lanyuanxiaoyao
9daff73589
- 更新 openspec/config.yaml 中 git 任务相关说明 - 将 scripts.core.* 改为 core.*，scripts.readers.* 改为 readers.* - 优化 lyxy_document_reader.py 中 sys.path 设置方式 - 同步更新所有测试文件的导入路径
23 lines
751 B
Python
23 lines
751 B
Python
"""使用 unstructured 库解析 DOCX 文件"""
|
|
|
|
from typing import Optional, Tuple
|
|
|
|
from readers._utils import convert_unstructured_to_markdown
|
|
|
|
|
|
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
|
"""使用 unstructured 库解析 DOCX 文件"""
|
|
try:
|
|
from unstructured.partition.docx import partition_docx
|
|
except ImportError:
|
|
return None, "unstructured 库未安装"
|
|
|
|
try:
|
|
elements = partition_docx(filename=file_path, infer_table_structure=True)
|
|
content = convert_unstructured_to_markdown(elements)
|
|
if not content.strip():
|
|
return None, "文档为空"
|
|
return content, None
|
|
except Exception as e:
|
|
return None, f"unstructured 解析失败: {str(e)}"
|