TXTPipe.py 906 Bytes
Newer Older
kernel.h@qq.com's avatar
kernel.h@qq.com committed
1
from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
赵小蒙's avatar
赵小蒙 committed
2
3
4
5
6
7
8
from magic_pdf.libs.json_compressor import JsonCompressor
from magic_pdf.pipe.AbsPipe import AbsPipe
from magic_pdf.user_api import parse_txt_pdf


class TXTPipe(AbsPipe):

kernel.h@qq.com's avatar
kernel.h@qq.com committed
9
10
    def __init__(self, pdf_bytes: bytes, model_list: list, image_writer: AbsReaderWriter, img_parent_path: str):
        super().__init__(pdf_bytes, model_list, image_writer, img_parent_path)
赵小蒙's avatar
赵小蒙 committed
11
12
13
14
15
16
17
18

    def pipe_classify(self):
        pass

    def pipe_parse(self):
        self.pdf_mid_data = parse_txt_pdf(self.pdf_bytes, self.model_list, self.image_writer)

    def pipe_mk_uni_format(self):
kernel.h@qq.com's avatar
kernel.h@qq.com committed
19
        content_list = AbsPipe.mk_uni_format(self.get_compress_pdf_mid_data(), self.img_parent_path)
赵小蒙's avatar
赵小蒙 committed
20
21
22
        return content_list

    def pipe_mk_markdown(self):
kernel.h@qq.com's avatar
kernel.h@qq.com committed
23
        md_content = AbsPipe.mk_markdown(self.get_compress_pdf_mid_data(), self.img_parent_path)
赵小蒙's avatar
赵小蒙 committed
24
        return md_content