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>
79 lines
3.8 KiB
JavaScript
79 lines
3.8 KiB
JavaScript
'use strict';
|
|
|
|
/**
|
|
* Player-name normalization (Session 46, completed Session 47) — the ONE source
|
|
* of truth for comparing/de-duplicating player names. PropLine sends the same
|
|
* player many ways: "A.J. Ewing"/"AJ Ewing", "Jazz Chisholm"/"Jazz Chisholm Jr.",
|
|
* "Iván Herrera"/"Ivan Herrera", "Matt Liberatore"/"Matthew Liberatore",
|
|
* "Jose Fermin (STL)". This collapses them all.
|
|
*
|
|
* normalizeName("A.J. Ewing") → { display: "AJ Ewing", key: "aj ewing" }
|
|
* normalizeName("Jose Fermin (STL)") → { display: "Jose Fermin", key: "jose fermin" }
|
|
* normalizeName("Ronald Acuña Jr.") → { display: "Ronald Acuña Jr", key: "ronald acuna" }
|
|
* nameKey("Matt Liberatore") === nameKey("Matthew Liberatore") === "matthew liberatore"
|
|
* nameKey("Iván Herrera") === nameKey("Ivan Herrera") === "ivan herrera"
|
|
*
|
|
* `display` keeps proper casing + accents (periods, suffix dots, and parenthetical
|
|
* team tags stripped). `key` is accent-folded, lowercased, suffix-stripped, and
|
|
* first-name-nickname-resolved for comparison.
|
|
*
|
|
* NOTE: an identical copy lives at web/src/lib/playerName.js for the frontend
|
|
* (the Next bundle can't import from src/). A test cross-checks they agree.
|
|
*/
|
|
|
|
const SUFFIXES = new Set(['jr', 'sr', 'ii', 'iii', 'iv', 'v']);
|
|
|
|
// Common first-name nicknames in sports. KEY = short form, VALUE = canonical
|
|
// long form. Both sides reduce to the long form so "Matt"/"Matthew" merge.
|
|
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",
|
|
// "J C E Escarra" → "JCE Escarra" (PropLine sends space-separated initials).
|
|
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, ' ') // strip parenthetical team tags "(STL)"
|
|
.replace(/\./g, '') // strip dots: "A.J." → "AJ", "Jr." → "Jr"
|
|
.replace(/-/g, ' ') // "Jung-hoo" → "Jung hoo" (matches "Jung Hoo")
|
|
.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 };
|
|
}
|
|
|
|
/**
|
|
* Comparison key: normalized + first-name nickname resolved to the canonical
|
|
* form ("matt" → "matthew") so nicknames collapse.
|
|
*/
|
|
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 };
|