/** Scientific invariants applied to normalized records (CLAUDE.md §110, §154). */

export interface ValidationIssue {
  field: string;
  message: string;
}

export function validateEpidemiology(o: { metric: string; value: number; year: number; lowerCi?: number | null; upperCi?: number | null; unit: string }): ValidationIssue[] {
  const issues: ValidationIssue[] = [];
  if (!Number.isFinite(o.value)) issues.push({ field: 'value', message: 'not finite' });
  if (o.value < 0) issues.push({ field: 'value', message: 'negative count/rate' });
  if (o.year < 1900 || o.year > new Date().getFullYear() + 30) issues.push({ field: 'year', message: `implausible year ${o.year}` });
  if (o.lowerCi != null && o.lowerCi > o.value) issues.push({ field: 'lowerCi', message: 'lowerCI > estimate' });
  if (o.upperCi != null && o.upperCi < o.value) issues.push({ field: 'upperCi', message: 'upperCI < estimate' });
  if (o.metric.endsWith('_count') && o.unit !== 'count') issues.push({ field: 'unit', message: 'count metric must use unit=count' });
  if (o.metric.endsWith('_rate') && o.unit !== 'per_100k') issues.push({ field: 'unit', message: 'rate metric must use unit=per_100k' });
  return issues;
}

export function validateSurvival(o: { probability?: number | null; durationMonths: number; lowerCi?: number | null; upperCi?: number | null; cohortSize?: number | null }): ValidationIssue[] {
  const issues: ValidationIssue[] = [];
  if (o.probability != null && (o.probability < 0 || o.probability > 1)) issues.push({ field: 'probability', message: 'survival must be within [0,1]' });
  if (o.durationMonths <= 0) issues.push({ field: 'durationMonths', message: 'duration must be positive' });
  if (o.probability != null && o.lowerCi != null && o.lowerCi > o.probability) issues.push({ field: 'lowerCi', message: 'lowerCI > estimate' });
  if (o.probability != null && o.upperCi != null && o.upperCi < o.probability) issues.push({ field: 'upperCi', message: 'upperCI < estimate' });
  if (o.cohortSize != null && o.cohortSize < 0) issues.push({ field: 'cohortSize', message: 'negative cohort' });
  return issues;
}

export const TRIAL_PHASES = new Set(['EARLY_PHASE1', 'PHASE1', 'PHASE2', 'PHASE3', 'PHASE4', 'NA']);
export const TRIAL_STATUSES = new Set(['ACTIVE_NOT_RECRUITING', 'COMPLETED', 'ENROLLING_BY_INVITATION', 'NOT_YET_RECRUITING', 'RECRUITING', 'SUSPENDED', 'TERMINATED', 'WITHDRAWN', 'AVAILABLE', 'NO_LONGER_AVAILABLE', 'TEMPORARILY_NOT_AVAILABLE', 'APPROVED_FOR_MARKETING', 'WITHHELD', 'UNKNOWN']);

export function validateTrial(o: { nctId: string; phases: string[]; overallStatus?: string | null }): ValidationIssue[] {
  const issues: ValidationIssue[] = [];
  if (!/^NCT\d{8}$/.test(o.nctId)) issues.push({ field: 'nctId', message: 'malformed NCT id' });
  for (const p of o.phases) if (!TRIAL_PHASES.has(p)) issues.push({ field: 'phases', message: `unknown phase enum ${p}` });
  if (o.overallStatus && !TRIAL_STATUSES.has(o.overallStatus)) issues.push({ field: 'overallStatus', message: `unknown status enum ${o.overallStatus}` });
  return issues;
}

export function validateFrequency(o: { casesAffected: number; casesProfiled: number }): ValidationIssue[] {
  const issues: ValidationIssue[] = [];
  if (o.casesProfiled <= 0) issues.push({ field: 'casesProfiled', message: 'denominator must be positive' });
  if (o.casesAffected < 0 || o.casesAffected > o.casesProfiled) issues.push({ field: 'casesAffected', message: 'numerator out of range' });
  return issues;
}

/** Gene symbol sanity (HGNC style). */
export const GENE_SYMBOL_RE = /^[A-Z][A-Z0-9-]{0,15}(?:@|orf\d+)?$/i;