Syllables at the end of a line in VMS

[bi3mw]

why not use Sukhotin's algorithm or some other algorithm to detect vowels?

Is the code correct ?

Code:

#!/usr/bin/env python from collections import defaultdict from operator import itemgetter import re import sys def classify_chars(text):     if not text:         return set(), set()     text = f"{text}{text[0]}"     matrix = defaultdict(int)     row_sums = defaultdict(int)     consonants = set()     vowels = set()     for first, second in zip(text, text[1:]):         consonants.add(first)         if first != second:             matrix[first, second] += 1             matrix[second, first] += 1             row_sums[first] += 1             row_sums[second] += 1     while any(row_sum > 0 for row_sum in row_sums.values()):         vowel = max(row_sums.items(), key=itemgetter(1))[0]         vowels.add(vowel)         consonants -= vowels         for consonant in consonants:             frequency = matrix.get((consonant, vowel), 0)             row_sums[consonant] -= 2 * frequency         row_sums = {key: value for key, value in row_sums.items() if key not in vowels}     return vowels, consonants def sukhotin_syllabification(text):     vowels, consonants = classify_chars(text)     syllables = []     current_syllable = ""     for char in text:         current_syllable += char         if char in consonants:             syllables.append(current_syllable)             current_syllable = ""     return syllables def calculate_syllable_statistics(text):     total_letters = len(re.sub(r'[^\w\s]', '', text))  # Count letters and spaces     total_syllables = len(sukhotin_syllabification(text))       lines = text.split('\n')     last_word_syllables = 0     total_lines = len(lines)     for line in lines:         words = line.split()         if words:             last_word = words[-1]             last_word_syllables += len(sukhotin_syllabification(last_word))     total_words = sum(len(line.split()) for line in lines)     average_syllables_per_word = total_syllables / total_words if total_words > 0 else 0     average_syllables_per_line = last_word_syllables / total_lines if total_lines > 0 else 0     # Calculate the percentage using the rule of three     syllable_percentage = (total_syllables * 100) / total_letters     return total_syllables, total_letters, syllable_percentage, average_syllables_per_word, last_word_syllables, average_syllables_per_line def detect_syllables_in_file(filename):     try:         with open(filename, 'r', encoding='utf-8') as file:             text = file.read()             total_syllables, total_letters, syllable_percentage, average_syllables_per_word, last_word_syllables, average_syllables_per_line = calculate_syllable_statistics(text)             return total_syllables, total_letters, syllable_percentage, average_syllables_per_word, last_word_syllables, average_syllables_per_line     except FileNotFoundError:         print(f"Error: File '{filename}' not found.")         return None, None, None, None, None, None if __name__ == "__main__":     if len(sys.argv) != 2:         print("Usage: python syllable_detection.py <text_file>")     else:         filename = sys.argv[1]         total_syllables, total_letters, syllable_percentage, average_syllables_per_word, last_word_syllables, average_syllables_per_line = detect_syllables_in_file(filename)         if total_syllables is not None and total_letters is not None and syllable_percentage is not None and average_syllables_per_word is not None and last_word_syllables is not None and average_syllables_per_line is not None:             print(f"Total letters and spaces: {total_letters}")             print(f"Total syllables: {total_syllables}")             print(f"Syllable percentage: {syllable_percentage:.9f}%")             print(f"Average syllables per word: {average_syllables_per_word:.9f}")             print(f"Total syllables in last words of lines: {last_word_syllables}")             print(f"Average syllables per line ( last words ): {average_syllables_per_line:.9f}")