feat: build reproducible dataset editor

2026-08-28 10:46:33 +09:00
parent 6a1197d60e
commit 08fcf578de
16 changed files with 2579 additions and 11 deletions
@@ -0,0 +1,128 @@
+export const MAX_DECODED_AUDIO_BYTES = 192 * 1024 * 1024;
+const MAX_WAV_HEADER_BYTES = 1024 * 1024;
+const CONSERVATIVE_COMPRESSED_CHANNELS = 32;
+
+function ascii(view, offset, length) {
+  let value = "";
+  for (let index = 0; index < length; index += 1) value += String.fromCharCode(view.getUint8(offset + index));
+  return value;
+}
+
+async function readWavMetadata(file, signal) {
+  throwIfAborted(signal);
+  const header = await file.slice(0, Math.min(file.size, MAX_WAV_HEADER_BYTES)).arrayBuffer();
+  throwIfAborted(signal);
+  const view = new DataView(header);
+  if (view.byteLength < 12 || ascii(view, 0, 4) !== "RIFF" || ascii(view, 8, 4) !== "WAVE") {
+    throw new Error(`${file.name} WAV의 RIFF/WAVE header가 올바르지 않습니다.`);
+  }
+  let offset = 12;
+  let format = null;
+  let dataByteLength = null;
+  while (offset + 8 <= view.byteLength) {
+    const chunkId = ascii(view, offset, 4);
+    const chunkSize = view.getUint32(offset + 4, true);
+    const payloadOffset = offset + 8;
+    if (chunkId === "fmt " && chunkSize >= 16 && payloadOffset + 16 <= view.byteLength) {
+      format = {
+        channels: view.getUint16(payloadOffset + 2, true),
+        sampleRate: view.getUint32(payloadOffset + 4, true),
+        byteRate: view.getUint32(payloadOffset + 8, true),
+      };
+    } else if (chunkId === "data") {
+      dataByteLength = chunkSize;
+      break;
+    }
+    const nextOffset = payloadOffset + chunkSize + (chunkSize % 2);
+    if (!Number.isSafeInteger(nextOffset) || nextOffset <= offset) break;
+    offset = nextOffset;
+  }
+  if (!format || dataByteLength === null || format.channels < 1 || format.channels > 32 || format.byteRate < 1) {
+    throw new Error(`${file.name} WAV의 fmt/data chunk를 안전하게 읽지 못했습니다.`);
+  }
+  return { channels: format.channels, duration: dataByteLength / format.byteRate };
+}
+
+function throwIfAborted(signal) {
+  if (signal?.aborted) throw new DOMException("오디오 decode가 취소됐습니다.", "AbortError");
+}
+
+async function probeAudioDuration(file, signal) {
+  throwIfAborted(signal);
+  const url = URL.createObjectURL(file);
+  const audio = document.createElement("audio");
+  audio.preload = "metadata";
+  try {
+    return await new Promise((resolve, reject) => {
+      let settled = false;
+      const finish = (value, error) => {
+        if (settled) return;
+        settled = true;
+        clearTimeout(timeout);
+        signal?.removeEventListener("abort", onAbort);
+        if (error) reject(error);
+        else resolve(value);
+      };
+      const onAbort = () => finish(null, new DOMException("오디오 metadata 확인이 취소됐습니다.", "AbortError"));
+      const timeout = setTimeout(() => finish(null), 10000);
+      audio.addEventListener("loadedmetadata", () => finish(Number.isFinite(audio.duration) ? audio.duration : null), { once: true });
+      audio.addEventListener("error", () => finish(null), { once: true });
+      signal?.addEventListener("abort", onAbort, { once: true });
+      audio.src = url;
+    });
+  } finally {
+    audio.removeAttribute("src");
+    audio.load();
+    URL.revokeObjectURL(url);
+  }
+}
+
+async function estimateDecodedBytes(file, targetSampleRate, signal) {
+  const isWav = /(?:audio\/(?:x-)?wav)/i.test(file.type) || /\.wav$/i.test(file.name);
+  if (isWav) {
+    const metadata = await readWavMetadata(file, signal);
+    return Math.ceil(metadata.duration * targetSampleRate) * metadata.channels * Float32Array.BYTES_PER_ELEMENT;
+  }
+  const duration = await probeAudioDuration(file, signal);
+  if (duration === null) {
+    throw new Error(`${file.name}의 decode 크기를 미리 확인할 수 없습니다. PCM WAV로 변환해 사용하세요.`);
+  }
+  return Math.ceil(duration * targetSampleRate) * CONSERVATIVE_COMPRESSED_CHANNELS * Float32Array.BYTES_PER_ELEMENT;
+}
+
+export async function decodeAudioFile(file, targetSampleRate, maximumDecodedBytes = MAX_DECODED_AUDIO_BYTES, signal) {
+  if (!Number.isInteger(targetSampleRate) || targetSampleRate < 8000 || targetSampleRate > 192000) {
+    throw new Error(`지원하지 않는 decode sample rate입니다: ${targetSampleRate}`);
+  }
+  try {
+    const estimatedBytes = await estimateDecodedBytes(file, targetSampleRate, signal);
+    throwIfAborted(signal);
+    if (!Number.isSafeInteger(estimatedBytes) || estimatedBytes < 0 || estimatedBytes > maximumDecodedBytes) {
+      throw new Error(
+        `${file.name} 예상 decode 크기 ${(estimatedBytes / 1024 ** 2).toFixed(1)} MiB가 ` +
+          `${(maximumDecodedBytes / 1024 ** 2).toFixed(1)} MiB 잔여 한도를 넘습니다.`,
+      );
+    }
+    const context = new OfflineAudioContext(1, 1, targetSampleRate);
+    const fileBytes = await file.arrayBuffer();
+    throwIfAborted(signal);
+    const decoded = await context.decodeAudioData(fileBytes);
+    throwIfAborted(signal);
+    const decodedBytes = decoded.length * decoded.numberOfChannels * Float32Array.BYTES_PER_ELEMENT;
+    if (decodedBytes > maximumDecodedBytes) {
+      throw new Error(
+        `${file.name} decode 크기 ${(decodedBytes / 1024 ** 2).toFixed(1)} MiB가 ` +
+          `${(maximumDecodedBytes / 1024 ** 2).toFixed(0)} MiB 한도를 넘습니다.`,
+      );
+    }
+    const channels = [];
+    for (let channel = 0; channel < decoded.numberOfChannels; channel += 1) {
+      channels.push(decoded.getChannelData(channel));
+    }
+    return { sampleRate: decoded.sampleRate, channels };
+  } catch (error) {
+    if (error?.name === "AbortError") throw error;
+    const reason = error instanceof Error ? error.message : String(error);
+    throw new Error(`${file.name} 오디오를 ${targetSampleRate} Hz로 decode하지 못했습니다: ${reason}`);
+  }
+}