From 18e65be489fedde6486d51aa418ff6bde75c88a6 Mon Sep 17 00:00:00 2001 From: drunkpig Date: Mon, 2 Sep 2024 17:17:44 +0800 Subject: [PATCH] fix: delete hyphen at end of line --- magic_pdf/dict2md/ocr_mkcontent.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/magic_pdf/dict2md/ocr_mkcontent.py b/magic_pdf/dict2md/ocr_mkcontent.py index f0f8584b..dc6b025f 100644 --- a/magic_pdf/dict2md/ocr_mkcontent.py +++ b/magic_pdf/dict2md/ocr_mkcontent.py @@ -205,8 +205,8 @@ def merge_para_with_text(para_block): para_text += content # 中文/日语/韩文语境下,content间不需要空格分隔 elif line_lang == 'en': # 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(para_text): - para_text += content + if __is_hyphen_at_line_end(content): + para_text += content[:-1] else: para_text += content + ' ' else: