Fix remaining type errors, bump version

dev/convert.html

@@ -24,7 +24,7 @@
 			chunked: true,
 			chunkSize: 2**20
 		});
-		const outputFormat = new Mediabunny.Mp4OutputFormat({});
+		const outputFormat = new Mediabunny.Mp3OutputFormat({});
 
 		const button = document.createElement('button');
 		button.textContent = 'Cancel';
@@ -41,7 +41,7 @@
 				target
 			}),
 			audio: {
-				discard: true,
+				//discard: true,
 				//codec: 'opus',
 				//bitrate: 128000,
 				//numberOfChannels: 1,
@@ -94,8 +94,8 @@
 				//height: 100,
 			}),
 			trim: {
-				start: 0,
-				end: 20
+				//start: 0,
+				//end: 20
 			},
 		});
 		console.log(conversion);

dev/demux.html

@@ -8,15 +8,6 @@
 	document.body.append(fileInput);
 
 	fileInput.addEventListener('change', async () => {
-		const videoUrl = "https://upload.wikimedia.org/wikipedia/commons/5/53/1941._%D0%9A%D0%BE%D0%BD%D1%91%D0%BA-%D0%B3%D0%BE%D1%80%D0%B1%D1%83%D0%BD%D0%BE%D0%BA.webm"
-		const source = new Mediabunny.UrlSource(videoUrl)
-		const input = new Mediabunny.Input({ formats: Mediabunny.ALL_FORMATS, source });
-
-		const videoTrack = await input.getPrimaryVideoTrack();
-
-		console.log(videoTrack);
-
-		/*
 		const file = fileInput.files[0];
 		const source = new Mediabunny.BlobSource(file);
 
@@ -25,6 +16,15 @@
 			source
 		});
 
+		const videoTrack = await input.getPrimaryVideoTrack();
+		const sink = new Mediabunny.EncodedPacketSink(videoTrack);
+
+		for await (const packet of sink.packets(undefined, undefined, { verifyKeyPackets: false })) {
+			console.log(packet);
+			if (packet.timestamp >= 2.4) break;
+		}
+
+		/*
 		const audioTrack = await input.getPrimaryAudioTrack();
 		const sink = new Mediabunny.EncodedPacketSink(audioTrack);
 

docs/guide/media-sources.md

@@ -123,6 +123,7 @@ const sampleSource = new VideoSampleSource({
 });
 
 await sampleSource.add(videoSample);
+videoSample.close(); // If it's not needed anymore
 
 // You may optionally force samples to be encoded as key frames:
 await sampleSource.add(videoSample, { keyFrame: true });
@@ -285,6 +286,7 @@ const sampleSource = new AudioSampleSource({
 });
 
