Method handle

apps/common/handle/impl/text/pdf_split_handle.py:50–103

(
        self,
        file,
        pattern_list: List,
        with_filter: bool,
        limit: int,
        get_buffer,
        save_image,
    )

class PdfSplitHandle(BaseSplitHandle):
    def handle(
        self,
        file,
        pattern_list: List,
        with_filter: bool,
        limit: int,
        get_buffer,
        save_image,
    ):
        with tempfile.NamedTemporaryFile(delete=False) as temp_file:
            # 将上传的文件保存到临时文件中
            for chunk in file.chunks():
                temp_file.write(chunk)
            # 获取临时文件的路径
            temp_file_path = temp_file.name

        try:
            with open(temp_file_path, "rb") as pdf_file:
                pdf_document = PdfReader(pdf_file)
                if type(limit) is str:
                    limit = int(limit)
                if type(with_filter) is str:
                    with_filter = with_filter.lower() == "true"
                # 处理有目录的pdf
                result = self.handle_toc(pdf_document, limit)
                if result is not None:
                    return {"name": file.name, "content": result}

                # 没目录但是有链接的pdf
                result = self.handle_links(
                    pdf_document, pattern_list, with_filter, limit
                )
                if result is not None and len(result) > 0:
                    return {"name": file.name, "content": result}

                # 没有目录的pdf
                content = self.handle_pdf_content(file, pdf_document)

                if pattern_list is not None and len(pattern_list) > 0:
                    split_model = SplitModel(pattern_list, with_filter, limit)
                else:
                    split_model = SplitModel(
                        default_pattern_list, with_filter=with_filter, limit=limit
                    )
        except BaseException as e:
            maxkb_logger.error(
                f"File: {file.name}, error: {e}, {traceback.format_exc()}"
            )
            return {"name": file.name, "content": []}
        finally:
            # 处理完后可以删除临时文件
            os.remove(temp_file_path)

        return {"name": file.name, "content": split_model.parse(content)}

    @staticmethod
    def handle_pdf_content(file, pdf_document):