Count muqattaʿat letters in Quran chapters

import json
from collections import Counter

from pyarabic import araby
from pyarabic.araby import strip_diacritics

quran = json.load(open('quran.json'))


def normalize_arabic(text):
    # Normalize the text by reducing different forms of Alif and other characters
    text = araby.strip_tashkeel(text)  # Remove diacritics
    text = araby.strip_tatweel(text)  # Remove Tatweel (kashida)
    text = araby.strip_diacritics(text)
    # Replace specific characters to their simpler forms
    replacements = {
        'آ': 'ا',
        'أ': 'ا',
        'إ': 'ا',
        'ٱ': 'ا',
        'ى': 'ي',
        'ة': 'ه',
        'ئ': 'ي',
        'ؤ': 'و',
    }
    for k, v in replacements.items():
        text = text.replace(k, v)

    return text


for chapter in quran:

    if len(normalize_arabic(chapter['verses'][0]['text'])) > 8:
        continue
    print(chapter['name'], chapter['verses'][0]['text'])
    whole = normalize_arabic(''.join(verse['text'] for verse in chapter['verses']))
    count = Counter(whole)
    del count[' ']
    sorted_chars = sorted(count.items(), key=lambda item: item[1], reverse=True)
    for char, freq in sorted_chars[:5]:
        print(f'Character: {char}, ord: {ord(char)}, Count: {freq}')

Download Quran from: https://cdn.jsdelivr.net/npm/[email protected]/dist/quran.json

This was a try to see if رشاد خلیفه was right.