Function collectGitStatus

src/extraction/index.ts:1105–1178

(repoDir: string, prefix: string, out: GitChanges, overrides?: Record<string, Language>, includeIgnored: Ignore | null = null, exclude: Ignore | null = null)

}

function collectGitStatus(repoDir: string, prefix: string, out: GitChanges, overrides?: Record<string, Language>, includeIgnored: Ignore | null = null, exclude: Ignore | null = null): void {
  const output = execFileSync(
    'git',
    ['status', '--porcelain', '--no-renames'],
    { cwd: repoDir, encoding: 'utf-8', timeout: 10000, maxBuffer: 50 * 1024 * 1024, stdio: ['pipe', 'pipe', 'pipe'], windowsHide: true }
  );

  // This repo's own ignore rules — built-in defaults (#407) plus its .gitignore.
  // Change detection must exclude the SAME files the full index does, but git
  // status hides neither: it ignores nothing for *tracked* paths, and the
  // built-in defaults aren't gitignore at all. Without this filter a committed
  // vendor/ dir, or a tracked file under a .gitignored dir, surfaces here as a
  // change — so `codegraph status` (which reads getChangedFiles) reports a
  // pending edit the full index never tracks and `sync` never clears. Matching
  // repo-relative `rel` at each recursion level mirrors getGitVisibleFiles'
  // ScopeIgnore: every embedded repo is judged by ITS OWN rules, never the
  // parent's. (#766)
  const ig = buildDefaultIgnore(repoDir);

  const untrackedDirs: string[] = [];
  for (const line of output.split('\n')) {
    if (line.length < 4) continue; // Minimum: "XY file"

    const statusCode = line.substring(0, 2);
    const rel = normalizePath(line.substring(3));

    // Untracked directory entries (trailing slash) may hide an embedded repo —
    // collect for the recursion below instead of treating as a file.
    if (statusCode === '??' && rel.endsWith('/')) {
      untrackedDirs.push(rel);
      continue;
    }

    const filePath = normalizePath(prefix + rel);
    if (!isSourceFile(filePath, overrides)) continue;

    if (statusCode.includes('D')) {
      // Deletions stay unfiltered: getChangedFiles acts on one only when the
      // path is already tracked in the DB, where removal is always correct — and
      // that lets a newly-excluded dir's stale rows clean themselves up. (#766)
      out.deleted.push(filePath);
      continue;
    }

    // Added (`??`) / modified files inside an excluded dir must not enter the
    // index — match against the repo-relative path, same as the full scan. (#766)
    if (ig.ignores(rel)) continue;
    // User `codegraph.json` `exclude` (#999) is project-root-relative, so it's
    // matched against the full path — sync must not re-add a tracked file the
    // full index now keeps out. Deletions above stay unfiltered so a file that
    // WAS indexed before an exclude was added still cleans itself out.
    if (exclude && exclude.ignores(filePath)) continue;

    if (statusCode === '??') {
      out.added.push(filePath);
    } else {
      // M, MM, AM, A (staged), etc. — treat as modified
      out.modified.push(filePath);