Hashing of an arbitrary Python object so that it can be used for cache identification or other hash-related use cases. Produces either bytes or a string

get_hash.py

from typing import Any, Optional
import hashlib
import base64
import json


def get_hash_bytes(value: Any, hash_bytes=10, salt=None) -> Optional[bytes]:
    """
    param hash_bytes: how many bytes to hake for the trimmed hash, 10 bytes of data -> 16 symbols string
    """
    if value is None:
        return None

    if hash_bytes <= 0:
        raise ValueError(f'Hash bytes value should be >0, but not "{hash_bytes}", ignoring it')

    value_str = json.dumps(value, sort_keys=True)

    if (salt is not None) and (salt != ''):
        value_str = value_str + salt

    s_bytes = value_str.encode('utf-8')
    hash_result = hashlib.sha1(s_bytes)
    bytes_taken = hash_result.digest() if hash_bytes is None else hash_result.digest()[-hash_bytes:]
    return bytes_taken


def get_hash(value: Any, hash_bytes=10, salt=None) -> Optional[str]:
    """
    Hashing of an arbitrary Python object so that it can be used for cache identification or other hash-related use cases.
    Source https://gist.github.com/artoby/49c4d24e28a49f01728a5b4e7e53798a
    """
    bytes_taken = get_hash_bytes(value=value, hash_bytes=hash_bytes, salt=salt)
    if bytes_taken is None:
        return None

    result = base64.b32encode(bytes_taken).decode('utf-8').rstrip('=')
    return result