Unverified Commit d95f5452 authored by myhloli's avatar myhloli Committed by GitHub

Merge pull request #50 from myhloli/master

统一使用ocr组装markdown
parents f6d8f6ca 1340a97a
......@@ -106,8 +106,9 @@ class AbsPipe(ABC):
parse_type = pdf_mid_data["_parse_type"]
pdf_info_list = pdf_mid_data["pdf_info"]
if parse_type == AbsPipe.PIP_TXT:
content_list = mk_universal_format(pdf_info_list, img_buket_path)
md_content = mk_mm_markdown(content_list)
# content_list = mk_universal_format(pdf_info_list, img_buket_path)
# md_content = mk_mm_markdown(content_list)
md_content = ocr_mk_mm_markdown_with_para(pdf_info_list, img_buket_path)
elif parse_type == AbsPipe.PIP_OCR:
md_content = ocr_mk_mm_markdown_with_para(pdf_info_list, img_buket_path)
return md_content
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment