ms-ai-architect/tests/kb-update/test-relabel-dialect.test.mjs

// tests/kb-update/test-relabel-dialect.test.mjs
// TDD for Enhet 1 (decision-b, path A, ⊥ R7) — pure value-preserving dialect relabel of the
// Norwegian header labels to their English equivalents on the 51 ref files that carry them:
//   **Sist oppdatert:** → **Last updated:**   (31 files)
//   **Kategori:**       → **Category:**        (42 files)   [22 files carry both → 73 relabels]
//
// The applier (relabel-dialect.mjs) is a manifest-driven driver over the pure primitive
// relabelHeaderDialect(). The ONLY new production logic is that primitive + the frozen MANIFEST.
// This suite pins the primitive's safety contract and the manifest's structural well-formedness.
//
// Explicitly OUT of Enhet 1 (deferred to later units, per the corrected residual):
//   - **Dato:** → **Last updated:** (16) — Dato also appears in BODY templates ([YYYY-MM-DD]),
//     a blind replace would corrupt them; needs a header-scoped ISO-date guard (Unit 2).
//   - Status backfill (27 none + 4 plain) and the ai-act dual-block dedup (Unit 3).
//   - decision-trees.md date backfill (Unit 4).

import { test } from 'node:test';
import assert from 'node:assert/strict';
import {
  relabelHeaderDialect,
  LABEL_MAP,
  MANIFEST,
} from '../../scripts/kb-update/relabel-dialect.mjs';

// ── primitive: value-preserving relabel ────────────────────────────────────

test('relabels **Sist oppdatert:** → **Last updated:**, value byte-identical', () => {
  const input = '# T\n\n**Sist oppdatert:** 2026-02 (v1.0)\n**Status:** GA\n\n---\n\n## Body\n';
  const { content, applied } = relabelHeaderDialect(input);
  assert.equal(applied.length, 1);
  assert.match(content, /\*\*Last updated:\*\* 2026-02 \(v1\.0\)/);
  assert.doesNotMatch(content, /\*\*Sist oppdatert:\*\*/);
  // Only the label token changed — reversing the sub reconstructs the original exactly.
  assert.equal(content.replace('**Last updated:**', '**Sist oppdatert:**'), input);
});

test('relabels **Kategori:** → **Category:**, value byte-identical', () => {
  const input = '# T\n\n**Kategori:** AI Security Engineering\n**Type:** reference\n\n## Body\n';
  const { content, applied } = relabelHeaderDialect(input);
  assert.equal(applied.length, 1);
  assert.match(content, /\*\*Category:\*\* AI Security Engineering/);
  assert.doesNotMatch(content, /\*\*Kategori:\*\*/);
  assert.equal(content.replace('**Category:**', '**Kategori:**'), input);
});

test('applies BOTH relabels when both norsk labels are present', () => {
  const input = '# T\n\n**Sist oppdatert:** 2026-06-19\n**Kategori:** X\n**Status:** GA\n\n---\n\n## Body\n';
  const { content, applied } = relabelHeaderDialect(input);
  assert.equal(applied.length, 2);
  assert.match(content, /\*\*Last updated:\*\* 2026-06-19/);
  assert.match(content, /\*\*Category:\*\* X/);
});

test('header-scoping: a norsk label in the BODY (past first --- / ##) is NOT touched', () => {
  // The template-contamination trap: only the header block above the first thematic break
  // or section heading is in scope.
  const input =
    '# T\n\n**Kategori:** Real Header Value\n\n---\n\n## Mal\n**Kategori:** [fyll inn]\n';
  const { content, applied } = relabelHeaderDialect(input);
  assert.equal(applied.length, 1);
  assert.match(content, /\*\*Category:\*\* Real Header Value/);
  // The body template line survives verbatim.
  assert.match(content, /## Mal\n\*\*Kategori:\*\* \[fyll inn\]/);
});

test('no-op when no norsk label is present (English-dialect file)', () => {
  const input = '# T\n\n**Last updated:** 2026-06\n**Category:** X\n**Status:** GA\n\n## Body\n';
  const { content, applied } = relabelHeaderDialect(input);
  assert.equal(applied.length, 0);
  assert.equal(content, input); // byte-identical
});

test('idempotent: re-running on the output is a no-op', () => {
  const input = '# T\n\n**Sist oppdatert:** 2026-02\n**Kategori:** X\n\n## Body\n';
  const once = relabelHeaderDialect(input);
  const twice = relabelHeaderDialect(once.content);
  assert.equal(twice.applied.length, 0);
  assert.equal(twice.content, once.content);
});

test('collision-guard: throws if the English target label already exists in the header', () => {
  // A dual-header file (bold **Category:** + norsk **Kategori:**) would duplicate on relabel.
  const input = '# T\n\n**Category:** X\n**Kategori:** X\n\n## Body\n';
  assert.throws(() => relabelHeaderDialect(input), /already present/i);
});

test('multi-occurrence-guard: throws if a norsk label appears twice in the header block', () => {
  const input = '# T\n\n**Kategori:** X\n**Kategori:** Y\n\n## Body\n';
  assert.throws(() => relabelHeaderDialect(input), /appears/i);
});

test('LABEL_MAP is exactly the two norsk→english pairs of Enhet 1 (no Dato)', () => {
  const froms = LABEL_MAP.map((p) => p[0]);
  assert.deepEqual(froms.sort(), ['**Kategori:**', '**Sist oppdatert:**']);
  // **Dato:** is intentionally excluded (body-template trap → deferred to Unit 2).
  assert.ok(!froms.some((f) => /Dato/.test(f)));
});

// ── MANIFEST: structural well-formedness ───────────────────────────────────

test('MANIFEST: exactly 51 distinct, well-formed reference paths', () => {
  assert.equal(MANIFEST.length, 51);
  const set = new Set(MANIFEST);
  assert.equal(set.size, 51, 'duplicate path in MANIFEST');
  for (const p of MANIFEST) {
    assert.match(p, /^skills\/ms-ai-[a-z]+\/references\/.+\.md$/, p);
  }
});

test('MANIFEST: excludes advisor files already English-normalised by R21', () => {
  // adr-template / poc-template etc. got their Status via R21 but were already English-dialect
  // for Category/Last-updated → they must NOT be in this relabel manifest.
  for (const p of MANIFEST) {
    assert.ok(!p.endsWith('adr-template.md'));
    assert.ok(!p.endsWith('poc-template.md'));
  }
});