[Cast] EncodedAudioFrame+EncodedVideoFrame+reference_time --> EncodedFrame

media/cast/transport/cast_transport_config.h

Index: media/cast/transport/cast_transport_config.h
diff --git a/media/cast/transport/cast_transport_config.h b/media/cast/transport/cast_transport_config.h
index d7d3196857e8389f08d4b2d738c45ffc800264fd..b25ce4e28513b847c15c634ff7a4b44326a92969 100644
--- a/media/cast/transport/cast_transport_config.h
+++ b/media/cast/transport/cast_transport_config.h
@@ -12,6 +12,7 @@
 #include "base/callback.h"
 #include "base/memory/linked_ptr.h"
 #include "base/memory/ref_counted.h"
+#include "base/stl_util.h"
 #include "media/cast/transport/cast_transport_defines.h"
 #include "net/base/ip_endpoint.h"
 
@@ -69,27 +70,68 @@ struct CastTransportVideoConfig {
   VideoCodec codec;
 };
 
-struct EncodedVideoFrame {
-  EncodedVideoFrame();
-  ~EncodedVideoFrame();
+// A combination of metadata and data for one encoded frame.  This can contain
+// audio data or video data or other.
+struct EncodedFrame {
+  enum Dependency {
+    // "null" value, used to indicate whether |dependency| has been set.
+    UNKNOWN_DEPENDENCY,
 
-  VideoCodec codec;
-  bool key_frame;
+    // Not decodable without the reference frame indicated by
+    // |referenced_frame_id|.
+    DEPENDENT,
+
+    // Independently decodable.
+    INDEPENDENT,
+
+    // Independently decodable, and no future frames will depend on any frames
+    // before this one.
+    KEY,
+
+    DEPENDENCY_LAST = KEY
+  };
+
+  EncodedFrame();
+  ~EncodedFrame();
+
+  // Convenience accessors to data as an array of uint8 elements.
+  const uint8* bytes() const {
+    return reinterpret_cast<uint8*>(string_as_array(
+        const_cast<std::string*>(&data)));
+  }
+  uint8* mutable_bytes() {
+    return reinterpret_cast<uint8*>(string_as_array(&data));
+  }
+
+  // This frame's dependency relationship with respect to other frames.
+  Dependency dependency;
+
+  // The label associated with this frame.  Implies an ordering relative to
+  // other frames in the same stream.
   uint32 frame_id;
-  uint32 last_referenced_frame_id;
-  uint32 rtp_timestamp;
-  std::string data;
-};
 
-struct EncodedAudioFrame {
-  EncodedAudioFrame();
-  ~EncodedAudioFrame();
+  // The label associated with the frame upon which this frame depends.  If
+  // this frame does not require any other frame in order to become decodable
+  // (e.g., key frames), |referenced_frame_id| must equal |frame_id|.
+  uint32 referenced_frame_id;
 
-  AudioCodec codec;
-  uint32 frame_id;  // Needed to release the frame.
+  // The stream timestamp, on the timeline of the signal data.  For example, RTP
+  // timestamps for audio are usually defined as the total number of audio
+  // samples encoded in all prior frames.  A playback system uses this value to
+  // detect gaps in the stream, and otherwise stretch the signal to match
+  // playout targets.
   uint32 rtp_timestamp;
-  // Support for max sampling rate of 48KHz, 2 channels, 100 ms duration.
-  static const int kMaxNumberOfSamples = 48 * 2 * 100;
+
+  // The common reference clock timestamp for this frame.  This value originates
+  // from a sender and is used to provide lip synchronization between streams in
+  // a receiver.  Thus, in the sender context, this is set to the time at which
+  // the frame was captured/recorded.  In the receiver context, this is set to
+  // the target playout time.  Over a sequence of frames, this time value is
+  // expected to drift with respect to the elapsed time implied by the RTP
+  // timestamps; and it may not necessarily increment with precise regularity.
+  base::TimeTicks reference_time;
+
+  // The encoded signal data.
   std::string data;
 };