[DASH] Fix TTML text input passthrough (regression)

Note that TTML in ISO-BMFF is not supported yet. Also updated packager_test.py: - Added a test using TTML passthrough. - Computed output extension from input extension unless output_format is specified. Fixes #478. Change-Id: Ia917fc4ed3c326782791ed67601fba02ea28b11d
shaka-project · Sep 19, 2018 · 42083d2 · 42083d2
1 parent 5a91281
commit 42083d2
Show file tree

Hide file tree

Showing 37 changed files with 209 additions and 249 deletions.
diff --git a/packager/app/test/packager_test.py b/packager/app/test/packager_test.py
diff --git a/...-ad-cues/bear-subtitle-english-text-1.vtt → ...text-with-ad-cues/bear-english-text-1.vtt b/...-ad-cues/bear-subtitle-english-text-1.vtt → ...text-with-ad-cues/bear-english-text-1.vtt
diff --git a/...-ad-cues/bear-subtitle-english-text-2.vtt → ...text-with-ad-cues/bear-english-text-2.vtt b/...-ad-cues/bear-subtitle-english-text-2.vtt → ...text-with-ad-cues/bear-english-text-2.vtt
diff --git a/...-ad-cues/bear-subtitle-english-text-3.vtt → ...text-with-ad-cues/bear-english-text-3.vtt b/...-ad-cues/bear-subtitle-english-text-3.vtt → ...text-with-ad-cues/bear-english-text-3.vtt
diff --git a/...-ad-cues/bear-subtitle-english-text-4.vtt → ...text-with-ad-cues/bear-english-text-4.vtt b/...-ad-cues/bear-subtitle-english-text-4.vtt → ...text-with-ad-cues/bear-english-text-4.vtt
diff --git a/...-ad-cues/bear-subtitle-english-text-5.vtt → ...text-with-ad-cues/bear-english-text-5.vtt b/...-ad-cues/bear-subtitle-english-text-5.vtt → ...text-with-ad-cues/bear-english-text-5.vtt
diff --git a/...-ad-cues/bear-subtitle-english-text-6.vtt → ...text-with-ad-cues/bear-english-text-6.vtt b/...-ad-cues/bear-subtitle-english-text-6.vtt → ...text-with-ad-cues/bear-english-text-6.vtt
diff --git a/...h-ad-cues/bear-subtitle-english-text.m3u8 → ...-text-with-ad-cues/bear-english-text.m3u8 b/...h-ad-cues/bear-subtitle-english-text.m3u8 → ...-text-with-ad-cues/bear-english-text.m3u8
@@ -4,16 +4,16 @@
 #EXT-X-TARGETDURATION:2
 #EXT-X-PLAYLIST-TYPE:VOD
 #EXTINF:1.000,
-bear-subtitle-english-text-1.vtt
+bear-english-text-1.vtt
 #EXTINF:1.000,
-bear-subtitle-english-text-2.vtt
+bear-english-text-2.vtt
 #EXTINF:0.001,
-bear-subtitle-english-text-3.vtt
+bear-english-text-3.vtt
 #EXT-X-PLACEMENT-OPPORTUNITY
 #EXTINF:1.000,
-bear-subtitle-english-text-4.vtt
+bear-english-text-4.vtt
 #EXTINF:1.000,
-bear-subtitle-english-text-5.vtt
+bear-english-text-5.vtt
 #EXTINF:1.000,
-bear-subtitle-english-text-6.vtt
+bear-english-text-6.vtt
 #EXT-X-ENDLIST
diff --git a/packager/app/test/testdata/hls-audio-video-text-with-ad-cues/output.m3u8 b/packager/app/test/testdata/hls-audio-video-text-with-ad-cues/output.m3u8
@@ -3,7 +3,7 @@
 
 #EXT-X-MEDIA:TYPE=AUDIO,URI="bear-640x360-audio.m3u8",GROUP-ID="default-audio-group",NAME="stream_1",AUTOSELECT=YES,CHANNELS="2"
 
