vyndr/src/services/model/hitsFactorContext.js

'use strict';

/**
 * hitsFactorContext — load the proven factors' inputs ONCE per slate.
 *
 * The three hits factors each need a database read (batter spray, team
 * positional defence, platoon splits, pitcher contact profile). Doing that per
 * prop would put four queries inside a loop that runs across the whole board, so
 * the tables are loaded once and indexed, and the per-prop lookup is a map hit.
 *
 * Loaded BEFORE grading, which is the whole point of this order — the same data
 * was previously fetched after the grade it should have informed.
 *
 * Every load is best-effort: a missing table yields an empty index, the factor
 * finds nothing readable, and the forecast is served unadjusted. A factor layer
 * must never be able to break the pipeline it rides in.
 */

const { knownNumber } = require('../../utils/known');
const { nameKey } = require('../../utils/playerName');

/** Rows a factor table must have before we trust it at all. */
const MIN_ROWS = 1;

/**
 * Page a factor table.
 *
 * ORDERING IS PER-TABLE. These tables have COMPOSITE primary keys
 * (as_of_date, sport, player_key) and NO `id` column, so ordering by `id`
 * errors — and an error here returns an empty index, which reads exactly like
 * "this feed has no data". That is the third time in this codebase that a
 * wiring fault has worn the costume of an honest absence, so the error is now
 * surfaced rather than swallowed.
 */
async function page(sb, table, select, orderBy, apply) {
  const out = [];
  for (let from = 0; ; from += 1000) {
    const q = apply ? apply(sb.from(table).select(select)) : sb.from(table).select(select);
    const { data, error } = await q.order(orderBy, { ascending: true }).range(from, from + 999);
    if (error) throw new Error(`${table}: ${error.message}`);
    if (!data || data.length === 0) break;
    out.push(...data);
    if (data.length < 1000) break;
  }
  return out;
}

/** Keep the most recent dated row per key. */
function latestBy(rows, keyFn, dateFn) {
  const m = new Map();
  for (const r of rows) {
    const k = keyFn(r);
    if (!k) continue;
    const prev = m.get(k);
    if (!prev || String(dateFn(r)) > String(dateFn(prev))) m.set(k, r);
  }
  return m;
}

/**
 * @returns {function|null} a `(prop, sport) => context` resolver, or null when
 *          nothing loaded — null means "serve unadjusted", never a stub context.
 */
async function build(sb, opts = {}) {
  if (!sb) return null;
  let spray; let defense; let platoon; let statcast;
  try {
    [spray, defense, platoon, statcast] = await Promise.all([
      page(sb, 'batter_spray', '*', 'player_key', (q) => q.eq('sport', 'mlb')),
      page(sb, 'team_defense', '*', 'team', (q) => q.eq('sport', 'mlb')),
      page(sb, 'platoon_splits', '*', 'player_key', (q) => q.eq('sport', 'mlb')),
      page(sb, 'statcast_aggregates', 'player_key, source_id, role, bats, throws, hard_hit_pct', 'player_key', (q) => q.eq('sport', 'mlb')),
    ]);
  } catch (e) {
    // Surfaced, not silent: a load failure must be distinguishable from a feed
    // that genuinely holds nothing.
    console.warn('[factors] context load FAILED (not an empty feed):', e.message);
    return null;
  }
  if (!spray.length && !defense.length && !platoon.length) return null;

  const sprayBy = latestBy(spray, (r) => r.player_key, (r) => r.as_of_date);
  const defBy = latestBy(defense, (r) => r.team, (r) => r.as_of_date);
  const platBy = latestBy(platoon, (r) => r.player_key, (r) => r.as_of_date);

  const batBy = new Map();
  const pitBy = new Map();
  for (const r of statcast) {
    if (!r.player_key) continue;
    if (r.role === 'pitcher') pitBy.set(r.player_key, r);
    else batBy.set(r.player_key, r);
  }

  // statcast stores PERCENTAGES (0-100); the factor wants a fraction.
  const asFraction = (v) => {
    const n = knownNumber(v);
    if (n === null) return null;
    return n > 1 ? n / 100 : n;
  };

  const resolver = (prop) => {
    const key = nameKey(prop && prop.player);
    if (!key) return null;
    const bat = batBy.get(key);
    const bats = bat && bat.bats ? String(bat.bats)[0] : null;

    // The opposing team and its starter, from whatever the prop carries.
    const oppName = prop && (prop.opponent || prop.opp_team || null);
    const def = oppName ? (defBy.get(oppName) || defBy.get(String(oppName).split(' ').pop())) : null;

    const pitKey = prop && prop.opposing_pitcher ? nameKey(prop.opposing_pitcher) : null;
    const pit = pitKey ? pitBy.get(pitKey) : null;

    const sp = platBy.get(key);
    const splits = sp ? {
      vl: { pa: sp.vl_pa, atBats: sp.vl_ab, hits: sp.vl_hits },
      vr: { pa: sp.vr_pa, atBats: sp.vr_ab, hits: sp.vr_hits },
    } : null;

    const ctx = {
      spray: sprayBy.get(key) || null,
      positionOaa: def && def.position_oaa ? def.position_oaa : null,
      bats,
      throws: pit && pit.throws ? String(pit.throws)[0] : null,
      pitcherHardHit: pit ? asFraction(pit.hard_hit_pct) : null,
      platoonSplits: splits,
    };
    // Nothing readable at all -> null, so the engine skips the factor block
    // entirely rather than walking an empty context.
    const anything = ctx.spray || ctx.pitcherHardHit !== null || ctx.platoonSplits;
    return anything ? ctx : null;
  };

  resolver.__stats = {
    spray_players: sprayBy.size,
    defense_teams: defBy.size,
    platoon_players: platBy.size,
    pitcher_profiles: pitBy.size,
    batter_profiles: batBy.size,
  };
  return resolver;
}

module.exports = { build, MIN_ROWS };