dict.py 文件源码

def load(self, filename):
        """Load pre-existing dictionary in 'token[<TAB>count]' format.
        Initialize counts from other dictionary, or 0 if they aren't included.
        """
        print('Dictionary: loading dictionary from {}'.format(
              filename))
        with open(filename) as read:
            for line in read:
                split = line.strip().split('\t')
                token = unescape(split[0])
                cnt = int(split[1]) if len(split) > 1 else 0
                self.freq[token] = cnt
                if token not in self.tok2ind:
                    index = len(self.tok2ind)
                    self.tok2ind[token] = index
                    self.ind2tok[index] = token
        print('[ num words =  %d ]' % len(self))