reader.py 文件源码

def read_texts(path: str, source_type: FileType) -> Iterator[str]:
        """
        ?????????? ???????.

        :param path: ???? ? ?????/?????.
        :param source_type: ??? ??????.
        """
        paths = Reader.get_paths(path, source_type.value)
        for filename in paths:
            with open(filename, "r", encoding="utf-8") as file:
                if source_type == FileType.XML:
                    for elem in Reader.__xml_iter(file, 'item'):
                        yield elem.find(".//text").text
                elif source_type == FileType.JSON:
                    # TODO: ??????? ???????
                    j = json.load(file)
                    for item in j['items']:
                        yield item['text']
                elif source_type == FileType.RAW:
                    text = file.read()
                    for t in text.split(RAW_SEPARATOR):
                        yield t