Merge main into release for tag v1.27.1

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "mediabunny",
-  "version": "1.27.0",
+  "version": "1.27.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "mediabunny",
-      "version": "1.27.0",
+      "version": "1.27.1",
       "license": "MPL-2.0",
       "workspaces": [
         "packages/*"
@@ -7739,9 +7739,9 @@
       }
     },
     "node_modules/mediabunny": {
-      "version": "1.26.0",
-      "resolved": "https://registry.npmjs.org/mediabunny/-/mediabunny-1.26.0.tgz",
-      "integrity": "sha512-0duZPn/vVpx+mKjOn3PNb/tBrtKUoq4n5+uO1JwyQm3cdaKYy7tVTEvTpXJxbpQ/CdnHn5YMVRg8mwi7fIgSYA==",
+      "version": "1.27.0",
+      "resolved": "https://registry.npmjs.org/mediabunny/-/mediabunny-1.27.0.tgz",
+      "integrity": "sha512-u1Xm/HRs4g+cJM8IWcraaWlDmPnAr0FvEbFNbTm46bFA1GPoNRpmBeCq3aPlj9sjyqb0c7TMbW/i/pPupjwJog==",
       "license": "MPL-2.0",
       "peer": true,
       "workspaces": [
@@ -12065,7 +12065,7 @@
     },
     "packages/mp3-encoder": {
       "name": "@mediabunny/mp3-encoder",
-      "version": "1.27.0",
+      "version": "1.27.1",
       "license": "MPL-2.0",
       "devDependencies": {
         "@types/emscripten": "^1.40.1"

package.json

@@ -1,7 +1,7 @@
 {
   "name": "mediabunny",
   "author": "Vanilagy",
-  "version": "1.27.0",
+  "version": "1.27.1",
   "description": "Pure TypeScript media toolkit for reading, writing, and converting media files, directly in the browser.",
   "type": "module",
   "workspaces": [

packages/mp3-encoder/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@mediabunny/mp3-encoder",
   "author": "Vanilagy",
-  "version": "1.27.0",
+  "version": "1.27.1",
   "description": "MP3 encoder extension for Mediabunny, based on LAME.",
   "main": "./dist/bundles/mediabunny-mp3-encoder.mjs",
   "module": "./dist/bundles/mediabunny-mp3-encoder.mjs",

src/codec-data.ts

@@ -24,6 +24,7 @@ import {
 	toUint8Array,
 	getChromiumVersion,
 	isChromium,
+	setUint24,
 } from './misc';
 import { PacketType } from './packet';
 import { MetadataTags } from './metadata';
@@ -161,38 +162,54 @@ const removeEmulationPreventionBytes = (data: Uint8Array) => {
 	return new Uint8Array(result);
 };
 
-/** Converts an AVC packet in Annex B format to length-prefixed format. */
-export const transformAnnexBToLengthPrefixed = (packetData: Uint8Array) => {
-	const NAL_UNIT_LENGTH_SIZE = 4;
+const ANNEX_B_START_CODE = new Uint8Array([0, 0, 0, 1]);
 
-	const nalUnits = findNalUnitsInAnnexB(packetData);
-
-	if (nalUnits.length === 0) {
-		// If no NAL units were found, it's not valid Annex B data
-		return null;
-	}
-
-	let totalSize = 0;
-	for (const nalUnit of nalUnits) {
-		totalSize += NAL_UNIT_LENGTH_SIZE + nalUnit.byteLength;
-	}
-
-	const avccData = new Uint8Array(totalSize);
-	const dataView = new DataView(avccData.buffer);
+export const concatNalUnitsInAnnexB = (nalUnits: Uint8Array[]) => {
+	const totalLength = nalUnits.reduce((a, b) => a + ANNEX_B_START_CODE.byteLength + b.byteLength, 0);
+	const result = new Uint8Array(totalLength);
 	let offset = 0;
 
-	// Write each NAL unit with its length prefix
 	for (const nalUnit of nalUnits) {
-		const length = nalUnit.byteLength;
+		result.set(ANNEX_B_START_CODE, offset);
+		offset += ANNEX_B_START_CODE.byteLength;
 
-		dataView.setUint32(offset, length, false);
-		offset += 4;
-
-		avccData.set(nalUnit, offset);
+		result.set(nalUnit, offset);
 		offset += nalUnit.byteLength;
 	}
 
