test: add coaster name matching test suite

Extract matching logic into lib/coaster-match.ts (isCoasterMatch + normalizeForMatch)
so it can be imported by both the scraper and tests without duplication.

Add tests/coaster-matching.test.ts covering all known match/false-positive cases:
- Trademark symbols, leading THE, possessives, punctuation
- Subtitle variants in both directions (Apocalypse, New Revolution - Classic)
- Space-split brand words (BAT GIRL vs Batgirl)
- 4D subtitle extension (THE JOKER™ 4D Free Fly Coaster vs Joker)
- False positives: Joker y Harley Quinn, conjunction connectors

Run with: npm test

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-04 15:43:20 -04:00
parent dc4fbeb7ec
commit 9cac86d241
5 changed files with 161 additions and 51 deletions

View File

@@ -65,15 +65,8 @@ export function areCoastersStale(entry: ParkMeta): boolean {
* 4. Collapse runs of whitespace
* 5. Lowercase and trim
*/
export function normalizeRideName(name: string): string {
return name
.replace(/[\u2122\u00ae\u00a9™®©]/g, "")
.replace(/^the\s+/i, "")
.replace(/[^\w\s]/g, " ")
.replace(/\s+/g, " ")
.toLowerCase()
.trim();
}
export { normalizeForMatch as normalizeRideName } from "./coaster-match.ts";
import { normalizeForMatch } from "./coaster-match.ts";
/**
* Returns a Set of normalized coaster names for fast membership checks.
@@ -82,5 +75,5 @@ export function normalizeRideName(name: string): string {
export function getCoasterSet(parkId: string, meta: ParkMetaMap): Set<string> | null {
const entry = meta[parkId];
if (!entry || entry.coasters.length === 0) return null;
return new Set(entry.coasters.map(normalizeRideName));
return new Set(entry.coasters.map(normalizeForMatch));
}