matcher.py 文件源码

def get_initial_matches(self):
        """
        This does the main work of finding matching n-gram sequences between
        the texts.
        """
        sequence = SequenceMatcher(None,self.textAgrams,self.textBgrams)
        matchingBlocks = sequence.get_matching_blocks()

        # Only return the matching sequences that are higher than the
        # threshold given by the user.
        highMatchingBlocks = [match for match in matchingBlocks if match.size > self.threshold]

        numBlocks = len(highMatchingBlocks)

        if numBlocks > 0:
            print('%s total matches found.' % numBlocks, flush=True)

        return highMatchingBlocks