-	return avccData;
+	return result;
+};
+
+export const concatNalUnitsInLengthPrefixed = (nalUnits: Uint8Array[], lengthSize: 1 | 2 | 3 | 4) => {
+	const totalLength = nalUnits.reduce((a, b) => a + lengthSize + b.byteLength, 0);
+	const result = new Uint8Array(totalLength);
+	let offset = 0;
+
+	for (const nalUnit of nalUnits) {
+		const dataView = new DataView(result.buffer, result.byteOffset, result.byteLength);
+
+		switch (lengthSize) {
+			case 1:
+				dataView.setUint8(offset, nalUnit.byteLength);
+				break;
+			case 2:
+				dataView.setUint16(offset, nalUnit.byteLength, false);
+				break;
+			case 3:
+				setUint24(dataView, offset, nalUnit.byteLength, false);
+				break;
+			case 4:
+				dataView.setUint32(offset, nalUnit.byteLength, false);
+				break;
+		}
+
+		offset += lengthSize;
+
+		result.set(nalUnit, offset);
+		offset += nalUnit.byteLength;
+	}
+
+	return result;
 };
 
 // Data specified in ISO 14496-15
@@ -227,7 +244,22 @@ export const extractAvcNalUnits = (packetData: Uint8Array, decoderConfig: VideoD
 	}
 };
 
-const extractNalUnitTypeForAvc = (data: Uint8Array) => {
+export const concatAvcNalUnits = (nalUnits: Uint8Array[], decoderConfig: VideoDecoderConfig) => {
+	if (decoderConfig.description) {
+		// Stream is length-prefixed. Let's extract the size of the length prefix from the decoder config
+
+		const bytes = toUint8Array(decoderConfig.description);
+		const lengthSizeMinusOne = bytes[4]! & 0b11;
+		const lengthSize = (lengthSizeMinusOne + 1) as 1 | 2 | 3 | 4;
+
+		return concatNalUnitsInLengthPrefixed(nalUnits, lengthSize);
+	} else {
+		// Stream is in Annex B format
+		return concatNalUnitsInAnnexB(nalUnits);
+	}
+};
+
+export const extractNalUnitTypeForAvc = (data: Uint8Array) => {
 	return data[0]! & 0x1F;
 };
 

src/isobmff/isobmff-muxer.ts

@@ -25,11 +25,12 @@ import {
 import { BufferTarget } from '../target';
 import { EncodedPacket, PacketType } from '../packet';
 import {
+	concatNalUnitsInLengthPrefixed,
 	extractAvcDecoderConfigurationRecord,
 	extractHevcDecoderConfigurationRecord,
+	findNalUnitsInAnnexB,
 	serializeAvcDecoderConfigurationRecord,
 	serializeHevcDecoderConfigurationRecord,
-	transformAnnexBToLengthPrefixed,
 } from '../codec-data';
 import { buildIsobmffMimeType } from './isobmff-misc';
 import { MAX_BOX_HEADER_SIZE, MIN_BOX_HEADER_SIZE } from './isobmff-reader';
@@ -464,15 +465,18 @@ export class IsobmffMuxer extends Muxer {
 
 			let packetData = packet.data;
 			if (trackData.info.requiresAnnexBTransformation) {
-				const transformedData = transformAnnexBToLengthPrefixed(packetData);
-				if (!transformedData) {
+				const nalUnits = findNalUnitsInAnnexB(packetData);
+				if (nalUnits.length === 0) {
+					// It's not valid Annex B data
 					throw new Error(
 						'Failed to transform packet data. Make sure all packets are provided in Annex B format, as'
 						+ ' specified in ITU-T-REC-H.264 and ITU-T-REC-H.265.',
 					);
 				}
 
-				packetData = transformedData;
+				// We don't strip things like SPS or PPS NALUs here, mainly because they can also appear in the middle
+				// of a stream and potentially modify the parameters of it. So, let's just leave them in to be sure.
+				packetData = concatNalUnitsInLengthPrefixed(nalUnits, 4);
 			}
 
 			const timestamp = this.validateAndNormalizeTimestamp(

src/media-sink.ts

@@ -8,9 +8,12 @@
 
 import { parsePcmCodec, PCM_AUDIO_CODECS, PcmAudioCodec, VideoCodec, AudioCodec } from './codec';
 import {
+	concatAvcNalUnits,
 	deserializeAvcDecoderConfigurationRecord,
 	determineVideoPacketType,
+	extractAvcNalUnits,
 	extractHevcNalUnits,
+	extractNalUnitTypeForAvc,
 	extractNalUnitTypeForHevc,
 	HevcNalUnitType,
 	parseAvcSps,
@@ -928,8 +931,6 @@ class VideoDecoderWrapper extends DecoderWrapper<VideoSample> {
 			this.raslSkipped = true;
 		}
 
