Always set ES_ID to 0 when writing ES Descriptor in mp4 (#798)

Required by ISO/IEC 14496-14:2018 and ISO/IEC 23000-19:2018.

Issue #755.

packager/app/test/testdata/audio-video-with-codec-switching/output.mpd

@@ -15,18 +15,18 @@
     <AdaptationSet id="1" contentType="video" maxWidth="1280" maxHeight="720" frameRate="30000/1001" subsegmentAlignment="true" par="16:9">
       <SupplementalProperty schemeIdUri="urn:mpeg:dash:adaptation-set-switching:2016" value="0"/>
       <Role schemeIdUri="urn:mpeg:dash:role:2011" value="main"/>
-      <Representation id="1" bandwidth="2627285" codecs="avc1.64001f" mimeType="video/mp4" sar="1:1" width="1280" height="720">
-        <BaseURL>bear-1280x720-video.mp4</BaseURL>
-        <SegmentBase indexRange="858-925" timescale="30000">
-          <Initialization range="0-857"/>
-        </SegmentBase>
-      </Representation>
-      <Representation id="2" bandwidth="973483" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1" width="640" height="360">
+      <Representation id="1" bandwidth="973483" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1" width="640" height="360">
         <BaseURL>bear-640x360-video.mp4</BaseURL>
         <SegmentBase indexRange="859-926" timescale="30000">
           <Initialization range="0-858"/>
         </SegmentBase>
       </Representation>
+      <Representation id="2" bandwidth="2627285" codecs="avc1.64001f" mimeType="video/mp4" sar="1:1" width="1280" height="720">
+        <BaseURL>bear-1280x720-video.mp4</BaseURL>
+        <SegmentBase indexRange="858-925" timescale="30000">
+          <Initialization range="0-857"/>
+        </SegmentBase>
+      </Representation>
     </AdaptationSet>
     <AdaptationSet id="2" contentType="audio" subsegmentAlignment="true">
       <Representation id="3" bandwidth="133334" codecs="mp4a.40.2" mimeType="audio/mp4" audioSamplingRate="44100">

packager/app/test/testdata/live-profile-and-encryption-and-mult-files/output.mpd

@@ -7,15 +7,7 @@
       <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
         <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAExMjM0NTY3ODkwMTIzNDU2AAAAAA==</cenc:pssh>
       </ContentProtection>
-      <Representation id="0" bandwidth="2632184" codecs="avc1.64001f" mimeType="video/mp4" sar="1:1" width="1280" height="720">
-        <SegmentTemplate timescale="30000" initialization="bear-1280x720-video-init.mp4" media="bear-1280x720-video-$Number$.m4s" startNumber="1">
-          <SegmentTimeline>
-            <S t="0" d="30030" r="1"/>
-            <S t="60060" d="22022"/>
-          </SegmentTimeline>
-        </SegmentTemplate>
-      </Representation>
-      <Representation id="1" bandwidth="978382" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1" width="640" height="360">
+      <Representation id="0" bandwidth="978382" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1" width="640" height="360">
         <SegmentTemplate timescale="30000" initialization="bear-640x360-video-init.mp4" media="bear-640x360-video-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
             <S t="0" d="30030" r="1"/>
@@ -23,7 +15,7 @@
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>
-      <Representation id="2" bandwidth="383593" codecs="avc1.64000d" mimeType="video/mp4" sar="1:1" width="320" height="180">
+      <Representation id="1" bandwidth="383593" codecs="avc1.64000d" mimeType="video/mp4" sar="1:1" width="320" height="180">
         <SegmentTemplate timescale="30000" initialization="bear-320x180-video-init.mp4" media="bear-320x180-video-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
             <S t="0" d="30030" r="1"/>
@@ -31,6 +23,14 @@
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>
+      <Representation id="2" bandwidth="2632184" codecs="avc1.64001f" mimeType="video/mp4" sar="1:1" width="1280" height="720">
+        <SegmentTemplate timescale="30000" initialization="bear-1280x720-video-init.mp4" media="bear-1280x720-video-$Number$.m4s" startNumber="1">
+          <SegmentTimeline>
+            <S t="0" d="30030" r="1"/>
+            <S t="60060" d="22022"/>
+          </SegmentTimeline>
+        </SegmentTemplate>
+      </Representation>
     </AdaptationSet>
     <AdaptationSet id="1" contentType="audio" segmentAlignment="true">
       <ContentProtection value="cenc" schemeIdUri="urn:mpeg:dash:mp4protection:2011" cenc:default_KID="31323334-3536-3738-3930-313233343536"/>
@@ -39,7 +39,7 @@
       </ContentProtection>
       <Representation id="3" bandwidth="134272" 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="bear-1280x720-audio-init.mp4" media="bear-1280x720-audio-$Number$.m4s" startNumber="1">
+        <SegmentTemplate timescale="44100" initialization="bear-640x360-audio-init.mp4" media="bear-640x360-audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
             <S t="0" d="45056"/>
             <S t="45056" d="44032"/>
@@ -49,7 +49,7 @@
       </Representation>
       <Representation id="4" bandwidth="134272" 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="bear-640x360-audio-init.mp4" media="bear-640x360-audio-$Number$.m4s" startNumber="1">
+        <SegmentTemplate timescale="44100" initialization="bear-1280x720-audio-init.mp4" media="bear-1280x720-audio-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
             <S t="0" d="45056"/>
             <S t="45056" d="44032"/>

