Fix WaveDemuxer reading too far in corrupted ID3 chunk (#301)

* Update read-mp4.test.ts

* Fix the bug

* Delete read-wav.test.ts

* Submit test file

* Small adjustments

---------

Co-authored-by: Vanilagy <[email protected]>

src/wave/wave-demuxer.ts

@@ -15,7 +15,7 @@ import { DEFAULT_TRACK_DISPOSITION, MetadataTags } from '../metadata';
 import { assert, UNDETERMINED_LANGUAGE } from '../misc';
 import { EncodedPacket, PLACEHOLDER_DATA } from '../packet';
 import { readAscii, readBytes, Reader, readU16, readU32, readU64 } from '../reader';
-import { parseId3V2Tag, readId3V2Header } from '../id3';
+import { ID3_V2_HEADER_SIZE, parseId3V2Tag, readId3V2Header } from '../id3';
 
 export enum WaveFormat {
 	PCM = 0x0001,
@@ -286,10 +286,15 @@ export class WaveDemuxer extends Demuxer {
 
 		const id3V2Header = readId3V2Header(slice);
 		if (id3V2Header) {
-			// Extract the content portion (skip the 10-byte header)
+			// Clamp to the available data in case the ID3 header claims more than the WAV chunk provides
-			const contentSlice = slice.slice(startPos + 10, id3V2Header.size);
+			// https://github.com/Vanilagy/mediabunny/issues/300
+			const availableSize = size - ID3_V2_HEADER_SIZE;
+			id3V2Header.size = Math.min(id3V2Header.size, availableSize);
 
-			parseId3V2Tag(contentSlice, id3V2Header, this.metadataTags);
+			if (id3V2Header.size > 0) {
+				const contentSlice = slice.slice(startPos + ID3_V2_HEADER_SIZE, id3V2Header.size);
+				parseId3V2Tag(contentSlice, id3V2Header, this.metadataTags);
+			}
 		}
 	}
 

test/node/read-wav.test.ts

@@ -0,0 +1,24 @@
+import { test } from 'vitest';
+import path from 'node:path';
+import { ALL_FORMATS, EncodedPacketSink, Input, FilePathSource } from '../../src/index.js';
+
+const __dirname = new URL('.', import.meta.url).pathname;
+
+test('Should handle WAV file with oversized ID3 chunk', async () => {
+	const filePath = path.join(__dirname, '..', 'public/oversized-id3.wav');
+	using input = new Input({
+		source: new FilePathSource(filePath),
+		formats: ALL_FORMATS,
+	});
+
+	const track = await input.getPrimaryAudioTrack();
+	if (!track) {
+		throw new Error('No audio track found');
+	}
+
+	const sink = new EncodedPacketSink(track);
+
+	for await (const packet of sink.packets()) {
+		void packet;
+	}
+});