ReadaBook/apps/api/src/scanner/scanner.service.test.ts

import { mkdtempSync, rmSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { afterEach, describe, expect, it } from "vitest";
import { DatabaseService } from "../database/database.service.js";
import { books, libraries } from "../database/schema.js";
import { JobsService } from "../jobs/jobs.service.js";
import { enrichmentDigest, preserveExistingBookValues, scanDigest } from "./scanner.service.js";
import { ScannerService } from "./scanner.service.js";

const previousDatabasePath = process.env.DATABASE_PATH;
const previousStorageDir = process.env.STORAGE_DIR;
const tempDirs: string[] = [];

afterEach(() => {
  process.env.DATABASE_PATH = previousDatabasePath;
  process.env.STORAGE_DIR = previousStorageDir;
  for (const dir of tempDirs.splice(0)) {
    rmSync(dir, { recursive: true, force: true });
  }
});

describe("scan digest", () => {
  it("reports incomplete files without exposing huge traces", () => {
    const detail = scanDigest(
      19,
      0,
      [
        { filePath: "/library/broken.cbr", error: "x".repeat(300) },
        { filePath: "/library/broken.epub", error: "Invalid EPUB" }
      ]
    );

    expect(detail).toContain("Scanned 19 file(s)");
    expect(detail).toContain("2 incomplete file(s)");
    expect(detail).toContain("broken.cbr");
    expect(detail.length).toBeLessThan(380);
  });

  it("reports metadata enrichment jobs as enrichment, not scans", () => {
    expect(enrichmentDigest(35, [])).toBe("Enriched 35 book(s)");
  });

  it("does not erase existing metadata or cover when a rescan has less information", () => {
    const existing: typeof books.$inferSelect = {
      id: 1,
      libraryId: 1,
      seriesId: null,
      title: "Daredevil",
      author: "Roy Thomas",
      description: "Existing description",
      isbn: "9782809476255",
      isbn13: "9782809476255",
      identifiersJson: null,
      localMetadataJson: null,
      language: "fre",
      publisher: "Panini comics",
      publishedDate: "2019",
      volumeNumber: null,
      volumeLabel: null,
      format: "cbz",
      filePath: "/library/Daredevil.cbz",
      coverPath: "/storage/covers/daredevil.jpg",
      metadataStatus: "enriched",
      metadataProvenanceJson: JSON.stringify({ author: "bnf", coverPath: "openlibrary" }),
      scanStatus: "succeeded",
      enrichmentStatus: "succeeded",
      fileSize: 12,
      fileMtime: "2026-08-23T00:00:00.000Z",
      createdAt: "2026-08-23T00:00:00.000Z",
      updatedAt: "2026-08-23T00:00:00.000Z"
    };

    const next = preserveExistingBookValues(
      {
        title: "Daredevil",
        author: null,
        description: null,
        isbn: null,
        isbn13: null,
        language: null,
        publisher: null,
        publishedDate: null,
        coverPath: null,
        metadataStatus: "none",
        metadataProvenanceJson: JSON.stringify({ title: "local" }),
        scanStatus: "succeeded" as const
      },
      existing
    );

    expect(next).toMatchObject({
      author: "Roy Thomas",
      description: "Existing description",
      isbn: "9782809476255",
      coverPath: "/storage/covers/daredevil.jpg",
      metadataStatus: "enriched"
    });
    expect(JSON.parse(String(next.metadataProvenanceJson))).toMatchObject({
      title: "local",
      author: "bnf",
      coverPath: "openlibrary"
    });
  });

