Fix the audio catalog, but disable audio for now.

dev/README.md

@@ -83,9 +83,16 @@ The following command runs a development instance, broadcasing `dev/source.mp4`
 ```
 
 It will print out a URL when you can use to watch.
-This will contain a random broadcast name so the below link won't work:
+By default, the broadcast name is `dev` but you can overwrite it with the `NAME` env.
 
-> Watch URL: https://quic.video/watch/REPLACE_WITH_NAME?server=localhost:4443
+> Watch URL: https://quic.video/watch/dev?server=localhost:4443
+
+If you're debugging encoding issues, you can use this script to dump the file to disk instead, defaulting to
+`dev/output.mp4`.
+
+```bash
+./dev/pub-file
+```
 
 ### moq-api
 

dev/pub

@@ -13,21 +13,28 @@ PORT="${PORT:-4443}"
 ADDR="${ADDR:-$HOST:$PORT}"
 
 # Generate a random 16 character name by default.
-NAME="${NAME:-$(head /dev/urandom | LC_ALL=C tr -dc 'a-zA-Z0-9' | head -c 16)}"
+#NAME="${NAME:-$(head /dev/urandom | LC_ALL=C tr -dc 'a-zA-Z0-9' | head -c 16)}"
+
+# JK use the name "dev" instead
+# TODO use that random name if the host is not localhost
+NAME="${NAME:-dev}"
 
 # Combine the host and name into a URL.
 URL="${URL:-"https://$ADDR/$NAME"}"
 
 # Default to a source video
-MEDIA="${MEDIA:-dev/source.mp4}"
+INPUT="${INPUT:-dev/source.mp4}"
 
 # Print out the watch URL
 echo "Watch URL: https://quic.video/watch/$NAME?server=$ADDR"
 
 # Run ffmpeg and pipe the output to moq-pub
+# TODO enable audio again once fixed.
 ffmpeg -hide_banner -v quiet \
 	-stream_loop -1 -re \
-	-i "$MEDIA" \
+	-i "$INPUT" \
+	-c copy \
 	-an \
-	-f mp4 -movflags empty_moov+frag_every_frame+separate_moof+omit_tfhd_offset - \
-	| cargo run --bin moq-pub -- "$URL" "$@"
+	-f mp4 -movflags cmaf+separate_moof+delay_moov+skip_trailer \
+	-frag_duration 1 \
+	- | cargo run --bin moq-pub -- "$URL" "$@"

dev/pub-file

@@ -0,0 +1,90 @@
+#!/bin/bash
+set -euo pipefail
+
+# Change directory to the root of the project
+cd "$(dirname "$0")/.."
+
+# Default to a source video
+INPUT="${INPUT:-dev/source.mp4}"
+
+# Output the fragmented MP4 to disk for testing.
+OUTPUT="${OUTPUT:-dev/output.mp4}"
+
+# Run ffmpeg the same as dev/pub, but:
+#   - print any errors/warnings
+#   - only loop twice
+#
+# Note this is artificially slowed down to real-time using the -re flag; you can remove it.
+ffmpeg \
+	-re \
+	-y \
+	-i "$INPUT" \
+	-c copy \
+	-fps_mode passthrough \
+	-f mp4 -movflags cmaf+separate_moof+delay_moov+skip_trailer \
+	-frag_duration 1 \
+	"${OUTPUT}"
+
+# % ffmpeg -f mp4 --ffmpeg -h muxer=mov
+#
+# ffmpeg version 6.0 Copyright (c) 2000-2023 the FFmpeg developers
+# Muxer mov [QuickTime / MOV]:
+#     Common extensions: mov.
+#     Default video codec: h264.
+#     Default audio codec: aac.
