lanyuanxiaoyao
aaa1171e60
- 新增 scripts/core/advice_generator.py 建议生成器模块 - 在 config.py 中添加 DEPENDENCIES 依赖配置 - 在 lyxy_document_reader.py 中添加 -a/--advice 参数 - 复用 Reader 实例的 supports 方法检测文件类型 - 支持平台检测，对 macOS x86_64 PDF 返回特殊命令 - 添加单元测试和集成测试 - 更新 SKILL.md，引导优先使用 --advice 参数 - 更新 README.md，添加项目结构说明 - 添加 openspec/specs/cli-advice/spec.md 规范文档
107 lines
2.6 KiB
Python
107 lines
2.6 KiB
Python
"""统一配置类，集中管理所有配置项。"""
|
||
|
||
|
||
class Config:
|
||
"""统一配置类"""
|
||
|
||
# 编码检测
|
||
# 回退编码列表，当 chardet 检测失败时依次尝试
|
||
FALLBACK_ENCODINGS = ['utf-8', 'gbk', 'gb2312', 'latin-1']
|
||
|
||
# HTML 下载
|
||
# 下载超时时间（秒）
|
||
DOWNLOAD_TIMEOUT = 30
|
||
# HTTP User-Agent 标识
|
||
USER_AGENT = "lyxy-document/0.1.0"
|
||
|
||
# 日志
|
||
# 日志等级，默认只输出 ERROR 级别避免干扰 Markdown 输出
|
||
LOG_LEVEL = "ERROR"
|
||
|
||
|
||
# 依赖配置：按文件类型和平台组织
|
||
# 每个平台配置包含 python 版本要求（None 表示使用默认）和依赖列表
|
||
DEPENDENCIES = {
|
||
"pdf": {
|
||
"default": {
|
||
"python": None,
|
||
"dependencies": [
|
||
"docling",
|
||
"unstructured[pdf]",
|
||
"markitdown[pdf]",
|
||
"pypdf",
|
||
"markdownify",
|
||
"chardet"
|
||
]
|
||
},
|
||
"Darwin-x86_64": {
|
||
"python": "3.12",
|
||
"dependencies": [
|
||
"docling==2.40.0",
|
||
"docling-parse==4.0.0",
|
||
"numpy<2",
|
||
"markitdown[pdf]",
|
||
"pypdf",
|
||
"markdownify",
|
||
"chardet"
|
||
]
|
||
}
|
||
},
|
||
"docx": {
|
||
"default": {
|
||
"python": None,
|
||
"dependencies": [
|
||
"docling",
|
||
"unstructured[docx]",
|
||
"markitdown[docx]",
|
||
"pypandoc-binary",
|
||
"python-docx",
|
||
"markdownify",
|
||
"chardet"
|
||
]
|
||
}
|
||
},
|
||
"xlsx": {
|
||
"default": {
|
||
"python": None,
|
||
"dependencies": [
|
||
"docling",
|
||
"unstructured[xlsx]",
|
||
"markitdown[xlsx]",
|
||
"pandas",
|
||
"tabulate",
|
||
"chardet"
|
||
]
|
||
}
|
||
},
|
||
"pptx": {
|
||
"default": {
|
||
"python": None,
|
||
"dependencies": [
|
||
"docling",
|
||
"unstructured[pptx]",
|
||
"markitdown[pptx]",
|
||
"python-pptx",
|
||
"markdownify",
|
||
"chardet"
|
||
]
|
||
}
|
||
},
|
||
"html": {
|
||
"default": {
|
||
"python": None,
|
||
"dependencies": [
|
||
"trafilatura",
|
||
"domscribe",
|
||
"markitdown",
|
||
"html2text",
|
||
"beautifulsoup4",
|
||
"httpx",
|
||
"chardet",
|
||
"pyppeteer",
|
||
"selenium"
|
||
]
|
||
}
|
||
}
|
||
}
|