feat: 新增 PPT 旧格式支持,重构 LibreOffice 转换工具
- 新增 PPT (旧格式) 解析器 - 重构 _utils.py,提取通用 convert_via_libreoffice 函数 - 更新依赖配置,添加 PPT 相关依赖 - 完善文档,更新 README 和 SKILL.md - 添加 PPT 文件检测函数 - 新增 PPT 解析器测试用例
This commit is contained in:
46
scripts/readers/ppt/__init__.py
Normal file
46
scripts/readers/ppt/__init__.py
Normal file
@@ -0,0 +1,46 @@
|
||||
"""PPT 文件阅读器,使用 LibreOffice 解析。"""
|
||||
|
||||
import os
|
||||
from typing import List, Optional, Tuple
|
||||
|
||||
from readers.base import BaseReader
|
||||
from utils import is_valid_ppt
|
||||
|
||||
from . import libreoffice
|
||||
|
||||
|
||||
PARSERS = [
|
||||
("LibreOffice", libreoffice.parse),
|
||||
]
|
||||
|
||||
|
||||
class PptReader(BaseReader):
|
||||
"""PPT 文件阅读器"""
|
||||
|
||||
def supports(self, file_path: str) -> bool:
|
||||
return file_path.lower().endswith('.ppt')
|
||||
|
||||
def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
|
||||
failures = []
|
||||
|
||||
# 检查文件是否存在
|
||||
if not os.path.exists(file_path):
|
||||
return None, ["文件不存在"]
|
||||
|
||||
# 验证文件格式
|
||||
if not is_valid_ppt(file_path):
|
||||
return None, ["不是有效的 PPT 文件"]
|
||||
|
||||
content = None
|
||||
|
||||
for parser_name, parser_func in PARSERS:
|
||||
try:
|
||||
content, error = parser_func(file_path)
|
||||
if content is not None:
|
||||
return content, failures
|
||||
else:
|
||||
failures.append(f"- {parser_name}: {error}")
|
||||
except Exception as e:
|
||||
failures.append(f"- {parser_name}: [意外异常] {type(e).__name__}: {str(e)}")
|
||||
|
||||
return None, failures
|
||||
Reference in New Issue
Block a user