data.py 文件源码

def tokenize(self, path):
        """Tokenizes a text file."""
        assert os.path.exists(path)
        # Add words to the dictionary
        with open(path, 'r') as f:
            tokens = 0
            for line in f:
                words = line.split() + ['<eos>']
                tokens += len(words)
                for word in words:
                    self.dictionary.add_word(word)

        # Tokenize file content
        with open(path, 'r') as f:
            ids = torch.LongTensor(tokens)
            token = 0
            for line in f:
                words = line.split() + ['<eos>']
                for word in words:
                    ids[token] = self.dictionary.word2idx[word]
                    token += 1

        return ids