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:
@@ -9,45 +9,7 @@
|
||||
|
||||
const BASE = "https://queue-times.com/parks";
|
||||
|
||||
/**
|
||||
* Normalize a ride name for fuzzy matching between Queue-Times and RCDB.
|
||||
*
|
||||
* - Strips trademark/copyright symbols (™ ® © and Unicode variants)
|
||||
* - Strips leading "THE " prefix
|
||||
* - Replaces ALL non-word, non-space characters with a space
|
||||
* (handles !, -, :, ', ' U+2019, ", and any other punctuation)
|
||||
* - Collapses whitespace, lowercases, trims
|
||||
*/
|
||||
function normalize(name: string): string {
|
||||
return name
|
||||
.replace(/[\u2122\u00ae\u00a9™®©]/g, "")
|
||||
.replace(/^the\s+/i, "")
|
||||
.replace(/[^\w\s]/g, " ")
|
||||
.replace(/\s+/g, " ")
|
||||
.toLowerCase()
|
||||
.trim();
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if a Queue-Times ride name matches any coaster in the RCDB set.
|
||||
*
|
||||
* Exact normalized match covers most cases. Prefix matching handles cases
|
||||
* where one source drops or adds a subtitle:
|
||||
* "Apocalypse" (QT) vs "Apocalypse the Ride" (RCDB)
|
||||
* "The New Revolution - Classic" (QT) vs "New Revolution" (RCDB)
|
||||
*
|
||||
* Minimum 5 chars on the shorter side prevents accidental short matches.
|
||||
*/
|
||||
function isCoaster(name: string, coasterSet: Set<string>): boolean {
|
||||
const norm = normalize(name);
|
||||
if (coasterSet.has(norm)) return true;
|
||||
for (const c of coasterSet) {
|
||||
const shorter = norm.length <= c.length ? norm : c;
|
||||
const longer = norm.length <= c.length ? c : norm;
|
||||
if (shorter.length >= 5 && longer.startsWith(shorter)) return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
import { isCoasterMatch, normalizeForMatch } from "../coaster-match.ts";
|
||||
|
||||
const HEADERS = {
|
||||
"User-Agent":
|
||||
@@ -131,7 +93,7 @@ export async function fetchLiveRides(
|
||||
isOpen: r.is_open,
|
||||
waitMinutes: r.wait_time ?? 0,
|
||||
lastUpdated: r.last_updated,
|
||||
isCoaster: coasterNames ? isCoaster(r.name, coasterNames) : false,
|
||||
isCoaster: coasterNames ? isCoasterMatch(r.name, coasterNames) : false,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user