vyndr/scripts/wnba-feed-verify.js

#!/usr/bin/env node
'use strict';

/**
 * wnba-feed-verify — prove the tap, the ingest and the as-of read on REAL data.
 *
 * Runs the production parsers over the live WNBA season and holds the rows in
 * memory, then drives `wnbaUsageService.profileAsOf` against them through a stub
 * client. It exercises the SAME functions the pipeline will call — not a
 * restatement of them — so a passing run is evidence about the code that ships.
 *
 *   node scripts/wnba-feed-verify.js [--from=2026-05-01] [--to=2026-08-12]
 */

const adapter = require('../src/services/adapters/espnWnbaAdapter');
const usage = require('../src/services/wnbaUsageService');
const { nameKey } = require('../src/utils/playerName');

const arg = (k, d) => {
  const hit = process.argv.find((a) => a.startsWith(`--${k}=`));
  return hit ? hit.split('=')[1] : d;
};

/** A stub client that serves in-memory rows through the real read path. */
function memClient(rows) {
  return {
    from() {
      const state = { rows: rows.slice(), order: [], range: null };
      const q = {
        select: () => q,
        eq: (col, val) => { state.rows = state.rows.filter((r) => r[col] === val); return q; },
        lt: (col, val) => { state.rows = state.rows.filter((r) => String(r[col]) < String(val)); return q; },
        order: (col, o) => { state.order.push([col, o && o.ascending !== false]); return q; },
        range: async (from, to) => {
          const sorted = state.rows.slice().sort((a, b) => {
            for (const [c, asc] of state.order) {
              const cmp = String(a[c]).localeCompare(String(b[c]));
              if (cmp) return asc ? cmp : -cmp;
            }
            return 0;
          });
          return { data: sorted.slice(from, to + 1), error: null };
        },
      };
      return q;
    },
  };
}

async function main() {
  const to = arg('to', usage.dateET());
  const from = arg('from', '2026-05-01');
  console.log(`\nWNBA FEED — pulling completed games ${from} .. ${to}\n`);

  const rows = [];
  const games = new Set();
  const dateStats = [];
  let errors = 0;

  for (const date of usage.eachDate(from, to)) {
    let ids = [];
    try { ids = await adapter.getFinalGameIds(date); } catch (e) { errors += 1; continue; }
    if (!ids.length) continue;
    let dayRows = 0;
    for (const id of ids) {
      try {
        const parsed = await adapter.getGameRows(id);
        if (parsed.skipped || !parsed.rows.length) continue;
        games.add(id);
        for (const r of parsed.rows) {
          if (!r.source_id || !r.player_name) continue;
          rows.push({ ...r, player_key: nameKey(r.player_name) });
          dayRows += 1;
        }
      } catch { errors += 1; }
    }
    dateStats.push({ date, games: ids.length, rows: dayRows });
    process.stdout.write(`  ${date}: ${ids.length} games, ${dayRows} rows\r`);
  }

  const dates = [...new Set(rows.map((r) => r.game_date))].sort();
  console.log('\n\n──────── COVERAGE ────────');
  console.log(`  rows            ${rows.length}`);
  console.log(`  games           ${games.size}`);
  console.log(`  players         ${new Set(rows.map((r) => r.player_key)).size}`);
  console.log(`  teams           ${new Set(rows.map((r) => r.team)).size}`);
  console.log(`  date range      ${dates[0]} .. ${dates[dates.length - 1]}  (${dates.length} game days)`);
  console.log(`  fetch errors    ${errors}`);
  const cov = (f) => `${rows.filter((r) => r[f] != null).length}/${rows.length}`;
  console.log('\n  FIELD COVERAGE (the chainFn inputs)');
  for (const f of ['minutes', 'usage_rate', 'team_possessions', 'team_pace', 'ts_pct', 'efg_pct', 'starter', 'final_margin']) {
    console.log(`    ${f.padEnd(20)} ${cov(f)}`);
  }