  it("does not replace an existing valid publication date with a sentinel date", () => {
    const existing = {
      id: 1,
      libraryId: 1,
      seriesId: null,
      title: "Lord of the Mysteries",
      author: null,
      description: null,
      isbn: null,
      isbn13: null,
      identifiersJson: null,
      localMetadataJson: null,
      language: null,
      publisher: null,
      publishedDate: "2018",
      volumeNumber: null,
      volumeLabel: null,
      format: "epub",
      filePath: "/library/Lord of the Mysteries.epub",
      coverPath: null,
      metadataStatus: "partial",
      metadataProvenanceJson: JSON.stringify({ publishedDate: "existing" }),
      scanStatus: "succeeded",
      enrichmentStatus: "succeeded",
      fileSize: 12,
      fileMtime: "2026-08-23T00:00:00.000Z",
      createdAt: "2026-08-23T00:00:00.000Z",
      updatedAt: "2026-08-23T00:00:00.000Z"
    } satisfies typeof books.$inferSelect;

    const next = preserveExistingBookValues(
      {
        title: "Lord of the Mysteries",
        publishedDate: "0101-01-01T00:00:00+00:00",
        metadataStatus: "partial",
        metadataProvenanceJson: JSON.stringify({ title: "local", publishedDate: "openlibrary" })
      },
      existing
    );

    expect(next.publishedDate).toBe("2018");
  });

  it.runIf(canLoadBetterSqlite())("updates the existing book when an insert races with books.file_path uniqueness", () => {
    const database = createDatabase();
    const now = database.now();
    const library = database.db
      .insert(libraries)
      .values({ name: "Corpus", path: "/library", enabled: true, createdAt: now, updatedAt: now })
      .returning()
      .get();
    database.db
      .insert(books)
      .values({
        libraryId: library.id,
        seriesId: null,
        title: "Daredevil",
        author: null,
        description: null,
        isbn: null,
        isbn13: null,
        identifiersJson: null,
        localMetadataJson: null,
        language: null,
        publisher: null,
        publishedDate: null,
        volumeNumber: null,
        volumeLabel: null,
        format: "cbz",
        filePath: "/library/Daredevil.cbz",
        coverPath: null,
        metadataStatus: "none",
        metadataProvenanceJson: null,
        scanStatus: "succeeded",
        enrichmentStatus: "succeeded",
        fileSize: 1,
        fileMtime: now,
        createdAt: now,
        updatedAt: now
      })
      .run();
    const scanner = new ScannerService(database, new JobsService(database), {} as never);
    const values: Omit<typeof books.$inferInsert, "createdAt"> = {
      libraryId: library.id,
      seriesId: null,
      title: "Daredevil",
      author: "Roy Thomas",
      description: "Updated metadata",
      isbn: null,
      isbn13: null,
      identifiersJson: null,
      localMetadataJson: null,
      language: null,
      publisher: null,
      publishedDate: null,
      volumeNumber: null,
      volumeLabel: null,
      format: "cbz",
      filePath: "/library/Daredevil.cbz",
      coverPath: "/storage/covers/daredevil.jpg",
      metadataStatus: "enriched",
      metadataProvenanceJson: JSON.stringify({ author: "bnf", coverPath: "local" }),
      scanStatus: "succeeded",
      enrichmentStatus: "succeeded",
      fileSize: 2,
      fileMtime: now,
      updatedAt: now
    };

    (scanner as unknown as {
      upsertBookByFilePath(values: Omit<typeof books.$inferInsert, "createdAt">, existing: undefined, createdAt: string): void;
    }).upsertBookByFilePath(
      values,
      undefined,
      now
    );

    const rows = database.db.select().from(books).all();
    expect(rows).toHaveLength(1);
    expect(rows[0]).toMatchObject({
      author: "Roy Thomas",
      coverPath: "/storage/covers/daredevil.jpg",
      metadataStatus: "enriched",
      fileSize: 2
    });

    database.onModuleDestroy();
  });
});

function createDatabase(): DatabaseService {
  const dir = mkdtempSync(join(tmpdir(), "readabook-scanner-service-"));
  tempDirs.push(dir);
  process.env.DATABASE_PATH = join(dir, "readabook.sqlite");
  process.env.STORAGE_DIR = join(dir, "storage");
  return new DatabaseService();
}

function canLoadBetterSqlite(): boolean {
  try {
    const database = createDatabase();
    database.onModuleDestroy();
    return true;
  } catch {
    return false;
  }
}