Integrate CueAlignmentHandler

Also changed ChunkingHandler to be one-one handler.

Issue: #355

Change-Id: Ie98a96bcc0ddded347699c9f333f604826976d11

packager/app/test/packager_test.py

@@ -806,8 +806,8 @@ class PackagerFunctionalTest(PackagerAppTest):
     self.assertPackageSuccess(
         self._GetStreams(['audio', 'video']),
         self._GetFlags(encryption=True, ad_cues='1.5'))
-    self._DiffGold(self.output[0], 'bear-640x360-a-cenc-golden.mp4')
+    self._DiffGold(self.output[0], 'bear-640x360-a-cenc-ad_cues-golden.mp4')
-    self._DiffGold(self.output[1], 'bear-640x360-v-cenc-golden.mp4')
+    self._DiffGold(self.output[1], 'bear-640x360-v-cenc-ad_cues-golden.mp4')
     self._DiffGold(self.mpd_output, 'bear-640x360-av-cenc-ad_cues-golden.mpd')
     self._VerifyDecryption(self.output[0], 'bear-640x360-a-demuxed-golden.mp4')
     self._VerifyDecryption(self.output[1], 'bear-640x360-v-golden.mp4')
@@ -1088,10 +1088,10 @@ class PackagerFunctionalTest(PackagerAppTest):
     self.assertPackageSuccess(
         self._GetStreams(['audio', 'video'], hls=True),
         self._GetFlags(encryption=True, output_hls=True, ad_cues='1.5'))
-    self._DiffGold(self.output[0], 'bear-640x360-a-cenc-golden.mp4')
+    self._DiffGold(self.output[0], 'bear-640x360-a-cenc-ad_cues-golden.mp4')
-    self._DiffGold(self.output[1], 'bear-640x360-v-cenc-golden.mp4')
+    self._DiffGold(self.output[1], 'bear-640x360-v-cenc-ad_cues-golden.mp4')
     self._DiffGold(self.hls_master_playlist_output,
-                   'bear-640x360-av-mp4-master-cenc-golden.m3u8')
+                   'bear-640x360-av-mp4-master-cenc-ad_cues-golden.m3u8')
     self._DiffGold(
         os.path.join(self.tmp_dir, 'audio.m3u8'),
         'bear-640x360-a-mp4-cenc-ad_cues-golden.m3u8')
@@ -1146,8 +1146,8 @@ class PackagerFunctionalTest(PackagerAppTest):
     self.assertPackageSuccess(
         self._GetStreams(['audio', 'video'], live=True),
         self._GetFlags(generate_static_mpd=True, ad_cues='1.5'))
-    self._DiffLiveGold(self.output[0], 'bear-640x360-a-live-golden')
+    self._DiffLiveGold(self.output[0], 'bear-640x360-a-live-ad_cues-golden')
-    self._DiffLiveGold(self.output[1], 'bear-640x360-v-live-golden')
+    self._DiffLiveGold(self.output[1], 'bear-640x360-v-live-ad_cues-golden')
     self._DiffGold(self.mpd_output,
                    'bear-640x360-av-live-static-ad_cues-golden.mpd')
 

packager/app/test/testdata/bear-320x240-opus-vp9-cenc-golden.mpd

@@ -7,7 +7,7 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="0" bandwidth="79930" codecs="opus" mimeType="audio/mp4" audioSamplingRate="48000">
+      <Representation id="0" bandwidth="81568" codecs="opus" mimeType="audio/mp4" audioSamplingRate="48000">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.mp4</BaseURL>
         <SegmentBase indexRange="975-1042" timescale="1000000">

packager/app/test/testdata/bear-320x240-vp9-opus-webm-golden.mpd

@@ -3,7 +3,7 @@
 <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="PT2.736S">
   <Period id="0">
     <AdaptationSet id="0" contentType="audio" subsegmentAlignment="true">
-      <Representation id="0" bandwidth="75444" codecs="opus" mimeType="audio/webm" audioSamplingRate="48000">
+      <Representation id="0" bandwidth="76531" codecs="opus" mimeType="audio/webm" audioSamplingRate="48000">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.webm</BaseURL>
         <SegmentBase indexRange="323-371" timescale="1000000">

packager/app/test/testdata/bear-640x360-a-cenc-golden.mp4.media_info

@@ -1,4 +1,4 @@
-bandwidth: 129185
+bandwidth: 129162
 audio_info {
   codec: "mp4a.40.2"
   sampling_frequency: 44100

packager/app/test/testdata/bear-640x360-a-enc-golden.m3u8

@@ -3,12 +3,12 @@
 ## Generated with https://github.com/google/shaka-packager version <tag>-<hash>-<test>
 #EXT-X-TARGETDURATION:2
 #EXT-X-PLAYLIST-TYPE:VOD
-#EXTINF:0.952,
+#EXTINF:0.975,
 output_audio-1.ts
 #EXT-X-DISCONTINUITY
 #EXT-X-KEY:METHOD=SAMPLE-AES,URI="data:text/plain;base64,MTIzNDU2Nzg5MDEyMzQ1Ng==",IV=0x3334353637383930,KEYFORMAT="identity"
 #EXTINF:0.998,
 output_audio-2.ts
-#EXTINF:0.813,
+#EXTINF:0.789,
 output_audio-3.ts
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-a-event-golden.m3u8

@@ -3,9 +3,9 @@
 ## Generated with https://github.com/google/shaka-packager version <tag>-<hash>-<test>
 #EXT-X-TARGETDURATION:2
 #EXT-X-PLAYLIST-TYPE:EVENT
-#EXTINF:0.952,
+#EXTINF:0.975,
 output_audio-1.ts
 #EXTINF:0.998,
 output_audio-2.ts
-#EXTINF:0.813,
+#EXTINF:0.789,
 output_audio-3.ts

packager/app/test/testdata/bear-640x360-a-fairplay-enc-golden.m3u8

@@ -3,12 +3,12 @@
 ## Generated with https://github.com/google/shaka-packager version <tag>-<hash>-<test>
 #EXT-X-TARGETDURATION:2
 #EXT-X-PLAYLIST-TYPE:VOD
-#EXTINF:0.952,
+#EXTINF:0.975,
 output_audio-1.ts
 #EXT-X-DISCONTINUITY
 #EXT-X-KEY:METHOD=SAMPLE-AES,URI="skd://www.license.com/getkey?KeyId=31323334-3536-3738-3930-313233343536",KEYFORMATVERSIONS="1",KEYFORMAT="com.apple.streamingkeydelivery"
 #EXTINF:0.998,
 output_audio-2.ts
-#EXTINF:0.813,
+#EXTINF:0.789,
 output_audio-3.ts
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-a-golden.m3u8

@@ -3,10 +3,10 @@
 ## Generated with https://github.com/google/shaka-packager version <tag>-<hash>-<test>
 #EXT-X-TARGETDURATION:2
 #EXT-X-PLAYLIST-TYPE:VOD
-#EXTINF:0.952,
+#EXTINF:0.975,
 output_audio-1.ts
 #EXTINF:0.998,
 output_audio-2.ts
-#EXTINF:0.813,
+#EXTINF:0.789,
 output_audio-3.ts
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-a-live-enc-rotation-golden.m3u8

@@ -4,9 +4,9 @@
 #EXT-X-TARGETDURATION:2
 #EXT-X-MEDIA-SEQUENCE:1
 #EXT-X-DISCONTINUITY-SEQUENCE:1
-#EXT-X-KEY:METHOD=SAMPLE-AES,URI="data:text/plain;base64,MTIzNDU2Nzg5MDEyMzQ1Ng==",IV=0x3334353637383930,KEYFORMAT="identity"
+#EXT-X-KEY:METHOD=SAMPLE-AES,URI="data:text/plain;base64,MjM0NTY3ODkwMTIzNDU2MQ==",IV=0x3334353637383930,KEYFORMAT="identity"
 #EXTINF:0.998,
 output_audio-2.ts
-#EXT-X-KEY:METHOD=SAMPLE-AES,URI="data:text/plain;base64,MjM0NTY3ODkwMTIzNDU2MQ==",IV=0x3334353637383930,KEYFORMAT="identity"
+#EXT-X-KEY:METHOD=SAMPLE-AES,URI="data:text/plain;base64,MzQ1Njc4OTAxMjM0NTYxMg==",IV=0x3334353637383930,KEYFORMAT="identity"
-#EXTINF:0.813,
+#EXTINF:0.789,
 output_audio-3.ts

packager/app/test/testdata/bear-640x360-a-live-golden.m3u8

@@ -5,5 +5,5 @@
 #EXT-X-MEDIA-SEQUENCE:1
 #EXTINF:0.998,
 output_audio-2.ts
-#EXTINF:0.813,
+#EXTINF:0.789,
 output_audio-3.ts

packager/app/test/testdata/bear-640x360-a-mp4-cenc-ad_cues-golden.m3u8

@@ -5,14 +5,17 @@
 #EXT-X-PLAYLIST-TYPE:VOD
 #EXT-X-MAP:URI="output_audio.mp4",BYTERANGE="967@0"
 #EXT-X-KEY:METHOD=SAMPLE-AES-CTR,URI="data:text/plain;base64,MTIzNDU2Nzg5MDEyMzQ1Ng==",KEYFORMAT="identity"
-#EXTINF:0.998,
+#EXTINF:1.022,
-#EXT-X-BYTERANGE:16279@1035
+#EXT-X-BYTERANGE:16655@1047
 output_audio.mp4
 #EXTINF:0.998,
-#EXT-X-BYTERANGE:16674
+#EXT-X-BYTERANGE:16650
+output_audio.mp4
+#EXTINF:0.046,
+#EXT-X-BYTERANGE:1014
 output_audio.mp4
 #EXT-X-PLACEMENT-OPPORTUNITY
-#EXTINF:0.766,
+#EXTINF:0.697,
-#EXT-X-BYTERANGE:10632
+#EXT-X-BYTERANGE:9415
 output_audio.mp4
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-a-mp4-cenc-golden.m3u8

@@ -5,13 +5,13 @@
 #EXT-X-PLAYLIST-TYPE:VOD
 #EXT-X-MAP:URI="output_audio.mp4",BYTERANGE="967@0"
 #EXT-X-KEY:METHOD=SAMPLE-AES-CTR,URI="data:text/plain;base64,MTIzNDU2Nzg5MDEyMzQ1Ng==",KEYFORMAT="identity"
-#EXTINF:0.998,
+#EXTINF:1.022,
-#EXT-X-BYTERANGE:16279@1035
+#EXT-X-BYTERANGE:16655@1035
 output_audio.mp4
 #EXTINF:0.998,
-#EXT-X-BYTERANGE:16674
+#EXT-X-BYTERANGE:16650
 output_audio.mp4
-#EXTINF:0.766,
+#EXTINF:0.743,
-#EXT-X-BYTERANGE:10632
+#EXT-X-BYTERANGE:10272
 output_audio.mp4
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-a-mp4-golden.m3u8

@@ -4,10 +4,10 @@
 #EXT-X-TARGETDURATION:2
 #EXT-X-PLAYLIST-TYPE:VOD
 #EXT-X-MAP:URI="audio-init.mp4"
-#EXTINF:0.998,
+#EXTINF:1.022,
 audio-1.m4s
 #EXTINF:0.998,
 audio-2.m4s
-#EXTINF:0.766,
+#EXTINF:0.743,
 audio-3.m4s
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-ac3-enc-golden.m3u8

