fix: add additional continuation markers for improved table merging

This commit is contained in:
myhloli
2025-12-31 16:57:00 +08:00
parent 190b4ea472
commit 1cde3fe5ad

View File

@@ -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.)",
"(contd)",
]
def calculate_table_total_columns(soup):