analyse.py 文件源码

def similarities(self):
        """
        Compute Levenshtein distance matrix between files (implemented in C++ pip package: editdistance)
        Later: https://docs.python.org/2/library/difflib.html
        :return:
        """

        ucos = sorted(self.filedb.keys())
        sims = {}

        for idx, uco in enumerate(ucos):
            logger.info('Comparing %s...' % uco)
            sims[uco] = {}

            for idx2, uco2 in enumerate(ucos[idx+1:]):
                dist = editdistance.eval(self.file_data[uco], self.file_data[uco2])
                sims[uco][uco2] = dist
                logger.info(' %6d vs %6d : %4d  %s  %s' % (uco, uco2, dist, self.filedb[uco], self.filedb[uco2]))