@@ -7,8 +7,8 @@
 output_audio-1.ts
 #EXT-X-DISCONTINUITY
 #EXT-X-KEY:METHOD=SAMPLE-AES,URI="data:text/plain;base64,MTIzNDU2Nzg5MDEyMzQ1Ng==",IV=0x3334353637383930,KEYFORMAT="identity"
-#EXTINF:0.975,
+#EXTINF:1.010,
 output_audio-2.ts
-#EXTINF:0.836,
+#EXTINF:0.801,
 output_audio-3.ts
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-ac3-golden.m3u8

@@ -5,8 +5,8 @@
 #EXT-X-PLAYLIST-TYPE:VOD
 #EXTINF:0.975,
 output_audio-1.ts
-#EXTINF:0.975,
+#EXTINF:1.010,
 output_audio-2.ts
-#EXTINF:0.836,
+#EXTINF:0.801,
 output_audio-3.ts
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-ac3-ts-to-mp4-golden.m3u8

@@ -7,10 +7,10 @@
 #EXTINF:0.975,
 #EXT-X-BYTERANGE:23728@794
 output_audio.mp4
-#EXTINF:0.975,
+#EXTINF:1.010,
-#EXT-X-BYTERANGE:23730
+#EXT-X-BYTERANGE:24574
 output_audio.mp4
-#EXTINF:0.836,
+#EXTINF:0.801,
-#EXT-X-BYTERANGE:20354
+#EXT-X-BYTERANGE:19510
 output_audio.mp4
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-av-ac3-master-golden.m3u8

@@ -3,5 +3,5 @@
 
 #EXT-X-MEDIA:TYPE=AUDIO,URI="audio.m3u8",GROUP-ID="default-audio-group",NAME="stream_0",AUTOSELECT=YES,CHANNELS="2"
 
-#EXT-X-STREAM-INF:BANDWIDTH=1242703,CODECS="avc1.64001e,ac-3",RESOLUTION=640x360,AUDIO="default-audio-group"
+#EXT-X-STREAM-INF:BANDWIDTH=1242861,CODECS="avc1.64001e,ac-3",RESOLUTION=640x360,AUDIO="default-audio-group"
 video.m3u8

packager/app/test/testdata/bear-640x360-av-ac3-ts-to-mp4-master-golden.m3u8

@@ -3,5 +3,5 @@
 
 #EXT-X-MEDIA:TYPE=AUDIO,URI="audio.m3u8",GROUP-ID="default-audio-group",NAME="stream_0",AUTOSELECT=YES,CHANNELS="2"
 
-#EXT-X-STREAM-INF:BANDWIDTH=1168277,CODECS="avc1.64001e,ac-3",RESOLUTION=640x360,AUDIO="default-audio-group"
+#EXT-X-STREAM-INF:BANDWIDTH=1168319,CODECS="avc1.64001e,ac-3",RESOLUTION=640x360,AUDIO="default-audio-group"
 video.m3u8

packager/app/test/testdata/bear-640x360-av-cbc1-golden.mpd

@@ -19,7 +19,7 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="1" bandwidth="129185" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="129162" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.mp4</BaseURL>
         <SegmentBase indexRange="967-1034" timescale="44100">

packager/app/test/testdata/bear-640x360-av-cenc-ad_cues-golden.mpd

@@ -2,57 +2,57 @@
 <!--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="PT2.73607S">
   <Period id="0" duration="PT2.002S">
-    <AdaptationSet id="0" contentType="video" width="640" height="360" frameRate="30000/1001" subsegmentAlignment="true" par="16:9">
+    <AdaptationSet id="0" contentType="audio" subsegmentAlignment="true">
       <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011" cenc:default_KID="31323334-3536-3738-3930-313233343536"/>
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="0" bandwidth="885590" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
+      <Representation id="0" bandwidth="129651" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+        <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
+        <BaseURL>output_audio.mp4</BaseURL>
+        <SegmentBase indexRange="967-1046" timescale="44100">
+          <Initialization range="0-966"/>
+        </SegmentBase>
+      </Representation>
+    </AdaptationSet>
+    <AdaptationSet id="2" contentType="video" width="640" height="360" frameRate="30000/1001" subsegmentAlignment="true" par="16:9">
+      <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011" cenc:default_KID="31323334-3536-3738-3930-313233343536"/>
+      <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
+        <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
+      </ContentProtection>
+      <Representation id="1" bandwidth="885590" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
         <BaseURL>output_video.mp4</BaseURL>
         <SegmentBase indexRange="1091-1158" timescale="30000">
           <Initialization range="0-1090"/>
         </SegmentBase>
       </Representation>
     </AdaptationSet>
-    <AdaptationSet id="2" contentType="audio" subsegmentAlignment="true">
+  </Period>
+  <Period id="1" duration="PT0.734067S">
+    <AdaptationSet id="0" contentType="audio" subsegmentAlignment="true">
       <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011" cenc:default_KID="31323334-3536-3738-3930-313233343536"/>
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="1" bandwidth="129185" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="0" bandwidth="129651" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.mp4</BaseURL>
-        <SegmentBase indexRange="967-1034" timescale="44100">
+        <SegmentBase indexRange="967-1046" timescale="44100" presentationTimeOffset="91230">
           <Initialization range="0-966"/>
         </SegmentBase>
       </Representation>
     </AdaptationSet>
-  </Period>
+    <AdaptationSet id="2" contentType="video" width="640" height="360" frameRate="30000/1001" subsegmentAlignment="true" par="16:9">
-  <Period id="1" duration="PT0.734067S">
-    <AdaptationSet id="0" contentType="video" width="640" height="360" frameRate="30000/1001" subsegmentAlignment="true" par="16:9">
       <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011" cenc:default_KID="31323334-3536-3738-3930-313233343536"/>
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="0" bandwidth="885590" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
+      <Representation id="1" bandwidth="885590" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
         <BaseURL>output_video.mp4</BaseURL>
         <SegmentBase indexRange="1091-1158" timescale="30000" presentationTimeOffset="62061">
           <Initialization range="0-1090"/>
         </SegmentBase>
       </Representation>
     </AdaptationSet>
-    <AdaptationSet id="2" contentType="audio" subsegmentAlignment="true">
-      <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011" cenc:default_KID="31323334-3536-3738-3930-313233343536"/>
-      <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
-        <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
-      </ContentProtection>
-      <Representation id="1" bandwidth="129185" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
-        <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
-        <BaseURL>output_audio.mp4</BaseURL>
-        <SegmentBase indexRange="967-1034" timescale="44100" presentationTimeOffset="91230">
-          <Initialization range="0-966"/>
-        </SegmentBase>
-      </Representation>
-    </AdaptationSet>
   </Period>
 </MPD>

packager/app/test/testdata/bear-640x360-av-cenc-golden.mpd

@@ -19,7 +19,7 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="1" bandwidth="129185" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="129162" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.mp4</BaseURL>
         <SegmentBase indexRange="967-1034" timescale="44100">

packager/app/test/testdata/bear-640x360-av-cenc-no-pssh-golden.mpd

@@ -19,7 +19,7 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="1" bandwidth="129035" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="129012" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.mp4</BaseURL>
         <SegmentBase indexRange="915-982" timescale="44100">

packager/app/test/testdata/bear-640x360-av-cenc-non-iop-golden.mpd

@@ -15,7 +15,7 @@
       </Representation>
     </AdaptationSet>
     <AdaptationSet id="1" contentType="audio" subsegmentAlignment="true">
-      <Representation id="1" bandwidth="129185" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="129162" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011" cenc:default_KID="31323334-3536-3738-3930-313233343536"/>
         <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">

packager/app/test/testdata/bear-640x360-av-cens-golden.mpd

@@ -19,7 +19,7 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="1" bandwidth="129185" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="129162" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.mp4</BaseURL>
         <SegmentBase indexRange="967-1034" timescale="44100">

packager/app/test/testdata/bear-640x360-av-live-cenc-golden.mpd

@@ -21,12 +21,13 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="1" bandwidth="124859" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="124634" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <SegmentTemplate timescale="44100" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="44032" r="1"/>
+            <S t="0" d="45056"/>
-            <S t="88064" d="33792"/>
+            <S t="45056" d="44032"/>
+            <S t="89088" d="32768"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>

packager/app/test/testdata/bear-640x360-av-live-cenc-non-iop-golden.mpd

@@ -17,7 +17,7 @@
       </Representation>
     </AdaptationSet>
     <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
-      <Representation id="1" bandwidth="124859" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="124634" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011" cenc:default_KID="31323334-3536-3738-3930-313233343536"/>
         <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
@@ -25,8 +25,9 @@
         </ContentProtection>
         <SegmentTemplate timescale="44100" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="44032" r="1"/>
+            <S t="0" d="45056"/>
-            <S t="88064" d="33792"/>
+            <S t="45056" d="44032"/>
+            <S t="89088" d="32768"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>

packager/app/test/testdata/bear-640x360-av-live-cenc-rotation-golden.mpd

@@ -17,12 +17,13 @@
     <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
       <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011"/>
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b"/>
-      <Representation id="1" bandwidth="125808" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="125598" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <SegmentTemplate timescale="44100" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="44032" r="1"/>
+            <S t="0" d="45056"/>
-            <S t="88064" d="33792"/>
+            <S t="45056" d="44032"/>
+            <S t="89088" d="32768"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>

packager/app/test/testdata/bear-640x360-av-live-cenc-rotation-no-pssh-golden.mpd

@@ -17,12 +17,13 @@
     <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
       <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011"/>
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b"/>
-      <Representation id="1" bandwidth="125337" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="125122" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <SegmentTemplate timescale="44100" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="44032" r="1"/>
+            <S t="0" d="45056"/>
-            <S t="88064" d="33792"/>
+            <S t="45056" d="44032"/>
+            <S t="89088" d="32768"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>

packager/app/test/testdata/bear-640x360-av-live-cenc-rotation-non-iop-golden.mpd

@@ -15,14 +15,15 @@
       </Representation>
     </AdaptationSet>
     <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
-      <Representation id="1" bandwidth="125808" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="125598" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011"/>
         <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b"/>
         <SegmentTemplate timescale="44100" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="44032" r="1"/>
+            <S t="0" d="45056"/>
-            <S t="88064" d="33792"/>
+            <S t="45056" d="44032"/>
+            <S t="89088" d="32768"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>

packager/app/test/testdata/bear-640x360-av-live-golden.mpd

@@ -13,12 +13,13 @@
       </Representation>
     </AdaptationSet>
     <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
-      <Representation id="1" bandwidth="122544" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="122308" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <SegmentTemplate timescale="44100" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="44032" r="1"/>
+            <S t="0" d="45056"/>
-            <S t="88064" d="33792"/>
+            <S t="45056" d="44032"/>
+            <S t="89088" d="32768"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>

