Method parse

ddparser/run.py:341–411

预测未切词的句子。 Args: x: list(str) | str, 未分词的句子，类型为str或list Returns: outputs: list, 依存分析结果 Example: >>> ddp = DDParser() >>> inputs = "百度是一家高科技公司" >>> ddp.parse(inputs) [{'word': ['百度', '是', '一家', '高科技', '公司'], 'h

(self, inputs)

            self.args.batch_size = 50

    def parse(self, inputs):
        """
        预测未切词的句子。

        Args:
            x: list(str) | str, 未分词的句子，类型为str或list

        Returns:
            outputs: list, 依存分析结果

        Example:
        >>> ddp = DDParser()
        >>> inputs = "百度是一家高科技公司"
        >>> ddp.parse(inputs)
        [{'word': ['百度', '是', '一家', '高科技', '公司'], 'head': [2, 0, 5, 5, 2], 'deprel': ['SBV', 'HED', 'ATT', 'ATT', 'VOB']}]

        >>> inputs = ["百度是一家高科技公司", "他送了一本书"]
        >>> ddp.parse(inputs)
        [{'word': ['百度', '是', '一家', '高科技', '公司'], 'head': [2, 0, 5, 5, 2], 'deprel': ['SBV', 'HED', 'ATT', 'ATT', 'VOB']},
         {'word': ['他', '送', '了', '一本', '书'], 'head': [2, 0, 2, 5, 2], 'deprel': ['SBV', 'HED', 'MT', 'ATT', 'VOB']}]

        >>> ddp = DDParser(prob=True, use_pos=True)
        >>> inputs = "百度是一家高科技公司"
        >>> ddp.parse(inputs)
        [{'word': ['百度', '是', '一家', '高科技', '公司'], 'postag': ['ORG', 'v', 'm', 'n', 'n'],
        'head': [2, 0, 5, 5, 2], 'deprel': ['SBV', 'HED', 'ATT', 'ATT', 'VOB'], 'prob': [1.0, 1.0, 1.0, 1.0, 1.0]}]
        """
        if not self.lac:
            self.lac = LAC.LAC(mode="lac" if self.use_pos else "seg", use_cuda=self.args.use_cuda)
        if not inputs:
            return
        if isinstance(inputs, six.string_types):
            inputs = [inputs]
        if all([isinstance(i, six.string_types) and i for i in inputs]):
            lac_results = []
            position = 0
            try:
                inputs = [query if isinstance(query, six.text_type) else query.decode("utf-8") for query in inputs]
            except UnicodeDecodeError:
                logging.warning("encoding only supports UTF-8!")
                return

            while position < len(inputs):
                lac_results += self.lac.run(inputs[position:position + self.args.batch_size])
                position += self.args.batch_size
            predicts = Corpus.load_lac_results(lac_results, self.env.fields)
        else:
            logging.warning("please check the foramt of your inputs.")
            return
        dataset = TextDataset(predicts, [self.env.WORD, self.env.FEAT], self.args.buckets)
        # set the data loader

        dataset.loader = batchify(
            dataset,
            self.args.batch_size,
            use_multiprocess=False,
            sequential_sampler=True if not self.args.buckets else False,
        )