UHD_Media_Tool/apps/server/test/scrape/nfo-mp-diff.test.ts

import { readFileSync } from "node:fs";
import { fetchRichDetail, fetchRichSeason } from "@umt/adapters";
import { episodeNfo, multiEpisodeNfo, planScrapeTargets, seasonNfo, seasonPosterName, workNfo } from "@umt/domain";
import { describe, expect, it } from "vitest";
import { nfoEpisode, nfoSeason, nfoWork } from "../../src/modules/acquisition-organize/services/scrape-input.ts";
import { richEntityFields } from "../../src/modules/sources-identity/service/metadata-rich.ts";

// SCR-1 NFO 差分:同一份 TMDB 原始响应(tmdb-raw.json),MP 走 set_tmdb_info + TmdbScraper(gen-scrape-mp.py → scrape-mp.json),
// 我们走 fetchRichDetail / fetchRichSeason → 字段投影(metadata)→ scrape-input → domain NFO 生成器。
// 双方去掉空元素后逐行比较,已登记的差异(nfo-deviations.json)按元素排除并要求确实不同。

const read = (f: string) => JSON.parse(readFileSync(new URL(f, import.meta.url), "utf8"));
const raw = read("./tmdb-raw.json") as Record<string, unknown>;
const mp = read("./scrape-mp.json") as Record<string, string>;
const devFile = read("./nfo-deviations.json");
const devs = devFile.deviations as { case: string; tag: string }[];

const LANGS = ["zh-CN", "zh-SG", "zh-TW", "zh-HK", "en-US"];
const client = {
  async getJson<T>(path: string): Promise<T> {
    const r = raw[path];
    if (!r) throw new Error(`fixture 缺 ${path}`);
    return structuredClone(r) as T;
  },
};
const final = (fields: Record<string, { value: unknown }>) =>
  Object.fromEntries(Object.entries(fields).map(([k, v]) => [k, { value: v.value }]));

async function ours(): Promise<Record<string, string>> {
  const out: Record<string, string> = {};
  const movie = await fetchRichDetail(client, "movie", 157336, LANGS);
  out.movie = workNfo(
    nfoWork(
      {
        kind: "movie",
        title: movie.title,
        original_title: movie.originalTitle,
        year: movie.year,
        metadata: final(richEntityFields(movie) as never),
      },
      { tmdb: "157336" },
    ),
  );
  const tv = await fetchRichDetail(client, "tv", 95396, LANGS);
  out.tvshow = workNfo(
    nfoWork(
      {
        kind: "series",
        title: tv.title,
        original_title: tv.originalTitle,
        year: tv.year,
        metadata: final(richEntityFields(tv) as never),
      },
      { tmdb: "95396" },
    ),
  );
  const sd = await fetchRichSeason(client, 95396, 1, LANGS, { now: new Date("2026-01-01") });
  out.season1 = seasonNfo(
    nfoSeason(1, {
      season_number: 1,
      episode_number: null,
      title: sd.name,
      air_date: sd.airDate,
      metadata: { name: { value: sd.name }, overview: { value: sd.overview }, airDate: { value: sd.airDate } },
    }),
  );
  const eps = sd.episodes.map((e) =>
    nfoEpisode(1, e.episodeNumber, {
      season_number: 1,
      episode_number: e.episodeNumber,
      title: e.name,
      air_date: e.airDate,
      metadata: {
        name: { value: e.name },
        overview: { value: e.overview },
        airDate: { value: e.airDate },
        runtime: { value: e.runtime },
        voteAverage: { value: e.voteAverage },
      },
    }),
  );
  for (const e of eps) out[`s01e${String(e.episode).padStart(2, "0")}`] = episodeNfo(e);
  out["s01e01-e02"] = multiEpisodeNfo(eps.slice(0, 2));
  return out;
}