packager/app/test/testdata/bear-640x360-av-live-static-ad_cues-golden.mpd

@@ -12,27 +12,19 @@
       </Representation>
     </AdaptationSet>
     <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
-      <Representation id="1" bandwidth="131035" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="143117" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <SegmentTemplate timescale="44100" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="44032" r="1"/>
+            <S t="0" d="45056"/>
+            <S t="45056" d="44032"/>
+            <S t="89088" d="2048"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>
     </AdaptationSet>
   </Period>
   <Period id="1" duration="PT0.734067S">
-    <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
-      <Representation id="1" bandwidth="108486" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
-        <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
-        <SegmentTemplate timescale="44100" presentationTimeOffset="91230" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="3">
-          <SegmentTimeline>
-            <S t="88064" d="33792"/>
-          </SegmentTimeline>
-        </SegmentTemplate>
-      </Representation>
-    </AdaptationSet>
     <AdaptationSet id="0" contentType="video" width="640" height="360" frameRate="30000/1001" segmentAlignment="true" par="16:9">
       <Representation id="0" bandwidth="869044" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
         <SegmentTemplate timescale="30000" presentationTimeOffset="62061" initialization="output_video-init.mp4" media="output_video-$Number$.m4s" startNumber="3">
@@ -42,5 +34,15 @@
         </SegmentTemplate>
       </Representation>
     </AdaptationSet>
+    <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
+      <Representation id="1" bandwidth="105634" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+        <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
+        <SegmentTemplate timescale="44100" presentationTimeOffset="91230" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="4">
+          <SegmentTimeline>
+            <S t="91136" d="30720"/>
+          </SegmentTimeline>
+        </SegmentTemplate>
+      </Representation>
+    </AdaptationSet>
   </Period>
 </MPD>

packager/app/test/testdata/bear-640x360-av-live-static-golden.mpd

@@ -13,12 +13,13 @@
       </Representation>
     </AdaptationSet>
     <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
-      <Representation id="1" bandwidth="122544" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="1" bandwidth="122308" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <SegmentTemplate timescale="44100" initialization="output_audio-init.mp4" media="output_audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="44032" r="1"/>
+            <S t="0" d="45056"/>
-            <S t="88064" d="33792"/>
+            <S t="45056" d="44032"/>
+            <S t="89088" d="32768"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>

packager/app/test/testdata/bear-640x360-av-mp4-master-cenc-ad_cues-golden.m3u8

@@ -0,0 +1,7 @@
+#EXTM3U
+## Generated with https://github.com/google/shaka-packager version <tag>-<hash>-<test>
+
+#EXT-X-MEDIA:TYPE=AUDIO,URI="audio.m3u8",GROUP-ID="default-audio-group",NAME="stream_0",AUTOSELECT=YES,CHANNELS="2"
+
+#EXT-X-STREAM-INF:BANDWIDTH=1152419,CODECS="avc1.64001e,mp4a.40.2",RESOLUTION=640x360,AUDIO="default-audio-group"
+video.m3u8

packager/app/test/testdata/bear-640x360-av-mp4-master-cenc-golden.m3u8

@@ -3,5 +3,5 @@
 
 #EXT-X-MEDIA:TYPE=AUDIO,URI="audio.m3u8",GROUP-ID="default-audio-group",NAME="stream_0",AUTOSELECT=YES,CHANNELS="2"
 
-#EXT-X-STREAM-INF:BANDWIDTH=1111340,CODECS="avc1.64001e,mp4a.40.2",RESOLUTION=640x360,AUDIO="default-audio-group"
+#EXT-X-STREAM-INF:BANDWIDTH=1111147,CODECS="avc1.64001e,mp4a.40.2",RESOLUTION=640x360,AUDIO="default-audio-group"
 video.m3u8

packager/app/test/testdata/bear-640x360-av-mp4-master-golden.m3u8

@@ -3,5 +3,5 @@
 
 #EXT-X-MEDIA:TYPE=AUDIO,URI="audio/audio.m3u8",GROUP-ID="default-audio-group",NAME="stream_0",AUTOSELECT=YES,CHANNELS="2"
 
-#EXT-X-STREAM-INF:BANDWIDTH=1105163,CODECS="avc1.64001e,mp4a.40.2",RESOLUTION=640x360,AUDIO="default-audio-group"
+#EXT-X-STREAM-INF:BANDWIDTH=1105129,CODECS="avc1.64001e,mp4a.40.2",RESOLUTION=640x360,AUDIO="default-audio-group"
 video/video.m3u8

packager/app/test/testdata/bear-640x360-av-trick-1-cenc-golden.mpd

@@ -32,7 +32,7 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="2" bandwidth="129185" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="2" bandwidth="129162" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.mp4</BaseURL>
         <SegmentBase indexRange="967-1034" timescale="44100">

packager/app/test/testdata/bear-640x360-av-trick-1-trick-2-cenc-golden.mpd

@@ -38,7 +38,7 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="3" bandwidth="129185" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
+      <Representation id="3" bandwidth="129162" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">
         <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
         <BaseURL>output_audio.mp4</BaseURL>
         <SegmentBase indexRange="967-1034" timescale="44100">

packager/app/test/testdata/bear-640x360-ec3-a-mp4-cenc-golden.m3u8

@@ -8,10 +8,10 @@
 #EXTINF:1.010,
 #EXT-X-BYTERANGE:24460@977
 output_audio.mp4
-#EXTINF:0.975,
+#EXTINF:1.010,
-#EXT-X-BYTERANGE:23899
+#EXT-X-BYTERANGE:24747
 output_audio.mp4
-#EXTINF:0.766,
+#EXTINF:0.731,
-#EXT-X-BYTERANGE:18811
+#EXT-X-BYTERANGE:17963
 output_audio.mp4
 #EXT-X-ENDLIST

packager/app/test/testdata/bear-640x360-ec3-av-mp4-master-cenc-golden.m3u8

@@ -3,5 +3,5 @@
 
 #EXT-X-MEDIA:TYPE=AUDIO,URI="audio.m3u8",GROUP-ID="default-audio-group",NAME="stream_0",AUTOSELECT=YES,CHANNELS="2"
 
-#EXT-X-STREAM-INF:BANDWIDTH=1174135,CODECS="avc1.64001e,ec-3",RESOLUTION=640x360,AUDIO="default-audio-group"
+#EXT-X-STREAM-INF:BANDWIDTH=1174212,CODECS="avc1.64001e,ec-3",RESOLUTION=640x360,AUDIO="default-audio-group"
 video.m3u8

packager/media/base/media_handler.cc

@@ -49,7 +49,7 @@ bool MediaHandler::ValidateOutputStreamIndex(size_t stream_index) const {
   return stream_index < num_input_streams_;
 }
 
-Status MediaHandler::Dispatch(std::unique_ptr<StreamData> stream_data) {
+Status MediaHandler::Dispatch(std::unique_ptr<StreamData> stream_data) const {
   size_t output_stream_index = stream_data->stream_index;
   auto handler_it = output_handlers_.find(output_stream_index);
   if (handler_it == output_handlers_.end()) {

packager/media/base/media_handler.h

@@ -185,43 +185,54 @@ class MediaHandler {
 
   /// Dispatch the stream data to downstream handlers. Note that
   /// stream_data.stream_index should be the output stream index.
-  Status Dispatch(std::unique_ptr<StreamData> stream_data);
+  Status Dispatch(std::unique_ptr<StreamData> stream_data) const;
 
   /// Dispatch the stream info to downstream handlers.
   Status DispatchStreamInfo(
-      size_t stream_index, std::shared_ptr<const StreamInfo> stream_info) {
+      size_t stream_index,
-    return Dispatch(StreamData::FromStreamInfo(stream_index, stream_info));
+      std::shared_ptr<const StreamInfo> stream_info) const {
+    return Dispatch(
+        StreamData::FromStreamInfo(stream_index, std::move(stream_info)));
   }
 
   /// Dispatch the media sample to downstream handlers.
   Status DispatchMediaSample(
-      size_t stream_index, std::shared_ptr<const MediaSample> media_sample) {
+      size_t stream_index,
-    return Dispatch(StreamData::FromMediaSample(stream_index, media_sample));
+      std::shared_ptr<const MediaSample> media_sample) const {
+    return Dispatch(
+        StreamData::FromMediaSample(stream_index, std::move(media_sample)));
   }
 
   /// Dispatch the text sample to downsream handlers.
   // DispatchTextSample should only be override for testing.
   Status DispatchTextSample(
-      size_t stream_index, std::shared_ptr<const TextSample> text_sample) {
+      size_t stream_index,
-    return Dispatch(StreamData::FromTextSample(stream_index, text_sample));
+      std::shared_ptr<const TextSample> text_sample) const {
+    return Dispatch(
+        StreamData::FromTextSample(stream_index, std::move(text_sample)));
   }
 
   /// Dispatch the segment info to downstream handlers.
   Status DispatchSegmentInfo(
-      size_t stream_index, std::shared_ptr<const SegmentInfo> segment_info) {
+      size_t stream_index,
-    return Dispatch(StreamData::FromSegmentInfo(stream_index, segment_info));
+      std::shared_ptr<const SegmentInfo> segment_info) const {
+    return Dispatch(
+        StreamData::FromSegmentInfo(stream_index, std::move(segment_info)));
   }
 
   /// Dispatch the scte35 event to downstream handlers.
-  Status DispatchScte35Event(size_t stream_index,
+  Status DispatchScte35Event(
-                             std::shared_ptr<const Scte35Event> scte35_event) {
+      size_t stream_index,
-    return Dispatch(StreamData::FromScte35Event(stream_index, scte35_event));
+      std::shared_ptr<const Scte35Event> scte35_event) const {
+    return Dispatch(
+        StreamData::FromScte35Event(stream_index, std::move(scte35_event)));
   }
 
   /// Dispatch the cue event to downstream handlers.
   Status DispatchCueEvent(size_t stream_index,
-                          std::shared_ptr<const CueEvent> cue_event) {
+                          std::shared_ptr<const CueEvent> cue_event) const {
-    return Dispatch(StreamData::FromCueEvent(stream_index, cue_event));
+    return Dispatch(
+        StreamData::FromCueEvent(stream_index, std::move(cue_event)));
   }
 
   /// Flush the downstream connected at the specified output stream index.

packager/media/chunking/chunking_handler.cc

@@ -9,46 +9,38 @@
 #include <algorithm>
 
 #include "packager/base/logging.h"
-#include "packager/base/threading/platform_thread.h"
 #include "packager/media/base/media_sample.h"
 
 namespace shaka {
 namespace media {
 namespace {
-int64_t kThreadIdUnset = -1;
+const size_t kStreamIndex = 0;
 }  // namespace
 
 ChunkingHandler::ChunkingHandler(const ChunkingParams& chunking_params)
-    : chunking_params_(chunking_params),
+    : chunking_params_(chunking_params) {
-      thread_id_(kThreadIdUnset),
-      media_sample_comparator_(this),
-      cached_media_sample_stream_data_(media_sample_comparator_) {
   CHECK_NE(chunking_params.segment_duration_in_seconds, 0u);
 }
 
-ChunkingHandler::~ChunkingHandler() {}
-
 Status ChunkingHandler::InitializeInternal() {
-  segment_info_.resize(num_input_streams());
+  if (num_input_streams() != 1 || next_output_stream_index() != 1) {
-  subsegment_info_.resize(num_input_streams());
+    return Status(error::INVALID_ARGUMENT,
-  time_scales_.resize(num_input_streams());
+                  "Expects exactly one input and one output.");
-  last_sample_end_timestamps_.resize(num_input_streams());
+  }
-  num_cached_samples_.resize(num_input_streams());
   return Status::OK;
 }
 
 Status ChunkingHandler::Process(std::unique_ptr<StreamData> stream_data) {
   switch (stream_data->stream_data_type) {
     case StreamDataType::kStreamInfo:
-      return OnStreamInfo(stream_data->stream_index, stream_data->stream_info);
+      return OnStreamInfo(std::move(stream_data->stream_info));
-    case StreamDataType::kScte35Event:
+    case StreamDataType::kCueEvent:
-      return OnScte35Event(stream_data->stream_index,
+      return OnCueEvent(std::move(stream_data->cue_event));
-                           stream_data->scte35_event);
     case StreamDataType::kSegmentInfo:
       VLOG(3) << "Droppping existing segment info.";
       return Status::OK;
     case StreamDataType::kMediaSample:
-      return OnMediaSample(std::move(stream_data));
+      return OnMediaSample(std::move(stream_data->media_sample));
     default:
       VLOG(3) << "Stream data type "
               << static_cast<int>(stream_data->stream_data_type) << " ignored.";
@@ -57,289 +49,103 @@ Status ChunkingHandler::Process(std::unique_ptr<StreamData> stream_data) {
 }
 
