lanyuanxiaoyao
15b63800a8
- 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。
74 lines
2.2 KiB
Python
74 lines
2.2 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_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_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://")
|
||
|
||
|
||
_FILE_TYPE_VALIDATORS = {
|
||
".docx": is_valid_docx,
|
||
".pptx": is_valid_pptx,
|
||
".xlsx": is_valid_xlsx,
|
||
".pdf": is_valid_pdf,
|
||
}
|
||
|
||
|
||
def detect_file_type(file_path: str) -> Optional[str]:
|
||
"""检测文件类型，返回 'docx'、'pptx'、'xlsx' 或 'pdf'"""
|
||
ext = os.path.splitext(file_path)[1].lower()
|
||
validator = _FILE_TYPE_VALIDATORS.get(ext)
|
||
if validator and validator(file_path):
|
||
return ext.lstrip(".")
|
||
return None
|