-		this.currentPacketIndex++;
-
 		if (this.customDecoder) {
 			this.customDecoderQueueSize++;
 			void this.customDecoderCallSerializer
@@ -942,9 +943,24 @@ class VideoDecoderWrapper extends DecoderWrapper<VideoSample> {
 				insertSorted(this.inputTimestamps, packet.timestamp, x => x);
 			}
 
+			// Workaround for https://issues.chromium.org/issues/470109459
+			if (isChromium() && this.currentPacketIndex === 0 && this.codec === 'avc') {
+				const nalUnits = extractAvcNalUnits(packet.data, this.decoderConfig);
+				const filteredNalUnits = nalUnits.filter((x) => {
+					const type = extractNalUnitTypeForAvc(x);
+					// These trip up Chromium's key frame detection, so let's strip them
+					return !(type >= 20 && type <= 31);
+				});
+
+				const newData = concatAvcNalUnits(filteredNalUnits, this.decoderConfig);
+				packet = new EncodedPacket(newData, packet.type, packet.timestamp, packet.duration);
+			}
+
 			this.decoder.decode(packet.toEncodedVideoChunk());
 			this.decodeAlphaData(packet);
 		}
+
+		this.currentPacketIndex++;
 	}
 
 	decodeAlphaData(packet: EncodedPacket) {

test/node/annex-b-conversion.test.ts

@@ -0,0 +1,54 @@
+import { expect, test } from 'vitest';
+import { Input } from '../../src/input.js';
+import { BufferSource, FilePathSource } from '../../src/source.js';
+import path from 'node:path';
+import { ALL_FORMATS } from '../../src/input-format.js';
+import { Output } from '../../src/output.js';
+import { Mp4OutputFormat } from '../../src/output-format.js';
+import { BufferTarget } from '../../src/target.js';
+import { Conversion } from '../../src/conversion.js';
+import { EncodedPacketSink } from '../../src/media-sink.js';
+import { extractAvcNalUnits } from '../../src/codec-data.js';
+
+const __dirname = new URL('.', import.meta.url).pathname;
+
+test('Annex B to length-prefixed conversion, MP4', async () => {
+	using originalInput = new Input({
+		source: new FilePathSource(path.join(__dirname, '..', 'public/annex-b-avc.mkv')),
+		formats: ALL_FORMATS,
+	});
+	const originalVideoTrack = (await originalInput.getPrimaryVideoTrack())!;
+	const originalDecoderConfig = (await originalVideoTrack.getDecoderConfig())!;
+	expect(originalDecoderConfig.description).toBeUndefined();
+	expect(originalVideoTrack.codec).toBe('avc');
+
+	const originalSink = new EncodedPacketSink(originalVideoTrack);
+	const originalFirstPacket = await originalSink.getFirstPacket();
+	expect([...originalFirstPacket!.data.slice(0, 4)]).toEqual([0, 0, 0, 1]);
+
+	const originalNalUnits = extractAvcNalUnits(originalFirstPacket!.data, originalDecoderConfig);
+
+	const output = new Output({
+		format: new Mp4OutputFormat(),
+		target: new BufferTarget(),
+	});
+
+	const conversion = await Conversion.init({ input: originalInput, output });
+	await conversion.execute();
+
+	using newInput = new Input({
+		source: new BufferSource(output.target.buffer!),
+		formats: ALL_FORMATS,
+	});
+	const newVideoTrack = (await newInput.getPrimaryVideoTrack())!;
+	const newDecoderConfig = (await newVideoTrack.getDecoderConfig())!;
+	expect(newDecoderConfig.description).toBeDefined();
+	expect(newVideoTrack.codec).toBe('avc');
+
+	const newSink = new EncodedPacketSink(newVideoTrack);
+	const newFirstPacket = await newSink.getFirstPacket();
+	expect([...newFirstPacket!.data.slice(0, 4)]).not.toEqual([0, 0, 0, 1]); // Successfully converted
+
+	const newNalUnits = extractAvcNalUnits(newFirstPacket!.data, newDecoderConfig);
+	expect(newNalUnits).toEqual(originalNalUnits); // Content is the same though
+});