 Status ChunkingHandler::OnFlushRequest(size_t input_stream_index) {
-  // Process all cached samples.
+  Status status = EndSegmentIfStarted();
-  while (!cached_media_sample_stream_data_.empty()) {
-    Status status =
-        ProcessMediaSampleStreamData(*cached_media_sample_stream_data_.top());
   if (!status.ok())
     return status;
-    --num_cached_samples_[cached_media_sample_stream_data_.top()->stream_index];
+  return FlushDownstream(kStreamIndex);
-    cached_media_sample_stream_data_.pop();
-  }
-  if (segment_info_[input_stream_index]) {
-    auto& segment_info = segment_info_[input_stream_index];
-    if (segment_info->start_timestamp != -1) {
-      segment_info->duration = last_sample_end_timestamps_[input_stream_index] -
-                               segment_info->start_timestamp;
-      Status status =
-          DispatchSegmentInfo(input_stream_index, std::move(segment_info));
-      if (!status.ok())
-        return status;
-    }
-  }
-  const size_t output_stream_index = input_stream_index;
-  return FlushDownstream(output_stream_index);
 }
 
-Status ChunkingHandler::OnStreamInfo(uint64_t stream_index,
+Status ChunkingHandler::OnStreamInfo(std::shared_ptr<const StreamInfo> info) {
-                                     std::shared_ptr<const StreamInfo> info) {
+  time_scale_ = info->time_scale();
-  // Make sure the inputs come from the same thread.
-  const int64_t thread_id =
-      static_cast<int64_t>(base::PlatformThread::CurrentId());
-
-  int64_t expected = kThreadIdUnset;
-  if (!thread_id_.compare_exchange_strong(expected, thread_id) &&
-      expected != thread_id) {
-    return Status(error::CHUNKING_ERROR,
-                  "Inputs should come from the same thread.");
-  }
-
-  const auto time_scale = info->time_scale();
-  time_scales_[stream_index] = time_scale;
-
-  // The video stream is treated as the main stream. If there is only one
-  // stream, it is the main stream.
-  const bool is_main_stream =
-      main_stream_index_ == kInvalidStreamIndex &&
-      (info->stream_type() == kStreamVideo || num_input_streams() == 1);
-  if (is_main_stream) {
-    main_stream_index_ = stream_index;
   segment_duration_ =
-        chunking_params_.segment_duration_in_seconds * time_scale;
+      chunking_params_.segment_duration_in_seconds * time_scale_;
   subsegment_duration_ =
-        chunking_params_.subsegment_duration_in_seconds * time_scale;
+      chunking_params_.subsegment_duration_in_seconds * time_scale_;
-  } else if (info->stream_type() == kStreamVideo) {
+  return DispatchStreamInfo(kStreamIndex, std::move(info));
-    return Status(error::CHUNKING_ERROR,
-                  "Only one video stream is allowed per chunking handler.");
-  }
-
-  return DispatchStreamInfo(stream_index, std::move(info));
 }
 
-Status ChunkingHandler::OnScte35Event(
+Status ChunkingHandler::OnCueEvent(std::shared_ptr<const CueEvent> event) {
-    uint64_t stream_index,
+  Status status = EndSegmentIfStarted();
-    std::shared_ptr<const Scte35Event> event) {
-  if (stream_index == main_stream_index_) {
-    scte35_events_.push(std::move(event));
-  } else {
-    VLOG(3) << "Dropping scte35 event from non main stream.";
-  }
-
-  return Status::OK;
-}
-
-Status ChunkingHandler::OnMediaSample(std::unique_ptr<StreamData> stream_data) {
-  DCHECK_EQ(StreamDataType::kMediaSample, stream_data->stream_data_type);
-
-  const size_t stream_index = stream_data->stream_index;
-  DCHECK_NE(time_scales_[stream_index], 0u)
-      << "kStreamInfo should arrive before kMediaSample";
-
-  if (stream_index != main_stream_index_ &&
-      !stream_data->media_sample->is_key_frame()) {
-    return Status(error::CHUNKING_ERROR,
-                  "All non video samples should be key frames.");
-  }
-  // The streams are expected to be roughly synchronized, so we don't expect
-  // to see a lot of samples from one stream but no samples from another
-  // stream.
-  // The value is kind of arbitrary here. For a 24fps video, it is ~40s.
-  const size_t kMaxCachedSamplesPerStream = 1000u;
-  if (num_cached_samples_[stream_index] >= kMaxCachedSamplesPerStream) {
-    LOG(ERROR) << "Streams are not synchronized:";
-    for (size_t i = 0; i < num_cached_samples_.size(); ++i)
-      LOG(ERROR) << " [Stream " << i << "] " << num_cached_samples_[i];
-    return Status(error::CHUNKING_ERROR, "Streams are not synchronized.");
-  }
-
-  cached_media_sample_stream_data_.push(std::move(stream_data));
-  ++num_cached_samples_[stream_index];
-
-  // If we have cached samples from every stream, the first sample in
-  // |cached_media_samples_stream_data_| is guaranteed to be the earliest
-  // sample. Extract and process that sample.
-  if (std::all_of(num_cached_samples_.begin(), num_cached_samples_.end(),
-                  [](size_t num_samples) { return num_samples > 0; })) {
-    while (true) {
-      const size_t top_stream_index =
-          cached_media_sample_stream_data_.top()->stream_index;
-      Status status =
-          ProcessMediaSampleStreamData(*cached_media_sample_stream_data_.top());
   if (!status.ok())
     return status;
-      cached_media_sample_stream_data_.pop();
+  // Force start new segment after cue event.
-      if (--num_cached_samples_[top_stream_index] == 0)
+  segment_start_time_ = base::nullopt;
-        break;
+  return DispatchCueEvent(kStreamIndex, std::move(event));
-    }
-  }
-  return Status::OK;
 }
 
-Status ChunkingHandler::ProcessMainMediaSample(const MediaSample* sample) {
+Status ChunkingHandler::OnMediaSample(
-  const bool is_key_frame = sample->is_key_frame();
+    std::shared_ptr<const MediaSample> sample) {
-  const int64_t timestamp = sample->dts();
+  DCHECK_NE(time_scale_, 0u) << "kStreamInfo should arrive before kMediaSample";
-  const int64_t time_scale = time_scales_[main_stream_index_];
-  const double dts_in_seconds = static_cast<double>(sample->dts()) / time_scale;
 
-  // Check if we need to terminate the current (sub)segment.
+  const int64_t timestamp = sample->dts();
-  bool new_segment = false;
+
-  bool new_subsegment = false;
+  bool started_new_segment = false;
-  std::shared_ptr<CueEvent> cue_event;
+  const bool can_start_new_segment =
-  if (is_key_frame || !chunking_params_.segment_sap_aligned) {
+      sample->is_key_frame() || !chunking_params_.segment_sap_aligned;
+  if (can_start_new_segment) {
     const int64_t segment_index = timestamp / segment_duration_;
-    if (segment_index != current_segment_index_) {
+    if (!segment_start_time_ || segment_index != current_segment_index_) {
       current_segment_index_ = segment_index;
       // Reset subsegment index.
       current_subsegment_index_ = 0;
-      new_segment = true;
-    }
-    // We use 'while' instead of 'if' to make sure to pop off multiple SCTE35
-    // events that may be very close to each other.
-    while (!scte35_events_.empty() &&
-           scte35_events_.top()->start_time_in_seconds <= dts_in_seconds) {
-      // For simplicity, don't change |current_segment_index_|.
-      current_subsegment_index_ = 0;
-      new_segment = true;
 
-      cue_event = std::make_shared<CueEvent>();
+      Status status = EndSegmentIfStarted();
-      cue_event->time_in_seconds =
-          static_cast<double>(sample->pts()) / time_scale;
-      cue_event->cue_data = scte35_events_.top()->cue_data;
-      LOG(INFO) << "Chunked at " << dts_in_seconds << " seconds for Ad Cue.";
-
-      scte35_events_.pop();
-    }
-  }
-  if (!new_segment && subsegment_duration_ > 0 &&
-      (is_key_frame || !chunking_params_.subsegment_sap_aligned)) {
-    const int64_t subsegment_index =
-        (timestamp - segment_info_[main_stream_index_]->start_timestamp) /
-        subsegment_duration_;
-    if (subsegment_index != current_subsegment_index_) {
-      current_subsegment_index_ = subsegment_index;
-      new_subsegment = true;
-    }
-  }
-
-  Status status;
-  if (new_segment) {
-    status.Update(DispatchSegmentInfoForAllStreams());
-    segment_info_[main_stream_index_]->start_timestamp = timestamp;
-
-    if (cue_event)
-      status.Update(DispatchCueEventForAllStreams(std::move(cue_event)));
-  }
-  if (subsegment_duration_ > 0 && (new_segment || new_subsegment)) {
-    status.Update(DispatchSubsegmentInfoForAllStreams());
-    subsegment_info_[main_stream_index_]->start_timestamp = timestamp;
-  }
-  return status;
-}
-
-Status ChunkingHandler::ProcessMediaSampleStreamData(
-    const StreamData& media_sample_stream_data) {
-  const size_t stream_index = media_sample_stream_data.stream_index;
-  const auto sample = std::move(media_sample_stream_data.media_sample);
-
-  if (stream_index == main_stream_index_) {
-    Status status = ProcessMainMediaSample(sample.get());
       if (!status.ok())
         return status;
+      segment_start_time_ = timestamp;
+      subsegment_start_time_ = timestamp;
+      started_new_segment = true;
+    }
+  }
+  if (!started_new_segment && IsSubsegmentEnabled()) {
+    const bool can_start_new_subsegment =
+        sample->is_key_frame() || !chunking_params_.subsegment_sap_aligned;
+    if (can_start_new_subsegment) {
+      const int64_t subsegment_index =
+          (timestamp - segment_start_time_.value()) / subsegment_duration_;
+      if (subsegment_index != current_subsegment_index_) {
+        current_subsegment_index_ = subsegment_index;
+
+        Status status = EndSubsegmentIfStarted();
+        if (!status.ok())
+          return status;
+        subsegment_start_time_ = timestamp;
+      }
+    }
   }
 
-  VLOG(3) << "Stream index: " << stream_index << " "
+  VLOG(3) << "Sample ts: " << timestamp << " "
-          << "Sample ts: " << sample->dts() << " "
+          << " duration: " << sample->duration() << " scale: " << time_scale_
-          << " duration: " << sample->duration()
+          << (segment_start_time_ ? " dispatch " : " discard ");
-          << " scale: " << time_scales_[stream_index] << "\n"
-          << " scale: " << time_scales_[main_stream_index_]
-          << (segment_info_[stream_index] ? " dispatch " : " discard ");
   // Discard samples before segment start. If the segment has started,
-  // |segment_info_[stream_index]| won't be null.
+  // |segment_start_time_| won't be null.
-  if (!segment_info_[stream_index])
+  if (!segment_start_time_)
     return Status::OK;
-  if (segment_info_[stream_index]->start_timestamp == -1)
+  last_sample_end_timestamp_ = timestamp + sample->duration();
-    segment_info_[stream_index]->start_timestamp = sample->dts();
+  return DispatchMediaSample(kStreamIndex, std::move(sample));
-  if (subsegment_info_[stream_index] &&
-      subsegment_info_[stream_index]->start_timestamp == -1) {
-    subsegment_info_[stream_index]->start_timestamp = sample->dts();
-  }
-  last_sample_end_timestamps_[stream_index] =
-      sample->dts() + sample->duration();
-  return DispatchMediaSample(stream_index, std::move(sample));
 }
 
