centersl/MinerU
1
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-03-27 11:08:32 +07:00
Code Issues Packages Projects Releases Wiki Activity

fix: refine caption merging logic to improve handling of continuation markers

Browse Source
This commit is contained in:
myhloli
2026-01-07 20:05:26 +08:00
parent c73e93bec0
commit 9e6e2bde85
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
mineru/utils/table_merge.py
View File

@@ -170,7 +170,7 @@ def can_merge_tables(current_table_block, previous_table_block):
if caption_blocks:
# 如果所有caption都不以"(续)"、"(续表)"、"(continued)"或"(cont.)"结尾,则不合并
if not any(
any(full_to_half(merge_para_with_text(block).strip()).lower().endswith(marker.lower())
any(marker.lower() in full_to_half(merge_para_with_text(block).strip()).lower()
for marker in CONTINUATION_MARKERS)
for block in caption_blocks
):