packager/app/test/testdata/vtt-text-to-mp4-with-ad-cues/output.mpd

@@ -2,22 +2,22 @@
 <!--Generated with https://github.com/google/shaka-packager version <tag>-<hash>-<test>-->
 <MPD xmlns="urn:mpeg:dash:schema:mpd:2011" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="urn:mpeg:dash:schema:mpd:2011 DASH-MPD.xsd" profiles="urn:mpeg:dash:profile:isoff-live:2011" minBufferTime="PT2S" type="static" mediaPresentationDuration="PT2.7360668182373047S">
   <Period id="0" duration="PT2.002S">
-    <AdaptationSet id="0" contentType="text" segmentAlignment="true">
-      <Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle"/>
-      <Representation id="0" bandwidth="1912" codecs="wvtt" mimeType="application/mp4">
-        <SegmentTemplate timescale="1000" initialization="bear-english-text-init.mp4" media="bear-english-text-$Number$.m4s" startNumber="1">
+    <AdaptationSet id="0" contentType="video" width="640" height="360" frameRate="30000/1001" segmentAlignment="true" par="16:9">
+      <Representation id="0" bandwidth="974122" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
+        <SegmentTemplate timescale="30000" initialization="bear-640x360-video-init.mp4" media="bear-640x360-video-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="1000" r="1"/>
-            <S t="2000" d="1"/>
+            <S t="0" d="30030" r="1"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>
     </AdaptationSet>
-    <AdaptationSet id="1" contentType="video" width="640" height="360" frameRate="30000/1001" segmentAlignment="true" par="16:9">
-      <Representation id="1" bandwidth="974122" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
-        <SegmentTemplate timescale="30000" initialization="bear-640x360-video-init.mp4" media="bear-640x360-video-$Number$.m4s" startNumber="1">
+    <AdaptationSet id="1" contentType="text" segmentAlignment="true">
+      <Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle"/>
+      <Representation id="1" bandwidth="1912" codecs="wvtt" mimeType="application/mp4">
+        <SegmentTemplate timescale="1000" initialization="bear-english-text-init.mp4" media="bear-english-text-$Number$.m4s" startNumber="1">
           <SegmentTimeline>
-            <S t="0" d="30030" r="1"/>
+            <S t="0" d="1000" r="1"/>
+            <S t="2000" d="1"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>
@@ -35,21 +35,21 @@
     </AdaptationSet>
   </Period>
   <Period id="1" duration="PT.7340666666666671S">
-    <AdaptationSet id="0" contentType="text" segmentAlignment="true">
-      <Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle"/>
-      <Representation id="0" bandwidth="2024" codecs="wvtt" mimeType="application/mp4">
-        <SegmentTemplate timescale="1000" presentationTimeOffset="2001" initialization="bear-english-text-init.mp4" media="bear-english-text-$Number$.m4s" startNumber="4">
+    <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="60059" initialization="bear-640x360-video-init.mp4" media="bear-640x360-video-$Number$.m4s" startNumber="3">
           <SegmentTimeline>
-            <S t="2001" d="1000" r="2"/>
+            <S t="60060" d="22022"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>
     </AdaptationSet>
-    <AdaptationSet id="1" contentType="video" width="640" height="360" frameRate="30000/1001" segmentAlignment="true" par="16:9">
-      <Representation id="1" bandwidth="869044" codecs="avc1.64001e" mimeType="video/mp4" sar="1:1">
-        <SegmentTemplate timescale="30000" presentationTimeOffset="60059" initialization="bear-640x360-video-init.mp4" media="bear-640x360-video-$Number$.m4s" startNumber="3">
+    <AdaptationSet id="1" contentType="text" segmentAlignment="true">
+      <Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle"/>
+      <Representation id="1" bandwidth="2024" codecs="wvtt" mimeType="application/mp4">
+        <SegmentTemplate timescale="1000" presentationTimeOffset="2001" initialization="bear-english-text-init.mp4" media="bear-english-text-$Number$.m4s" startNumber="4">
           <SegmentTimeline>
-            <S t="60060" d="22022"/>
+            <S t="2001" d="1000" r="2"/>
           </SegmentTimeline>
         </SegmentTemplate>
       </Representation>

