Consider DASH stream descriptor field "roles" for WebVTT text streams. (

#740) Fixes #708.
shaka-project · Mar 29, 2020 · 2f31bea · 2f31bea
1 parent 82bc7a3
commit 2f31bea
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 4 deletions.
diff --git a/packager/app/test/packager_test.py b/packager/app/test/packager_test.py
@@ -656,6 +656,11 @@ def testAudioVideoWithAccessibilitiesAndRoles(self):
         self._GetStream('video'),
     ]
 
+    streams += self._GetStreams(
+        ['text'],
+        test_files=['bear-english.vtt'],
+        dash_roles='caption')
+
     self.assertPackageSuccess(streams, self._GetFlags(output_dash=True))
     self._CheckTestResults('audio-video-with-accessibilities-and-roles')
 

diff --git a/packager/app/test/testdata/audio-video-with-accessibilities-and-roles/bear-english-text.vtt b/packager/app/test/testdata/audio-video-with-accessibilities-and-roles/bear-english-text.vtt
@@ -0,0 +1,10 @@
+WEBVTT
+
+STYLE
+::cue { color:lime }
+
+00:00:00.000 --> 00:00:00.800
+Yup, that's a bear, eh.
+
+00:00:01.000 --> 00:00:04.700
+He 's... um... doing bear-like stuff.
diff --git a/packager/app/test/testdata/audio-video-with-accessibilities-and-roles/output.mpd b/packager/app/test/testdata/audio-video-with-accessibilities-and-roles/output.mpd
@@ -2,18 +2,24 @@
 <!--Generated with https://github.com/google/shaka-packager version <tag>-<hash>-<test>-->
 <MPD xmlns="urn:mpeg:dash:schema:mpd:2011" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="urn:mpeg:dash:schema:mpd:2011 DASH-MPD.xsd" profiles="urn:mpeg:dash:profile:isoff-on-demand:2011" minBufferTime="PT2S" type="static" mediaPresentationDuration="PT2.7360665798187256S">
   <Period id="0">
-    <AdaptationSet id="0" contentType="video" width="640" height="360" frameRate="30000/1001" subsegmentAlignment="true" par="16:9">
-      <Representation id="0" bandwidth="973483" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
+    <AdaptationSet id="0" contentType="text" subsegmentAlignment="true">
+      <Role schemeIdUri="urn:mpeg:dash:role:2011" value="caption"/>
+      <Representation id="0" bandwidth="256" mimeType="text/vtt">
+        <BaseURL>bear-english-text.vtt</BaseURL>
+      </Representation>
+    </AdaptationSet>
+    <AdaptationSet id="1" contentType="video" width="640" height="360" frameRate="30000/1001" subsegmentAlignment="true" par="16:9">
+      <Representation id="1" bandwidth="973483" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
         <BaseURL>bear-640x360-video.mp4</BaseURL>
         <SegmentBase indexRange="859-926" timescale="30000">
           <Initialization range="0-858"/>
         </SegmentBase>
       </Representation>
     </AdaptationSet>
-    <AdaptationSet id="1" contentType="audio" subsegmentAlignment="true">
+    <AdaptationSet id="2" contentType="audio" subsegmentAlignment="true">
       <Accessibility schemeIdUri="urn:tva:metadata:cs:AudioPurposeCS:2007" value="1"/>
       <Role schemeIdUri="urn:mpeg:dash:role:2011" value="alternate"/>
-      <Representation id="1" bandwidth="133334" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="2" bandwidth="133334" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>bear-640x360-audio.mp4</BaseURL>
         <SegmentBase indexRange="793-860" timescale="44100">

diff --git a/packager/packager.cc b/packager/packager.cc
@@ -400,6 +400,12 @@ bool StreamInfoToTextMediaInfo(const StreamDescriptor& stream_descriptor,
     text_media_info->set_bandwidth(kDefaultTextBandwidth);
   }
 
+  if (!stream_descriptor.dash_roles.empty()) {
+    for (const auto& dash_role : stream_descriptor.dash_roles) {
+      text_media_info->add_dash_roles(dash_role);
+    }
+  }
+
   return true;
 }