Skip to content

GitLab

Commit ec7271fa authored by liukaiwen's avatar liukaiwen
Browse files

fix table recognition bug#321

parent b8adb630
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
magic_pdf/dict2md/ocr_mkcontent.py
View file @ ec7271fa
...@@ -255,7 +255,7 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx): ...@@ -255,7 +255,7 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx):
for block in para_block['blocks']: for block in para_block['blocks']:
if block['type'] == BlockType.TableBody: if block['type'] == BlockType.TableBody:
if block["lines"][0]["spans"][0].get('latex', ''): if block["lines"][0]["spans"][0].get('latex', ''):
para_content['table_body'] = f"\n\n$\n {block['lines'][0]['spans'][0]['content']}\n$\n\n" para_content['table_body'] = f"\n\n$\n {block['lines'][0]['spans'][0]['latex']}\n$\n\n"
para_content['img_path'] = join_path(img_buket_path, block["lines"][0]["spans"][0]['image_path']) para_content['img_path'] = join_path(img_buket_path, block["lines"][0]["spans"][0]['image_path'])
if block['type'] == BlockType.TableCaption: if block['type'] == BlockType.TableCaption:
para_content['table_caption'] = merge_para_with_text(block) para_content['table_caption'] = merge_para_with_text(block)
......
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