import type { CandidateKind, DeepCandidate } from "@websensor/connectors";
import { factoryConfig } from "../config";

/**
 * Candidate scoring (Source Factory, stage "signal/noise evaluation before shadow"). Combines the discovery
 * value (evidence quality) with the organization's importance, the class of page, first-party confidence,
 * expected change frequency and fetch cost. Explainable: every score carries its reasons.
 */
export interface ScoredCandidate {
  cand: DeepCandidate;
  score: number;
  reasons: string[];
}

/** How much a page class is worth for change intelligence (1 = neutral). */
export const KIND_WEIGHT: Record<CandidateKind, number> = {
  status: 1.15,
  security: 1.15,
  press: 1.1,
  news: 1.05,
  filings: 1.1,
  changelog: 1.05,
  releases: 1.0,
  pricing: 1.05,
  models: 1.05,
  ir: 0.95,
  legal: 0.9,
  blog: 0.9,
  api: 0.9,
  leadership: 0.85,
  data: 0.85,
  sitemap: 0.8,
  docs: 0.7,
  careers: 0.6,
  posture: 0.6,
  other: 0.7,
};

export function scoreCandidate(c: DeepCandidate, seed: { importance: number; weight?: number }): ScoredCandidate {
  const reasons: string[] = [];
  let score = c.value;
  reasons.push(`evidence ${c.value.toFixed(2)} (${c.evidence})`);
  const kw = KIND_WEIGHT[c.kind] ?? 0.7;
  score *= kw;
  if (kw !== 1) reasons.push(`${c.kind} ×${kw.toFixed(2)}`);
  const imp = seed.importance === 3 ? 1.1 : seed.importance === 1 ? 0.85 : 1;
  score *= imp * (seed.weight ?? 1);
  if (imp !== 1) reasons.push(`organization importance ${seed.importance} ×${imp.toFixed(2)}`);
  score *= c.firstPartyConfidence;
  if (c.firstPartyConfidence < 1) reasons.push(`first-party confidence ${c.firstPartyConfidence}`);
  if (c.itemsPerDay !== null && c.itemsPerDay !== undefined) {
    if (c.itemsPerDay > 60) {
      score *= 0.85;
      reasons.push(`firehose ${c.itemsPerDay}/day ×0.85`);
    } else if (c.itemsPerDay < 0.02) {
      score *= 0.8;
      reasons.push(`nearly dormant ${c.itemsPerDay}/day ×0.80`);
    } else if (c.itemsPerDay >= 0.2) {
      score *= 1.05;
      reasons.push(`active ${c.itemsPerDay}/day ×1.05`);
    }
  }
  if (c.fetchCost.ms > 8000) {
    score -= 0.08;
    reasons.push(`slow (${Math.round(c.fetchCost.ms)} ms) −0.08`);
  }
  if (c.fetchCost.bytes > 5 * 1024 * 1024) {
    score -= 0.08;
    reasons.push(`heavy (${Math.round(c.fetchCost.bytes / 1048576)} MB) −0.08`);
  }
  score = Math.round(Math.max(0, Math.min(1.2, score)) * 1000) / 1000;
  return { cand: c, score, reasons };
}

/** Promotion policy: caps per organization and per class, best score first. Returns the selected candidates and the reason for the others. */
export function selectForShadow(scored: ScoredCandidate[], existing: { kinds: Map<CandidateKind, number>; total: number }): { selected: ScoredCandidate[]; skipped: { s: ScoredCandidate; reason: string }[] } {
  const caps = factoryConfig.caps;
  const groupOf = (k: CandidateKind): keyof typeof caps => (k === "news" || k === "press" || k === "blog" || k === "ir" || k === "changelog" || k === "security" ? "feeds" : k === "pricing" || k === "legal" || k === "careers" || k === "leadership" || k === "docs" || k === "data" || k === "other" ? "pages" : (k as keyof typeof caps));
  const used = new Map<string, number>();
  for (const [k, n] of existing.kinds) used.set(groupOf(k), (used.get(groupOf(k)) ?? 0) + n);
  let total = existing.total;
  const selected: ScoredCandidate[] = [];
  const skipped: { s: ScoredCandidate; reason: string }[] = [];
  const legal = (existing.kinds.get("legal") ?? 0);
  let legalUsed = legal;
  for (const s of [...scored].sort((a, b) => b.score - a.score)) {
    if (s.score < factoryConfig.minScore) {
      skipped.push({ s, reason: `score ${s.score} < ${factoryConfig.minScore}` });
      continue;
    }
    if (total >= caps.total) {
      skipped.push({ s, reason: `organization cap ${caps.total} reached` });
      continue;
    }
    // Feed-type candidates (rss connector) and HTML pages are capped by group; connectors with their own cap by kind.
    const g = s.cand.connector === "rss" ? "feeds" : s.cand.connector === "http" && s.cand.kind !== "posture" ? "pages" : groupOf(s.cand.kind);
    const cap = caps[g as keyof typeof caps] ?? 1;
    if ((used.get(g) ?? 0) >= cap) {
      skipped.push({ s, reason: `${g} cap ${cap} reached` });
      continue;
    }
    if (s.cand.kind === "legal") {
      if (legalUsed >= caps.legal) {
        skipped.push({ s, reason: `legal cap ${caps.legal} reached` });
        continue;
      }
      legalUsed++;
    }
    used.set(g, (used.get(g) ?? 0) + 1);
    total++;
    selected.push(s);
  }
  return { selected, skipped };
}