+# mov/mp4/tgp/psp/tg2/ipod/ismv/f4v muxer AVOptions:
+#   -movflags          <flags>      E.......... MOV muxer flags (default 0)
+#      rtphint                      E.......... Add RTP hint tracks
+#      empty_moov                   E.......... Make the initial moov atom empty
+#      frag_keyframe                E.......... Fragment at video keyframes
+#      frag_every_frame              E.......... Fragment at every frame
+#      separate_moof                E.......... Write separate moof/mdat atoms for each track
+#      frag_custom                  E.......... Flush fragments on caller requests
+#      isml                         E.......... Create a live smooth streaming feed (for pushing to a publishing point)
+#      faststart                    E.......... Run a second pass to put the index (moov atom) at the beginning of the file
+#      omit_tfhd_offset              E.......... Omit the base data offset in tfhd atoms
+#      disable_chpl                 E.......... Disable Nero chapter atom
+#      default_base_moof              E.......... Set the default-base-is-moof flag in tfhd atoms
+#      dash                         E.......... Write DASH compatible fragmented MP4
+#      cmaf                         E.......... Write CMAF compatible fragmented MP4
+#      frag_discont                 E.......... Signal that the next fragment is discontinuous from earlier ones
+#      delay_moov                   E.......... Delay writing the initial moov until the first fragment is cut, or until the first fragment flush
+#      global_sidx                  E.......... Write a global sidx index at the start of the file
+#      skip_sidx                    E.......... Skip writing of sidx atom
+#      write_colr                   E.......... Write colr atom even if the color info is unspecified (Experimental, may be renamed or changed, do not use from scripts)
+#      prefer_icc                   E.......... If writing colr atom prioritise usage of ICC profile if it exists in stream packet side data
+#      write_gama                   E.......... Write deprecated gama atom
+#      use_metadata_tags              E.......... Use mdta atom for metadata.
+#      skip_trailer                 E.......... Skip writing the mfra/tfra/mfro trailer for fragmented files
+#      negative_cts_offsets              E.......... Use negative CTS offsets (reducing the need for edit lists)
+#   -moov_size         <int>        E.......... maximum moov size so it can be placed at the begin (from 0 to INT_MAX) (default 0)
+#   -rtpflags          <flags>      E.......... RTP muxer flags (default 0)
+#      latm                         E.......... Use MP4A-LATM packetization instead of MPEG4-GENERIC for AAC
+#      rfc2190                      E.......... Use RFC 2190 packetization instead of RFC 4629 for H.263
+#      skip_rtcp                    E.......... Don't send RTCP sender reports
+#      h264_mode0                   E.......... Use mode 0 for H.264 in RTP
+#      send_bye                     E.......... Send RTCP BYE packets when finishing
+#   -skip_iods         <boolean>    E.......... Skip writing iods atom. (default true)
+#   -iods_audio_profile <int>        E.......... iods audio profile atom. (from -1 to 255) (default -1)
+#   -iods_video_profile <int>        E.......... iods video profile atom. (from -1 to 255) (default -1)
+#   -frag_duration     <int>        E.......... Maximum fragment duration (from 0 to INT_MAX) (default 0)
+#   -min_frag_duration <int>        E.......... Minimum fragment duration (from 0 to INT_MAX) (default 0)
+#   -frag_size         <int>        E.......... Maximum fragment size (from 0 to INT_MAX) (default 0)
+#   -ism_lookahead     <int>        E.......... Number of lookahead entries for ISM files (from 0 to 255) (default 0)
+#   -video_track_timescale <int>        E.......... set timescale of all video tracks (from 0 to INT_MAX) (default 0)
+#   -brand             <string>     E.......... Override major brand
+#   -use_editlist      <boolean>    E.......... use edit list (default auto)
+#   -fragment_index    <int>        E.......... Fragment number of the next fragment (from 1 to INT_MAX) (default 1)
+#   -mov_gamma         <float>      E.......... gamma value for gama atom (from 0 to 10) (default 0)
+#   -frag_interleave   <int>        E.......... Interleave samples within fragments (max number of consecutive samples, lower is tighter interleaving, but with more overhead) (from 0 to INT_MAX) (default 0)
+#   -encryption_scheme <string>     E.......... Configures the encryption scheme, allowed values are none, cenc-aes-ctr
+#   -encryption_key    <binary>     E.......... The media encryption key (hex)
+#   -encryption_kid    <binary>     E.......... The media encryption key identifier (hex)
+#   -use_stream_ids_as_track_ids <boolean>    E.......... use stream ids as track ids (default false)
+#   -write_btrt        <boolean>    E.......... force or disable writing btrt (default auto)
+#   -write_tmcd        <boolean>    E.......... force or disable writing tmcd (default auto)
+#   -write_prft        <int>        E.......... Write producer reference time box with specified time source (from 0 to 2) (default 0)
+#      wallclock       1            E..........
+#      pts             2            E..........
+#   -empty_hdlr_name   <boolean>    E.......... write zero-length name string in hdlr atoms within mdia and minf atoms (default false)
+#   -movie_timescale   <int>        E.......... set movie timescale (from 1 to INT_MAX) (default 1000)

moq-pub/src/media.rs

@@ -4,6 +4,7 @@ use moq_transport::cache::{broadcast, segment, track};
 use moq_transport::VarInt;
 use mp4::{self, ReadBox};
 use serde_json::json;
+use std::cmp::max;
 use std::collections::HashMap;
 use std::io::Cursor;
 use std::time;
@@ -15,11 +16,12 @@ pub struct Media {
 	_catalog: track::Publisher,
 	_init: track::Publisher,
 
-	tracks: HashMap<String, Track>,
+	// Tracks based on their track ID.
