lyxy-document/scripts/config.py

"""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==2.80.0",
                "unstructured[pdf]==0.21.5",
                "markitdown[pdf]==0.1.5",
                "pypdf==6.9.0",
                "markdownify==1.2.2"
            ]
        },
        "Darwin-x86_64": {
            "python": "3.12",
            "dependencies": [
                "docling==2.40.0",
                "docling-parse==4.0.0",
                "numpy<2",
                "markitdown[pdf]==0.1.5",
                "pypdf==6.9.0",
                "markdownify==1.2.2"
            ]
        }
    },
    "docx": {
        "default": {
            "python": None,
            "dependencies": [
                "docling==2.80.0",
                "unstructured[docx]==0.21.5",
                "markitdown[docx]==0.1.5",
                "pypandoc-binary==1.17",
                "python-docx==1.2.0",
                "markdownify==1.2.2"
            ]
        },
        "Darwin-x86_64": {
            "python": "3.12",
            "dependencies": [
                "docling==2.40.0",
                "docling-parse==4.0.0",
                "numpy<2",
                "markitdown[docx]==0.1.5",
                "pypandoc-binary==1.17",
                "python-docx==1.2.0",
                "markdownify==1.2.2"
            ]
        }
    },
    "xlsx": {
        "default": {
            "python": None,
            "dependencies": [
                "docling==2.80.0",
                "unstructured[xlsx]==0.21.5",
                "markitdown[xlsx]==0.1.5",
                "pandas==3.0.1",
                "tabulate==0.10.0",
                "openpyxl==3.1.5"
            ]
        },
        "Darwin-x86_64": {
            "python": "3.12",
            "dependencies": [
                "docling==2.40.0",
                "docling-parse==4.0.0",
                "numpy<2",
                "markitdown[xlsx]==0.1.5",
                "pandas<3.0.0",
                "tabulate==0.10.0",
                "openpyxl==3.1.5"
            ]
        }
    },
    "pptx": {
        "default": {
            "python": None,
            "dependencies": [
                "docling==2.80.0",
                "unstructured[pptx]==0.21.5",
                "markitdown[pptx]==0.1.5",
                "python-pptx==1.0.2",
                "markdownify==1.2.2"
            ]
        },
        "Darwin-x86_64": {
            "python": "3.12",
            "dependencies": [
                "docling==2.40.0",
                "docling-parse==4.0.0",
                "numpy<2",
                "markitdown[pptx]==0.1.5",
                "python-pptx==1.0.2",
                "markdownify==1.2.2"
            ]
        }
    },
    "html": {
        "default": {
            "python": None,
            "dependencies": [
                "trafilatura==2.0.0",
                "domscribe==0.1.3",
                "markitdown==0.1.5",
                "html2text==2025.4.15",
                "beautifulsoup4==4.14.3",
                "httpx==0.28.1",
                "chardet==7.1.0",
                "pyppeteer==2.0.0",
                "selenium==4.25.0"
            ]
        },
        "Darwin-x86_64": {
            "python": "3.12",
            "dependencies": [
                "trafilatura==2.0.0",
                "domscribe==0.1.3",
                "markitdown==0.1.5",
                "html2text==2025.4.15",
                "beautifulsoup4==4.14.3",
                "httpx==0.28.1",
                "chardet==7.1.0",
                "pyppeteer==2.0.0",
                "selenium==4.25.0"
            ]
        }
    },
    "xls": {
        "default": {
            "python": None,
            "dependencies": [
                "unstructured[xlsx]==0.21.5",
                "markitdown[xls]==0.1.5",
                "pandas==3.0.1",
                "tabulate==0.10.0",
                "xlrd==2.0.2",
                "olefile==0.47"
            ]
        },
        "Darwin-x86_64": {
            "python": "3.12",
            "dependencies": [
                "markitdown[xls]==0.1.5",
                "pandas<3.0.0",
                "tabulate==0.10.0",
                "xlrd==2.0.2",
                "olefile==0.47",
                "openpyxl==3.1.5"
            ]
        }
    },
    "doc": {
        "default": {
            "python": None,
            "dependencies": []
        }
    },
    "ppt": {
        "default": {
            "python": None,
            "dependencies": [
                "docling==2.80.0",
                "unstructured[pptx]==0.21.5",
                "markitdown[pptx]==0.1.5",
                "python-pptx==1.0.2",
                "markdownify==1.2.2",
                "olefile==0.47"
            ]
        },
        "Darwin-x86_64": {
            "python": "3.12",
            "dependencies": [
                "docling==2.40.0",
                "docling-parse==4.0.0",
                "numpy<2",
                "markitdown[pptx]==0.1.5",
                "python-pptx==1.0.2",
                "markdownify==1.2.2",
                "olefile==0.47"
            ]
        }
    }
}