-#EXT-X-MEDIA:TYPE=SUBTITLES,URI="bear-subtitle-english-text.m3u8",GROUP-ID="default-text-group",NAME="stream_0",AUTOSELECT=YES
+#EXT-X-MEDIA:TYPE=SUBTITLES,URI="bear-english-text.m3u8",GROUP-ID="default-text-group",NAME="stream_0",AUTOSELECT=YES
 
 #EXT-X-STREAM-INF:BANDWIDTH=1108051,AVERAGE-BANDWIDTH=1005999,CODECS="avc1.64001e,mp4a.40.2",RESOLUTION=640x360,AUDIO="default-audio-group",SUBTITLES="default-text-group"
 bear-640x360-video.m3u8

diff --git a/...d-webvtt/bear-subtitle-english-text-1.vtt → ...-segmented-webvtt/bear-english-text-1.vtt b/...d-webvtt/bear-subtitle-english-text-1.vtt → ...-segmented-webvtt/bear-english-text-1.vtt
diff --git a/...d-webvtt/bear-subtitle-english-text-2.vtt → ...-segmented-webvtt/bear-english-text-2.vtt b/...d-webvtt/bear-subtitle-english-text-2.vtt → ...-segmented-webvtt/bear-english-text-2.vtt
diff --git a/...d-webvtt/bear-subtitle-english-text-3.vtt → ...-segmented-webvtt/bear-english-text-3.vtt b/...d-webvtt/bear-subtitle-english-text-3.vtt → ...-segmented-webvtt/bear-english-text-3.vtt
diff --git a/...d-webvtt/bear-subtitle-english-text-4.vtt → ...-segmented-webvtt/bear-english-text-4.vtt b/...d-webvtt/bear-subtitle-english-text-4.vtt → ...-segmented-webvtt/bear-english-text-4.vtt
diff --git a/...d-webvtt/bear-subtitle-english-text-5.vtt → ...-segmented-webvtt/bear-english-text-5.vtt b/...d-webvtt/bear-subtitle-english-text-5.vtt → ...-segmented-webvtt/bear-english-text-5.vtt
diff --git a/packager/app/test/testdata/hls-segmented-webvtt/stream_0.m3u8 b/packager/app/test/testdata/hls-segmented-webvtt/stream_0.m3u8
@@ -4,13 +4,13 @@
 #EXT-X-TARGETDURATION:2
 #EXT-X-PLAYLIST-TYPE:VOD
 #EXTINF:1.000,
-bear-subtitle-english-text-1.vtt
+bear-english-text-1.vtt
 #EXTINF:1.000,
-bear-subtitle-english-text-2.vtt
+bear-english-text-2.vtt
 #EXTINF:1.000,
-bear-subtitle-english-text-3.vtt
+bear-english-text-3.vtt
 #EXTINF:1.000,
-bear-subtitle-english-text-4.vtt
+bear-english-text-4.vtt
 #EXTINF:1.000,
-bear-subtitle-english-text-5.vtt
+bear-english-text-5.vtt
 #EXT-X-ENDLIST
diff --git a/packager/app/test/testdata/video-audio-ttml/bear-640x360-audio.mp4 b/packager/app/test/testdata/video-audio-ttml/bear-640x360-audio.mp4
diff --git a/packager/app/test/testdata/video-audio-ttml/bear-640x360-video.mp4 b/packager/app/test/testdata/video-audio-ttml/bear-640x360-video.mp4
diff --git a/packager/app/test/testdata/video-audio-ttml/bear-english-text.ttml b/packager/app/test/testdata/video-audio-ttml/bear-english-text.ttml
@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="utf-8"?>
+<tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en">
