detect_file_type (detect.py)

Detects file type by sniffing magic bytes and MIME content via Python CLI.

#!/usr/bin/env python3
"""Detect whether a file is natural language (compressible) or code/config (skip)."""

import json
import re
from pathlib import Path

# Extensions that are natural language and compressible
COMPRESSIBLE_EXTENSIONS = {".md", ".txt", ".markdown", ".rst", ".typ", ".typst", ".tex"}

# Extensions that are code/config and should be skipped
SKIP_EXTENSIONS = {
    ".py", ".js", ".ts", ".tsx", ".jsx", ".json", ".yaml", ".yml",
    ".toml", ".env", ".lock", ".css", ".scss", ".html", ".xml",
    ".sql", ".sh", ".bash", ".zsh", ".go", ".rs", ".java", ".c",
    ".cpp", ".h", ".hpp", ".rb", ".php", ".swift", ".kt", ".lua",
    ".dockerfile", ".makefile", ".csv", ".ini", ".cfg",
}

# Well-known build/config files that carry no (or a misleading) extension —
# `Dockerfile` has no s

... (truncated -- full source via MCP)