+	tracks: HashMap<u32, Track>,
 }
 
 impl Media {
-	pub async fn new(config: &Config, mut broadcast: broadcast::Publisher) -> anyhow::Result<Self> {
+	pub async fn new(_config: &Config, mut broadcast: broadcast::Publisher) -> anyhow::Result<Self> {
 		let mut stdin = tokio::io::stdin();
 		let ftyp = read_atom(&mut stdin).await?;
 		anyhow::ensure!(&ftyp[4..8] == b"ftyp", "expected ftyp atom");
@@ -39,7 +41,7 @@ impl Media {
 		let moov = mp4::MoovBox::read_box(&mut moov_reader, moov_header.size)?;
 
 		// Create the catalog track with a single segment.
-		let mut init_track = broadcast.create_track("1.mp4")?;
+		let mut init_track = broadcast.create_track("0.mp4")?;
 		let mut init_segment = init_track.create_segment(segment::Info {
 			sequence: VarInt::ZERO,
 			priority: i32::MAX,
@@ -52,20 +54,20 @@ impl Media {
 
 		for trak in &moov.traks {
 			let id = trak.tkhd.track_id;
-			let name = id.to_string();
+			let name = format!("{}.m4s", id);
 
 			let timescale = track_timescale(&moov, id);
 
 			// Store the track publisher in a map so we can update it later.
 			let track = broadcast.create_track(&name)?;
 			let track = Track::new(track, timescale);
-			tracks.insert(name, track);
+			tracks.insert(id, track);
 		}
 
 		let mut catalog = broadcast.create_track(".catalog")?;
 
 		// Create the catalog track
-		Self::serve_catalog(&mut catalog, config, init_track.name.to_string(), &moov, &tracks)?;
+		Self::serve_catalog(&mut catalog, &init_track.name, &moov)?;
 
 		Ok(Media {
 			_broadcast: broadcast,
@@ -78,7 +80,7 @@ impl Media {
 	pub async fn run(&mut self) -> anyhow::Result<()> {
 		let mut stdin = tokio::io::stdin();
 		// The current track name
-		let mut track_name = None;
+		let mut current = None;
 
 		loop {
 			let atom = read_atom(&mut stdin).await?;
@@ -92,22 +94,21 @@ impl Media {
 
 					// Process the moof.
 					let fragment = Fragment::new(moof)?;
-					let name = fragment.track.to_string();
 
 					// Get the track for this moof.
-					let track = self.tracks.get_mut(&name).context("failed to find track")?;
+					let track = self.tracks.get_mut(&fragment.track).context("failed to find track")?;
 
 					// Save the track ID for the next iteration, which must be a mdat.
-					anyhow::ensure!(track_name.is_none(), "multiple moof atoms");
-					track_name.replace(name);
+					anyhow::ensure!(current.is_none(), "multiple moof atoms");
+					current.replace(fragment.track);
 
 					// Publish the moof header, creating a new segment if it's a keyframe.
 					track.header(atom, fragment).context("failed to publish moof")?;
 				}
 				mp4::BoxType::MdatBox => {
 					// Get the track ID from the previous moof.
-					let name = track_name.take().context("missing moof")?;
-					let track = self.tracks.get_mut(&name).context("failed to find track")?;
+					let track = current.take().context("missing moof")?;
+					let track = self.tracks.get_mut(&track).context("failed to find track")?;
 
 					// Publish the mdat atom.
