Parsing of encoded duration for unencrypted opus streams.

media/formats/webm/webm_cluster_parser.h

 // Copyright 2014 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
 #ifndef MEDIA_FORMATS_WEBM_WEBM_CLUSTER_PARSER_H_
 #define MEDIA_FORMATS_WEBM_WEBM_CLUSTER_PARSER_H_
 
 #include <deque>
 #include <map>
 #include <set>
 #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"
 #include "media/base/stream_parser_buffer.h"
 #include "media/formats/webm/webm_parser.h"
 #include "media/formats/webm/webm_tracks_parser.h"
 
 namespace media {
 
 class MEDIA_EXPORT WebMClusterParser : public WebMParserClient {
  public:

[wolenetz, 2015/02/03 22:47:02]

fyi: I just noticed this class has multiple public: and multiple private:
sections. Is this necessary? (If not, seems a clean-up could be fodder for a
separate CL.)

[chcunningham, 2015/02/05 02:48:22]

I don't think its needed. Happy to clean up in later cl.

[wolenetz, 2015/02/05 23:04:59]

Acknowledged.

   typedef StreamParser::TrackId TrackId;
   typedef std::deque<scoped_refptr<StreamParserBuffer> > BufferQueue;
   typedef std::map<TrackId, const BufferQueue> TextBufferQueueMap;
 
   // Arbitrarily-chosen numbers to estimate the duration of a buffer if none is
   // set and there is not enough information to get a better estimate.
-  // TODO(wolenetz/acolwell): Parse audio codebook to determine missing audio
-  // frame durations. See http://crbug.com/351166.
   enum {
     kDefaultAudioBufferDurationInMs = 23,  // Common 1k samples @44.1kHz
     kDefaultVideoBufferDurationInMs = 42  // Low 24fps to reduce stalls
   };
 
+  // Opus packets encode the duration and other parameters in the 5 most
+  // 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

[wolenetz, 2015/02/03 22:47:02]

I was wrong. Using full URL is more common. Also lets readers see real target
before/without loading it. s/full/shortened/ URL here and in .h please.

[chcunningham, 2015/02/05 02:48:22]

Done.

+  static const uint16 kOpusFrameDurationsMu[];

[wolenetz, 2015/02/03 22:47:02]

_t

[chcunningham, 2015/02/05 02:48:22]

Done.

+
  private:
   // Helper class that manages per-track state.
   class Track {
    public:
     Track(int track_num,
           bool is_video,
           base::TimeDelta default_duration,
           const LogCB& log_cb);
     ~Track();
 
@@ skipping 88 matching lines @@
  public:
   WebMClusterParser(int64 timecode_scale,
                     int audio_track_num,
                     base::TimeDelta audio_default_duration,
                     int video_track_num,
                     base::TimeDelta video_default_duration,
                     const WebMTracksParser::TextTracks& text_tracks,
                     const std::set<int64>& ignored_tracks,
                     const std::string& audio_encryption_key_id,
                     const std::string& video_encryption_key_id,
+                    const AudioCodec audio_codec_,
                     const LogCB& log_cb);
   ~WebMClusterParser() override;
 
   // Resets the parser state so it can accept a new cluster.
   void Reset();
 
   // Parses a WebM cluster element in |buf|.
   //
   // Returns -1 if the parse fails.
   // Returns 0 if more data is needed.
@@ skipping 64 matching lines @@
   // bound.)
   // Parse() or Reset() must be called between calls to UpdateReadyBuffers() to
   // clear each track's ready buffers and to reset |ready_buffer_upper_bound_|
   // to kNoDecodeTimestamp().
   void UpdateReadyBuffers();
 
   // Search for the indicated track_num among the text tracks.  Returns NULL
   // if that track num is not a text track.
   Track* FindTextTrack(int track_num);
 
+  // Attempts to read the duration from the encoded audio data. 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 for Blocks at the
+  // end of a Cluster (the next 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.

[wolenetz, 2015/02/03 22:47:02]

nit: though private, would be nice to have retval documented here.

[chcunningham, 2015/02/05 02:48:22]

Done.

+  base::TimeDelta TryGetEncodedAudioDuration(const uint8* data, int size);

[wolenetz, 2015/02/03 22:47:02]

nit: const method?

[chcunningham, 2015/02/05 02:48:22]

We chatted. The MEDIA_LOGS break const-ness :(

[wolenetz, 2015/02/05 23:04:59]

Acknowledged.

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

[wolenetz, 2015/02/03 22:47:02]

nit: ditto retval documentation

[chcunningham, 2015/02/05 02:48:22]

Done.

+  base::TimeDelta ReadOpusDuration(const uint8* data, int size);

[wolenetz, 2015/02/03 22:47:02]

nit: const method?

[chcunningham, 2015/02/05 02:48:22]

Same issue with MEDIA_LOG

[wolenetz, 2015/02/05 23:04:59]

Acknowledged.

+
   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 AudioCodec audio_codec_;
 
   WebMListParser parser_;
 
   int64 last_block_timecode_;
   scoped_ptr<uint8[]> block_data_;
   int block_data_size_;
   int64 block_duration_;
   int64 block_add_id_;
 
   scoped_ptr<uint8[]> block_additional_data_;
@@ skipping 26 matching lines @@
   DecodeTimestamp ready_buffer_upper_bound_;
 
   LogCB log_cb_;
 
   DISALLOW_IMPLICIT_CONSTRUCTORS(WebMClusterParser);
 };
 
 }  // namespace media
 
 #endif  // MEDIA_FORMATS_WEBM_WEBM_CLUSTER_PARSER_H_