UHD_Media_Tool/apps/server/test/sources-identity/organize-metadata.test.ts

import { workNfo } from "@umt/domain";
import { createMockTmdb } from "@umt/testkit";
import { afterAll, beforeAll, describe, expect, it } from "vitest";
import { imagePathsOf, nfoWork } from "../../src/modules/acquisition-organize/services/scrape-input.ts";
import { saveDetailPage } from "../../src/modules/sources-identity/service/detail-page.ts";
import {
  ptDetailFacts,
  resolveOrganizeMetadata,
} from "../../src/modules/sources-identity/service/organize-metadata.ts";
import { createHarness, type Harness, pgAvailable, seedSite } from "./harness.ts";

const ptText =
  "◎译 名 未收录的故事\n◎原 名 Unlisted Story\n◎年 代 2025\n◎产 地 中国大陆\n◎语 言 汉语普通话\n◎类 别 剧情\n◎导 演 张三\n◎主 演 李四 / 王五\n◎简 介 一位主人公在旅途中发现了一段不为人知的故事，并开始寻找失踪的朋友。";
const up = await pgAvailable();
describe("PT detail extraction", () => {
  it("reads evidenced labels and leaves missing fields empty", () => {
    const facts = ptDetailFacts(ptText, "https://pt.example/details.php?id=1");
    expect(facts.names).toEqual(["未收录的故事", "Unlisted Story"]);
    expect(facts.year).toBe(2025);
    expect(facts.extras).toContainEqual({ field: "originCountry", value: ["CN"] });
    expect(facts.extras).toContainEqual({ field: "originalLanguage", value: "zh" });
    expect(ptDetailFacts("Unknown.2025.1080p", "https://pt.example/").candidates).toEqual([]);
  });
  it("local final fields reuse NFO input and external poster", () => {
    const metadata = {
      overview: { value: "简介" },
      posterUrl: { value: "https://img.example/cover.jpg" },
      originCountry: { value: ["CN"] },
      cast: { value: [{ id: -1, name: "本地主演", role: null, profilePath: null }] },
      crew: { value: [{ id: -2, name: "本地导演", role: "Director", profilePath: null }] },
    };
    expect(imagePathsOf(metadata).posterPath).toBe("https://img.example/cover.jpg");
    const nfo = nfoWork({ kind: "movie", title: "本地作品", year: 2025, original_title: null, metadata }, {});
    expect(nfo.ids.tmdb).toBeNull();
    expect(nfo.overview).toBe("简介");
    expect(nfo.countries).toEqual(["中国"]);
    expect(nfo.actors?.[0]?.tmdbId).toBeNull();
    expect(nfo.directors?.[0]?.tmdbId).toBeNull();
    const xml = workNfo(nfo);
    expect(xml).toContain("本地主演");
    expect(xml).toContain("本地导演");
    expect(xml).not.toContain("-1");
    expect(xml).not.toContain("-2");
  });
});
describe.skipIf(!up)("organize metadata local recovery (isolated PG)", () => {
  let h: Harness;
  let siteId: string;
  beforeAll(async () => {
    h = await createHarness("local_metadata", { tmdb: () => null });
    siteId = (await seedSite(h, { baseUrl: "https://pt.example/" })).site.id;
  });
  afterAll(async () => {
    await h?.close();
  });
  const add = async (n: string, text: string, title?: string) => {
    const release = await h.db
      .insertInto("source_release")
      .values({
        site_id: siteId,
        site_release_id: n,
        title: title ?? `Unlisted Story ${n} 2025 1080p`,
        detail_fetched_at: new Date(),
      })
      .returning("id")
      .executeTakeFirstOrThrow();
    await saveDetailPage(
      h.rt,
      h.db,
      release.id,
      {
        descriptionText: text,
        mediaInfo: null,
        screenshots: ["https://img.example/cover.jpg"],
        imdbId: null,
        doubanId: null,
        tmdb: null,
        files: [],
        tags: [],
        uploader: null,
        probe: { labels: [], hasDescription: true, imageCount: 1 },
      },
      3600,
    );
    return release.id;
  };
  const deps = {
    search: async () => [],
    fetch: async () => {
      throw new Error("unexpected fetch");
    },
    complete: async () => null,
  };
  it("creates Local with sourced fields, remains revisitable and reuses identity", async () => {
    const id = await add("1", ptText);
    const out = await resolveOrganizeMetadata(h.rt, id, deps, { actor: { type: "system", id: "system:organize" } });
    expect(out.mode).toBe("local");
    expect(out.mediaEntityId).toBeTruthy();
    const entity = await h.db
      .selectFrom("media_entity")
      .selectAll()
      .where("id", "=", out.mediaEntityId!)
      .executeTakeFirstOrThrow();
    expect(entity.status).toBe("provisional");
    expect(entity.title).toBe("未收录的故事");
    expect((entity.metadata as Record<string, { value: unknown }>).originCountry?.value).toEqual(["CN"]);
    expect((entity.metadata as Record<string, { value: unknown }>).posterUrl?.value).toBe(
      "https://img.example/cover.jpg",
    );
    const release = await h.db.selectFrom("source_release").selectAll().where("id", "=", id).executeTakeFirstOrThrow();
    expect(release.resolution_locked).toBe(false);
    const again = await resolveOrganizeMetadata(h.rt, id, deps, { actor: { type: "system", id: "system:organize" } });
    expect(again.mediaEntityId).toBe(out.mediaEntityId);
  });
  it("series fallback preserves actual season and episode instead of fabricating season one", async () => {
    const id = await add(
      "season",
      "◎译 名 独立剧集\n◎年 代 2025\n◎集 数 12\n◎类 别 剧情",
      "Distinct Local Series S02E03 2025 1080p",
    );
    const out = await resolveOrganizeMetadata(h.rt, id, deps, { actor: { type: "system", id: "system:organize" } });
    expect(out.mode).toBe("local");
    const units = await h.db
      .selectFrom("content_unit")
      .select(["season_number", "episode_number"])
      .where("media_entity_id", "=", out.mediaEntityId!)
      .execute();
    expect(units.some((u) => u.season_number === 1)).toBe(false);
    expect(units.some((u) => u.season_number === 2 && u.episode_number === 3)).toBe(true);
  });
  it("does not create a filename placeholder when facts are insufficient", async () => {
    const id = await add("2", "no metadata available");
    const out = await resolveOrganizeMetadata(h.rt, id, deps, { actor: { type: "system", id: "system:organize" } });
    expect(out.mediaEntityId).toBeNull();
  });
});