-Status ChunkingHandler::DispatchSegmentInfoForAllStreams() {
+Status ChunkingHandler::EndSegmentIfStarted() const {
-  Status status;
+  if (!segment_start_time_)
-  for (size_t i = 0; i < segment_info_.size() && status.ok(); ++i) {
+    return Status::OK;
-    if (segment_info_[i] && segment_info_[i]->start_timestamp != -1) {
+
-      segment_info_[i]->duration =
+  auto segment_info = std::make_shared<SegmentInfo>();
-          last_sample_end_timestamps_[i] - segment_info_[i]->start_timestamp;
+  segment_info->start_timestamp = segment_start_time_.value();
-      status.Update(DispatchSegmentInfo(i, std::move(segment_info_[i])));
+  segment_info->duration =
-    }
+      last_sample_end_timestamp_ - segment_start_time_.value();
-    segment_info_[i].reset(new SegmentInfo);
+  return DispatchSegmentInfo(kStreamIndex, std::move(segment_info));
-    subsegment_info_[i].reset();
-  }
-  return status;
 }
 
-Status ChunkingHandler::DispatchSubsegmentInfoForAllStreams() {
+Status ChunkingHandler::EndSubsegmentIfStarted() const {
-  Status status;
+  if (!subsegment_start_time_)
-  for (size_t i = 0; i < subsegment_info_.size() && status.ok(); ++i) {
+    return Status::OK;
-    if (subsegment_info_[i] && subsegment_info_[i]->start_timestamp != -1) {
-      subsegment_info_[i]->duration =
-          last_sample_end_timestamps_[i] - subsegment_info_[i]->start_timestamp;
-      status.Update(DispatchSegmentInfo(i, std::move(subsegment_info_[i])));
-    }
-    subsegment_info_[i].reset(new SegmentInfo);
-    subsegment_info_[i]->is_subsegment = true;
-  }
-  return status;
-}
 
-Status ChunkingHandler::DispatchCueEventForAllStreams(
+  auto subsegment_info = std::make_shared<SegmentInfo>();
-    std::shared_ptr<CueEvent> cue_event) {
+  subsegment_info->start_timestamp = subsegment_start_time_.value();
-  Status status;
+  subsegment_info->duration =
-  for (size_t i = 0; i < segment_info_.size() && status.ok(); ++i) {
+      last_sample_end_timestamp_ - subsegment_start_time_.value();
-    status.Update(DispatchCueEvent(i, cue_event));
+  subsegment_info->is_subsegment = true;
-  }
+  return DispatchSegmentInfo(kStreamIndex, std::move(subsegment_info));
-  return status;
-}
-
-ChunkingHandler::MediaSampleTimestampGreater::MediaSampleTimestampGreater(
-    const ChunkingHandler* const chunking_handler)
-    : chunking_handler_(chunking_handler) {}
-
-bool ChunkingHandler::MediaSampleTimestampGreater::operator()(
-    const std::unique_ptr<StreamData>& lhs,
-    const std::unique_ptr<StreamData>& rhs) const {
-  DCHECK(lhs);
-  DCHECK(rhs);
-  return GetSampleTimeInSeconds(*lhs) > GetSampleTimeInSeconds(*rhs);
-}
-
-double ChunkingHandler::MediaSampleTimestampGreater::GetSampleTimeInSeconds(
-    const StreamData& media_sample_stream_data) const {
-  const size_t stream_index = media_sample_stream_data.stream_index;
-  const auto& sample = media_sample_stream_data.media_sample;
-  DCHECK(sample);
-  // Order main samples by left boundary and non main samples by mid-point. This
-  // ensures non main samples are properly chunked, i.e. if the portion of the
-  // sample in the next chunk is bigger than the portion of the sample in the
-  // previous chunk, the sample is placed in the next chunk.
-  const uint64_t timestamp =
-      stream_index == chunking_handler_->main_stream_index_
-          ? sample->dts()
-          : (sample->dts() + sample->duration() / 2);
-  return static_cast<double>(timestamp) /
-         chunking_handler_->time_scales_[stream_index];
-}
-
-bool ChunkingHandler::Scte35EventTimestampGreater::operator()(
-    const std::shared_ptr<const Scte35Event>& lhs,
-    const std::shared_ptr<const Scte35Event>& rhs) const {
-  DCHECK(lhs);
-  DCHECK(rhs);
-  return lhs->start_time_in_seconds > rhs->start_time_in_seconds;
 }
 
 }  // namespace media

packager/media/chunking/chunking_handler.h

@@ -11,6 +11,7 @@
 #include <queue>
 
 #include "packager/base/logging.h"
+#include "packager/base/optional.h"
 #include "packager/media/base/media_handler.h"
 #include "packager/media/public/chunking_params.h"
 
@@ -19,9 +20,7 @@ namespace media {
 
 /// ChunkingHandler splits the samples into segments / subsegments based on the
 /// specified chunking params.
-/// This handler is a multi-in multi-out handler. If more than one input is
+/// This handler is a one-in one-out handler.
-/// provided, there should be one and only one video stream; also, all inputs
-/// should come from the same thread and are synchronized.
 /// There can be multiple chunking handler running in different threads or even
 /// different processes, we use the "consistent chunking algorithm" to make sure
 /// the chunks in different streams are aligned without explicit communcating
@@ -36,17 +35,11 @@ namespace media {
 ///  2. Chunk only at the consistent chunkable boundary
 ///
 /// This algorithm will make sure the chunks from different video streams are
-/// aligned if they have aligned GoPs. However, this algorithm will only work
+/// aligned if they have aligned GoPs.
-/// for video streams. To be able to chunk non video streams at similar
-/// positions as video streams, ChunkingHandler is designed to accept one video
-/// input and multiple non video inputs, the non video inputs are chunked when
-/// the video input is chunked. If the inputs are synchronized - which is true
-/// if the inputs come from the same demuxer, the video and non video chunks
-/// are aligned.
 class ChunkingHandler : public MediaHandler {
  public:
   explicit ChunkingHandler(const ChunkingParams& chunking_params);
-  ~ChunkingHandler() override;
+  ~ChunkingHandler() override = default;
 
  protected:
   /// @name MediaHandler implementation overrides.
@@ -62,84 +55,34 @@ class ChunkingHandler : public MediaHandler {
   ChunkingHandler(const ChunkingHandler&) = delete;
   ChunkingHandler& operator=(const ChunkingHandler&) = delete;
 
-  Status OnStreamInfo(uint64_t stream_index,
+  Status OnStreamInfo(std::shared_ptr<const StreamInfo> info);
-                      std::shared_ptr<const StreamInfo> info);
+  Status OnCueEvent(std::shared_ptr<const CueEvent> event);
-  Status OnScte35Event(uint64_t stream_index,
+  Status OnMediaSample(std::shared_ptr<const MediaSample> sample);
-                       std::shared_ptr<const Scte35Event> event);
 
-  Status OnMediaSample(std::unique_ptr<StreamData> stream_data);
+  Status EndSegmentIfStarted() const;
+  Status EndSubsegmentIfStarted() const;
 
-  // Processes main media sample and apply chunking if needed.
+  bool IsSubsegmentEnabled() {
-  Status ProcessMainMediaSample(const MediaSample* sample);
+    return subsegment_duration_ > 0 &&
-
+           subsegment_duration_ != segment_duration_;
-  // Processes and dispatches media sample.
+  }
-  Status ProcessMediaSampleStreamData(const StreamData& media_data);
-
-  // The (sub)segments are aligned and dispatched together.
-  Status DispatchSegmentInfoForAllStreams();
-  Status DispatchSubsegmentInfoForAllStreams();
-  Status DispatchCueEventForAllStreams(std::shared_ptr<CueEvent> cue_event);
 
   const ChunkingParams chunking_params_;
 
-  // The inputs are expected to come from the same thread.
+  // Segment and subsegment duration in stream's time scale.
-  std::atomic<int64_t> thread_id_;
-
-  // The video stream is the main stream; if there is only one stream, it is the
-  // main stream. The chunking is based on the main stream.
-  const size_t kInvalidStreamIndex = static_cast<size_t>(-1);
-  size_t main_stream_index_ = kInvalidStreamIndex;
-  // Segment and subsegment duration in main stream's time scale.
   int64_t segment_duration_ = 0;
   int64_t subsegment_duration_ = 0;
 
-  class MediaSampleTimestampGreater {
-   public:
-    explicit MediaSampleTimestampGreater(
-        const ChunkingHandler* const chunking_handler);
-
-    // Comparison operator. Used by |media_samples_| priority queue below to
-    // sort the media samples.
-    bool operator()(const std::unique_ptr<StreamData>& lhs,
-                    const std::unique_ptr<StreamData>& rhs) const;
-
-   private:
-    double GetSampleTimeInSeconds(
-        const StreamData& media_sample_stream_data) const;
-
-    const ChunkingHandler* const chunking_handler_ = nullptr;
-  };
-  MediaSampleTimestampGreater media_sample_comparator_;
-  // Caches media samples and sort the samples.
-  std::priority_queue<std::unique_ptr<StreamData>,
-                      std::vector<std::unique_ptr<StreamData>>,
-                      MediaSampleTimestampGreater>
-      cached_media_sample_stream_data_;
-  // Tracks number of cached samples in input streams.
-  std::vector<size_t> num_cached_samples_;
-
   // Current segment index, useful to determine where to do chunking.
   int64_t current_segment_index_ = -1;
   // Current subsegment index, useful to determine where to do chunking.
   int64_t current_subsegment_index_ = -1;
 
-  std::vector<std::shared_ptr<SegmentInfo>> segment_info_;
+  base::Optional<int64_t> segment_start_time_;
-  std::vector<std::shared_ptr<SegmentInfo>> subsegment_info_;
+  base::Optional<int64_t> subsegment_start_time_;
-  std::vector<uint32_t> time_scales_;
+  uint32_t time_scale_ = 0;
   // The end timestamp of the last dispatched sample.
-  std::vector<int64_t> last_sample_end_timestamps_;
+  int64_t last_sample_end_timestamp_ = 0;
-
-  struct Scte35EventTimestampGreater {
-    bool operator()(const std::shared_ptr<const Scte35Event>& lhs,
-                    const std::shared_ptr<const Scte35Event>& rhs) const;
-  };
-  // Captures all incoming SCTE35 events to identify chunking points. Events
-  // will be removed from this queue one at a time as soon as the correct
-  // chunking point is identified in the incoming samples.
-  std::priority_queue<std::shared_ptr<const Scte35Event>,
-                      std::vector<std::shared_ptr<const Scte35Event>>,
-                      Scte35EventTimestampGreater>
-      scte35_events_;
 };
 