packager/media/codecs/es_descriptor.cc

@@ -219,7 +219,10 @@ bool ESDescriptor::ReadData(BitReader* reader) {
 void ESDescriptor::WriteInternal(BufferWriter* writer) {
   WriteHeader(writer);
 
-  writer->AppendInt(esid_);
+  // According to ISO/IEC 14496-14:2018 Section 4.1.2, 
+  // ES_ID is set to 0 when stored
+  const uint16_t kEsid = 0;
+  writer->AppendInt(kEsid);
   const uint8_t kNoEsFlags = 0;
   writer->AppendInt(kNoEsFlags);
 

packager/media/codecs/es_descriptor.h

@@ -175,7 +175,6 @@ class ESDescriptor : public BaseDescriptor {
   ESDescriptor() : BaseDescriptor(DescriptorTag::kES) {}
 
   uint16_t esid() const { return esid_; }
-  void set_esid(uint16_t esid) { esid_ = esid; }
 
   const DecoderConfigDescriptor& decoder_config_descriptor() const {
     return decoder_config_descriptor_;

packager/media/codecs/es_descriptor_unittest.cc

@@ -21,7 +21,7 @@ TEST(ESDescriptorTest, SingleByteLengthTest) {
       // ESDescriptor tag with one byte size.
       0x03, 0x19,
         // ESDescriptor fields.
-        0x00, 0x01, 0x00,
+        0x00, 0x00, 0x00,
         // DecoderConfigDescriptor tag with one byte size.
         0x04, 0x11,
           // Object Type.
@@ -56,6 +56,19 @@ TEST(ESDescriptorTest, SingleByteLengthTest) {
   EXPECT_THAT(
       std::vector<uint8_t>(writer.Buffer(), writer.Buffer() + writer.Size()),
       ElementsAreArray(kBuffer));
+  
+  EXPECT_EQ(0u, es_desc.esid());
+  const size_t kEsIdOffset = 3;
+  const uint8_t kEsId = 5;
+  data[kEsIdOffset] = kEsId;
+  ASSERT_TRUE(es_desc.Parse(data));
+  EXPECT_EQ(kEsId, es_desc.esid());
+
+  writer.Clear();
+  es_desc.Write(&writer);
+  EXPECT_THAT(
+      std::vector<uint8_t>(writer.Buffer(), writer.Buffer() + writer.Size()),
+      ElementsAreArray(kBuffer));
 }
 
 TEST(ESDescriptorTest, NonAACTest) {
@@ -64,7 +77,7 @@ TEST(ESDescriptorTest, NonAACTest) {
       // ESDescriptor tag with one byte size.
       0x03, 0x19,
         // ESDescriptor fields.
-        0x00, 0x01, 0x00,
+        0x00, 0x00, 0x00,
         // DecoderConfigDescriptor tag with one byte size.
         0x04, 0x11,
           // Object Type.

packager/media/formats/mp4/box_definitions_unittest.cc

@@ -383,7 +383,6 @@ class BoxDefinitionsTestGeneral : public testing::Test {
 
   void Fill(ElementaryStreamDescriptor* esds) {
     const uint8_t kDecoderSpecificInfo[] = {18, 16};
-    esds->es_descriptor.set_esid(1);
     esds->es_descriptor.mutable_decoder_config_descriptor()->set_object_type(
         ObjectType::kISO_14496_3);
     std::vector<uint8_t> decoder_specific_info(
@@ -394,10 +393,6 @@ class BoxDefinitionsTestGeneral : public testing::Test {
         ->set_data(decoder_specific_info);
   }
 
