uni_md5_generator

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Filename: uni_md5_generator.py
# Version: 1.0.0
# Author: Jeoi Reqi

"""
Description:
    - This script calculates MD5 sums for all Unicode characters and saves them to a file.

Functions:
    - md5sum(string):
        Return the MD5 sum of a given string.
    - save_unicode_md5(filename):
        Save MD5 sums for all Unicode characters to a file.

Requirements:
    - Python 3.x

Usage:
    - Run the script to generate MD5 sums for Unicode characters and save them to 'sum_uni.txt'.

Additional Notes:
    - This script may take some time to complete, depending on the speed of the system.
"""

import hashlib
import unicodedata

def md5sum(string):
    """Return the MD5 sum of a given string."""
    return hashlib.md5(string.encode('utf-8', errors='ignore')).hexdigest()

def save_unicode_md5(filename):
    """Save MD5 sums for all Unicode characters to a file."""
    unicode_md5_dict = {}
    print("Calculating MD5 sums for Unicode characters. This may take some time...")
    # Iterate over all Unicode characters
    for code_point in range(0x110000):
        character = chr(code_point)  # Get Unicode character
        name = unicodedata.name(character, f"<{code_point:04X}>")  # Get character name
        md5_hash = md5sum(character)  # Calculate MD5 sum
        unicode_md5_dict[name] = md5_hash  # Store in dictionary

    # Write the dictionary to the output file with JSON-like formatting
    with open(filename, 'w', encoding='utf-8') as outfile:
        for name, md5_hash in sorted(unicode_md5_dict.items()):
            outfile.write(f'"{name}": "{md5_hash}",\n')

    print(f"\nMD5 sums for Unicode characters saved to:", filename)

if __name__ == "__main__":
    output_filename = 'sum_uni.txt'
    save_unicode_md5(output_filename)