 }  // namespace media

packager/media/chunking/chunking_handler_unittest.cc

@@ -18,12 +18,10 @@ using ::testing::IsEmpty;
 namespace shaka {
 namespace media {
 namespace {
-const size_t kStreamIndex0 = 0;
+const size_t kStreamIndex = 0;
-const size_t kStreamIndex1 = 1;
 const uint32_t kTimeScale0 = 800;
 const uint32_t kTimeScale1 = 1000;
-const int64_t kDuration0 = 200;
+const int64_t kDuration = 300;
-const int64_t kDuration1 = 300;
 const bool kKeyFrame = true;
 const bool kIsSubsegment = true;
 const bool kEncrypted = true;
@@ -57,34 +55,34 @@ TEST_F(ChunkingHandlerTest, AudioNoSubsegmentsThenFlush) {
   SetUpChunkingHandler(1, chunking_params);
 
   ASSERT_OK(Process(StreamData::FromStreamInfo(
-      kStreamIndex0, GetAudioStreamInfo(kTimeScale0))));
+      kStreamIndex, GetAudioStreamInfo(kTimeScale0))));
   EXPECT_THAT(
       GetOutputStreamDataVector(),
-      ElementsAre(IsStreamInfo(kStreamIndex0, kTimeScale0, !kEncrypted)));
+      ElementsAre(IsStreamInfo(kStreamIndex, kTimeScale0, !kEncrypted)));
 
   for (int i = 0; i < 5; ++i) {
     ClearOutputStreamDataVector();
     ASSERT_OK(Process(StreamData::FromMediaSample(
-        kStreamIndex0, GetMediaSample(i * kDuration1, kDuration1, kKeyFrame))));
+        kStreamIndex, GetMediaSample(i * kDuration, kDuration, kKeyFrame))));
     // One output stream_data except when i == 3, which also has SegmentInfo.
     if (i == 3) {
       EXPECT_THAT(GetOutputStreamDataVector(),
-                  ElementsAre(IsSegmentInfo(kStreamIndex0, 0, kDuration1 * 3,
+                  ElementsAre(IsSegmentInfo(kStreamIndex, 0, kDuration * 3,
                                             !kIsSubsegment, !kEncrypted),
-                              IsMediaSample(kStreamIndex0, i * kDuration1,
+                              IsMediaSample(kStreamIndex, i * kDuration,
-                                            kDuration1, !kEncrypted)));
+                                            kDuration, !kEncrypted)));
     } else {
       EXPECT_THAT(GetOutputStreamDataVector(),
-                  ElementsAre(IsMediaSample(kStreamIndex0, i * kDuration1,
+                  ElementsAre(IsMediaSample(kStreamIndex, i * kDuration,
-                                            kDuration1, !kEncrypted)));
+                                            kDuration, !kEncrypted)));
     }
   }
 
   ClearOutputStreamDataVector();
-  ASSERT_OK(OnFlushRequest(kStreamIndex0));
+  ASSERT_OK(OnFlushRequest(kStreamIndex));
   EXPECT_THAT(
       GetOutputStreamDataVector(),
-      ElementsAre(IsSegmentInfo(kStreamIndex0, kDuration1 * 3, kDuration1 * 2,
+      ElementsAre(IsSegmentInfo(kStreamIndex, kDuration * 3, kDuration * 2,
                                 !kIsSubsegment, !kEncrypted)));
 }
 
@@ -95,25 +93,24 @@ TEST_F(ChunkingHandlerTest, AudioWithSubsegments) {
   SetUpChunkingHandler(1, chunking_params);
 
   ASSERT_OK(Process(StreamData::FromStreamInfo(
-      kStreamIndex0, GetAudioStreamInfo(kTimeScale0))));
+      kStreamIndex, GetAudioStreamInfo(kTimeScale0))));
   for (int i = 0; i < 5; ++i) {
     ASSERT_OK(Process(StreamData::FromMediaSample(
-        kStreamIndex0, GetMediaSample(i * kDuration1, kDuration1, kKeyFrame))));
+        kStreamIndex, GetMediaSample(i * kDuration, kDuration, kKeyFrame))));
   }
   EXPECT_THAT(
       GetOutputStreamDataVector(),
       ElementsAre(
-          IsStreamInfo(kStreamIndex0, kTimeScale0, !kEncrypted),
+          IsStreamInfo(kStreamIndex, kTimeScale0, !kEncrypted),
-          IsMediaSample(kStreamIndex0, 0, kDuration1, !kEncrypted),
+          IsMediaSample(kStreamIndex, 0, kDuration, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kDuration1, kDuration1, !kEncrypted),
+          IsMediaSample(kStreamIndex, kDuration, kDuration, !kEncrypted),
-          IsSegmentInfo(kStreamIndex0, 0, kDuration1 * 2, kIsSubsegment,
+          IsSegmentInfo(kStreamIndex, 0, kDuration * 2, kIsSubsegment,
                         !kEncrypted),
-          IsMediaSample(kStreamIndex0, 2 * kDuration1, kDuration1, !kEncrypted),
+          IsMediaSample(kStreamIndex, 2 * kDuration, kDuration, !kEncrypted),
-          IsSegmentInfo(kStreamIndex0, 0, kDuration1 * 3, !kIsSubsegment,
+          IsSegmentInfo(kStreamIndex, 0, kDuration * 3, !kIsSubsegment,
                         !kEncrypted),
-          IsMediaSample(kStreamIndex0, 3 * kDuration1, kDuration1, !kEncrypted),
+          IsMediaSample(kStreamIndex, 3 * kDuration, kDuration, !kEncrypted),
-          IsMediaSample(kStreamIndex0, 4 * kDuration1, kDuration1,
+          IsMediaSample(kStreamIndex, 4 * kDuration, kDuration, !kEncrypted)));
-                        !kEncrypted)));
 }
 
 TEST_F(ChunkingHandlerTest, VideoAndSubsegmentAndNonzeroStart) {
@@ -123,193 +120,79 @@ TEST_F(ChunkingHandlerTest, VideoAndSubsegmentAndNonzeroStart) {
   SetUpChunkingHandler(1, chunking_params);
 
   ASSERT_OK(Process(StreamData::FromStreamInfo(
-      kStreamIndex0, GetVideoStreamInfo(kTimeScale1))));
+      kStreamIndex, GetVideoStreamInfo(kTimeScale1))));
   const int64_t kVideoStartTimestamp = 12345;
   for (int i = 0; i < 6; ++i) {
     // Alternate key frame.
     const bool is_key_frame = (i % 2) == 1;
     ASSERT_OK(Process(StreamData::FromMediaSample(
-        kStreamIndex0, GetMediaSample(kVideoStartTimestamp + i * kDuration1,
+        kStreamIndex, GetMediaSample(kVideoStartTimestamp + i * kDuration,
-                                      kDuration1, is_key_frame))));
+                                     kDuration, is_key_frame))));
   }
   EXPECT_THAT(
       GetOutputStreamDataVector(),
       ElementsAre(
-          IsStreamInfo(kStreamIndex0, kTimeScale1, !kEncrypted),
+          IsStreamInfo(kStreamIndex, kTimeScale1, !kEncrypted),
           // The first samples @ kStartTimestamp is discarded - not key frame.
-          IsMediaSample(kStreamIndex0, kVideoStartTimestamp + kDuration1,
+          IsMediaSample(kStreamIndex, kVideoStartTimestamp + kDuration,
-                        kDuration1, !kEncrypted),
+                        kDuration, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kVideoStartTimestamp + kDuration1 * 2,
+          IsMediaSample(kStreamIndex, kVideoStartTimestamp + kDuration * 2,
-                        kDuration1, !kEncrypted),
+                        kDuration, !kEncrypted),
           // The next segment boundary 13245 / 1000 != 12645 / 1000.
-          IsSegmentInfo(kStreamIndex0, kVideoStartTimestamp + kDuration1,
+          IsSegmentInfo(kStreamIndex, kVideoStartTimestamp + kDuration,
-                        kDuration1 * 2, !kIsSubsegment, !kEncrypted),
+                        kDuration * 2, !kIsSubsegment, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kVideoStartTimestamp + kDuration1 * 3,
+          IsMediaSample(kStreamIndex, kVideoStartTimestamp + kDuration * 3,
-                        kDuration1, !kEncrypted),
+                        kDuration, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kVideoStartTimestamp + kDuration1 * 4,
+          IsMediaSample(kStreamIndex, kVideoStartTimestamp + kDuration * 4,
-                        kDuration1, !kEncrypted),
+                        kDuration, !kEncrypted),
-          // The subsegment has duration kDuration1 * 2 since it can only
+          // The subsegment has duration kDuration * 2 since it can only
           // terminate before key frame.
-          IsSegmentInfo(kStreamIndex0, kVideoStartTimestamp + kDuration1 * 3,
+          IsSegmentInfo(kStreamIndex, kVideoStartTimestamp + kDuration * 3,
-                        kDuration1 * 2, kIsSubsegment, !kEncrypted),
+                        kDuration * 2, kIsSubsegment, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kVideoStartTimestamp + kDuration1 * 5,
+          IsMediaSample(kStreamIndex, kVideoStartTimestamp + kDuration * 5,
-                        kDuration1, !kEncrypted)));
+                        kDuration, !kEncrypted)));
 }
 
