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 -8
View File
@@ -3,6 +3,8 @@
* Documentation: documentation/integrations/audible.md
*/
import type { SupportedLanguage } from '../constants/language-config';
export type AudibleRegion = 'us' | 'ca' | 'uk' | 'au' | 'in' | 'de' | 'es';
export interface AudibleRegionConfig {
@@ -10,7 +12,7 @@ export interface AudibleRegionConfig {
name: string;
baseUrl: string;
audnexusParam: string;
isEnglish: boolean;
language: SupportedLanguage;
}
export const AUDIBLE_REGIONS: Record<AudibleRegion, AudibleRegionConfig> = {
@@ -19,49 +21,49 @@ export const AUDIBLE_REGIONS: Record<AudibleRegion, AudibleRegionConfig> = {
name: 'United States',
baseUrl: 'https://www.audible.com',
audnexusParam: 'us',
isEnglish: true,
language: 'en',
},
ca: {
code: 'ca',
name: 'Canada',
baseUrl: 'https://www.audible.ca',
audnexusParam: 'ca',
isEnglish: true,
language: 'en',
},
uk: {
code: 'uk',
name: 'United Kingdom',
baseUrl: 'https://www.audible.co.uk',
audnexusParam: 'uk',
isEnglish: true,
language: 'en',
},
au: {
code: 'au',
name: 'Australia',
baseUrl: 'https://www.audible.com.au',
audnexusParam: 'au',
isEnglish: true,
language: 'en',
},
in: {
code: 'in',
name: 'India',
baseUrl: 'https://www.audible.in',
audnexusParam: 'in',
isEnglish: true,
language: 'en',
},
de: {
code: 'de',
name: 'Germany',
baseUrl: 'https://www.audible.de',
audnexusParam: 'de',
isEnglish: false,
language: 'de',
},
es: {
code: 'es',
name: 'Spain',
baseUrl: 'https://www.audible.es',
audnexusParam: 'es',
isEnglish: false,
language: 'es',
}
};