6e8898b82f4591fe2256ca56be3c98836fe94b88,simhash/__init__.py,Simhash,__init__,#Simhash#Any#Any#Any#Any#,25

Before Change

            self.value = value.value
        elif isinstance(value, basestring):
            self.build_by_text(unicode(value))
        elif isinstance(value, collections.Iterable):
            self.build_by_features(value)
        elif isinstance(value, long):
            self.value = value
        else:
            raise Exception("Bad parameter with type {}".format(type(value)))

    def _slide(self, content, width=4):
        return [content[i:i + width] for i in range(max(len(content) - width + 1, 1))]

After Change

        count = len(objs)

        if log is None:
            self.log = logging.getLogger("simhash")
        else:
            self.log = log

        self.log.info("Initializing %s data.", count)

        self.bucket = collections.defaultdict(set)

        for i, q in enumerate(objs):
            if i % 10000 == 0 or i == count - 1:
                self.log.info("%s/%s", i + 1, count)

            self.add(*q)

    def get_near_dups(self, simhash):
        

Instances