Class CopyrightDetector

src/cluecode/copyrights.py:231–392

Detect copyrights and authors.

class CopyrightDetector(object):
    """
    Detect copyrights and authors.
    """

    def __init__(self):
        """
        Initialize this detector with a lexer and a parser.
        """
        self.lexer = lex.Lexer(matchers=PATTERNS)
        self.parser = parse.Parser(
            grammar=GRAMMAR,
            loop=1,
            trace=TRACE_DEEP,
            validate=VALIDATE,
        )

    def detect(self,
        numbered_lines,
        include_copyrights=True,
        include_holders=True,
        include_authors=True,
        include_copyright_years=True,
        include_copyright_allrights=False,
    ):
        """
        Yield Detection objects detected in a ``numbered_lines`` sequence of
        tuples of (line number, text).

        The flags ``include_copyrights``, ``include_holders`` and
        ``include_authors`` drive which actual detections are done and returned.

        For copyrights only:
        - If ``include_copyright_years`` is True, include years and year ranges.
        - If ``include_copyright_allrights`` is True, include trailing
          "all rights reserved"-style mentions
        """

        include_copyright_years = include_copyrights and include_copyright_years
        include_copyright_allrights = include_copyrights and include_copyright_allrights

        if not numbered_lines:
            return

        if TRACE or TRACE_TOK:
            logger_debug(f'CopyrightDetector: numbered_lines: {numbered_lines}')

        tokens = list(get_tokens(numbered_lines))

        if TRACE:
            logger_debug(f'CopyrightDetector: initial tokens: {tokens}')

        if not tokens:
            return

        # first, POS tag each token using token regexes
        lexed_text = list(self.lexer.lex_tokens(tokens, trace=TRACE_TOK))