,streams=a,b,c id=y,streams=d,e" and so on, descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015. +And descriptor_str must be a properly formatted XML element, which is encoded by base64. @item timeout @var{timeout} Set timeout for socket I/O operations. Applicable only for HTTP output. @item index_correction @var{index_correction} diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c index b25afb4..a48031c 100644 --- a/libavformat/dashenc.c +++ b/libavformat/dashenc.c @@ -34,6 +34,7 @@ #include "libavutil/rational.h" #include "libavutil/time.h" #include "libavutil/time_internal.h" +#include "libavutil/base64.h" #include "avc.h" #include "avformat.h" @@ -68,6 +69,7 @@ typedef struct Segment { typedef struct AdaptationSet { char id[10]; + char descriptor[1024]; enum AVMediaType media_type; AVDictionary *metadata; AVRational min_frame_rate, max_frame_rate; @@ -748,7 +750,8 @@ static int write_adaptation_set(AVFormatContext *s, AVIOContext *out, int as_ind role = av_dict_get(as->metadata, "role", NULL, 0); if (role) avio_printf(out, "\t\t\t<Role schemeIdUri=\"urn:mpeg:dash:role:2011\" value=\"%s\"/>\n", role->value); - + if (strlen(as->descriptor)) + avio_printf(out, "\t\t\t%s\n", as->descriptor); for (i = 0; i < s->nb_streams; i++) { OutputStream *os = &c->streams[i]; char bandwidth_str[64] = {'\0'}; @@ -820,7 +823,7 @@ static int parse_adaptation_sets(AVFormatContext *s) { DASHContext *c = s->priv_data; const char *p = c->adaptation_sets; - enum { new_set, parse_id, parsing_streams } state; + enum { new_set, parse_id, parsing_streams, parse_descriptor } state; AdaptationSet *as; int i, n, ret; @@ -837,6 +840,9 @@ static int parse_adaptation_sets(AVFormatContext *s) } // syntax id=0,streams=0,1,2 id=1,streams=3,4 and so on + // option id=0,descriptor=descriptor_str,streams=0,1,2 and so on + // descriptor is useful to the scheme defined by ISO/IEC 23009-1:2014/Amd.2:2015 + // descriptor_str must be a properly formatted XML element, encoded by base64. state = new_set; while (*p) { if (*p == ' ') { @@ -854,7 +860,30 @@ static int parse_adaptation_sets(AVFormatContext *s) if (*p) p++; state = parse_id; - } else if (state == parse_id && av_strstart(p, "streams=", &p)) { + } else if (state == parse_id && av_strstart(p, "descriptor=", &p)) { + char *encode_str, *decode_str; + int decode_size, ret; + + n = strcspn(p, ","); + encode_str = av_strndup(p, n); + decode_size = AV_BASE64_DECODE_SIZE(n); + decode_str = av_mallocz(decode_size); + if (decode_str) { + ret = av_base64_decode(decode_str, encode_str, decode_size); + if (ret >= 0) + snprintf(as->descriptor, sizeof(as->descriptor), "%.*s", decode_size, decode_str); + else + av_log(s, AV_LOG_WARNING, "descriptor string is invalid base64 encode\n"); + } else { + av_log(s, AV_LOG_WARNING, "av_mallocz failed, will not parse descriptor\n"); + } + p += n; + if (*p) + p++; + state = parse_descriptor; + av_freep(&encode_str); + av_freep(&decode_str); + } else if ((state == parse_id || state == parse_descriptor) && av_strstart(p, "streams=", &p)) { //descriptor is optional state = parsing_streams; } else if (state == parsing_streams) { AdaptationSet *as = &c->as[c->nb_as - 1];
change history: 1. remove unnecessary cast. 2. add some braces. Please comment, Thanks Signed-off-by: leozhang <leozhang@qiyi.com> --- doc/muxers.texi | 3 +++ libavformat/dashenc.c | 35 ++++++++++++++++++++++++++++++++--- 2 files changed, 35 insertions(+), 3 deletions(-)