+  <body>
+    <div>
+      <p begin="0.1s" end="0.8s">Yup, that's a bear, eh.</p>
+      <p begin="1.0s" end="4.7s">He 's... um... doing bear-like stuff.</p>
+    </div>
+  </body>
+</tt>
diff --git a/packager/app/test/testdata/video-audio-ttml/output.mpd b/packager/app/test/testdata/video-audio-ttml/output.mpd
@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--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" xmlns:xlink="http://www.w3.org/1999/xlink" xsi:schemaLocation="urn:mpeg:dash:schema:mpd:2011 DASH-MPD.xsd" xmlns:cenc="urn:mpeg:cenc:2013" profiles="urn:mpeg:dash:profile:isoff-on-demand:2011" minBufferTime="PT2S" type="static" mediaPresentationDuration="PT2.7360665798187256S">
+  <Period id="0">
+    <AdaptationSet id="0" contentType="text" subsegmentAlignment="true">
+      <Representation id="0" bandwidth="256" mimeType="application/ttml+xml">
+        <BaseURL>bear-english-text.ttml</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="2" contentType="audio" subsegmentAlignment="true">
+      <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">
+          <Initialization range="0-792"/>
+        </SegmentBase>
+      </Representation>
+    </AdaptationSet>
+  </Period>
+</MPD>
diff --git a/packager/app/test/testdata/video-audio-webvtt/bear-640x360-audio.mp4 b/packager/app/test/testdata/video-audio-webvtt/bear-640x360-audio.mp4
diff --git a/packager/app/test/testdata/video-audio-webvtt/bear-640x360-video.mp4 b/packager/app/test/testdata/video-audio-webvtt/bear-640x360-video.mp4
diff --git a/...media/test/data/bear-subtitle-english.vtt → .../video-audio-webvtt/bear-english-text.vtt b/...media/test/data/bear-subtitle-english.vtt → .../video-audio-webvtt/bear-english-text.vtt
diff --git a/packager/app/test/testdata/video-audio-webvtt/output.mpd b/packager/app/test/testdata/video-audio-webvtt/output.mpd
@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--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" xmlns:xlink="http://www.w3.org/1999/xlink" xsi:schemaLocation="urn:mpeg:dash:schema:mpd:2011 DASH-MPD.xsd" xmlns:cenc="urn:mpeg:cenc:2013" profiles="urn:mpeg:dash:profile:isoff-on-demand:2011" minBufferTime="PT2S" type="static" mediaPresentationDuration="PT2.7360665798187256S">
+  <Period id="0">
+    <AdaptationSet id="0" contentType="text" subsegmentAlignment="true">
+      <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="2" contentType="audio" subsegmentAlignment="true">
+      <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">
+          <Initialization range="0-792"/>
