Add language config and locale-aware parsing

Introduce centralized language configuration and wire locale-aware behavior across scraping and ranking. Adds src/lib/constants/language-config.ts with per-language scraping rules, stop words, and character replacements; replaces AudibleRegion.isEnglish with a language field in types and AUDIBLE_REGIONS. Update AudibleService, ebook scraper, processors, and API routes to use getLanguageForRegion so Anna's Archive searches, scraping selectors, runtime/rating parsing, and ranking use language-specific params and filters. Extend ranking algorithm to accept stopWords and characterReplacements and apply them during normalization and matching. Update UI selects to mark non-English regions and adjust tests accordingly.
This commit is contained in:
kikootwo
2026-02-20 06:32:44 -05:00
parent c146383735
commit 5d8ac2f73d
18 changed files with 525 additions and 112 deletions
@@ -10,6 +10,7 @@ const prismaMock = createPrismaMock();
const configServiceMock = vi.hoisted(() => ({
get: vi.fn(),
getAudibleRegion: vi.fn().mockResolvedValue('us'),
}));
const jobQueueMock = vi.hoisted(() => ({
@@ -39,6 +40,7 @@ vi.mock('@/lib/services/ebook-scraper', () => ebookScraperMock);
describe('processSearchEbook', () => {
beforeEach(() => {
vi.clearAllMocks();
configServiceMock.getAudibleRegion.mockResolvedValue('us');
configServiceMock.get.mockImplementation(async (key: string) => {
if (key === 'ebook_sidecar_preferred_format') return 'epub';
if (key === 'ebook_sidecar_base_url') return 'https://annas-archive.li';
@@ -79,7 +81,8 @@ describe('processSearchEbook', () => {
'epub',
'https://annas-archive.li',
expect.anything(),
undefined
undefined,
'en'
);
expect(jobQueueMock.addStartDirectDownloadJob).toHaveBeenCalledWith(
'req-1',
@@ -123,7 +126,8 @@ describe('processSearchEbook', () => {
'epub',
'https://annas-archive.li',
expect.anything(),
undefined
undefined,
'en'
);
});
@@ -253,7 +257,8 @@ describe('processSearchEbook', () => {
'epub',
'https://annas-archive.li',
expect.anything(),
'http://flaresolverr:8191'
'http://flaresolverr:8191',
'en'
);
});
@@ -8,7 +8,7 @@ import { createPrismaMock } from '../helpers/prisma';
import { createJobQueueMock } from '../helpers/job-queue';
const prismaMock = createPrismaMock();
const configMock = vi.hoisted(() => ({ get: vi.fn() }));
const configMock = vi.hoisted(() => ({ get: vi.fn(), getAudibleRegion: vi.fn().mockResolvedValue('us') }));
const jobQueueMock = createJobQueueMock();
const prowlarrMock = vi.hoisted(() => ({ search: vi.fn(), searchWithVariations: vi.fn() }));
@@ -35,6 +35,7 @@ vi.mock('@/lib/integrations/audible.service', () => ({
describe('processSearchIndexers', () => {
beforeEach(() => {
vi.clearAllMocks();
configMock.getAudibleRegion.mockResolvedValue('us');
});
it('marks request awaiting_search when no results found', async () => {