Source code for askemblaex.hash

"""
askemblaex/hash.py

Content-based file hashing utilities.
"""

from __future__ import annotations

import hashlib
from pathlib import Path

BUF_SIZE = 1024 * 1024  # 1MB chunks



[docs]
def hash_file(path: Path, algo: str = "sha256") -> str:
    """
    Hash a file by content and return the hex digest.

    Reads the file in chunks so large files do not require loading
    the entire content into memory.

    Args:
        path: Path to the file to hash.
        algo: Hash algorithm name accepted by hashlib (default "sha256").

    Returns:
        Lowercase hex digest string e.g. "2e7698fc5e3744fd...".

    Raises:
        FileNotFoundError: If path does not exist.
    """
    h = hashlib.new(algo)

    with path.open("rb") as f:
        for chunk in iter(lambda: f.read(BUF_SIZE), b""):
            h.update(chunk)

    return h.hexdigest()