Function detect

graphify/detect.py:1027–1200

(root: Path, *, follow_symlinks: bool | None = None, google_workspace: bool | None = None, extra_excludes: list[str] | None = None)

def detect(root: Path, *, follow_symlinks: bool | None = None, google_workspace: bool | None = None, extra_excludes: list[str] | None = None) -> dict:
    root = root.resolve()
    if follow_symlinks is None:
        follow_symlinks = False
    google_workspace = google_workspace_enabled() if google_workspace is None else google_workspace
    files: dict[FileType, list[str]] = {
        FileType.CODE: [],
        FileType.DOCUMENT: [],
        FileType.PAPER: [],
        FileType.IMAGE: [],
        FileType.VIDEO: [],
    }
    total_words = 0

    def _wc(path: Path) -> int:
        # Cache word counts against each file's stat signature so unchanged
        # PDFs/docx aren't re-parsed on every run just to size the corpus (#1656).
        from graphify import cache as _cache
        return _cache.cached_word_count(path, root, count_words)

    skipped_sensitive: list[str] = []
    ignore_patterns = _load_graphifyignore(root)
    ignore_cache: dict[Path, bool] = {}  # shared across all _is_ignored calls in this scan
    # CLI --exclude patterns are anchored at the scan root and appended last
    # so they win over any .graphifyignore/.gitignore rules (#947).
    if extra_excludes:
        for pat in extra_excludes:
            line = _parse_gitignore_line(pat)
            if line:
                ignore_patterns.append((root, line))
    include_patterns = _load_graphifyinclude(root)

    # Always include graphify-out/memory/ - query results filed back into the graph
    memory_dir = root / GRAPHIFY_OUT / "memory"
    scan_paths = [root]
    if memory_dir.exists():
        scan_paths.append(memory_dir)

    seen: set[Path] = set()
    all_files: list[Path] = []

    for scan_root in scan_paths:
        in_memory_tree = memory_dir.exists() and str(scan_root).startswith(str(memory_dir))
        for dirpath, dirnames, filenames in os.walk(scan_root, followlinks=follow_symlinks):
            dp = Path(dirpath)
            if follow_symlinks and os.path.islink(dirpath):
                real = os.path.realpath(dirpath)
                parent_real = os.path.realpath(os.path.dirname(dirpath))
                if parent_real == real or parent_real.startswith(real + os.sep):
                    dirnames.clear()
                    continue
            if not in_memory_tree:
                # Prune noise dirs in-place so os.walk never descends into them.
                # Dot dirs are allowed — users often want .github/, .claude/, etc.
                # Framework caches (.next, .nuxt, …) are caught by _is_noise_dir.
                # Negations need no special-casing here: _is_ignored already applies
                # last-match-wins (so `!dir/` un-ignores a directory and it won't be
                # pruned) and the gitignore parent-exclusion rule (a `!` cannot rescue