describe.skipIf(!up)("organize metadata translated name recovery", () => {
  it("retries TMDB using evidenced PT aliases after normal title lookup fails", async () => {
    const tmdb = await createMockTmdb({
      fixtures: [
        {
          type: "movie",
          id: 990087,
          original_title: "True Original",
          original_language: "en",
          origin_country: ["US"],
          date: "2025-01-01",
          titles: { "zh-CN": "正确译名", "en-US": "True Original" },
          popularity: 10,
          alternative_titles: [],
          external_ids: { imdb_id: null },
        },
      ],
    });
    const h = await createHarness("local_alias", { tmdbUrl: tmdb.url });
    try {
      const siteId = (await seedSite(h, { baseUrl: "https://pt.example/" })).site.id;
      const release = await h.db
        .insertInto("source_release")
        .values({
          site_id: siteId,
          site_release_id: "alias",
          title: "Unknown Translation 2025 1080p",
          detail_fetched_at: new Date(),
        })
        .returning("id")
        .executeTakeFirstOrThrow();
      await saveDetailPage(
        h.rt,
        h.db,
        release.id,
        {
          descriptionText: "◎译 名 另类译名\n◎原 名 True Original\n◎年 代 2025\n◎类 别 剧情",
          mediaInfo: null,
          screenshots: [],
          imdbId: null,
          doubanId: null,
          tmdb: null,
          files: [],
          tags: [],
          uploader: null,
          probe: { labels: [], hasDescription: true, imageCount: 0 },
        },
        3600,
      );
      let completions = 0;
      const out = await resolveOrganizeMetadata(
        h.rt,
        release.id,
        {
          search: async () => [],
          fetch: async () => {
            throw new Error("unexpected fetch");
          },
          complete: async () => {
            completions++;
            return { text: "{}", model: "fixture-agent", inputTokens: 100, outputTokens: 5 };
          },
        },
        { actor: { type: "system", id: "system:organize" } },
      );
      expect(completions).toBe(1);
      expect(out.mode).toBe("tmdb");
      const identity = await h.db
        .selectFrom("external_identity")
        .selectAll()
        .where("media_entity_id", "=", out.mediaEntityId!)
        .where("provider", "=", "tmdb")
        .executeTakeFirstOrThrow();
      expect(identity.external_id).toBe("990087");
      const enrichment = await h.db
        .selectFrom("metadata_enrichment")
        .selectAll()
        .where("id", "=", out.enrichmentId!)
        .executeTakeFirstOrThrow();
      expect((enrichment.usage as { inputTokens: number }).inputTokens).toBe(100);
    } finally {
      await h.close();
      await tmdb.close();
    }
  });
});