+        </SegmentBase>
+      </Representation>
+    </AdaptationSet>
+  </Period>
+</MPD>
diff --git a/...-ad-cues/bear-subtitle-english-text-1.m4s → ...-mp4-with-ad-cues/bear-english-text-1.m4s b/...-ad-cues/bear-subtitle-english-text-1.m4s → ...-mp4-with-ad-cues/bear-english-text-1.m4s
diff --git a/...-ad-cues/bear-subtitle-english-text-2.m4s → ...-mp4-with-ad-cues/bear-english-text-2.m4s b/...-ad-cues/bear-subtitle-english-text-2.m4s → ...-mp4-with-ad-cues/bear-english-text-2.m4s
diff --git a/...-ad-cues/bear-subtitle-english-text-3.m4s → ...-mp4-with-ad-cues/bear-english-text-3.m4s b/...-ad-cues/bear-subtitle-english-text-3.m4s → ...-mp4-with-ad-cues/bear-english-text-3.m4s
diff --git a/...-ad-cues/bear-subtitle-english-text-4.m4s → ...-mp4-with-ad-cues/bear-english-text-4.m4s b/...-ad-cues/bear-subtitle-english-text-4.m4s → ...-mp4-with-ad-cues/bear-english-text-4.m4s
diff --git a/...-ad-cues/bear-subtitle-english-text-5.m4s → ...-mp4-with-ad-cues/bear-english-text-5.m4s b/...-ad-cues/bear-subtitle-english-text-5.m4s → ...-mp4-with-ad-cues/bear-english-text-5.m4s
diff --git a/...-ad-cues/bear-subtitle-english-text-6.m4s → ...-mp4-with-ad-cues/bear-english-text-6.m4s b/...-ad-cues/bear-subtitle-english-text-6.m4s → ...-mp4-with-ad-cues/bear-english-text-6.m4s
diff --git a/...-cues/bear-subtitle-english-text-init.mp4 → ...4-with-ad-cues/bear-english-text-init.mp4 b/...-cues/bear-subtitle-english-text-init.mp4 → ...4-with-ad-cues/bear-english-text-init.mp4
diff --git a/...h-ad-cues/bear-subtitle-english-text.m3u8 → ...o-mp4-with-ad-cues/bear-english-text.m3u8 b/...h-ad-cues/bear-subtitle-english-text.m3u8 → ...o-mp4-with-ad-cues/bear-english-text.m3u8
@@ -3,18 +3,18 @@
 ## Generated with https://github.com/google/shaka-packager version <tag>-<hash>-<test>
 #EXT-X-TARGETDURATION:2
 #EXT-X-PLAYLIST-TYPE:VOD
-#EXT-X-MAP:URI="bear-subtitle-english-text-init.mp4"
+#EXT-X-MAP:URI="bear-english-text-init.mp4"
 #EXTINF:1.000,
-bear-subtitle-english-text-1.m4s
+bear-english-text-1.m4s
 #EXTINF:1.000,
-bear-subtitle-english-text-2.m4s
+bear-english-text-2.m4s
 #EXTINF:0.001,
-bear-subtitle-english-text-3.m4s
+bear-english-text-3.m4s
 #EXT-X-PLACEMENT-OPPORTUNITY
 #EXTINF:1.000,
-bear-subtitle-english-text-4.m4s
+bear-english-text-4.m4s
 #EXTINF:1.000,
-bear-subtitle-english-text-5.m4s
+bear-english-text-5.m4s
 #EXTINF:1.000,
-bear-subtitle-english-text-6.m4s
+bear-english-text-6.m4s
 #EXT-X-ENDLIST
diff --git a/packager/app/test/testdata/vtt-text-to-mp4-with-ad-cues/output.m3u8 b/packager/app/test/testdata/vtt-text-to-mp4-with-ad-cues/output.m3u8
@@ -3,7 +3,7 @@
 