 await sampleSource.add(audioSample);
+audioSample.close(); // If it's not needed anymore
 ```
 
 ### `AudioBufferSource`

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "mediabunny",
-  "version": "1.7.1",
+  "version": "1.7.4",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "mediabunny",
-      "version": "1.7.1",
+      "version": "1.7.4",
       "license": "MPL-2.0",
       "workspaces": [
         "packages/*"
@@ -5900,9 +5900,9 @@
       }
     },
     "node_modules/mediabunny": {
-      "version": "1.7.0",
-      "resolved": "https://registry.npmjs.org/mediabunny/-/mediabunny-1.7.0.tgz",
-      "integrity": "sha512-QcTdptOtvjAHb4KQpgWWWHRS0+DgGwTXelTwPWaZwQu85iYy11bzsLS4e29rfH4nLL/eq8K/dBsjj1LuApc2Qw==",
+      "version": "1.7.3",
+      "resolved": "https://registry.npmjs.org/mediabunny/-/mediabunny-1.7.3.tgz",
+      "integrity": "sha512-wh0bTZ0bLKIdkn0gMMF/uxEVh85Ft/qH1OtUKJO8k5tdqP0RG7rMfoXLZI6r+wZ9VadfQ4xxYZTEallAWZ74jw==",
       "license": "MPL-2.0",
       "peer": true,
       "workspaces": [
@@ -9017,7 +9017,7 @@
     },
     "packages/mp3-encoder": {
       "name": "@mediabunny/mp3-encoder",
-      "version": "1.7.1",
+      "version": "1.7.4",
       "license": "MPL-2.0",
       "devDependencies": {
         "@types/emscripten": "^1.40.1"

package.json

@@ -1,7 +1,7 @@
 {
   "name": "mediabunny",
   "author": "Vanilagy",
-  "version": "1.7.1",
+  "version": "1.7.4",
   "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": "1.7.1",
+  "version": "1.7.4",
   "description": "MP3 encoder extension for Mediabunny, based on LAME.",
   "main": "./dist/bundles/mediabunny-mp3-encoder.mjs",
   "module": "./dist/bundles/mediabunny-mp3-encoder.mjs",

src/input-format.ts

@@ -10,7 +10,7 @@ import { Demuxer } from './demuxer';
 import { Input } from './input';
 import { IsobmffDemuxer } from './isobmff/isobmff-demuxer';
 import { IsobmffReader } from './isobmff/isobmff-reader';
-import { EBMLId, EBMLReader } from './matroska/ebml';
+import { EBMLId, EBMLReader, MIN_HEADER_SIZE } from './matroska/ebml';
 import { MatroskaDemuxer } from './matroska/matroska-demuxer';
 import { Mp3Demuxer } from './mp3/mp3-demuxer';
 import { FRAME_HEADER_SIZE } from '../shared/mp3-misc';
@@ -106,6 +106,10 @@ export class QuickTimeInputFormat extends IsobmffInputFormat {
 	}
 }
 
+function foo() {
+	return 5;
+}
+
 /**
  * Matroska file format.
  * @public
@@ -120,6 +124,12 @@ export class MatroskaInputFormat extends InputFormat {
 
 		const ebmlReader = new EBMLReader(input._mainReader);
 		const varIntSize = ebmlReader.readVarIntSize();
+		if (varIntSize === null) {
+			return false;
+		}
+
+		foo();
+
 		if (varIntSize < 1 || varIntSize > 8) {
 			return false;
 		}
@@ -135,8 +145,11 @@ export class MatroskaInputFormat extends InputFormat {
 		}
 
 		const startPos = ebmlReader.pos;
-		while (ebmlReader.pos < startPos + dataSize) {
-			const { id, size } = ebmlReader.readElementHeader();
+		while (ebmlReader.pos <= startPos + dataSize - MIN_HEADER_SIZE) {
+			const header = ebmlReader.readElementHeader();
+			if (!header) break;
+
+			const { id, size } = header;
 			const dataStartPos = ebmlReader.pos;
 			if (size === null) return false;
 

src/isobmff/isobmff-demuxer.ts

@@ -1459,6 +1459,12 @@ export class IsobmffDemuxer extends Demuxer {
 					const sampleIndex = this.metadataReader.readU32() - 1; // Convert to 0-indexed
 					track.sampleTable.keySampleIndices.push(sampleIndex);
 				}
+
+				if (track.sampleTable.keySampleIndices[0] !== 0) {
+					// Some files don't mark the first sample a key sample, which is basically almost always incorrect.
+					// Here, we correct for that mistake:
+					track.sampleTable.keySampleIndices.unshift(0);
+				}
 			}; break;
 
 			case 'stsc': {

