def textsegmentation(): | |
# Read the contract text from the file | |
with open(contract_file_path, 'r') as file: | |
contract_text = file.read() | |
# Tokenize the contract text into sentences | |
sentences = nltk.sent_tokenize(contract_text) | |
# Prepare data for CSV | |
data = [(i+1, sentence) for i, sentence in enumerate(sentences)] | |
# Write the data to CSV file | |
with open(output_csv_file, 'w', newline='', encoding='utf-8') as file: | |
writer = csv.writer(file) | |
writer.writerow(['Sentence ID', 'Sentence Text']) # Write header | |
writer.writerows(data) | |
print("Output saved to CSV file.") |