Commit 056aed86 authored by kernel.h@qq.com's avatar kernel.h@qq.com
Browse files

制作OCR markdown

parent ef5d9137
......@@ -72,7 +72,7 @@ def ocr_mk_mm_markdown_with_para(pdf_info_dict: dict):
para_text += f" ${span['content']}$ "
elif span_type == ContentType.InterlineEquation:
para_text += f"$$\n{span['content']}\n$$ "
elif span_type == ContentType.Image:
elif span_type in [ ContentType.Image, ContentType.Table ]:
para_text += f"![]({join_path(s3_image_save_path, span['image_path'])})"
markdown.append(para_text)
......
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