nltk.cli

@click.group(context_settings=CONTEXT_SETTINGS)
@click.version_option()
def cli(): (source) ¶

@cli.command('tokenize')
@click.option('--language', '-l', default='en', help='The language for the Punkt sentence tokenization.')
@click.option('--preserve-line', '-l', default=True, is_flag=True, help='An option to keep the preserve the sentence and not sentence tokenize it.')
@click.option('--processes', '-j', default=1, help='No. of processes.')
@click.option('--encoding', '-e', default='utf8', help='Specify encoding of file.')
@click.option('--delimiter', '-d', default=' ', help='Specify delimiter to join the tokens.')
def tokenize_file(language, preserve_line, processes, encoding, delimiter): (source) ¶