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:
   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
+  // https://tools.ietf.org/html/rfc6716#page-14
+  static const uint16_t kOpusFrameDurationsMu[];
+
  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 32 matching lines @@
 
     // Clears all buffer state, including any possibly held-aside buffer that
     // was missing duration, and all contents of |buffers_| and
     // |ready_buffers_|.
     void Reset();
 
     // Helper function used to inspect block data to determine if the
     // block is a keyframe.
     // |data| contains the bytes in the block.
     // |size| indicates the number of bytes in |data|.
-    bool IsKeyframe(const uint8* data, int size) const;
+    bool IsKeyframe(const uint8_t* data, int size) const;
 
     base::TimeDelta default_duration() const { return default_duration_; }
 
    private:
     // Helper that sanity-checks |buffer| duration, updates
     // |estimated_next_frame_duration_|, and adds |buffer| to |buffers_|.
     // Returns false if |buffer| failed sanity check and therefore was not added
     // to |buffers_|. Returns true otherwise.
     bool QueueBuffer(const scoped_refptr<StreamParserBuffer>& buffer);
 
@@ skipping 35 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.
   // Returns the number of bytes parsed on success.
-  int Parse(const uint8* buf, int size);
+  int Parse(const uint8_t* buf, int size);
 
   base::TimeDelta cluster_start_time() const { return cluster_start_time_; }
 
   // Get the current ready buffers resulting from Parse().
   // If the parse reached the end of cluster and the last buffer was held aside
   // due to missing duration, the buffer is given an estimated duration and
   // included in the result.
   // Otherwise, if there are is a buffer held aside due to missing duration for
   // any of the tracks, no buffers with same or greater (decode) timestamp will
   // be included in the buffers.
@@ skipping 19 matching lines @@
   const TextBufferQueueMap& GetTextBuffers();
 
   // Returns true if the last Parse() call stopped at the end of a cluster.
   bool cluster_ended() const { return cluster_ended_; }
 
  private:
   // WebMParserClient methods.
   WebMParserClient* OnListStart(int id) override;
   bool OnListEnd(int id) override;
   bool OnUInt(int id, int64 val) override;
-  bool OnBinary(int id, const uint8* data, int size) override;
+  bool OnBinary(int id, const uint8_t* data, int size) override;
 
-  bool ParseBlock(bool is_simple_block, const uint8* buf, int size,
-                  const uint8* additional, int additional_size, int duration,
+  bool ParseBlock(bool is_simple_block,
+                  const uint8_t* buf,
+                  int size,
+                  const uint8_t* additional,
+                  int additional_size,
+                  int duration,
                   int64 discard_padding);
-  bool OnBlock(bool is_simple_block, int track_num, int timecode, int duration,
-               int flags, const uint8* data, int size,
-               const uint8* additional, int additional_size,
+  bool OnBlock(bool is_simple_block,
+               int track_num,
+               int timecode,
+               int duration,
+               int flags,
+               const uint8_t* data,
+               int size,
+               const uint8_t* additional,
+               int additional_size,
                int64 discard_padding);
 
   // Resets the Track objects associated with each text track.
   void ResetTextTracks();
 
   // Clears the the ready buffers associated with each text track.
   void ClearTextTrackReadyBuffers();
 
   // Helper method for Get{Audio,Video,Text}Buffers() that recomputes
   // |ready_buffer_upper_bound_| and calls ExtractReadyBuffers() on each track.
   // If |cluster_ended_| is true, first applies duration estimate if needed for
   // |audio_| and |video_| and sets |ready_buffer_upper_bound_| to
   // kInfiniteDuration(). Otherwise, sets |ready_buffer_upper_bound_| to the
   // minimum upper bound across |audio_| and |video_|. (Text tracks can have no
   // buffers missing duration, so they are not involved in calculating the upper
   // 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, returning as
+  // TimeDelta or kNoTimestamp() if duration cannot be retrieved. 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.
+  base::TimeDelta TryGetEncodedAudioDuration(const uint8_t* data, int size);
+
+  // Reads Opus packet header to determine packet duration. Duration returned
+  // as TimeDelta or kNoTimestamp() upon failure to read duration from packet.
+  base::TimeDelta ReadOpusDuration(const uint8_t* data, int size);
+
+  // Tracks the number of MEDIA_LOGs made in process of reading encoded
+  // duration. Useful to prevent log spam.
+  int num_duration_errors_;
+
   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_;
+  scoped_ptr<uint8_t[]> block_data_;
   int block_data_size_;
   int64 block_duration_;
   int64 block_add_id_;
 
-  scoped_ptr<uint8[]> block_additional_data_;
+  scoped_ptr<uint8_t[]> block_additional_data_;
   // Must be 0 if |block_additional_data_| is null. Must be > 0 if
   // |block_additional_data_| is NOT null.
   int block_additional_data_size_;
 
   int64 discard_padding_;
   bool discard_padding_set_;
 
   int64 cluster_timecode_;
   base::TimeDelta cluster_start_time_;
   bool cluster_ended_;
@@ skipping 16 matching lines @@
   DecodeTimestamp ready_buffer_upper_bound_;
 
   LogCB log_cb_;
 
   DISALLOW_IMPLICIT_CONSTRUCTORS(WebMClusterParser);
 };
 
 }  // namespace media
 
 #endif  // MEDIA_FORMATS_WEBM_WEBM_CLUSTER_PARSER_H_