From 1cde3fe5ad0a23fd4ef4a7906b7a903718311034 Mon Sep 17 00:00:00 2001 From: myhloli Date: Wed, 31 Dec 2025 16:57:00 +0800 Subject: [PATCH] fix: add additional continuation markers for improved table merging --- mineru/utils/table_merge.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mineru/utils/table_merge.py b/mineru/utils/table_merge.py index 7c59f892..b3c9e003 100644 --- a/mineru/utils/table_merge.py +++ b/mineru/utils/table_merge.py @@ -9,7 +9,14 @@ from mineru.utils.char_utils import full_to_half from mineru.utils.enum_class import BlockType, SplitFlag -CONTINUATION_MARKERS = ["(续)", "(续表)", "(continued)", "(cont.)"] +CONTINUATION_MARKERS = [ + "(续)", + "(续表)", + "(续上表)", + "(continued)", + "(cont.)", + "(cont’d)", +] def calculate_table_total_columns(soup):