From f834681ab6e2d0ae0c135ecb971f1097938176f6 Mon Sep 17 00:00:00 2001 From: Youenn Fablet Date: Fri, 25 Apr 2025 11:32:29 +0200 Subject: [PATCH] Introduce RTCEncodedFrameMetadata dictionary --- index.bs | 281 ++++++++++++++++++++----------------------------------- 1 file changed, 102 insertions(+), 179 deletions(-) diff --git a/index.bs b/index.bs index 620628e..7de99c1 100644 --- a/index.bs +++ b/index.bs @@ -313,8 +313,104 @@ The setEncryptionKey(|key|, |keyID|) met # RTCRtpScriptTransform # {#scriptTransform} In this section, the capture system refers to the system where media is sourced from and the sender system -refers to the system that is sending RTP and RTCP packets to the receiver system where {{RTCEncodedVideoFrameMetadata}} data -or {{RTCEncodedAudioFrameMetadata}} data is populated. +refers to the system that is sending RTP and RTCP packets to the receiver system where {{RTCEncodedFrameMetadata}} data is populated. + +## RTCEncodedFrameMetadata dictionary ## {#RTCEncodedFrameMetadata} +
+dictionary RTCEncodedFrameMetadata {
+    unsigned long synchronizationSource;
+    octet payloadType;
+    sequence<unsigned long> contributingSources;
+    unsigned long rtpTimestamp;
+    DOMHighResTimeStamp receiveTime;
+    DOMHighResTimeStamp captureTime;
+    DOMHighResTimeStamp senderCaptureTimeOffset;
+    DOMString mimeType;
+};
+
+ +### Members ### {#RTCEncodedFrameMetadata-members} + +
+
+ synchronizationSource unsigned long +
+
+

+ The synchronization source (ssrc) identifier is an unsigned integer value per [[RFC3550]] + used to identify the stream of RTP packets that the encoded frame object is describing. +

+
+
+ payloadType octet +
+
+

+ The payload type is an unsigned integer value in the range from 0 to 127 per [[RFC3550]] + that is used to describe the format of the RTP payload. +

+
+
+ contributingSources sequence<unsigned long> +
+
+

+ The list of contribution sources (csrc list) as defined in [[RFC3550]]. +

+
+
+ rtpTimestamp unsigned long +
+
+

+ The RTP timestamp identifier is an unsigned integer value per [[RFC3550]] + that reflects the sampling instant of the first octet in the RTP data packet. +

+
+
+ receiveTime DOMHighResTimeStamp +
+
+

+ For frames coming from an RTCRtpReceiver, represents the timestamp + of the last received packet used to produce this media frame. This + timestamp is relative to {{Performance}}.{{Performance/timeOrigin}}. +

+
+
+ captureTime DOMHighResTimeStamp +
+
+

+ The capture time of this frame in the capture system's clock. + On populating this member, the user agent MUST return the value of the frame's `[[captureTime]]` slot, + shifted to be relative to {{Performance}}.{{Performance/timeOrigin}}. +

+
+
+ senderCaptureTimeOffset DOMHighResTimeStamp +
+
+

+ The {{RTCEncodedFrameMetadata/senderCaptureTimeOffset}} is the sender system's estimate of the offset + between its own NTP clock and the capture system's NTP clock, for the same frame that the + {{RTCEncodedFrameMetadata/captureTime}} was originated from. + On populating this member, the user agent MUST return the value of the frame's `[[senderCaptureTimeOffset]]` slot. +

+
+
+ mimeType DOMString +
+
+

+ The codec MIME media type/subtype defined in the IANA media types registry + [[!IANA-MEDIA-TYPES]], e.g. audio/opus or video/VP8. +

+
+
## RTCEncodedVideoFrameType dictionary ## {#RTCEncodedVideoFrameType} 
@@ -369,22 +465,14 @@ enum RTCEncodedVideoFrameType {
 
