Function prepare_text_line

src/cluecode/copyrights.py:4475–4654

Prepare a text ``line`` for copyright detection. Always convert line to ASCII.

(line)

def prepare_text_line(line):
    """
    Prepare a text ``line`` for copyright detection.
    Always convert line to ASCII.
    """
    if TRACE_TOK:
        logger_debug('    prepare_text_line: initial: ' + repr(line))

    # remove some junk in man pages: \(co
    line = (line
        .replace('\\\\ co', ' ')
        .replace('\\ co', ' ')
        .replace('(co ', ' ')
    )
    line = remove_printf_format_codes(' ', line)
    if TRACE_TOK:
        logger_debug('    prepare_text_line: after remove_printf_format_codes: ' + repr(line))

    # less common comment line prefixes
    line = remove_weird_comment_markers(' ', line)
    if TRACE_TOK:
        logger_debug('    prepare_text_line: after remove_weird_comment_markers: ' + repr(line))

    line = remove_man_comment_markers(' ', line)
    if TRACE_TOK:
        logger_debug('    prepare_text_line: after remove_man_comment_markers: ' + repr(line))

    line = remove_code_comment_markers(line)
    if TRACE_TOK:
        logger_debug('    prepare_text_line: after remove_code_comment_markers: ' + repr(line))

    line = (line
        # C and C++ style comment markers
        # in rst
        .replace('|copy|', ' (c) ')
        # un common pipe chars in some ascii art
        .replace('|', ' ')

        # normalize copyright signs, quotes and spacing around them
        .replace('"Copyright', '" Copyright')
        .replace('( C)', ' (c) ')
        .replace('(C)', ' (c) ')
        .replace('(c)', ' (c) ')
        .replace('( © )', ' (c) ')
        .replace('(©)', ' (c) ')
        .replace('(© )', ' (c) ')
        .replace('( ©)', ' (c) ')
        .replace('©', ' (c) ')
        # the case of \251 is tested by 'weirdencoding.h'
        .replace('\251', ' (c) ')
        .replace('©', ' (c) ')
        .replace('&copy', ' (c) ')
        .replace('©', ' (c) ')
        .replace('©', ' (c) ')
        .replace('©', ' (c) ')
        .replace('©', ' (c) ')
        .replace('©', ' (c) ')
        .replace('u00A9', ' (c) ')