process_proverbs.py

import re

def process_proverbs(input_path, output_path):
    try:
        # Attempt to open the input file and read lines
        with open(input_path, 'r', encoding='utf-8') as file:
            lines = file.readlines()
        print("Successfully read the input file.")
    except FileNotFoundError:
        print(f"File not found: {input_path}")
        return

    proverbs = []
    current_proverb = ""
    
    for line in lines:
        # Clean the line by stripping leading/trailing whitespace
        line = line.strip()
        print(f"Processing line: {line}")  # Debug output for each line

        # Identify proverbs or meanings based on specific patterns, e.g., numbers at the start
        if re.match(r'^\d+', line):  # This line has a number, possibly a new entry
            if current_proverb:
                # Save the accumulated proverb/meaning pair
                proverbs.append(current_proverb.strip())
            current_proverb = line
        else:
            # Continue accumulating lines for the current entry
            current_proverb += " " + line

    # Save any remaining proverb
    if current_proverb:
        proverbs.append(current_proverb.strip())

    # Write formatted proverbs to the output file
    try:
        with open(output_path, 'w', encoding='utf-8') as f:
            for entry in proverbs:
                f.write(entry + '\n')
                print(f"Writing line to file: {entry}")  # Debug print for each line written
        print(f"Data successfully saved to {output_path}")
    except Exception as e:
        print(f"Error writing to file: {e}")

# Example usage
input_path = "iraqi_proverbs.txt"  # Replace with the path to your text file
output_path = "data/raw_data/iraqi_data.txt"  # Adjust this path if necessary
process_proverbs(input_path, output_path)