lanyuanxiaoyao
a490b2642c
- 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
85 lines
2.5 KiB
Python
85 lines
2.5 KiB
Python
"""文件类型检测模块，用于验证和检测输入文件类型。"""
|
||
|
||
import os
|
||
import zipfile
|
||
from typing import List, Optional
|
||
|
||
|
||
def _is_valid_ole(file_path: str) -> bool:
|
||
"""验证 OLE2 格式文件（XLS/DOC）"""
|
||
try:
|
||
import olefile
|
||
except ImportError:
|
||
# 如果 olefile 未安装，就不做严格验证
|
||
return True
|
||
try:
|
||
return olefile.isOleFile(file_path)
|
||
except Exception:
|
||
return False
|
||
|
||
|
||
def _is_valid_ooxml(file_path: str, required_files: List[str]) -> bool:
|
||
"""验证 OOXML 格式文件（DOCX/PPTX/XLSX）"""
|
||
try:
|
||
with zipfile.ZipFile(file_path, "r") as zip_file:
|
||
names = set(zip_file.namelist())
|
||
return all(r in names for r in required_files)
|
||
except (zipfile.BadZipFile, zipfile.LargeZipFile):
|
||
return False
|
||
|
||
|
||
_DOCX_REQUIRED = ["[Content_Types].xml", "_rels/.rels", "word/document.xml"]
|
||
_PPTX_REQUIRED = ["[Content_Types].xml", "_rels/.rels", "ppt/presentation.xml"]
|
||
_XLSX_REQUIRED = ["[Content_Types].xml", "_rels/.rels", "xl/workbook.xml"]
|
||
|
||
|
||
def is_valid_docx(file_path: str) -> bool:
|
||
"""验证文件是否为有效的 DOCX 格式"""
|
||
return _is_valid_ooxml(file_path, _DOCX_REQUIRED)
|
||
|
||
|
||
def is_valid_pptx(file_path: str) -> bool:
|
||
"""验证文件是否为有效的 PPTX 格式"""
|
||
return _is_valid_ooxml(file_path, _PPTX_REQUIRED)
|
||
|
||
|
||
def is_valid_xlsx(file_path: str) -> bool:
|
||
"""验证文件是否为有效的 XLSX 格式"""
|
||
return _is_valid_ooxml(file_path, _XLSX_REQUIRED)
|
||
|
||
|
||
def is_valid_xls(file_path: str) -> bool:
|
||
"""验证文件是否为有效的 XLS 格式"""
|
||
return _is_valid_ole(file_path)
|
||
|
||
|
||
def is_valid_doc(file_path: str) -> bool:
|
||
"""验证文件是否为有效的 DOC 格式（OLE2）"""
|
||
return _is_valid_ole(file_path)
|
||
|
||
|
||
def is_valid_ppt(file_path: str) -> bool:
|
||
"""验证文件是否为有效的 PPT 格式（OLE2）"""
|
||
return _is_valid_ole(file_path)
|
||
|
||
|
||
def is_valid_pdf(file_path: str) -> bool:
|
||
"""验证文件是否为有效的 PDF 格式"""
|
||
try:
|
||
with open(file_path, "rb") as f:
|
||
header = f.read(4)
|
||
return header == b"%PDF"
|
||
except (IOError, OSError):
|
||
return False
|
||
|
||
|
||
def is_html_file(file_path: str) -> bool:
|
||
"""判断文件是否为 HTML 文件（仅检查扩展名）"""
|
||
ext = file_path.lower()
|
||
return ext.endswith(".html") or ext.endswith(".htm")
|
||
|
||
|
||
def is_url(input_str: str) -> bool:
|
||
"""判断输入是否为 URL"""
|
||
return input_str.startswith("http://") or input_str.startswith("https://")
|