-TEST_F(ChunkingHandlerTest, AudioAndVideo) {
+TEST_F(ChunkingHandlerTest, CueEvent) {
-  ChunkingParams chunking_params;
-  chunking_params.segment_duration_in_seconds = 1;
-  chunking_params.subsegment_duration_in_seconds = 0.3;
-  SetUpChunkingHandler(2, chunking_params);
-
-  ASSERT_OK(Process(StreamData::FromStreamInfo(
-      kStreamIndex0, GetAudioStreamInfo(kTimeScale0))));
-  ASSERT_OK(Process(StreamData::FromStreamInfo(
-      kStreamIndex1, GetVideoStreamInfo(kTimeScale1))));
-  EXPECT_THAT(
-      GetOutputStreamDataVector(),
-      ElementsAre(IsStreamInfo(kStreamIndex0, kTimeScale0, !kEncrypted),
-                  IsStreamInfo(kStreamIndex1, kTimeScale1, !kEncrypted)));
-  ClearOutputStreamDataVector();
-
-  // Equivalent to 12345 in video timescale.
-  const int64_t kAudioStartTimestamp = 9876;
-  const int64_t kVideoStartTimestamp = 12345;
-  // Burst of audio and video samples. They will be properly ordered.
-  for (int i = 0; i < 5; ++i) {
-    ASSERT_OK(Process(StreamData::FromMediaSample(
-        kStreamIndex0, GetMediaSample(kAudioStartTimestamp + kDuration0 * i,
-                                      kDuration0, true))));
-  }
-  for (int i = 0; i < 5; ++i) {
-    // Alternate key frame.
-    const bool is_key_frame = (i % 2) == 1;
-    ASSERT_OK(Process(StreamData::FromMediaSample(
-        kStreamIndex1, GetMediaSample(kVideoStartTimestamp + kDuration1 * i,
-                                      kDuration1, is_key_frame))));
-  }
-
-  EXPECT_THAT(
-      GetOutputStreamDataVector(),
-      ElementsAre(
-          // The first samples @ kStartTimestamp is discarded - not key frame.
-          IsMediaSample(kStreamIndex1, kVideoStartTimestamp + kDuration1,
-                        kDuration1, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kAudioStartTimestamp + kDuration0,
-                        kDuration0, !kEncrypted),
-          IsMediaSample(kStreamIndex1, kVideoStartTimestamp + kDuration1 * 2,
-                        kDuration1, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kAudioStartTimestamp + kDuration0 * 2,
-                        kDuration0, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kAudioStartTimestamp + kDuration0 * 3,
-                        kDuration0, !kEncrypted),
-          // The audio segment is terminated together with video stream.
-          IsSegmentInfo(kStreamIndex0, kAudioStartTimestamp + kDuration0,
-                        kDuration0 * 3, !kIsSubsegment, !kEncrypted),
-          // The next segment boundary 13245 / 1000 != 12645 / 1000.
-          IsSegmentInfo(kStreamIndex1, kVideoStartTimestamp + kDuration1,
-                        kDuration1 * 2, !kIsSubsegment, !kEncrypted),
-          IsMediaSample(kStreamIndex1, kVideoStartTimestamp + kDuration1 * 3,
-                        kDuration1, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kAudioStartTimestamp + kDuration0 * 4,
-                        kDuration0, !kEncrypted)));
-  ClearOutputStreamDataVector();
-
-  // The side comments below show the equivalent timestamp in video timescale.
-  // The audio and video are made ~aligned.
-  ASSERT_OK(Process(StreamData::FromMediaSample(
-      kStreamIndex0,
-      GetMediaSample(kAudioStartTimestamp + kDuration0 * 5, kDuration0,
-                     true))));  // 13595
-  ASSERT_OK(Process(StreamData::FromMediaSample(
-      kStreamIndex1,
-      GetMediaSample(kVideoStartTimestamp + kDuration1 * 5, kDuration1,
-                     true))));  // 13845
-  ASSERT_OK(Process(StreamData::FromMediaSample(
-      kStreamIndex0,
-      GetMediaSample(kAudioStartTimestamp + kDuration0 * 6, kDuration0,
-                     true))));  // 13845
-  // This expectation are separated from the expectation above because
-  // ElementsAre supports at most 10 elements.
-  EXPECT_THAT(
-      GetOutputStreamDataVector(),
-      ElementsAre(
-          IsMediaSample(kStreamIndex1, kVideoStartTimestamp + kDuration1 * 4,
-                        kDuration1, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kAudioStartTimestamp + kDuration0 * 5,
-                        kDuration0, !kEncrypted),
-          // Audio is terminated along with video below.
-          IsSegmentInfo(kStreamIndex0, kAudioStartTimestamp + kDuration0 * 4,
-                        kDuration0 * 2, kIsSubsegment, !kEncrypted),
-          // The subsegment has duration kDuration1 * 2 since it can only
-          // terminate before key frame.
-          IsSegmentInfo(kStreamIndex1, kVideoStartTimestamp + kDuration1 * 3,
-                        kDuration1 * 2, kIsSubsegment, !kEncrypted),
-          IsMediaSample(kStreamIndex1, kVideoStartTimestamp + kDuration1 * 5,
-                        kDuration1, !kEncrypted)));
-
-  ClearOutputStreamDataVector();
-  ASSERT_OK(OnFlushRequest(kStreamIndex0));
-  EXPECT_THAT(
-      GetOutputStreamDataVector(),
-      ElementsAre(
-          IsMediaSample(kStreamIndex0, kAudioStartTimestamp + kDuration0 * 6,
-                        kDuration0, !kEncrypted),
-          IsSegmentInfo(kStreamIndex0, kAudioStartTimestamp + kDuration0 * 4,
-                        kDuration0 * 3, !kIsSubsegment, !kEncrypted)));
-
-  ClearOutputStreamDataVector();
-  ASSERT_OK(OnFlushRequest(kStreamIndex1));
-  EXPECT_THAT(GetOutputStreamDataVector(),
-              ElementsAre(IsSegmentInfo(
-                  kStreamIndex1, kVideoStartTimestamp + kDuration1 * 3,
-                  kDuration1 * 3, !kIsSubsegment, !kEncrypted)));
-
-  // Flush again will do nothing.
-  ClearOutputStreamDataVector();
-  ASSERT_OK(OnFlushRequest(kStreamIndex0));
-  ASSERT_OK(OnFlushRequest(kStreamIndex1));
-  EXPECT_THAT(GetOutputStreamDataVector(), IsEmpty());
-}
-
-TEST_F(ChunkingHandlerTest, Scte35Event) {
   ChunkingParams chunking_params;
   chunking_params.segment_duration_in_seconds = 1;
   chunking_params.subsegment_duration_in_seconds = 0.5;
   SetUpChunkingHandler(1, chunking_params);
 
   ASSERT_OK(Process(StreamData::FromStreamInfo(
-      kStreamIndex0, GetVideoStreamInfo(kTimeScale1))));
+      kStreamIndex, GetVideoStreamInfo(kTimeScale1))));
 
   const int64_t kVideoStartTimestamp = 12345;
-  const double kScte35TimeInSeconds =
+  const double kCueTimeInSeconds =
-      static_cast<double>(kVideoStartTimestamp + kDuration1) / kTimeScale1;
+      static_cast<double>(kVideoStartTimestamp + kDuration) / kTimeScale1;
 
-  auto scte35_event = std::make_shared<Scte35Event>();
+  auto cue_event = std::make_shared<CueEvent>();
-  scte35_event->start_time_in_seconds = kScte35TimeInSeconds;
+  cue_event->time_in_seconds = kCueTimeInSeconds;
-  ASSERT_OK(Process(StreamData::FromScte35Event(kStreamIndex0, scte35_event)));
 
   for (int i = 0; i < 3; ++i) {
     const bool is_key_frame = true;
     ASSERT_OK(Process(StreamData::FromMediaSample(
-        kStreamIndex0, GetMediaSample(kVideoStartTimestamp + i * kDuration1,
+        kStreamIndex, GetMediaSample(kVideoStartTimestamp + i * kDuration,
-                                      kDuration1, is_key_frame))));
+                                     kDuration, is_key_frame))));
+    if (i == 0) {
+      ASSERT_OK(Process(StreamData::FromCueEvent(kStreamIndex, cue_event)));
+    }
   }
 
   EXPECT_THAT(
       GetOutputStreamDataVector(),
       ElementsAre(
-          IsStreamInfo(kStreamIndex0, kTimeScale1, !kEncrypted),
+          IsStreamInfo(kStreamIndex, kTimeScale1, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kVideoStartTimestamp, kDuration1,
+          IsMediaSample(kStreamIndex, kVideoStartTimestamp, kDuration,
                         !kEncrypted),
           // A new segment is created due to the existance of Cue.
-          IsSegmentInfo(kStreamIndex0, kVideoStartTimestamp, kDuration1,
+          IsSegmentInfo(kStreamIndex, kVideoStartTimestamp, kDuration,
                         !kIsSubsegment, !kEncrypted),
-          IsCueEvent(kStreamIndex0, kScte35TimeInSeconds),
+          IsCueEvent(kStreamIndex, kCueTimeInSeconds),
-          IsMediaSample(kStreamIndex0, kVideoStartTimestamp + kDuration1 * 1,
+          IsMediaSample(kStreamIndex, kVideoStartTimestamp + kDuration * 1,
-                        kDuration1, !kEncrypted),
+                        kDuration, !kEncrypted),
-          IsMediaSample(kStreamIndex0, kVideoStartTimestamp + kDuration1 * 2,
+          IsMediaSample(kStreamIndex, kVideoStartTimestamp + kDuration * 2,
-                        kDuration1, !kEncrypted)));
+                        kDuration, !kEncrypted)));
 }
 
 }  // namespace media

packager/media/chunking/cue_alignment_handler.cc

@@ -20,7 +20,18 @@ double TimeInSeconds(const StreamInfo& info, const StreamData& data) {
   switch (data.stream_data_type) {
     case StreamDataType::kMediaSample:
       time_scale = info.time_scale();
+      if (info.stream_type() == kStreamAudio) {
+        // Return the start time for video and mid-point for audio, so that for
+        // an audio sample, if the portion of the sample after the cue point is
+        // bigger than the portion of the sample before the cue point, the
+        // sample is placed after the cue.
+        // It does not matter for text samples as text samples will be cut at
+        // cue point.
+        scaled_time =
+            data.media_sample->pts() + data.media_sample->duration() / 2;
+      } else {
         scaled_time = data.media_sample->pts();
+      }
       break;
     case StreamDataType::kTextSample:
       // Text is always in MS but the stream info time scale is 0.
@@ -80,7 +91,7 @@ Status CueAlignmentHandler::OnFlushRequest(size_t stream_index) {
     if (!stream_state.samples.empty()) {
       LOG(WARNING) << "Unexpected data seen on stream " << i;
       while (!stream_state.samples.empty()) {
-        Status status(Dispatch(std::move(stream_state.samples.front())));
+        Status status = Dispatch(std::move(stream_state.samples.front()));
         if (!status.ok())
           return status;
         stream_state.samples.pop_front();
@@ -141,7 +152,7 @@ Status CueAlignmentHandler::OnSample(std::unique_ptr<StreamData> sample) {
 
   // Accept the sample. This will output it if it comes before the hint point or
   // will cache it if it comes after the hint point.
-  Status status(AcceptSample(std::move(sample), &stream_state));
+  Status status = AcceptSample(std::move(sample), &stream_state);
   if (!status.ok()) {
     return status;
   }
@@ -180,6 +191,8 @@ Status CueAlignmentHandler::UseNewSyncPoint(
     // No stream should be so out of sync with the others that they would
     // still be working on an old cue.
     if (stream_state.cue) {
+      // TODO(kqyang): Could this happen for text when there are no text samples
+      // between the two cues?
       LOG(ERROR) << "Found two cue events that are too close together. One at "
                  << stream_state.cue->time_in_seconds << " and the other at "
                  << new_sync->time_in_seconds;

packager/packager.cc

@@ -33,6 +33,7 @@
 #include "packager/media/base/muxer_options.h"
 #include "packager/media/base/muxer_util.h"
 #include "packager/media/chunking/chunking_handler.h"
+#include "packager/media/chunking/cue_alignment_handler.h"
 #include "packager/media/crypto/encryption_handler.h"
 #include "packager/media/demuxer/demuxer.h"
 #include "packager/media/event/muxer_listener_factory.h"
@@ -55,6 +56,7 @@ namespace shaka {
 using media::Demuxer;
 using media::KeySource;
 using media::MuxerOptions;
+using media::SyncPointQueue;
 
 namespace media {
 namespace {
@@ -375,8 +377,15 @@ std::shared_ptr<MediaHandler> CreateEncryptionHandler(
 Status CreateMp4ToMp4TextJob(const StreamDescriptor& stream,
                              const PackagingParams& packaging_params,
                              std::unique_ptr<MuxerListener> muxer_listener,
+                             SyncPointQueue* sync_points,
                              MuxerFactory* muxer_factory,
                              std::shared_ptr<OriginHandler>* root) {
+  // TODO(kqyang): This need to be integrated back to media pipeline since we
+  // may want to get not only text streams from the demuxer, in which case, the
+  // same demuxer should be used to get all streams instead of having a demuxer
+  // specifically for text.
+  // TODO(kqyang): Support Cue Alignment if |sync_points| is not null.
+
   Status status;
   std::shared_ptr<Demuxer> demuxer;
 
@@ -385,14 +394,15 @@ Status CreateMp4ToMp4TextJob(const StreamDescriptor& stream,
     demuxer->SetLanguageOverride(stream.stream_selector, stream.language);
   }
 
