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

feat: refactor line object construction in DOCX processing to streamline block handling

Browse Source
This commit is contained in:
myhloli
2026-01-21 11:08:19 +08:00
parent 5026faa458
commit ee4065ffd5
1 changed files with 0 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
mineru/backend/office/office_magic_model.py
View File

@@ -117,19 +117,11 @@ class MagicModel:
else:
raise ValueError(f"Invalid span type: {span_type}, expected dict or list, got {type(span)}")
# 构造line对象
if block_type in [BlockType.CODE_BODY]:
if switch_code_to_algorithm and code_block_sub_type == "code":
code_block_sub_type = "algorithm"
line = {"bbox": block_bbox, "spans": spans, "extra": {"type": code_block_sub_type, "guess_lang": guess_lang}}
else:
line = {"bbox": block_bbox, "spans": spans}
blocks.append(
{
"bbox": block_bbox,
"type": block_type,
"angle": block_angle,
"lines": [line],
"index": index,
}