Function collectGitFiles

src/extraction/index.ts:913–1010

* Collect git-visible files (tracked + untracked, .gitignore-respected) from the * git repository rooted at `repoDir`, adding each to `files` with `prefix` * prepended so paths stay relative to the original scan root. * * Recurses into embedded git repositories — nested repos that are NOT submod

(repoDir: string, prefix: string, files: Set<string>, embeddedRoots?: Set<string>, includeIgnored: Ignore | null = null)

 * parent's own gitignore rules.
 */
function collectGitFiles(repoDir: string, prefix: string, files: Set<string>, embeddedRoots?: Set<string>, includeIgnored: Ignore | null = null): void {
  const gitOpts = { cwd: repoDir, encoding: 'utf-8' as const, timeout: 30000, maxBuffer: 50 * 1024 * 1024, stdio: ['pipe', 'pipe', 'pipe'] as ['pipe', 'pipe', 'pipe'], windowsHide: true };

  // Tracked files. --recurse-submodules pulls in files from active submodules,
  // which the index would otherwise represent only as a commit pointer.
  // Without this, monorepos using submodules index 0 files. (See issue #147.)
  // Note: --recurse-submodules only supports -c/--cached and --stage modes — it
  // can't be combined with -o, so untracked files are gathered separately below.
  //
  // We use --stage (-s) rather than -c so each entry carries its file mode. That
  // lets us spot gitlink entries (mode 160000) that --recurse-submodules did NOT
  // expand: a nested repo `git add`ed without a `.gitmodules` entry, or a
  // submodule that isn't active/initialized in this checkout. Such a gitlink
  // falls through every pass — it's tracked, so the untracked `-o` listing below
  // never reports it, and --recurse-submodules only expands ACTIVE submodules —
  // so its source would be silently skipped, leaving only the super-repo's own
  // files indexed. We collect those gitlinks here and recurse into them below.
  // (An active submodule is expanded inline by --recurse-submodules and so never
  // surfaces as a 160000 entry — only the unhandled gitlinks do.) (#1031, #1033)
  //
  // -z gives NUL-separated, unquoted output so non-ASCII (e.g. CJK) paths
  // survive verbatim. Without it git octal-escapes and double-quotes such paths
  // (the core.quotepath default), and the quoted form never matches a real file
  // on disk → those files are silently dropped from the index. (#541) With -s the
  // path follows a TAB after the `<mode> <object> <stage>` prefix.
  const gitlinkRels: string[] = [];
  const tracked = execFileSync('git', ['ls-files', '-z', '-s', '--recurse-submodules'], gitOpts);
  for (const entry of tracked.split('\0')) {
    if (!entry) continue;
    const tab = entry.indexOf('\t');
    if (tab === -1) continue; // --stage always emits "<mode> <object> <stage>\t<path>"
    const rel = entry.slice(tab + 1);
    if (entry.slice(0, 6) === '160000') {
      gitlinkRels.push(rel); // an unexpanded gitlink — recursed into below, not a source file itself
      continue;
    }
    files.add(normalizePath(prefix + rel));
  }

  // Untracked files (submodules manage their own untracked state). Embedded git
  // repos surface here as a single "subdir/" entry that git refuses to descend
  // into — recurse into those as their own repos so their source gets indexed.
  const untracked = execFileSync('git', ['ls-files', '-z', '-o', '--exclude-standard'], gitOpts);
  for (const rel of untracked.split('\0')) {
    if (!rel) continue;
    if (rel.endsWith('/')) {
      // git only emits a trailing-slash directory entry for an embedded repo.
      // Guard with a .git check anyway, and skip anything else exactly as git
      // itself skips it (we never descend into a non-repo opaque dir). Never
      // descend into default-ignored locations — an embedded repo inside
      // node_modules is an npm git-dependency, not project code.
      const childDir = path.join(repoDir, rel);
      // A git worktree surfaces here as an opaque untracked dir too — skip it,
      // it's a duplicate working view of an already-indexed repo (#848).
      if (classifyGitDir(childDir) === 'embedded' && !defaultsOnlyIgnore().ignores(rel)) {
        embeddedRoots?.add(normalizePath(prefix + rel));
        collectGitFiles(childDir, prefix + rel, files, embeddedRoots, includeIgnored);
      }