-  void Modify(ElementaryStreamDescriptor* esds) {
-    esds->es_descriptor.set_esid(2);
-  }
-
   void Fill(DTSSpecific* ddts) {
     const uint8_t kDdtsExtraData[] = {0xe4, 0x7c, 0, 4, 0, 0x0f, 0};
     ddts->max_bitrate = 768000;

packager/media/formats/mp4/mp4_muxer.cc

@@ -250,15 +250,15 @@ Status MP4Muxer::DelayInitializeMuxer() {
     switch (stream->stream_type()) {
       case kStreamVideo:
         generate_trak_result = GenerateVideoTrak(
-            static_cast<const VideoStreamInfo*>(stream), &trak, i + 1);
+            static_cast<const VideoStreamInfo*>(stream), &trak);
         break;
       case kStreamAudio:
         generate_trak_result = GenerateAudioTrak(
-            static_cast<const AudioStreamInfo*>(stream), &trak, i + 1);
+            static_cast<const AudioStreamInfo*>(stream), &trak);
         break;
       case kStreamText:
         generate_trak_result = GenerateTextTrak(
-            static_cast<const TextStreamInfo*>(stream), &trak, i + 1);
+            static_cast<const TextStreamInfo*>(stream), &trak);
         break;
       default:
         NOTIMPLEMENTED() << "Not implemented for stream type: "
@@ -395,8 +395,7 @@ void MP4Muxer::InitializeTrak(const StreamInfo* info, Track* trak) {
 }
 
 bool MP4Muxer::GenerateVideoTrak(const VideoStreamInfo* video_info,
-                                 Track* trak,
-                                 uint32_t track_id) {
+                                 Track* trak) {
   InitializeTrak(video_info, trak);
 
   // width and height specify the track's visual presentation size as
@@ -449,8 +448,7 @@ bool MP4Muxer::GenerateVideoTrak(const VideoStreamInfo* video_info,
 }
 
 bool MP4Muxer::GenerateAudioTrak(const AudioStreamInfo* audio_info,
-                                 Track* trak,
-                                 uint32_t track_id) {
+                                 Track* trak) {
   InitializeTrak(audio_info, trak);
 
   trak->header.volume = 0x100;
@@ -460,7 +458,6 @@ bool MP4Muxer::GenerateAudioTrak(const AudioStreamInfo* audio_info,
       CodecToFourCC(audio_info->codec(), H26xStreamFormat::kUnSpecified);
   switch(audio_info->codec()){
     case kCodecAAC: {
-      audio.esds.es_descriptor.set_esid(track_id);
       DecoderConfigDescriptor* decoder_config =
           audio.esds.es_descriptor.mutable_decoder_config_descriptor();
       decoder_config->set_object_type(ObjectType::kISO_14496_3);  // MPEG4 AAC.
@@ -494,7 +491,6 @@ bool MP4Muxer::GenerateAudioTrak(const AudioStreamInfo* audio_info,
       audio.dfla.data = audio_info->codec_config();
       break;
     case kCodecMP3: {
-      audio.esds.es_descriptor.set_esid(track_id);
       DecoderConfigDescriptor* decoder_config =
           audio.esds.es_descriptor.mutable_decoder_config_descriptor();
       uint32_t samplerate = audio_info->sampling_frequency();
@@ -567,8 +563,7 @@ bool MP4Muxer::GenerateAudioTrak(const AudioStreamInfo* audio_info,
 }
 
 bool MP4Muxer::GenerateTextTrak(const TextStreamInfo* text_info,
-                                Track* trak,
-                                uint32_t track_id) {
+                                Track* trak) {
   InitializeTrak(text_info, trak);
 
   if (text_info->codec_string() == "wvtt") {

packager/media/formats/mp4/mp4_muxer.h

@@ -48,15 +48,9 @@ class MP4Muxer : public Muxer {
 
   // Generate Audio/Video Track box.
   void InitializeTrak(const StreamInfo* info, Track* trak);
-  bool GenerateAudioTrak(const AudioStreamInfo* audio_info,
-                         Track* trak,
-                         uint32_t track_id);
-  bool GenerateVideoTrak(const VideoStreamInfo* video_info,
-                         Track* trak,
-                         uint32_t track_id);
-  bool GenerateTextTrak(const TextStreamInfo* video_info,
-                        Track* trak,
-                        uint32_t track_id);
+  bool GenerateAudioTrak(const AudioStreamInfo* audio_info, Track* trak);
+  bool GenerateVideoTrak(const VideoStreamInfo* video_info, Track* trak);
+  bool GenerateTextTrak(const TextStreamInfo* video_info, Track* trak);
 
   // Gets |start| and |end| initialization range. Returns true if there is an
   // init range and sets start-end byte-range-spec specified in RFC2616.