corpusbuilder.py 文件源码

def process_file(self, file_name):
        data = self.read_file(file_name, self.encoding)
        data = self.preprocess_data(data)
        try:
            stream = IO_Stream(bytearray("\n".join(data), encoding="utf-8"))
            self.tree = ET.iterparse(stream)
            if self._strip_namespace:
                for _, element in self.tree:
                    element.tag = element.tag.rpartition("}")[-1]
        except Exception as e:
            print(self._current_file)
            print_error_context(str(e), "\n".join(data).split("\n"))
            raise e
        self.process_tree(self.tree)