josh
9cac86d241
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>
80 lines
2.8 KiB
TypeScript
80 lines
2.8 KiB
TypeScript
/**
|
|
* park-meta.json — persisted alongside the SQLite DB in data/
|
|
*
|
|
* This file stores per-park metadata that doesn't belong in the schedule DB:
|
|
* - rcdb_id: user-supplied RCDB park ID (fills into https://rcdb.com/{id}.htm)
|
|
* - coasters: list of operating roller coaster names scraped from RCDB
|
|
* - coasters_scraped_at: ISO timestamp of last RCDB scrape
|
|
*
|
|
* discover.ts: ensures every park has a skeleton entry (rcdb_id null by default)
|
|
* scrape.ts: populates coasters[] for parks with a known rcdb_id (30-day staleness)
|
|
*/
|
|
|
|
import fs from "fs";
|
|
import path from "path";
|
|
|
|
const META_PATH = path.join(process.cwd(), "data", "park-meta.json");
|
|
|
|
export interface ParkMeta {
|
|
/** RCDB park page ID — user fills this in manually after discover creates the skeleton */
|
|
rcdb_id: number | null;
|
|
/** Operating roller coaster names scraped from RCDB */
|
|
coasters: string[];
|
|
/** ISO timestamp of when coasters was last scraped from RCDB */
|
|
coasters_scraped_at: string | null;
|
|
}
|
|
|
|
export type ParkMetaMap = Record<string, ParkMeta>;
|
|
|
|
export function readParkMeta(): ParkMetaMap {
|
|
try {
|
|
return JSON.parse(fs.readFileSync(META_PATH, "utf8")) as ParkMetaMap;
|
|
} catch {
|
|
return {};
|
|
}
|
|
}
|
|
|
|
export function writeParkMeta(meta: ParkMetaMap): void {
|
|
fs.mkdirSync(path.dirname(META_PATH), { recursive: true });
|
|
fs.writeFileSync(META_PATH, JSON.stringify(meta, null, 2) + "\n");
|
|
}
|
|
|
|
/** Default skeleton entry for a park that has never been configured. */
|
|
export function defaultParkMeta(): ParkMeta {
|
|
return { rcdb_id: null, coasters: [], coasters_scraped_at: null };
|
|
}
|
|
|
|
const COASTER_STALE_MS = 30 * 24 * 60 * 60 * 1000; // 30 days
|
|
|
|
/** Returns true when the coaster list needs to be re-scraped from RCDB. */
|
|
export function areCoastersStale(entry: ParkMeta): boolean {
|
|
if (!entry.coasters_scraped_at) return true;
|
|
return Date.now() - new Date(entry.coasters_scraped_at).getTime() > COASTER_STALE_MS;
|
|
}
|
|
|
|
/**
|
|
* Normalize a ride name for fuzzy matching between data sources.
|
|
*
|
|
* Queue-Times uses branded names (BATMAN™ The Ride, THE JOKER™ Funhouse Coaster)
|
|
* while RCDB uses clean names (Batman The Ride, Joker Funhouse Coaster).
|
|
*
|
|
* Normalization steps:
|
|
* 1. Strip trademark/copyright symbols (™ ® ©)
|
|
* 2. Strip leading "THE " / "THE" prefix
|
|
* 3. Replace punctuation (- : ' ") with spaces
|
|
* 4. Collapse runs of whitespace
|
|
* 5. Lowercase and 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.
|
|
* Returns null when no coaster data exists for the park.
|
|
*/
|
|
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(normalizeForMatch));
|
|
}
|