refactor: 将核心代码迁移到 scripts 目录
- 创建 scripts/ 目录作为核心代码根目录 - 移动 core/, readers/, utils/ 到 scripts/ 下 - 移动 config.py, lyxy_document_reader.py 到 scripts/ - 移动 encoding_detection.py 到 scripts/utils/ - 更新 pyproject.toml 中的入口点路径和 pytest 配置 - 更新所有内部导入语句为 scripts.* 模块 - 更新 README.md 目录结构说明 - 更新 openspec/config.yaml 添加目录结构说明 - 删除无用的 main.py 此变更使项目结构更清晰,便于区分核心代码与测试、文档等支撑文件。
This commit is contained in:
29
scripts/readers/docx/pypandoc.py
Normal file
29
scripts/readers/docx/pypandoc.py
Normal file
@@ -0,0 +1,29 @@
|
||||
"""使用 pypandoc-binary 库解析 DOCX 文件"""
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
|
||||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 pypandoc-binary 库解析 DOCX 文件"""
|
||||
try:
|
||||
import pypandoc
|
||||
except ImportError:
|
||||
return None, "pypandoc-binary 库未安装"
|
||||
|
||||
try:
|
||||
content = pypandoc.convert_file(
|
||||
source_file=file_path,
|
||||
to="md",
|
||||
format="docx",
|
||||
outputfile=None,
|
||||
extra_args=["--wrap=none"],
|
||||
)
|
||||
except OSError as exc:
|
||||
return None, f"pypandoc-binary 缺少 Pandoc 可执行文件: {exc}"
|
||||
except RuntimeError as exc:
|
||||
return None, f"pypandoc-binary 解析失败: {exc}"
|
||||
|
||||
content = content.strip()
|
||||
if not content:
|
||||
return None, "文档为空"
|
||||
return content, None
|
||||
Reference in New Issue
Block a user