From ec7271faee9f175507ccdbcfcd2f081836fbdc97 Mon Sep 17 00:00:00 2001 From: liukaiwen Date: Mon, 5 Aug 2024 16:54:35 +0800 Subject: [PATCH] fix table recognition bug#321 --- magic_pdf/dict2md/ocr_mkcontent.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/magic_pdf/dict2md/ocr_mkcontent.py b/magic_pdf/dict2md/ocr_mkcontent.py index 2195f7c5..0cc887ce 100644 --- a/magic_pdf/dict2md/ocr_mkcontent.py +++ b/magic_pdf/dict2md/ocr_mkcontent.py @@ -255,7 +255,7 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx): for block in para_block['blocks']: if block['type'] == BlockType.TableBody: 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']) if block['type'] == BlockType.TableCaption: para_content['table_caption'] = merge_para_with_text(block)