builtbykev
8629021774
P1 name edge cases (BOTH playerName.js copies, kept identical): - normalizeName strips hyphens (display+key): "Jung-hoo Lee" === "Jung Hoo Lee". - nameKey strips single-letter MIDDLE tokens: "Josh H Smith" === "Josh Smith" (keeps first+last; real middle names + collapsed initials untouched). - richie -> richard added to NICKNAMES. P2 polish: - Team Hub names normalized at the source (teamService.getTeamHub) so "J.C. Escarra" renders as "JC Escarra" like the dashboard. - snapshotService dedup keeps the highest-confidence GRADE but the richest DISPLAY (accented "José" over "Jose") so prop rows match the pitcher line. - correlationWarning names the game: "2 legs from the same game (NYY @ BOS)". Backend 2246 -> 2255 tests (+9), 194 suites. Web build clean (exit 0). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
54 lines
2.3 KiB
JavaScript
54 lines
2.3 KiB
JavaScript
/* Player-name normalization (Session 46, completed Session 47) — frontend copy
|
|
of src/utils/playerName.js (the Next bundle can't import from src/). Keep the
|
|
two IDENTICAL; a test cross-checks they agree. CommonJS so .tsx imports it AND
|
|
Jest requires it directly. */
|
|
|
|
const SUFFIXES = new Set(['jr', 'sr', 'ii', 'iii', 'iv', 'v']);
|
|
|
|
const NICKNAMES = {
|
|
matt: 'matthew', mike: 'michael', chris: 'christopher', jake: 'jacob',
|
|
josh: 'joshua', nick: 'nicholas', nate: 'nathaniel', dan: 'daniel',
|
|
danny: 'daniel', dave: 'david', rob: 'robert', bob: 'robert', joe: 'joseph',
|
|
joey: 'joseph', jon: 'jonathan', johnny: 'john', tony: 'anthony',
|
|
alex: 'alexander', andy: 'andrew', drew: 'andrew', ben: 'benjamin',
|
|
will: 'william', bill: 'william', billy: 'william', willy: 'william',
|
|
zach: 'zachary', zack: 'zachary', tom: 'thomas', tommy: 'thomas',
|
|
ty: 'tyler', ed: 'edward', eddie: 'edward', teddy: 'theodore',
|
|
charlie: 'charles', chuck: 'charles', rick: 'richard', dick: 'richard',
|
|
jim: 'james', jimmy: 'james', ray: 'raymond', fred: 'frederick',
|
|
kenny: 'kenneth', sam: 'samuel', pat: 'patrick', greg: 'gregory',
|
|
steve: 'steven', tim: 'timothy', frank: 'francis', mickey: 'michael',
|
|
richie: 'richard',
|
|
};
|
|
|
|
// Collapse adjacent single-letter words: "J C Escarra" → "JC Escarra".
|
|
function collapseInitials(s) {
|
|
return s.replace(/\b([A-Za-z])(?: ([A-Za-z]))+\b(?=\s|$)/g, (m) => m.replace(/ /g, ''));
|
|
}
|
|
|
|
function normalizeName(raw) {
|
|
const display = collapseInitials(String(raw == null ? '' : raw)
|
|
.replace(/\s*\([^)]*\)\s*/g, ' ')
|
|
.replace(/\./g, '')
|
|
.replace(/-/g, ' ')
|
|
.replace(/\s+/g, ' ')
|
|
.trim());
|
|
const folded = display.normalize('NFD').replace(/[̀-ͯ]/g, '').toLowerCase();
|
|
const key = folded.split(' ').filter((t) => t && !SUFFIXES.has(t)).join(' ');
|
|
return { display, key };
|
|
}
|
|
|
|
function nameKey(raw) {
|
|
const { key } = normalizeName(raw);
|
|
let parts = key.split(/\s+/).filter(Boolean);
|
|
if (parts.length >= 2 && NICKNAMES[parts[0]]) parts[0] = NICKNAMES[parts[0]];
|
|
// Strip single-letter MIDDLE tokens ("josh h smith" → "josh smith"); keep the
|
|
// first (may be a collapsed initial like "jc") and last token.
|
|
if (parts.length >= 3) {
|
|
parts = parts.filter((p, i, arr) => i === 0 || i === arr.length - 1 || p.length > 1);
|
|
}
|
|
return parts.join(' ');
|
|
}
|
|
|
|
module.exports = { normalizeName, nameKey, SUFFIXES, NICKNAMES };
|