 ## RTCEncodedVideoFrameMetadata dictionary ## {#RTCEncodedVideoFrameMetadata}
 
-dictionary RTCEncodedVideoFrameMetadata {
+dictionary RTCEncodedVideoFrameMetadata : RTCEncodedFrameMetadata {
     unsigned long long frameId;
     sequence<unsigned long long> dependencies;
     unsigned short width;
     unsigned short height;
     unsigned long spatialIndex;
     unsigned long temporalIndex;
-    unsigned long synchronizationSource;
-    octet payloadType;
-    sequence<unsigned long> contributingSources;
     long long timestamp;    // microseconds
-    unsigned long rtpTimestamp;
-    DOMHighResTimeStamp receiveTime;
-    DOMHighResTimeStamp captureTime;
-    DOMHighResTimeStamp senderCaptureTimeOffset;
-    DOMString mimeType;
 };
 

 
@@ -410,33 +498,6 @@ dictionary RTCEncodedVideoFrameMetadata {
             Only present for received frames if the AV1 Dependency Descriptor Header Extension defined in Appendix A of [[AV1-RTP-SPEC]] is present.
         

     
-    

-        synchronizationSource unsigned long
-    

-    

-        

-            The synchronization source (ssrc) identifier is an unsigned integer value per [[RFC3550]]
-            used to identify the stream of RTP packets that the encoded frame object is describing.
-        

-    

-    

-        payloadType octet
-    

-    

-        

-            The payload type is an unsigned integer value in the range from 0 to 127 per [[RFC3550]]
-            that is used to describe the format of the RTP payload.
-        

-    

-    

-        contributingSources sequence<unsigned long>
-    

-    

-        

-            The list of contribution sources (csrc list) as defined in [[RFC3550]].
-        

-    

     

         timestamp long long
@@ -447,58 +508,6 @@ dictionary RTCEncodedVideoFrameMetadata {
             {{VideoFrame/timestamp}} for raw frames which correspond to this frame.
         

     
-    

-        rtpTimestamp unsigned long
-    

-    

-        

-            The RTP timestamp identifier is an unsigned integer value per [[RFC3550]]
-            that reflects the sampling instant of the first octet in the RTP data packet.
-        

-    

-    

-        receiveTime DOMHighResTimeStamp
-    

-    

-        

-            For frames coming from an RTCRtpReceiver, represents the timestamp
-            of the last received packet used to produce this video frame. This
-            timestamp is relative to {{Performance}}.{{Performance/timeOrigin}}.
-            Only exists for incoming video frames.
-        

-    

-    

-        captureTime DOMHighResTimeStamp
-    

-    

-        

-            The capture time of this frame in the capture system's clock.
-            On populating this member, the user agent MUST return the value of the frame's `[[captureTime]]` slot,
-            shifted to be relative to {{Performance}}.{{Performance/timeOrigin}}.
-        

-    

-    

-        senderCaptureTimeOffset DOMHighResTimeStamp
-    

-    

-        

-            The {{RTCEncodedVideoFrameMetadata/senderCaptureTimeOffset}} is the sender system's estimate of the offset
-            between its own NTP clock and the capture system's NTP clock, for the same frame that the
-            {{RTCEncodedVideoFrameMetadata/captureTime}} was originated from.
-            On populating this member, the user agent MUST return the value of the frame's `[[senderCaptureTimeOffset]]` slot.
-        

-    

-    

-        mimeType DOMString
-    

-    

-        

-            The codec MIME media type/subtype defined in the IANA media types registry
-            [[!IANA-MEDIA-TYPES]], e.g. video/VP8.
-        

-    

 
 
 
@@ -562,7 +571,7 @@ interface RTCEncodedVideoFrame {
         

             The encoded frame data. The format of the data depends on the video codec that is
             used to encode/decode the frame which can be determined by looking at the
-            {{RTCEncodedVideoFrameMetadata/mimeType}}.
+            {{RTCEncodedFrameMetadata/mimeType}}.
             For SVC, each spatial layer
             is transformed separately.
         