  // A worked example, so the derivation is checkable by hand.
  const sample = rows.find((r) => r.minutes > 25 && r.usage_rate != null);
  if (sample) {
    console.log('\n  WORKED EXAMPLE (derivation is exact arithmetic, not a proxy)');
    console.log(`    ${sample.player_name} (${sample.team}) ${sample.game_date}`);
    console.log(`    MIN ${sample.minutes}  FGA ${sample.fga}  FTA ${sample.fta}  TOV ${sample.tov}  PTS ${sample.points}`);
    console.log(`    team: MIN ${sample.team_minutes} FGA ${sample.team_fga} FTA ${sample.team_fta} TOV ${sample.team_tov} OREB ${sample.team_oreb}`);
    const poss = sample.team_fga - sample.team_oreb + sample.team_tov + 0.44 * sample.team_fta;
    const usg = 100 * ((sample.fga + 0.44 * sample.fta + sample.tov) * (sample.team_minutes / 5))
      / (sample.minutes * (sample.team_fga + 0.44 * sample.team_fta + sample.team_tov));
    console.log(`    possessions  stored ${sample.team_possessions}  recomputed ${poss.toFixed(3)}`);
    console.log(`    usage_rate   stored ${sample.usage_rate}  recomputed ${usg.toFixed(3)}`);
    console.log(`    pace ${sample.team_pace}  TS% ${sample.ts_pct}  starter ${sample.starter}  margin ${sample.final_margin}`);
  }

  // ── AS-OF VERIFICATION, through the REAL read path ──────────────────────
  console.log('\n──────── AS-OF READ (through wnbaUsageService.profileAsOf) ────────');
  const sb = memClient(rows);
  const counts = new Map();
  for (const r of rows) counts.set(r.player_key, (counts.get(r.player_key) || 0) + 1);
  const busiest = [...counts.entries()].sort((a, b) => b[1] - a[1])[0];
  const pk = busiest[0];
  const theirs = rows.filter((r) => r.player_key === pk).sort((a, b) => a.game_date.localeCompare(b.game_date));
  const name = theirs[0].player_name;
  console.log(`  player: ${name} (${pk}) — ${theirs.length} games on record\n`);

  const mid = theirs[Math.floor(theirs.length / 2)].game_date;
  for (const asOf of [theirs[2].game_date, mid, theirs[theirs.length - 1].game_date, '2026-12-31']) {
    const p = await usage.profileAsOf(sb, { playerKey: pk, asOf });
    const expected = theirs.filter((r) => r.game_date < asOf).length;
    const ok = p ? p.games === expected : expected < usage.MIN_GAMES;
    console.log(`  asOf ${asOf}  games=${p ? p.games : 'REFUSED'} (expected ${expected}) ${ok ? 'OK' : 'MISMATCH'}`
      + (p ? `  usage ${p.usage_rate}  min/g ${p.minutes_per_game}  pace ${p.team_pace}  TS ${p.ts_pct}` : ''));
  }

  // THE LEAK TEST: a game ON the as-of date must never be counted.
  const onDate = theirs[theirs.length - 1].game_date;
  const p = await usage.profileAsOf(sb, { playerKey: pk, asOf: onDate });
  const includesSameDay = p && p.last_game_date === onDate;
  console.log(`\n  STRICT CUTOFF — a game ON the as-of date is ${includesSameDay ? 'INCLUDED (LEAK)' : 'EXCLUDED (correct)'}`);
  console.log(`    last game counted: ${p ? p.last_game_date : 'n/a'} vs as-of ${onDate}`);

  // And the refusal.
  const thin = await usage.profileAsOf(sb, { playerKey: pk, asOf: theirs[0].game_date });
  console.log(`  THIN HISTORY — asOf before his first game returns ${thin === null ? 'null (refused, correct)' : 'A PROFILE (WRONG)'}`);

  process.exit(0);
}

if (require.main === module) main().catch((e) => { console.error(e); process.exit(1); });