src/matroska/ebml.ts

@@ -379,7 +379,7 @@ export class EBMLWriter {
 
 const MAX_VAR_INT_SIZE = 8;
 export const MIN_HEADER_SIZE = 2; // 1-byte ID and 1-byte size
-export const MAX_HEADER_SIZE = 4 + MAX_VAR_INT_SIZE; // 4-byte ID and 8-byte size
+export const MAX_HEADER_SIZE = 2 * MAX_VAR_INT_SIZE; // 8-byte ID and 8-byte size
 
 export class EBMLReader {
 	pos = 0;
@@ -411,9 +411,13 @@ export class EBMLReader {
 		const { view, offset } = this.reader.getViewAndOffset(this.pos, this.pos + 1);
 		const firstByte = view.getUint8(offset);
 
+		if (firstByte === 0) {
+			return null; // Invalid VINT
+		}
+
 		let width = 1;
 		let mask = 0x80;
-		while ((firstByte & mask) === 0 && width < 8) {
+		while ((firstByte & mask) === 0) {
 			width++;
 			mask >>= 1;
 		}
@@ -426,10 +430,14 @@ export class EBMLReader {
 		const { view, offset } = this.reader.getViewAndOffset(this.pos, this.pos + 1);
 		const firstByte = view.getUint8(offset);
 
+		if (firstByte === 0) {
+			return null; // Invalid VINT
+		}
+
 		// Find the position of VINT_MARKER, which determines the width
 		let width = 1;
 		let mask = 1 << 7;
-		while ((firstByte & mask) === 0 && width < MAX_VAR_INT_SIZE) {
+		while ((firstByte & mask) === 0) {
 			width++;
 			mask >>= 1;
 		}
@@ -509,8 +517,11 @@ export class EBMLReader {
 
 	readElementId() {
 		const size = this.readVarIntSize();
-		const id = this.readUnsignedInt(size);
+		if (size === null) {
+			return null;
+		}
 
+		const id = this.readUnsignedInt(size);
 		return id;
 	}
 
@@ -538,6 +549,10 @@ export class EBMLReader {
 
 	readElementHeader() {
 		const id = this.readElementId();
+		if (id === null) {
+			return null;
+		}
+
 		const size = this.readElementSize();
 
 		return { id, size };
@@ -548,13 +563,17 @@ export class EBMLReader {
 		const loadChunkSize = 2 ** 20; // 1 MiB
 		const idsSet = new Set(ids);
 
-		while (this.pos < until - MAX_HEADER_SIZE) {
-			if (!this.reader.rangeIsLoaded(this.pos, this.pos + MAX_HEADER_SIZE)) {
+		while (this.pos <= until - MIN_HEADER_SIZE) {
+			if (!this.reader.rangeIsLoaded(this.pos, Math.min(this.pos + MAX_HEADER_SIZE, until))) {
 				await this.reader.loadRange(this.pos, Math.min(this.pos + loadChunkSize, until));
 			}
 
 			const elementStartPos = this.pos;
 			const elementHeader = this.readElementHeader();
+			if (!elementHeader) {
+				break;
+			}
+
 			if (idsSet.has(elementHeader.id)) {
 				return elementStartPos;
 			}

src/matroska/matroska-demuxer.ts

@@ -239,6 +239,10 @@ export class MatroskaDemuxer extends Demuxer {
 				);
 
 				const header = this.metadataReader.readElementHeader();
+				if (!header) {
+					break; // Zero padding at the end of the file triggers this, for example
+				}
+
 				const id = header.id;
 				let size = header.size;
 				const startPos = this.metadataReader.pos;
@@ -318,14 +322,19 @@ export class MatroskaDemuxer extends Demuxer {
 		);
 
 		let clusterEncountered = false;
-		while (this.metadataReader.pos < this.currentSegment.elementEndPos) {
+		while (this.metadataReader.pos <= this.currentSegment.elementEndPos - MIN_HEADER_SIZE) {
 			await this.metadataReader.reader.loadRange(
 				this.metadataReader.pos,
 				this.metadataReader.pos + MAX_HEADER_SIZE,
 			);
 
 			const elementStartPos = this.metadataReader.pos;
-			const { id, size } = this.metadataReader.readElementHeader();
+			const header = this.metadataReader.readElementHeader();
+			if (!header) {
+				break;
+			}
+
+			const { id, size } = header;
 			const dataStartPos = this.metadataReader.pos;
 
 			const metadataElementIndex = METADATA_ELEMENTS.findIndex(x => x.id === id);
@@ -392,7 +401,10 @@ export class MatroskaDemuxer extends Demuxer {
 				this.metadataReader.pos,
 				this.metadataReader.pos + 2 ** 12, // Load a larger range, assuming the correct element will be there