-  std::shared_ptr<MediaHandler> chunker(
+  auto chunker =
-      new ChunkingHandler(packaging_params.chunking_params));
+      std::make_shared<ChunkingHandler>(packaging_params.chunking_params);
   std::shared_ptr<Muxer> muxer =
       muxer_factory->CreateMuxer(GetOutputFormat(stream), stream);
   muxer->SetMuxerListener(std::move(muxer_listener));
 
   status.Update(chunker->AddHandler(std::move(muxer)));
-  status.Update(demuxer->SetHandler(stream.stream_selector, chunker));
+  status.Update(
+      demuxer->SetHandler(stream.stream_selector, std::move(chunker)));
 
   return status;
 }
@@ -400,7 +410,10 @@ Status CreateMp4ToMp4TextJob(const StreamDescriptor& stream,
 Status CreateHlsTextJob(const StreamDescriptor& stream,
                         const PackagingParams& packaging_params,
                         std::unique_ptr<MuxerListener> muxer_listener,
+                        SyncPointQueue* sync_points,
                         JobManager* job_manager) {
+  // TODO(kqyang): Support Cue Alignment if |sync_points| is not null.
+
   DCHECK(muxer_listener);
   DCHECK(job_manager);
 
@@ -421,9 +434,8 @@ Status CreateHlsTextJob(const StreamDescriptor& stream,
   MuxerOptions muxer_options = CreateMuxerOptions(stream, packaging_params);
   muxer_options.bandwidth = stream.bandwidth ? stream.bandwidth : 256;
 
-  std::shared_ptr<WebVttSegmentedOutputHandler> output(
+  auto output = std::make_shared<WebVttSegmentedOutputHandler>(
-      new WebVttSegmentedOutputHandler(muxer_options,
+      muxer_options, std::move(muxer_listener));
-                                       std::move(muxer_listener)));
 
   std::unique_ptr<FileReader> reader;
   Status open_status = FileReader::Open(stream.input, &reader);
@@ -431,10 +443,9 @@ Status CreateHlsTextJob(const StreamDescriptor& stream,
     return open_status;
   }
 
-  std::shared_ptr<OriginHandler> parser(
+  auto parser =
-      new WebVttParser(std::move(reader), stream.language));
+      std::make_shared<WebVttParser>(std::move(reader), stream.language);
-  std::shared_ptr<MediaHandler> segmenter(
+  auto segmenter = std::make_shared<WebVttSegmenter>(segment_length_in_ms);
-      new WebVttSegmenter(segment_length_in_ms));
 
   // Build in reverse to allow us to move the pointers.
   Status status;
@@ -451,8 +462,11 @@ Status CreateHlsTextJob(const StreamDescriptor& stream,
 Status CreateWebVttToMp4TextJob(const StreamDescriptor& stream,
                                 const PackagingParams& packaging_params,
                                 std::unique_ptr<MuxerListener> muxer_listener,
+                                SyncPointQueue* sync_points,
                                 MuxerFactory* muxer_factory,
                                 std::shared_ptr<OriginHandler>* root) {
+  // TODO(kqyang): Support Cue Alignment if |sync_points| is not null.
+
   Status status;
   std::unique_ptr<FileReader> reader;
   status = FileReader::Open(stream.input, &reader);
@@ -461,11 +475,11 @@ Status CreateWebVttToMp4TextJob(const StreamDescriptor& stream,
     return status;
   }
 
-  std::shared_ptr<OriginHandler> parser(
+  auto parser =
-      new WebVttParser(std::move(reader), stream.language));
+      std::make_shared<WebVttParser>(std::move(reader), stream.language);
-  std::shared_ptr<MediaHandler> text_to_mp4(new WebVttToMp4Handler);
+  auto text_to_mp4 = std::make_shared<WebVttToMp4Handler>();
-  std::shared_ptr<MediaHandler> chunker(
+  auto chunker =
-      new ChunkingHandler(packaging_params.chunking_params));
+      std::make_shared<ChunkingHandler>(packaging_params.chunking_params);
   std::shared_ptr<Muxer> muxer =
       muxer_factory->CreateMuxer(GetOutputFormat(stream), stream);
   muxer->SetMuxerListener(std::move(muxer_listener));
@@ -482,6 +496,7 @@ Status CreateWebVttToMp4TextJob(const StreamDescriptor& stream,
 Status CreateTextJobs(
     const std::vector<std::reference_wrapper<const StreamDescriptor>>& streams,
     const PackagingParams& packaging_params,
+    SyncPointQueue* sync_points,
     MuxerListenerFactory* muxer_listener_factory,
     MuxerFactory* muxer_factory,
     MpdNotifier* mpd_notifier,
@@ -498,14 +513,14 @@ Status CreateTextJobs(
 
       switch (DetermineContainerFromFileName(stream.input)) {
         case CONTAINER_WEBVTT:
-          status.Update(CreateWebVttToMp4TextJob(stream, packaging_params,
+          status.Update(CreateWebVttToMp4TextJob(
-                                                 std::move(muxer_listener),
+              stream, packaging_params, std::move(muxer_listener), sync_points,
               muxer_factory, &root));
           break;
 
         case CONTAINER_MOV:
-          status.Update(CreateMp4ToMp4TextJob(stream, packaging_params,
+          status.Update(CreateMp4ToMp4TextJob(
-                                              std::move(muxer_listener),
+              stream, packaging_params, std::move(muxer_listener), sync_points,
               muxer_factory, &root));
           break;
 
@@ -543,8 +558,9 @@ Status CreateTextJobs(
       // If we are outputting to HLS, then create the HLS test pipeline that
       // will create segmented text output.
       if (hls_listener) {
-        Status status = CreateHlsTextJob(stream, packaging_params,
+        Status status =
-                                         std::move(hls_listener), job_manager);
+            CreateHlsTextJob(stream, packaging_params, std::move(hls_listener),
+                             sync_points, job_manager);
         if (!status.ok()) {
           return status;
         }
@@ -592,6 +608,7 @@ Status CreateAudioVideoJobs(
     const std::vector<std::reference_wrapper<const StreamDescriptor>>& streams,
     const PackagingParams& packaging_params,
     KeySource* encryption_key_source,
+    SyncPointQueue* sync_points,
     MuxerListenerFactory* muxer_listener_factory,
     MuxerFactory* muxer_factory,
     JobManager* job_manager) {
@@ -601,14 +618,14 @@ Status CreateAudioVideoJobs(
 
   // Demuxers are shared among all streams with the same input.
   std::shared_ptr<Demuxer> demuxer;
-  // Chunkers can be shared among all streams with the same input (except for
+  // When |sync_points| is not null, there should be one CueAlignmentHandler per
-  // WVM files), which allows samples from the same input to be synced when
+  // input. All CueAlignmentHandler shares the same |sync_points|, which allows
-  // doing chunking.
+  // sync points / cues to be aligned across streams, whether they are from the
-  std::shared_ptr<MediaHandler> chunker;
+  // same input or not.
-  bool is_wvm_file = false;
+  std::shared_ptr<CueAlignmentHandler> cue_aligner;
   // Replicators are shared among all streams with the same input and stream
   // selector.
-  std::shared_ptr<MediaHandler> replicator;
+  std::shared_ptr<Replicator> replicator;
 
   std::string previous_input;
   std::string previous_selector;
@@ -624,15 +641,8 @@ Status CreateAudioVideoJobs(
 
       job_manager->Add("RemuxJob", demuxer);
 
-      // Share chunkers among all streams with the same input except for WVM
+      if (sync_points)
-      // file, which may contain multiple video files and the samples may not be
+        cue_aligner = std::make_shared<CueAlignmentHandler>(sync_points);
-      // interleaved either.
-      is_wvm_file =
-          DetermineContainerFromFileName(stream.input) == CONTAINER_WVM;
-      if (!is_wvm_file) {
-        chunker =
-            std::make_shared<ChunkingHandler>(packaging_params.chunking_params);
-      }
     }
 
     if (!stream.language.empty()) {
@@ -651,16 +661,8 @@ Status CreateAudioVideoJobs(
     }
 
     if (new_stream) {
-      std::shared_ptr<MediaHandler> ad_cue_generator;
+      auto chunker =
-      if (!packaging_params.ad_cue_generator_params.cue_points.empty()) {
-        ad_cue_generator = std::make_shared<AdCueGenerator>(
-            packaging_params.ad_cue_generator_params);
-      }
-
-      if (is_wvm_file) {
-        chunker =
           std::make_shared<ChunkingHandler>(packaging_params.chunking_params);
-      }
 
       std::shared_ptr<MediaHandler> encryptor = CreateEncryptionHandler(
           packaging_params, stream, encryption_key_source);
@@ -668,10 +670,9 @@ Status CreateAudioVideoJobs(
       replicator = std::make_shared<Replicator>();
 
       Status status;
-      if (ad_cue_generator) {
+      if (cue_aligner) {
-        status.Update(
+        status.Update(demuxer->SetHandler(stream.stream_selector, cue_aligner));
-            demuxer->SetHandler(stream.stream_selector, ad_cue_generator));
+        status.Update(cue_aligner->AddHandler(chunker));
-        status.Update(ad_cue_generator->AddHandler(chunker));
       } else {
         status.Update(demuxer->SetHandler(stream.stream_selector, chunker));
       }
@@ -729,6 +730,7 @@ Status CreateAllJobs(const std::vector<StreamDescriptor>& stream_descriptors,
                      const PackagingParams& packaging_params,
                      MpdNotifier* mpd_notifier,
                      KeySource* encryption_key_source,
+                     SyncPointQueue* sync_points,
                      MuxerListenerFactory* muxer_listener_factory,
                      MuxerFactory* muxer_factory,
                      JobManager* job_manager) {
@@ -758,11 +760,11 @@ Status CreateAllJobs(const std::vector<StreamDescriptor>& stream_descriptors,
             media::StreamDescriptorCompareFn);
 
   Status status;
-  status.Update(CreateTextJobs(text_streams, packaging_params,
+  status.Update(CreateTextJobs(text_streams, packaging_params, sync_points,
                                muxer_listener_factory, muxer_factory,
                                mpd_notifier, job_manager));
   status.Update(CreateAudioVideoJobs(
-      audio_video_streams, packaging_params, encryption_key_source,
+      audio_video_streams, packaging_params, encryption_key_source, sync_points,
       muxer_listener_factory, muxer_factory, job_manager));
 
   if (!status.ok()) {
@@ -783,6 +785,7 @@ struct Packager::PackagerInternal {
   std::unique_ptr<KeySource> encryption_key_source;
   std::unique_ptr<MpdNotifier> mpd_notifier;
   std::unique_ptr<hls::HlsNotifier> hls_notifier;
+  std::unique_ptr<SyncPointQueue> sync_points;
   BufferCallbackParams buffer_callback_params;
   media::JobManager job_manager;
 };
@@ -854,6 +857,11 @@ Status Packager::Initialize(
     internal->hls_notifier.reset(new hls::SimpleHlsNotifier(hls_params));
   }
 
+  if (!packaging_params.ad_cue_generator_params.cue_points.empty()) {
+    internal->sync_points.reset(
+        new SyncPointQueue(packaging_params.ad_cue_generator_params));
+  }
+
   std::vector<StreamDescriptor> streams_for_jobs;
 
   for (const StreamDescriptor& descriptor : stream_descriptors) {
@@ -896,8 +904,8 @@ Status Packager::Initialize(
 
   Status status = media::CreateAllJobs(
       streams_for_jobs, packaging_params, internal->mpd_notifier.get(),
-      internal->encryption_key_source.get(), &muxer_listener_factory,
+      internal->encryption_key_source.get(), internal->sync_points.get(),
-      &muxer_factory, &internal->job_manager);
+      &muxer_listener_factory, &muxer_factory, &internal->job_manager);
 
   if (!status.ok()) {
     return status;