ASR/dictionary/dictionary_to_rows.py

def process_file(input_file, output_file):
    unique_terms = set()

    # Read the input file and collect unique terms
    with open(input_file, 'r', encoding='utf-8') as f:
        for line in f:
            terms = line.strip().split()
            unique_terms.update(terms)

    # Sort the unique terms alphabetically
    sorted_terms = sorted(unique_terms)

    # Write the unique terms to the output file
    with open(output_file, 'w', encoding='utf-8') as f:
        for term in sorted_terms:
            f.write(f"{term}\n")

    print(f"Processed {len(unique_terms)} unique terms.")

# Process the file
input_file = 'dictionary_reviewed.txt'  # Replace with your input file name
output_file = 'dictionary_reviewed_rows.txt'

process_file(input_file, output_file)