 					track.data(atom).context("failed to publish mdat")?;
@@ -122,10 +123,8 @@ impl Media {
 
 	fn serve_catalog(
 		track: &mut track::Publisher,
-		config: &Config,
-		init_track_name: String,
+		init_track_name: &str,
 		moov: &mp4::MoovBox,
-		_tracks: &HashMap<String, Track>,
 	) -> Result<(), anyhow::Error> {
 		let mut segment = track.create_segment(segment::Info {
 			sequence: VarInt::ZERO,
@@ -133,47 +132,82 @@ impl Media {
 			expires: None,
 		})?;
 
-		// avc1[.PPCCLL]
-		//
-		// let profile = 0x64;
-		// let constraints = 0x00;
-		// let level = 0x1f;
+		let mut tracks = Vec::new();
 
-		// TODO: do build multi-track catalog by looping through moov.traks
-		let trak = moov.traks[0].clone();
-		let avc1 = trak
-			.mdia
-			.minf
-			.stbl
-			.stsd
-			.avc1
-			.ok_or(anyhow::anyhow!("avc1 atom not found"))?;
+		for trak in &moov.traks {
+			let mut track = json!({
+				"container": "mp4",
+				"init_track": init_track_name,
+				"data_track": format!("{}.m4s", trak.tkhd.track_id),
+			});
 
-		let profile = avc1.avcc.avc_profile_indication;
-		let constraints = avc1.avcc.profile_compatibility; // Not 100% certain here, but it's 0x00 on my current test video
-		let level = avc1.avcc.avc_level_indication;
+			let stsd = &trak.mdia.minf.stbl.stsd;
+			if let Some(avc1) = &stsd.avc1 {
+				// avc1[.PPCCLL]
+				//
+				// let profile = 0x64;
+				// let constraints = 0x00;
+				// let level = 0x1f;
+				let profile = avc1.avcc.avc_profile_indication;
+				let constraints = avc1.avcc.profile_compatibility; // Not 100% certain here, but it's 0x00 on my current test video
+				let level = avc1.avcc.avc_level_indication;
 
-		let width = avc1.width;
-		let height = avc1.height;
+				let width = avc1.width;
+				let height = avc1.height;
 
-		let codec = rfc6381_codec::Codec::avc1(profile, constraints, level);
-		let codec_str = codec.to_string();
+				let codec = rfc6381_codec::Codec::avc1(profile, constraints, level);
+				let codec_str = codec.to_string();
+
+				track["kind"] = json!("video");
+				track["codec"] = json!(codec_str);
+				track["width"] = json!(width);
+				track["height"] = json!(height);
+			} else if let Some(_hev1) = &stsd.hev1 {
+				// TODO https://github.com/gpac/mp4box.js/blob/325741b592d910297bf609bc7c400fc76101077b/src/box-codecs.js#L106
+				anyhow::bail!("HEVC not yet supported")
+			} else if let Some(mp4a) = &stsd.mp4a {
+				let desc = &mp4a
+					.esds
+					.as_ref()
+					.context("missing esds box for MP4a")?
+					.es_desc
+					.dec_config;
+				let codec_str = format!("mp4a.{:02x}.{}", desc.object_type_indication, desc.dec_specific.profile);
+
+				track["kind"] = json!("audio");
+				track["codec"] = json!(codec_str);
+				track["channel_count"] = json!(mp4a.channelcount);
+				track["sample_rate"] = json!(mp4a.samplerate.value());
+				track["sample_size"] = json!(mp4a.samplesize);
+
+				let bitrate = max(desc.max_bitrate, desc.avg_bitrate);
+				if bitrate > 0 {
+					track["bit_rate"] = json!(bitrate);
+				}
+			} else if let Some(vp09) = &stsd.vp09 {
+				// https://github.com/gpac/mp4box.js/blob/325741b592d910297bf609bc7c400fc76101077b/src/box-codecs.js#L238
+				let vpcc = &vp09.vpcc;
+				let codec_str = format!("vp09.0.{:02x}.{:02x}.{:02x}", vpcc.profile, vpcc.level, vpcc.bit_depth);
+
+				track["kind"] = json!("video");
+				track["codec"] = json!(codec_str);
+				track["width"] = json!(vp09.width); // no idea if this needs to be multiplied
+				track["height"] = json!(vp09.height); // no idea if this needs to be multiplied
+
+				// TODO Test if this actually works; I'm just guessing based on mp4box.js
+				anyhow::bail!("VP9 not yet supported")
+			} else {
+				// TODO add av01 support: https://github.com/gpac/mp4box.js/blob/325741b592d910297bf609bc7c400fc76101077b/src/box-codecs.js#L251
+				anyhow::bail!("unknown codec for track: {}", trak.tkhd.track_id);
+			}
+
+			tracks.push(track);
+		}
 
 		let catalog = json!({
-			"tracks": [
-				{
-				"container": "mp4",
-				"kind": "video",
-				"init_track": init_track_name,
-				"data_track": "1", // assume just one track for now
-				"codec": codec_str,
-				"width": width,
-				"height": height,
-				"frame_rate": config.fps,
-				"bit_rate": config.bitrate,
-				}
-			]
+			"tracks": tracks
 		});
+
 		let catalog_str = serde_json::to_string_pretty(&catalog)?;
 		log::info!("catalog: {}", catalog_str);