feat(scrape): 入库后自动刮削缺省开启,没排上时在整理记录上记「未刮削（原因）」

- scrape_record 状态加 skipped(迁移 0074);目标不在媒体库、库根只登记、作品没有 TMDB id 也没有本地元数据、排队失败时留一条挂在整理记录上的「未刮削」记录(同原因只记一次),设置关闭不记; - 缺省开启 scrapeAfterImport,只对有 TMDB id 或本地元数据的作品排; - 已结束记录重放与收尾同一口径补排刮削(按整理记录幂等); - 整理详情「整理后刮削」显示未刮削原因,并列出失败与非预期跳过(缺元数据、认不出集号)的文件。 Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei
2026-10-03 23:19:28 +08:00
1 parent 8c4c7d028a
commit cdf62dbf02
@@ -0,0 +1,125 @@
+import { createTempTree, type TempTree } from "@umt/testkit";
+import { afterAll, beforeAll, describe, expect, it } from "vitest";
+import { executeRecord, planImport } from "../../src/modules/acquisition-organize/services/organize.ts";
+import { SCRAPE_TASK, scrapeAfterImport } from "../../src/modules/acquisition-organize/services/scrape.ts";
+import { createHarness, type Harness, pgAvailable, seedBase, seedEntity } from "./harness.ts";
+
+// 入库后自动刮削(缺省开):只对有 TMDB id 或本地元数据的作品排;没排上(库根只登记、作品没有元数据、排队失败)时
+// 在整理记录上留一条「未刮削（原因）」的刮削记录;设置关闭是预期,不留。
+
+const hasPg = await pgAvailable();
+const SIZE = 200_000;
+
+describe.skipIf(!hasPg)("入库后自动刮削:缺省开启,没排上时整理记录上可见", () => {
+  let h: Harness;
+  let lib: TempTree;
+  let src: TempTree;
+  let rootId = "";
+
+  beforeAll(async () => {
+    lib = await createTempTree({}, { sentinel: true, prefix: "umt-sailib-" });
+    src = await createTempTree(
+      {
+        "Tenet.2020.1080p.BluRay.x264-GRP.mkv": SIZE,
+        "Dune.2021.1080p.BluRay.x264-GRP.mkv": SIZE,
+        "Arrival.2016.1080p.BluRay.x264-GRP.mkv": SIZE,
+        "Heat.1995.1080p.BluRay.x264-GRP.mkv": SIZE,
+      },
+      { prefix: "umt-saisrc-" },
+    );
+    h = await createHarness("scrape_after_import");
+    rootId = (await seedBase(h.db, { libraryPath: lib.root, cachePath: src.root, qbUrl: "http://127.0.0.1:9" })).rootId;
+  }, 60_000);
+  afterAll(async () => {
+    await h?.close();
+    for (const t of [lib, src]) await t?.cleanup();
+  });
+
+  async function movie(title: string, opts: { tmdb?: string; metadata?: object } = {}) {
+    const id = await seedEntity(h.db, { kind: "movie", title, year: 2020 });
+    if (opts.metadata)
+      await h.db
+        .updateTable("media_entity")
+        .set({ metadata: JSON.stringify(opts.metadata) })
+        .where("id", "=", id)
+        .execute();
+    if (opts.tmdb)
+      await h.db
+        .insertInto("external_identity")
+        .values({
+          media_entity_id: id,
+          provider: "tmdb",
+          entity_type: "movie",
+          external_id: opts.tmdb,
+          status: "accepted",
+        })
+        .execute();
+    return id;
+  }
+  async function organize(entity: string, file: string) {
+    const plan = await planImport(h.d, {
+      sourcePaths: [src.path(file)],
+      mediaEntityId: entity,
+      action: "copy",
+      trigger: "manual",
+      actorType: "user",
+    });
+    const ex = await executeRecord(h.d, plan.recordId!);
+    expect(ex.status).toBe("succeeded");
+    return plan.recordId!;
+  }
+  const recordsOf = (orgId: string) =>
+    h.db
+      .selectFrom("scrape_record")
+      .select(["status", "reason", "trigger"])
+      .where("organization_record_id", "=", orgId)
+      .execute();
+
+  it("缺省设置:有 TMDB id 的作品入库后排上刮削", async () => {
+    const id = await movie("信条", { tmdb: "577922" });
