Function scanDirectoryWalk

src/extraction/index.ts:989–1110

* Filesystem walk fallback for non-git projects.

(
  rootDir: string,
  onProgress?: (current: number, file: string) => void
)

 * Filesystem walk fallback for non-git projects.
 */
function scanDirectoryWalk(
  rootDir: string,
  onProgress?: (current: number, file: string) => void
): string[] {
  const files: string[] = [];
  let count = 0;
  const visitedDirs = new Set<string>();
  // Custom extension → language overrides from the project's codegraph.json.
  const overrides = loadExtensionOverrides(rootDir);

  // A .gitignore matcher scoped to the directory that declared it. Patterns in
  // a nested .gitignore are relative to that directory, so we keep the dir
  // alongside the matcher and test paths relative to it — mirroring how git
  // applies .gitignore files at every level.
  interface ScopedIgnore {
    dir: string;
    ig: Ignore;
  }

  const loadIgnore = (dir: string): ScopedIgnore | null => {
    const giPath = path.join(dir, '.gitignore');
    if (!fs.existsSync(giPath)) return null;
    // readGitignorePatterns is defensive: a non-UTF-8 (DLP-encrypted) or
    // uncompilable .gitignore is skipped/filtered with a warning, never thrown
    // (issue #682) — so the per-file `.ignores()` calls below can't crash.
    const patterns = readGitignorePatterns(giPath);
    return patterns ? { dir, ig: ignore().add(patterns) } : null;
  };

  const isIgnored = (fullPath: string, isDir: boolean, matchers: ScopedIgnore[]): boolean => {
    for (const { dir, ig } of matchers) {
      let rel = normalizePath(path.relative(dir, fullPath));
      if (!rel || rel.startsWith('..')) continue; // not under this matcher's dir
      if (isDir) rel += '/'; // dir-only rules (e.g. `build/`) only match with the slash
      if (ig.ignores(rel)) return true;
    }
    return false;
  };

  function walk(dir: string, matchers: ScopedIgnore[]): void {
    let realDir: string;
    try {
      realDir = fs.realpathSync(dir);
    } catch {
      logDebug('Skipping unresolvable directory', { dir });
      return;
    }

    if (visitedDirs.has(realDir)) {
      logDebug('Skipping already-visited directory (symlink cycle)', { dir, realDir });
      return;
    }
    visitedDirs.add(realDir);

    // This directory's own .gitignore (if present) applies to everything below it.
    // The root's .gitignore is already merged into the seeded base matcher (so a
    // negation there can override a built-in default), so skip it here.
    const own = dir === rootDir ? null : loadIgnore(dir);