From 87b9eeee59fe13a11de1f36f8bf5a6d090cd22a7 Mon Sep 17 00:00:00 2001 From: myhloli Date: Fri, 1 Nov 2024 23:35:36 +0800 Subject: [PATCH] fix(ocr): handle inline equations consistently with text content - Include InlineEquation in the condition for handling text content - Remove separate block for InlineEquation processing - Ensures consistent handling of inline equations and text, improving content formatting --- magic_pdf/dict2md/ocr_mkcontent.py | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/magic_pdf/dict2md/ocr_mkcontent.py b/magic_pdf/dict2md/ocr_mkcontent.py index 7c40668c..6f7a9647 100644 --- a/magic_pdf/dict2md/ocr_mkcontent.py +++ b/magic_pdf/dict2md/ocr_mkcontent.py @@ -153,7 +153,7 @@ def merge_para_with_text(para_block): elif span_type == ContentType.InlineEquation: para_text += f" {content} " else: - if span_type == ContentType.Text: + if span_type in [ContentType.Text, ContentType.InlineEquation]: # 如果是前一行带有-连字符,那么末尾不应该加空格 if __is_hyphen_at_line_end(content): para_text += content[:-1] @@ -161,8 +161,6 @@ def merge_para_with_text(para_block): para_text += f"{content.strip()} " elif span_type == ContentType.InterlineEquation: para_text += content - elif span_type == ContentType.InlineEquation: - para_text += f"{content} " else: continue