ipp7_1_count_digrams

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Filename: ipp7_1_count_digrams.py
# Version: 1.0.0
# Author: Jeoi Reqi

"""
Description:
    - This script demonstrates "Chapter 3: Practice Project #1: Finding Digrams: Count Digrams" from the book "Impractical Python Projects" by Lee Vaughan.
    - Generate letter pairs in Voldemort & find their frequency in a dictionary.
    - Requires dictionary.txt (English dictionary) file in the current working directory.

Requirements:
    - Python 3.x
    - The following modules:
        - sys
        - collections

Functions:
    - main():
        Main function to generate letter pairs from Voldemort and find their frequency in a dictionary.

Usage:
    - Run the script directly in a Python 3.x environment:

            $ python ipp7_1_count_digrams.py

Additional Notes:
    - This script uses a dictionary.txt file containing English words to find the frequency of letter pairs in the name 'Voldemort'.
    - It generates unique letter pairs from the name and then counts their occurrences in the dictionary file.
"""

import sys
from collections import defaultdict

def load(file):
    """
    Open a text file & turn contents into a list of lowercase strings.

    Arguments:
        file (str): The name of the text file to open.

    Returns:
        list: A list of lowercase strings representing the contents of the file.
    """
    try:
        with open(file, encoding='utf-8') as in_file:
            loaded_txt = in_file.read().strip().split('\n')
            loaded_txt = [x.lower() for x in loaded_txt]
            return loaded_txt
    except IOError as e:
        print("{}\nError opening {}. Terminating program.".format(e, file))
        sys.exit(1)

def main():
    """
    Main function to generate letter pairs from Voldemort and find their frequency in a dictionary.
    """
    # Load dictionary
    print("Loading Dictionary...\n")
    word_list = load('dictionary.txt')

    # Define name and convert to lowercase
    name = 'Voldemort'  # (tmvoordle)
    print("Name:", name, "\n\nGathering Digrams...\n")
    name = name.lower()

    # Generate unique letter pairs from name
    digrams = {''.join(pair) for pair in zip(name, name[1:])}
    print(*sorted(digrams), sep='\n')
    print("\nNumber of Digrams = {}\n".format(len(digrams)))

    # Use regular expressions to find repeating digrams in a word
    mapped: defaultdict[str, int] = defaultdict(int)
    for word in word_list:
        word = word.lower()
        for digram in digrams:
            mapped[digram] += word.count(digram)

    print("Digram Frequency Count:\n")
    for k in sorted(mapped):
        print("{} {}".format(k, mapped[k]))
    print("")

    print("_" * 100)
    print("\nThis concludes the demonstration of \"Chapter 3: Practice Project #1: Finding Digrams: Count Digrams\"\n\n\t\t\t   Thank you for your attention...   Goodbye!")
    print("_" * 100)

if __name__ == '__main__':
    main()