Parsing of encoded duration for unencrypted opus streams.

media/formats/webm/webm_cluster_parser.h

Index: media/formats/webm/webm_cluster_parser.h
diff --git a/media/formats/webm/webm_cluster_parser.h b/media/formats/webm/webm_cluster_parser.h
index 2af102eaa0ce58b28909a6aa15fffd1bdbe4ed00..f3d5541ec516da8e2eeba89d4d3b2c5f1d5ff0b6 100644
--- a/media/formats/webm/webm_cluster_parser.h
+++ b/media/formats/webm/webm_cluster_parser.h
@@ -11,6 +11,7 @@
 #include <string>
 
 #include "base/memory/scoped_ptr.h"
+#include "media/base/audio_decoder_config.h"
 #include "media/base/media_export.h"
 #include "media/base/media_log.h"
 #include "media/base/stream_parser.h"
@@ -35,6 +36,17 @@ class MEDIA_EXPORT WebMClusterParser : public WebMParserClient {
     kDefaultVideoBufferDurationInMs = 42  // Low 24fps to reduce stalls
   };
 
+  // Opus packets encode the duration and other parameters in the 5 most

[wolenetz, 2015/01/30 01:48:08]

move to impl. drop last ','

[chcunningham, 2015/02/03 20:34:43]

Done.

+  // significant bits of the first byte. The index in this array corresponds
+  // to the duration of each frame of the packet in microseconds. See
+  // http://goo.gl/2RmoxA
+  const uint16 kOpusFrameDurationsMu[32] = {
+      10000, 20000, 40000, 60000, 10000, 20000, 40000, 60000,
+      10000, 20000, 40000, 60000, 10000, 20000, 10000, 20000,
+      2500,  5000,  10000, 20000, 2500,  5000,  10000, 20000,
+      2500,  5000,  10000, 20000, 2500,  5000,  10000, 20000,
+  };
+
  private:
   // Helper class that manages per-track state.
   class Track {
@@ -143,6 +155,7 @@ class MEDIA_EXPORT WebMClusterParser : public WebMParserClient {
                     const std::set<int64>& ignored_tracks,
                     const std::string& audio_encryption_key_id,
                     const std::string& video_encryption_key_id,
+                    const AudioDecoderConfig& audio_config,
                     const LogCB& log_cb);
   ~WebMClusterParser() override;
 
@@ -227,11 +240,24 @@ class MEDIA_EXPORT WebMClusterParser : public WebMParserClient {
   // if that track num is not a text track.
   Track* FindTextTrack(int track_num);
 
+  // Attempts to read the duration from the encoded audio data, storing output
+  // in |duration| in microseconds. This obviously violates layering rules, but
+  // is useful for MSE to know duration in cases where it isn't explicitly given
+  // and cannot be calculated when for Blocks at the end of a Cluster (The next

[wolenetz, 2015/01/30 01:48:08]

nits: grammar (when for), un-cap (The

[chcunningham, 2015/02/03 20:34:43]

Done.

+  // Cluster in playback-order may not be the next Cluster we parse, so we can't
+  // simply use the delta of the first Block in the next Cluster). Avoid calling
+  // if encrypted; may produce unexpected output. See implementation for
+  // supported codecs.
+  bool TryGetEncodedAudioDuration(const uint8* data, int size, int64* duration);

[wolenetz, 2015/01/30 01:48:08]

What is bool retval?

[chcunningham, 2015/02/03 20:34:43]

Now base::TimeDelta

+  // Reads Opus packet header to determine packet duration.

[wolenetz, 2015/01/30 01:48:08]

nit: insert blank link prior.

[chcunningham, 2015/02/03 20:34:43]

Done.

+  bool ReadOpusDuration(const uint8* data, int size, int64* duration);
+
   double timecode_multiplier_;  // Multiplier used to convert timecodes into
                                 // microseconds.
   std::set<int64> ignored_tracks_;
   std::string audio_encryption_key_id_;
   std::string video_encryption_key_id_;
+  const AudioDecoderConfig& audio_config_;

[wolenetz, 2015/01/30 01:48:08]

Do we need the whole config? Or just some specific info like codec id?
Also, I don't like refs-as-members in general (and I don't see any usage of
refs-as-members elsewhere in chromium). If you need a non-copy of some class,
consider smart pointers. Lifetime, backing-store, etc issues... refs-as-members
sound like a path to eventual pain ;)

[chcunningham, 2015/02/03 20:34:43]

Done. Now just taking in the codec.

 
   WebMListParser parser_;