 			);
-			const { id, size } = this.metadataReader.readElementHeader();
+			const header = this.metadataReader.readElementHeader();
+			if (!header) continue;
+
+			const { id, size } = header;
 			if (id !== target.id) continue;
 
 			assertDefinedSize(size);
@@ -469,6 +481,8 @@ export class MatroskaDemuxer extends Demuxer {
 
 		const elementStartPos = this.metadataReader.pos;
 		const elementHeader = this.metadataReader.readElementHeader();
+		assert(elementHeader);
+
 		const id = elementHeader.id;
 		let size = elementHeader.size;
 		const dataStartPos = this.metadataReader.pos;
@@ -720,12 +734,20 @@ export class MatroskaDemuxer extends Demuxer {
 		const startIndex = reader.pos;
 
 		while (reader.pos - startIndex <= totalSize - MIN_HEADER_SIZE) {
-			this.traverseElement(reader);
+			const foundElement = this.traverseElement(reader);
+			if (!foundElement) {
+				break;
+			}
 		}
 	}
 
-	traverseElement(reader: EBMLReader) {
-		const { id, size } = reader.readElementHeader();
+	traverseElement(reader: EBMLReader): boolean {
+		const header = reader.readElementHeader();
+		if (!header) {
+			return false;
+		}
+
+		const { id, size } = header;
 		const dataStartPos = reader.pos;
 		assertDefinedSize(size);
 
@@ -1113,6 +1135,8 @@ export class MatroskaDemuxer extends Demuxer {
 				if (!this.currentCluster) break;
 
 				const trackNumber = reader.readVarInt();
+				if (trackNumber === null) break;
+
 				const relativeTimestamp = reader.readS16();
 
 				const flags = reader.readU8();
@@ -1148,6 +1172,8 @@ export class MatroskaDemuxer extends Demuxer {
 				if (!this.currentCluster) break;
 
 				const trackNumber = reader.readVarInt();
+				if (trackNumber === null) break;
+
 				const relativeTimestamp = reader.readS16();
 
 				const flags = reader.readU8();
@@ -1184,6 +1210,7 @@ export class MatroskaDemuxer extends Demuxer {
 		}
 
 		reader.pos = dataStartPos + size;
+		return true;
 	}
 }
 
@@ -1562,7 +1589,7 @@ abstract class MatroskaTrackBacking implements InputTrackBacking {
 				}
 			}
 
-			while (metadataReader.pos < segment.elementEndPos) {
+			while (metadataReader.pos <= segment.elementEndPos - MIN_HEADER_SIZE) {
 				if (prevCluster) {
 					const trackData = prevCluster.trackData.get(this.internalTrack.id);
 					if (trackData && trackData.startTimestamp > latestTimestamp) {
@@ -1582,6 +1609,10 @@ abstract class MatroskaTrackBacking implements InputTrackBacking {
 				await metadataReader.reader.loadRange(metadataReader.pos, metadataReader.pos + MAX_HEADER_SIZE);
 				const elementStartPos = metadataReader.pos;
 				const elementHeader = metadataReader.readElementHeader();
+				if (!elementHeader) {
+					break;
+				}
+
 				const id = elementHeader.id;
 				let size = elementHeader.size;
 				const dataStartPos = metadataReader.pos;

src/media-sink.ts

@@ -1248,9 +1248,15 @@ class AudioDecoderWrapper extends DecoderWrapper<AudioSample> {
 		super(onSample, onError);
 
 		const sampleHandler = (sample: AudioSample) => {
-			const sampleRate = decoderConfig.sampleRate;
+			if (sample.numberOfFrames === 0) {
+				// We skip zero-data (empty) AudioSamples. These are sometimes emitted, for example, by Firefox when it
+				// decodes Vorbis (at the start).
+				sample.close();
+				return;
+			}
 
 			// Round the timestamp to the sample rate
+			const sampleRate = decoderConfig.sampleRate;
 			sample.setTimestamp(Math.round(sample.timestamp * sampleRate) / sampleRate);
 
 			onSample(sample);

src/media-source.ts

@@ -158,7 +158,8 @@ export class EncodedVideoPacketSource extends VideoSource {
 	}
 
 	/**
-	 * Adds an encoded packet to the output video track.
+	 * Adds an encoded packet to the output video track. Packets must be added in *decode order*, while a packet's
