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: update continuation markers to be case-insensitive in table merging logic

Browse Source
This commit is contained in:
myhloli
2025-12-12 16:55:37 +08:00
parent 8d1866ab9f
commit 7810f5ef83
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
mineru/utils/table_merge.py
View File

@@ -7,7 +7,7 @@ from mineru.backend.vlm.vlm_middle_json_mkcontent import merge_para_with_text
from mineru.utils.enum_class import BlockType, SplitFlag
continuation_markers = ["(续)", "(续表)", "(continued)", "(cont.)"]
CONTINUATION_MARKERS = ["(续)", "(续表)", "(continued)", "(cont.)"]
def full_to_half(text: str) -> str:
@@ -180,8 +180,8 @@ def can_merge_tables(current_table_block, previous_table_block):
# 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)
for marker in continuation_markers)
any(full_to_half(merge_para_with_text(block).strip()).lower().endswith(marker.lower())
for marker in CONTINUATION_MARKERS)
for block in caption_blocks
):
return False, None, None, None, None