@@ -667,47 +676,12 @@ An implementation is therefore free to choose whatever method works best.
 
 ## RTCEncodedAudioFrameMetadata dictionary ## {#RTCEncodedAudioFrameMetadata}
 
-dictionary RTCEncodedAudioFrameMetadata {
-    unsigned long synchronizationSource;
-    octet payloadType;
-    sequence<unsigned long> contributingSources;
+dictionary RTCEncodedAudioFrameMetadata : RTCEncodedFrameMetadata {
     short sequenceNumber;
-    unsigned long rtpTimestamp;
-    DOMHighResTimeStamp receiveTime;
-    DOMHighResTimeStamp captureTime;
-    DOMHighResTimeStamp senderCaptureTimeOffset;
-    DOMString mimeType;
 };
 

 ### Members ### {#RTCEncodedAudioFrameMetadata-members}
 

-    

-        synchronizationSource unsigned long
-    

-    

-        

-            The synchronization source (ssrc) identifier is an unsigned integer value per [[RFC3550]]
-            used to identify the stream of RTP packets that the encoded frame object is describing.
-        

-    

-    

-        payloadType octet
-    

-    

-        

-            The payload type is an unsigned integer value in the range from 0 to 127 per [[RFC3550]]
-            that is used to describe the format of the RTP payload.
-        

-    

-    

-        contributingSources sequence<unsigned long>
-    

-    

-        

-            The list of contribution sources (csrc list) as defined in [[RFC3550]].
-        

-    

     

         sequenceNumber short
@@ -720,57 +694,6 @@ dictionary RTCEncodedAudioFrameMetadata {
             Comparing two sequence numbers requires serial number arithmetic described in [[RFC1982]].
         

     
-    

-        rtpTimestamp unsigned long
-    

-    

-        

-            The RTP timestamp identifier is an unsigned integer value per [[RFC3550]]
-            that reflects the sampling instant of the first octet in the RTP data packet.
-        

-    

-    

-        receiveTime DOMHighResTimeStamp
-    

-    

-        

-            For frames coming from an RTCRtpReceiver, represents the timestamp
-            of the last received packet used to produce this audio frame. This
-            timestamp is relative to {{Performance}}.{{Performance/timeOrigin}}.
-            Only exists for incoming audio frames.
-        

-   

-    

-        captureTime DOMHighResTimeStamp
-    

-    

-        

-            The capture time of this frame in the capture system's clock.
-            On populating this member, the user agent MUST return the value of the frame's `[[captureTime]]` slot,
-            shifted to be relative to {{Performance}}.{{Performance/timeOrigin}}.
-        

-    

-    

-        senderCaptureTimeOffset DOMHighResTimeStamp
-    

-    

-        

-            The {{RTCEncodedAudioFrameMetadata/senderCaptureTimeOffset}} is the sender system's estimate of the offset
-            between its own NTP clock and the capture system's NTP clock, for the same frame that the
-            {{RTCEncodedAudioFrameMetadata/captureTime}} was originated from.
-            On populating this member, the user agent MUST return the value of the frame's `[[senderCaptureTimeOffset]]` slot.
-        

-    

-    

-        mimeType DOMString
-    

-    

-        

-            The codec MIME media type/subtype defined in the IANA media types registry
-            [[!IANA-MEDIA-TYPES]], e.g. audio/opus.
-        

-    

 

 
 ## RTCEncodedAudioFrame interface ## {#RTCEncodedAudioFrame-interface}
@@ -820,7 +743,7 @@ interface RTCEncodedAudioFrame {
         

             The encoded frame data. The format of the data depends on the audio codec that is
             used to encode/decode the frame which can be determined by looking at the
-            {{RTCEncodedAudioFrameMetadata/mimeType}}.
+            {{RTCEncodedFrameMetadata/mimeType}}.
             The following table gives a number of examples: