// tests/kb-update/test-validate-kb-file.test.mjs
// The executable create-guard (Spor 3 Port 2): scripts/kb-update/validate-kb-file.mjs
// is the gate any generator calls AFTER writing a candidate file and BEFORE committing.
// It wraps transform.validateKbFile over one or more paths and exits non-zero if any
// file violates the contract (no source / not born-verified / large file without a TOC).
//
// validatePaths is a pure function with an injectable reader, so these tests never
// touch disk — they feed synthetic content and assert the verdict + ok flag.

import { test } from 'node:test';
import assert from 'node:assert/strict';
import { validatePaths } from '../../scripts/kb-update/validate-kb-file.mjs';
import {
  buildKbHeader,
  insertHeaderFields,
  validateKbFile,
} from '../../scripts/kb-update/lib/transform.mjs';
import { parseTypeHeader, parseSourceHeader } from '../../scripts/kb-update/lib/kb-headers.mjs';

const GOOD = buildKbHeader({
  title: 'Azure AI Search - Hybrid Retrieval',
  status: 'GA',
  category: 'rag-architecture',
  type: 'reference',
  source: 'https://learn.microsoft.com/azure/search/hybrid-search-overview',
  lastUpdated: '2026-06',
  verified: '2026-06-29',
  verified_by: 'judge-v2',
}) + '\n## Introduksjon\n\nNoe innhold.\n';

// A reference file with a Source but NOT born-verified (no Verified / Verified by).
const NOT_VERIFIED =
  '# T\n\n**Last updated:** 2026-06\n**Status:** GA\n**Type:** reference\n' +
  '**Source:** https://learn.microsoft.com/x\n\n---\n\n## A\n\ntekst\n';

// A reference file with no Source header at all (the 0%-coverage failure mode).
const NO_SOURCE = '# T\n\n**Last updated:** 2026-06\n**Status:** GA\n\n---\n\n## A\n\ntekst\n';

function reader(map) {
  return (p) => {
    if (!(p in map)) throw new Error(`unexpected read: ${p}`);
    return map[p];
  };
}

test('validatePaths — all files valid → ok:true', () => {
  const r = validatePaths(['a.md', 'b.md'], reader({ 'a.md': GOOD, 'b.md': GOOD }));
  assert.equal(r.ok, true);
  assert.equal(r.results.length, 2);
  assert.ok(r.results.every((x) => x.valid));
});

test('validatePaths — a file missing source fails the gate', () => {
  const r = validatePaths(['bad.md'], reader({ 'bad.md': NO_SOURCE }));
  assert.equal(r.ok, false);
  assert.equal(r.results[0].valid, false);
  assert.ok(r.results[0].missing.includes('source'));
});

test('validatePaths — a reference file that is not born-verified fails the gate', () => {
  const r = validatePaths(['nv.md'], reader({ 'nv.md': NOT_VERIFIED }));
  assert.equal(r.ok, false);
  assert.ok(r.results[0].missing.includes('verified'));
  assert.ok(r.results[0].missing.includes('verified_by'));
});

test('validatePaths — one bad file in a batch fails the whole gate', () => {
  const r = validatePaths(['ok.md', 'bad.md'], reader({ 'ok.md': GOOD, 'bad.md': NO_SOURCE }));
  assert.equal(r.ok, false);
  assert.equal(r.results.find((x) => x.path === 'ok.md').valid, true);
  assert.equal(r.results.find((x) => x.path === 'bad.md').valid, false);
});

test('validatePaths — a path that cannot be read is reported as invalid, not thrown', () => {
  const r = validatePaths(['missing.md'], () => { throw new Error('ENOENT'); });
  assert.equal(r.ok, false);
  assert.equal(r.results[0].valid, false);
  assert.ok(r.results[0].missing.some((m) => /read|enoent/i.test(m)));
});

test('validatePaths — no paths → ok:true (nothing to gate)', () => {
  const r = validatePaths([], reader({}));
  assert.equal(r.ok, true);
  assert.deepEqual(r.results, []);
});

// --- Spor 1 acceptance: the residual criterion after the substrate migration ---
// These generate the migrated file through the REAL Session-2 primitive
// (insertHeaderFields), then assert the create-guard's residual — proving the
// substrate closes the worklist-relevant fields (type+source) even where base
// fields lag. `verified`/`verified_by` stay open by design (the judge fills them,
// next brief), so the residual for a conformant file is EXACTLY those two.

// A base-field-CONFORMANT legacy file: title + English **Last updated:** + **Status:**,
// small (no TOC required). Migrated → Type + Source stamped, still no Verified.
const LEGACY_CONFORMANT =
  '# Azure AI Foundry\n\n**Last updated:** 2026-06\n**Status:** GA\n\n---\n\n## Oversikt\n\ntekst\n';
// A base-field-INCOMPLETE legacy file: Norwegian **Sist oppdatert:** (RE_LAST_UPDATED is
// English-only) + **Kategori:** but NO **Status:**. Migrated → Type + Source stamped.
const LEGACY_INCOMPLETE =
  '# Copilot Studio\n\n**Kategori:** Styring\n**Sist oppdatert:** 2026-06\n\n---\n\n## Oversikt\n\ntekst\n';

test('acceptance — a migrated base-field-conformant reference has residual EXACTLY [verified, verified_by]', () => {
  const migrated = insertHeaderFields(LEGACY_CONFORMANT, {
    type: 'reference',
    source: 'https://learn.microsoft.com/azure/ai-foundry',
  });
  assert.equal(parseTypeHeader(migrated), 'reference');
  assert.equal(parseSourceHeader(migrated), 'https://learn.microsoft.com/azure/ai-foundry');
  assert.deepEqual(validateKbFile(migrated).missing, ['verified', 'verified_by']);
});

test('acceptance — a migrated base-field-incomplete reference has residual ⊆ the 4-set, with type+source present', () => {
  const migrated = insertHeaderFields(LEGACY_INCOMPLETE, {
    type: 'reference',
    source: 'https://learn.microsoft.com/power-platform/copilot',
  });
  const { missing } = validateKbFile(migrated);
  const FOUR_SET = ['last_updated', 'status', 'verified', 'verified_by'];
  assert.ok(missing.every((m) => FOUR_SET.includes(m)), `residual ${JSON.stringify(missing)} ⊆ 4-set`);
  // The substrate DID complete the worklist-relevant fields — type + source are present,
  // never in the residual, even though base fields (Norwegian date / no Status) lag.
  assert.ok(!missing.includes('source'));
  assert.equal(parseTypeHeader(migrated), 'reference');
  assert.equal(parseSourceHeader(migrated), 'https://learn.microsoft.com/power-platform/copilot');
});