/** 去空元素(MP 缺值写 <x/>、空 CDATA、评分 0) */
const normalize = (xml: string) =>
  xml
    .split("\n")
    .filter((l) => l.trim() !== "")
    .filter((l) => !/^\s*<[\w]+(\s[^>]*)?\/>$/.test(l))
    .filter((l) => !/<!\[CDATA\[\]\]>/.test(l))
    .filter((l) => !/^\s*<rating>0<\/rating>$/.test(l));
const tagOf = (l: string) => /^ {2}<(\w+)/.exec(l)?.[1] ?? null;

describe("NFO 与 MP 差分", async () => {
  const mine = await ours();
  const cases = ["movie", "tvshow", "season1", "s01e01", "s01e02"];

  it.each(cases)("%s:结构与取值一致(已登记差异除外)", (c) => {
    const skip = new Set(devs.filter((d) => d.case === c).map((d) => d.tag));
    const a = normalize(mp[c]!).filter((l) => !skip.has(tagOf(l) ?? ""));
    const b = normalize(mine[c]!).filter((l) => !skip.has(tagOf(l) ?? ""));
    expect(b).toEqual(a);
    for (const tag of skip) {
      const ma = normalize(mp[c]!).filter((l) => tagOf(l) === tag);
      const mb = normalize(mine[c]!).filter((l) => tagOf(l) === tag);
      expect(mb, `登记的差异 ${c}.${tag} 已消失,删掉登记`).not.toEqual(ma);
    }
  });

  it("多集文件:按登记的偏离写多个 <episodedetails> 块,每块与 MP 对应单集一致(MP 只写首集)", () => {
    expect(devFile.multiEpisode?.reason).toBeTruthy();
    const xml = mine["s01e01-e02"]!;
    const [decl, ...body] = xml.split("\n");
    expect(decl).toBe(mp.s01e01!.split("\n")[0]);
    const blocks = body
      .join("\n")
      .split(/(?=<episodedetails>)/)
      .filter((b) => b.trim());
    expect(blocks).toHaveLength(2);
    for (const [i, c] of ["s01e01", "s01e02"].entries()) {
      const skip = new Set(devs.filter((d) => d.case === c).map((d) => d.tag));
      const a = normalize(mp[c]!).filter((l) => !skip.has(tagOf(l) ?? "") && !l.startsWith("<?xml"));
      const b = normalize(blocks[i]!).filter((l) => !skip.has(tagOf(l) ?? ""));
      expect(b).toEqual(a);
    }
  });

  it("编码与声明:UTF-8、两空格缩进、末尾换行,和 MP 一致", () => {
    for (const c of cases) {
      expect(mine[c]!.split("\n")[0]).toBe(mp[c]!.split("\n")[0]);
      expect(mine[c]!.endsWith("\n")).toBe(true);
    }
  });

  it("季海报命名与 MP get_season_poster 一致", () => {
    expect(seasonPosterName(1)).toBe(mp.seasonPosterName);
    expect(seasonPosterName(0)).toBe(mp.seasonSpecialsPosterName);
  });

  it("文件命名:对照 MP scraping.py 的目标路径(差异见 nfo-deviations.json images)", () => {
    const t = planScrapeTargets({
      kind: "tv",
      workDir: "人生切割术 (2022)",
      videos: [{ path: "人生切割术 (2022)/Season 1/人生切割术 - S01E01 - 第 1 集.mkv", season: 1, episode: 1 }],
      images: {
        posterPath: "/p.jpg",
        backdropPath: "/b.jpg",
        seasonPosters: new Map([[1, "/s.jpg"]]),
        stills: new Map([["1:1", "/e.jpg"]]),
      },
      options: { images: true, episodeThumbs: true },
    });
    // MP:tvshow.nfo(TV)、season.nfo(SEASON)、<stem>.nfo(EPISODE);季海报根目录 seasonXX-poster + 季目录 poster
    expect(t.map((x) => x.path)).toEqual([
      "人生切割术 (2022)/tvshow.nfo",
      "人生切割术 (2022)/poster.jpg",
      "人生切割术 (2022)/fanart.jpg",
      "人生切割术 (2022)/Season 1/season.nfo",
      "人生切割术 (2022)/season01-poster.jpg",
      "人生切割术 (2022)/Season 1/poster.jpg",
      "人生切割术 (2022)/Season 1/人生切割术 - S01E01 - 第 1 集.nfo",
      "人生切割术 (2022)/Season 1/人生切割术 - S01E01 - 第 1 集-thumb.jpg",
    ]);
  });
});