pipeline/scripts/dump-video-document.mjs

// 只跑【文字 + 音频】两模块（不调 Remotion、不需要 Chrome），把 VideoDocument 契约
// 导出成 JSON，并打印一份人读摘要。用于快速验证重构后的契约与口播/卡片/字幕。
//
// 用法： node scripts/dump-video-document.mjs
//   TEMPLATE=knowledge INPUT=test/fixtures/sample-knowledge.json node scripts/dump-video-document.mjs
//   NO_TTS=1 node scripts/dump-video-document.mjs          # 跳过真实 TTS（用静音估算时长）
//
// 需要的：.env 里的 LLM key（除非用 INPUT 直接给合法 JSON + skipLlm）。TTS key（除非 NO_TTS）。

import { readFile, writeFile, mkdir } from "node:fs/promises";
import { existsSync } from "node:fs";
import { fileURLToPath, pathToFileURL } from "node:url";
import { createRequire } from "node:module";
import { resolve, join } from "node:path";

const root = resolve(fileURLToPath(new URL("..", import.meta.url)));
process.chdir(root);

// --- .env (填充未设置的 key) ---
const envPath = join(root, ".env");
if (existsSync(envPath)) {
  for (const line of (await readFile(envPath, "utf8")).split("\n")) {
    const t = line.trim();
    if (!t || t.startsWith("#")) continue;
    const eq = t.indexOf("=");
    if (eq < 0) continue;
    const k = t.slice(0, eq).trim();
    if (k && process.env[k] === undefined) process.env[k] = t.slice(eq + 1).trim();
  }
}

// --- config/default.yaml (yaml 通过 createRequire 从 shared 的依赖上下文解析出确切 dist 路径) ---
const sharedRequire = createRequire(join(root, "packages/shared/package.json"));
const yamlPath = sharedRequire.resolve("yaml");
const yamlMod = await import(pathToFileURL(yamlPath).href);
const config = yamlMod.parse(await readFile(join(root, "config/default.yaml"), "utf8"));

// --- 模块（从编译好的 dist 导入） ---
const { generateDocument } = await import(join(root, "packages/text/dist/index.js"));
const { generateAudio } = await import(join(root, "packages/audio/dist/index.js"));
const { resolveOutputDir } = await import(join(root, "packages/shared/dist/node.js"));

const template = process.env.TEMPLATE ?? "github-trending";
const source = process.env.INPUT ? undefined : (process.env.SOURCE ?? "github-trending");
const providerName = process.env.TTS_PROVIDER ?? config.tts?.provider ?? "openai-tts";
const providerConfig = config.tts?.[providerName];
const outputDir = resolveOutputDir(config.output?.dir);
const workDir = join(outputDir, "tmp", "dump");
await mkdir(workDir, { recursive: true });

const text = process.env.INPUT
  ? await readFile(resolve(process.env.INPUT), "utf8")
  : undefined;

console.log(`\n=== 文字模块 (template=${template}, source=${source ?? "(input file)"}) ===`);
const { doc: textDoc, publish } = await generateDocument({
  template,
  text,
  source,
  sourceArgs: undefined,
  collectorConfig: source ? config.collect?.[source] : undefined,
  llm: { model: process.env.LLM_MODEL ?? config.llm?.model ?? "glm-5.1" },
  skipLlm: process.env.SKIP_LLM === "1",
});
let doc = textDoc;
await writeFile(join(workDir, "doc-after-text.json"), JSON.stringify(doc, null, 2));
console.log(`  ✓ 产出了 ${doc.data.length} 个段（cover=${doc.data.find(s => s.kind === "cover") ? "有" : "无"}）。已写到 ${join(workDir, "doc-after-text.json")}`);
if (publish) console.log(`  publish (独立产物，不在 VideoDocument 内): title="${publish.title}"  tags=[${(publish.tags ?? []).join(",")}]`);

console.log(`\n=== 音频模块 (provider=${providerName}${process.env.NO_TTS === "1" ? ", 静音" : ""}) ===`);
doc = await generateAudio(doc, {
  workDir,
  provider: providerName,
  voiceId: providerConfig?.defaultVoice,
  model: providerConfig?.model,
  format: config.tts?.format,
  speed: config.tts?.speed,
  skip: process.env.NO_TTS === "1",
  alignment: config.tts?.alignment,
});
await writeFile(join(workDir, "doc-after-audio.json"), JSON.stringify(doc, null, 2));

// --- 人读摘要 ---
const totalDur = doc.data.reduce((a, s) => a + (s.duration ?? 0), 0);
console.log(`\n================ VideoDocument 摘要 ================`);
console.log(`template=${doc.template}  段数=${doc.data.length}  总时长≈${totalDur.toFixed(1)}s`);
console.log(`meta: title="${doc.meta?.title ?? ""}"  subtitle="${doc.meta?.subtitle ?? ""}"  trendSummary="${doc.meta?.trendSummary ?? ""}"`);
if (publish) console.log(`publish (独立): title="${publish.title}"  tags=[${(publish.tags ?? []).join(",")}]`);
console.log(`----------------------------------------------------`);
for (const s of doc.data) {
  const cards = s.cardList?.length ?? 0;
  const caps = s.caption?.length ?? 0;
  const origin = (s.captionOrigin ?? "").replace(/\s+/g, " ").slice(0, 48);
  console.log(`  [${s.id}] kind=${s.kind}  dur=${(s.duration ?? 0).toFixed(1)}s  cards=${cards}  captions=${caps}`);
  if (origin) console.log(`          口播: ${origin}${(s.captionOrigin ?? "").length > 48 ? "…" : ""}`);
  if (s.extension?.type === "github-trending") {
    const g = s.extension;
    console.log(`          repo: ${g.repo.fullName}  ★${g.repo.stars ?? "?"}  今日+${g.repo.todayStars ?? "?"}  (extension)`);
  }
}
console.log(`====================================================`);
console.log(`完整 JSON: ${join(workDir, "doc-after-audio.json")}`);
console.log(`\n下一步: 确认口播/卡片/字幕无误后，用 ./scripts/verify-refactor.sh 跑完整渲染。`);