 #EXT-X-MEDIA:TYPE=AUDIO,URI="bear-640x360-audio.m3u8",GROUP-ID="default-audio-group",NAME="stream_1",AUTOSELECT=YES,CHANNELS="2"
 
-#EXT-X-MEDIA:TYPE=SUBTITLES,URI="bear-subtitle-english-text.m3u8",GROUP-ID="default-text-group",NAME="stream_0",AUTOSELECT=YES
+#EXT-X-MEDIA:TYPE=SUBTITLES,URI="bear-english-text.m3u8",GROUP-ID="default-text-group",NAME="stream_0",AUTOSELECT=YES
 
 #EXT-X-STREAM-INF:BANDWIDTH=1108051,AVERAGE-BANDWIDTH=1005999,CODECS="avc1.64001e,mp4a.40.2",RESOLUTION=640x360,AUDIO="default-audio-group",SUBTITLES="default-text-group"
 bear-640x360-video.m3u8

diff --git a/packager/app/test/testdata/vtt-text-to-mp4-with-ad-cues/output.mpd b/packager/app/test/testdata/vtt-text-to-mp4-with-ad-cues/output.mpd
@@ -5,7 +5,7 @@
     <AdaptationSet id="0" contentType="text" segmentAlignment="true">
       <Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle"/>
       <Representation id="0" bandwidth="1896000" codecs="wvtt" mimeType="application/mp4">
-        <SegmentTemplate timescale="1000" initialization="bear-subtitle-english-text-init.mp4" media="bear-subtitle-english-text-$Number$.m4s" startNumber="1">
+        <SegmentTemplate timescale="1000" initialization="bear-english-text-init.mp4" media="bear-english-text-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
             <S t="0" d="1000" r="1"/>
             <S t="2000" d="1"/>
@@ -38,7 +38,7 @@
     <AdaptationSet id="0" contentType="text" segmentAlignment="true">
       <Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle"/>
       <Representation id="0" bandwidth="2024" codecs="wvtt" mimeType="application/mp4">
-        <SegmentTemplate timescale="1000" presentationTimeOffset="2001" initialization="bear-subtitle-english-text-init.mp4" media="bear-subtitle-english-text-$Number$.m4s" startNumber="4">
+        <SegmentTemplate timescale="1000" presentationTimeOffset="2001" initialization="bear-english-text-init.mp4" media="bear-english-text-$Number$.m4s" startNumber="4">
           <SegmentTimeline>
             <S t="2001" d="1000" r="2"/>
           </SegmentTimeline>

diff --git a/packager/media/test/data/bear-english.ttml b/packager/media/test/data/bear-english.ttml
@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="utf-8"?>
+<tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en">
+  <body>
+    <div>
+      <p begin="0.1s" end="0.8s">Yup, that's a bear, eh.</p>
+      <p begin="1.0s" end="4.7s">He 's... um... doing bear-like stuff.</p>
+    </div>
+  </body>
+</tt>
diff --git a/packager/media/test/data/bear-english.vtt b/packager/media/test/data/bear-english.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/media/test/data/subtitle-english.vtt b/packager/media/test/data/subtitle-english.vtt
diff --git a/packager/packager.cc b/packager/packager.cc
@@ -536,20 +536,29 @@ Status CreateTextJobs(
   DCHECK(muxer_listener_factory);
   DCHECK(job_manager);
   for (const StreamDescriptor& stream : streams) {
-    // There are currently four options:
+    // There are currently options:
+    //    TEXT TTML --> TEXT TTML [ supported ], for DASH only.
     //    TEXT WEBVTT --> TEXT WEBVTT [ supported ]
     //    TEXT WEBVTT --> MP4 WEBVTT  [ supported ]
     //    MP4 WEBVTT  --> MP4 WEBVTT  [ unsupported ]
     //    MP4 WEBVTT  --> TEXT WEBVTT [ unsupported ]
     const auto input_container = DetermineContainerFromFileName(stream.input);
     const auto output_container = GetOutputFormat(stream);
 
-    if (input_container != CONTAINER_WEBVTT) {
+    if (input_container != CONTAINER_WEBVTT &&
+        input_container != CONTAINER_TTML) {
       return Status(error::INVALID_ARGUMENT,
                     "Text output format is not support for " + stream.input);
     }
 
     if (output_container == CONTAINER_MOV) {
+      if (input_container == CONTAINER_TTML) {
+        return Status(error::INVALID_ARGUMENT,
+                      "TTML in MP4 is not supported yet. Please follow "
+                      "https://github.com/google/shaka-packager/issues/87 for "
+                      "the updates.");
+      }
+
       std::unique_ptr<MuxerListener> muxer_listener =
           muxer_listener_factory->CreateListener(ToMuxerListenerData(stream));
 
@@ -566,6 +575,10 @@ Status CreateTextJobs(
 
       // Check input to ensure that output is possible.
       if (hls_listener) {
+        if (input_container == CONTAINER_TTML) {
+          return Status(error::INVALID_ARGUMENT,
+                        "HLS does not support TTML in xml format.");
+        }
         if (stream.segment_template.empty() || !stream.output.empty()) {
           return Status(error::INVALID_ARGUMENT,
                         "segment_template needs to be specified for HLS text "