ms-ai-architect/scripts/kb-update/build-registry.mjs

#!/usr/bin/env node
// build-registry.mjs — Build URL registry from existing reference files.
// Extracts all learn.microsoft.com URLs and maps them to their source reference files.
// Usage: node build-registry.mjs [--merge]
//   --merge: preserve existing sitemap_lastmod data, only add new URLs

import { readdirSync, readFileSync, existsSync } from 'node:fs';
import { join, relative, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { normalizeUrl, extractUrls } from './lib/url-normalize.mjs';
import { loadRegistry, saveRegistry } from './lib/registry-io.mjs';
import { parseSourceHeader } from './lib/kb-headers.mjs';

const __dirname = dirname(fileURLToPath(import.meta.url));
const PLUGIN_ROOT = join(__dirname, '..', '..');
const SKILLS_DIR = join(PLUGIN_ROOT, 'skills');
const merge = process.argv.includes('--merge');

// Walk directory recursively for .md files
function walkMd(dir) {
  const results = [];
  if (!existsSync(dir)) return results;
  for (const entry of readdirSync(dir, { withFileTypes: true })) {
    const full = join(dir, entry.name);
    if (entry.isDirectory()) {
      results.push(...walkMd(full));
    } else if (entry.name.endsWith('.md') && entry.name !== 'SKILL.md') {
      results.push(full);
    }
  }
  return results;
}

// --- Main ---
const existing = merge ? loadRegistry() : null;
const urlToFiles = new Map(); // normalizedUrl → Set<relativePath>
let totalFiles = 0;
let filesWithSourceHeader = 0; // coverage of the optional **Source:** authority header

const skillDirs = readdirSync(SKILLS_DIR, { withFileTypes: true })
  .filter(d => d.isDirectory())
  .map(d => d.name);

for (const skill of skillDirs) {
  const refsDir = join(SKILLS_DIR, skill, 'references');
  const files = walkMd(refsDir);

  for (const file of files) {
    totalFiles++;
    const content = readFileSync(file, 'utf8');
    const urls = extractUrls(content);
    const relPath = relative(PLUGIN_ROOT, file);

    // Read the optional **Source:**/**Primary source:** authority header.
    // 0% coverage today; tracked here so we can populate authority_source as
    // files adopt it (population semantics designed in the verification layer).
    if (parseSourceHeader(content)) filesWithSourceHeader++;

    for (const url of urls) {
      if (!urlToFiles.has(url)) urlToFiles.set(url, new Set());
      urlToFiles.get(url).add(relPath);
    }
  }
}

// Build registry
const today = new Date().toISOString().split('T')[0];
const registry = {
  version: 1,
  created_at: today,
  last_poll: merge ? existing?.last_poll || null : null,
  sitemap_state: merge ? existing?.sitemap_state || {} : {},
  urls: {},
};

for (const [url, files] of urlToFiles) {
  const prev = merge ? existing?.urls?.[url] : null;
  registry.urls[url] = {
    sitemap_lastmod: prev?.sitemap_lastmod || null,
    reference_files: [...files].sort(),
    status: prev?.status || 'unpolled',
    // Reserved schema (lag 0): authority_source = declared verification source
    // (**Source:** header, 0% coverage today); course = Learn course-track ref.
    authority_source: prev?.authority_source ?? null,
    course: prev?.course ?? null,
  };
}

saveRegistry(registry);

// Stats
const multiRef = [...urlToFiles.values()].filter(s => s.size > 1).length;
console.log(`Registry built: ${urlToFiles.size} unique URLs from ${totalFiles} files`);
console.log(`  URLs referenced by multiple files: ${multiRef}`);
console.log(`  Files declaring **Source:** header: ${filesWithSourceHeader}/${totalFiles}`);
if (merge && existing?.urls) {
  const newUrls = [...urlToFiles.keys()].filter(u => !existing.urls[u]).length;
  console.log(`  New URLs added (merge): ${newUrls}`);
}