+    const org = await organize(id, "Tenet.2020.1080p.BluRay.x264-GRP.mkv");
+    expect(await recordsOf(org)).toEqual([{ status: "queued", reason: null, trigger: "auto" }]);
+    expect(h.engine.enqueued.some((x) => x.task === SCRAPE_TASK)).toBe(true);
+  });
+
+  it("没有 TMDB id 也没有本地元数据:不排任务,记「未刮削」scrape_no_metadata;重放不重复记", async () => {
+    const before = h.engine.enqueued.filter((x) => x.task === SCRAPE_TASK).length;
+    const id = await movie("沙丘");
+    const org = await organize(id, "Dune.2021.1080p.BluRay.x264-GRP.mkv");
+    expect(await recordsOf(org)).toEqual([{ status: "skipped", reason: "scrape_no_metadata", trigger: "auto" }]);
+    expect(h.engine.enqueued.filter((x) => x.task === SCRAPE_TASK).length).toBe(before);
+    await executeRecord(h.d, org);
+    expect(await recordsOf(org)).toHaveLength(1);
+  });
+
+  it("库根是只登记模式:记 scrape_root_read_only;排队失败:记 task_enqueue_failed", async () => {
+    const id = await movie("降临", { tmdb: "329865" });
+    const org = await organize(id, "Arrival.2016.1080p.BluRay.x264-GRP.mkv");
+    await h.db.deleteFrom("scrape_record").where("organization_record_id", "=", org).execute();
+    await h.db.updateTable("library_root").set({ management_mode: "register_only" }).where("id", "=", rootId).execute();
+    try {
+      await scrapeAfterImport(h.d, id, org);
+      expect(await recordsOf(org)).toEqual([{ status: "skipped", reason: "scrape_root_read_only", trigger: "auto" }]);
+    } finally {
+      await h.db.updateTable("library_root").set({ management_mode: "managed" }).where("id", "=", rootId).execute();
+    }
+    await h.db.deleteFrom("scrape_record").where("organization_record_id", "=", org).execute();
+    const enqueue = h.d.ctx.engine.enqueue;
+    h.d.ctx.engine.enqueue = (async () => {
+      throw new Error("引擎不可用");
+    }) as never;
+    try {
+      await scrapeAfterImport(h.d, id, org);
+    } finally {
+      h.d.ctx.engine.enqueue = enqueue;
+    }
+    expect(await recordsOf(org)).toEqual([{ status: "failed", reason: "task_enqueue_failed", trigger: "auto" }]);
+  });
+
+  it("设置关闭:不排也不记", async () => {
+    await h.setSettings("organize", { scrapeAfterImport: false });
+    const id = await movie("盗火线", { tmdb: "949" });
+    const org = await organize(id, "Heat.1995.1080p.BluRay.x264-GRP.mkv");
+    expect(await recordsOf(org)).toEqual([]);
+  });
+});
@@ -205,9 +205,14 @@ describe.skipIf(skip)("file manager in-place import", () => {
    try {
      const r = await queue(s.items, { scrapeAfterImport: true });
      expect((await executeRecord(h.module.deps().ao, r.recordId)).status).toBe("succeeded");
+      // 不刮削,只在整理记录上留一条「未刮削（只登记模式）」
      expect(
-        await h.db.selectFrom("scrape_record").select("id").where("organization_record_id", "=", r.recordId).execute(),
-      ).toEqual([]);
+        await h.db
+          .selectFrom("scrape_record")
+          .select(["status", "reason"])
+          .where("organization_record_id", "=", r.recordId)
+          .execute(),
+      ).toEqual([{ status: "skipped", reason: "scrape_root_read_only" }]);
      expect(await readdir(join(h.lib, s.path.split("/")[0]!))).toEqual(["original.name.mkv"]);
    } finally {
      await h.db.updateTable("library_root").set({ management_mode: "managed" }).where("id", "=", rootId).execute();