+	 * timestamp must be its *presentation timestamp*. B-frames are handled automatically.
 	 *
 	 * @param meta - Additional metadata from the encoder. You should pass this for the first call, including a valid
 	 * decoder config.
@@ -322,17 +323,17 @@ class VideoEncoderWrapper {
 
 			if (this.customEncoder) {
 				this.customEncoderQueueSize++;
-				const promise = this.customEncoderCallSerializer
-					.call(() => this.customEncoder!.encode(videoSample, finalEncodeOptions))
-					.then(() => {
-						this.customEncoderQueueSize--;
 
-						if (shouldClose) {
-							videoSample.close();
-						}
-					})
-					.catch((error: Error) => {
-						this.encoderError ??= error;
+				// We clone the sample so it cannot be closed on us from the outside before it reaches the encoder
+				const clonedSample = videoSample.clone();
+
+				const promise = this.customEncoderCallSerializer
+					.call(() => this.customEncoder!.encode(clonedSample, finalEncodeOptions))
+					.then(() => this.customEncoderQueueSize--)
+					.catch((error: Error) => this.encoderError ??= error)
+					.finally(() => {
+						clonedSample.close();
+						// `videoSample` gets closed in the finally block at the end of the method
 					});
 
 				if (this.customEncoderQueueSize >= 4) {
@@ -439,6 +440,7 @@ class VideoEncoderWrapper {
 						void this.muxer!.addEncodedVideoPacket(this.source._connectedTrack!, packet, meta);
 					},
 					error: (error) => {
+						error.stack = new Error().stack; // Provide a more useful stack trace
 						this.encoderError ??= error;
 					},
 				});
@@ -482,7 +484,6 @@ class VideoEncoderWrapper {
 
 	checkForEncoderError() {
 		if (this.encoderError) {
-			this.encoderError.stack = new Error().stack; // Provide a more useful stack trace
 			throw this.encoderError;
 		}
 	}
@@ -788,7 +789,7 @@ export class EncodedAudioPacketSource extends AudioSource {
 	}
 
 	/**
-	 * Adds an encoded packet to the output audio track.
+	 * Adds an encoded packet to the output audio track. Packets must be added in *decode order*.
 	 *
 	 * @param meta - Additional metadata from the encoder. You should pass this for the first call, including a valid
 	 * decoder config.
@@ -938,17 +939,17 @@ class AudioEncoderWrapper {
 
 			if (this.customEncoder) {
 				this.customEncoderQueueSize++;
-				const promise = this.customEncoderCallSerializer
-					.call(() => this.customEncoder!.encode(audioSample))
-					.then(() => {
-						this.customEncoderQueueSize--;
 
-						if (shouldClose) {
-							audioSample.close();
-						}
-					})
-					.catch((error: Error) => {
-						this.encoderError ??= error;
+				// We clone the sample so it cannot be closed on us from the outside before it reaches the encoder
+				const clonedSample = audioSample.clone();
+
+				const promise = this.customEncoderCallSerializer
+					.call(() => this.customEncoder!.encode(clonedSample))
+					.then(() => this.customEncoderQueueSize--)
+					.catch((error: Error) => this.encoderError ??= error)
+					.finally(() => {
+						clonedSample.close();
+						// `audioSample` gets closed in the finally block at the end of the method
 					});
 
 				if (this.customEncoderQueueSize >= 4) {
@@ -1127,6 +1128,7 @@ class AudioEncoderWrapper {
 						void this.muxer!.addEncodedAudioPacket(this.source._connectedTrack!, packet, meta);
 					},
 					error: (error) => {
+						error.stack = new Error().stack; // Provide a more useful stack trace
 						this.encoderError ??= error;
 					},
 				});
@@ -1265,7 +1267,6 @@ class AudioEncoderWrapper {
 
 	checkForEncoderError() {
 		if (this.encoderError) {
-			this.encoderError.stack = new Error().stack; // Provide a more useful stack trace
 			throw this.encoderError;
 		}
 	}