Function discoverEmbeddedRepoRoots

src/extraction/index.ts:557–613

(rootDir: string)

 * there already.
 */
export function discoverEmbeddedRepoRoots(rootDir: string): string[] {
  try {
    execFileSync('git', ['rev-parse', '--git-dir'], { cwd: rootDir, encoding: 'utf-8', timeout: 5000, stdio: ['pipe', 'pipe', 'pipe'], windowsHide: true });
  } catch {
    return [];
  }
  const out: string[] = [];
  const defaults = defaultsOnlyIgnore();
  const includeIgnored = loadIncludeIgnoredMatcher(rootDir);
  const visit = (repoAbs: string, prefix: string): void => {
    const candidates: string[] = [];
    try {
      const o = execFileSync(
        'git',
        ['ls-files', '-z', '-o', '--exclude-standard', '--directory'],
        { cwd: repoAbs, encoding: 'utf-8', timeout: 30000, maxBuffer: 50 * 1024 * 1024, stdio: ['pipe', 'pipe', 'pipe'], windowsHide: true }
      );
      for (const e of o.split('\0')) {
        if (e.endsWith('/') && !isWholeCwdEntry(e) && !defaults.ignores(e)) {
          candidates.push(...findNestedGitRepos(path.join(repoAbs, e), e));
        }
      }
    } catch { /* untracked listing failed — ignored-side discovery still runs */ }
    // Unexpanded gitlinks (mode 160000) with a real checkout on disk — embedded
    // repos `git add`ed without `.gitmodules`, or submodules not active here. The
    // untracked listing above can't see them (they're tracked), so find them the
    // same way collectGitFiles does, keeping watcher scope == indexer scope.
    // (#1031, #1033)
    try {
      const staged = execFileSync(
        'git',
        ['ls-files', '-z', '-s', '--recurse-submodules'],
        { cwd: repoAbs, encoding: 'utf-8', timeout: 30000, maxBuffer: 50 * 1024 * 1024, stdio: ['pipe', 'pipe', 'pipe'], windowsHide: true }
      );
      const repoIgnore = buildDefaultIgnore(repoAbs);
      for (const entry of staged.split('\0')) {
        if (!entry || entry.slice(0, 6) !== '160000') continue;
        const tab = entry.indexOf('\t');
        if (tab === -1) continue;
        const rel = entry.slice(tab + 1);
        const relDir = rel.endsWith('/') ? rel : rel + '/';
        // A gitlink under a gitignored path is respected (not indexed) unless the
        // project opted it in — same rule as the untracked-ignored kind (#1065).
        if (gitlinkEmbeddedRepoSkipped(relDir, prefix, defaults, repoIgnore, includeIgnored)) continue;
        if (classifyGitDir(path.join(repoAbs, rel)) === 'embedded') candidates.push(relDir);
      }
    } catch { /* staged listing failed — other discovery still runs */ }
    candidates.push(...findIgnoredEmbeddedRepos(repoAbs, includeIgnored, prefix));
    for (const rel of candidates) {
      const full = normalizePath(prefix + rel);
      out.push(full);
      visit(path.join(repoAbs, rel), full);
    }
  };
  visit(rootDir, '');
  return out;
}