Metadata-Version: 2.4
Name: dhcckb-classical-collation
Version: 0.1.0
Summary: 古典文献异文自动校验与分析 MCP Server — 多版本文本对齐、六类理据分类、标准化校勘记生成
Author: Digital Humanities Platform
License: MIT
Keywords: classical-chinese,collation,dh,mcp,textual-criticism
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Text Processing
Requires-Python: >=3.10
Requires-Dist: fastmcp>=2.0.0
Requires-Dist: numpy>=1.24.0
Requires-Dist: openai>=1.0.0
Requires-Dist: pydantic>=2.0.0
Provides-Extra: dev
Requires-Dist: pytest-asyncio>=0.21.0; extra == 'dev'
Requires-Dist: pytest>=7.0.0; extra == 'dev'
Requires-Dist: ruff>=0.1.0; extra == 'dev'
Description-Content-Type: text/markdown

# 古典文献异文自动校验与分析 MCP Server

基于 Python/FastMCP 构建的古籍校勘 MCP 工具，提供多版本文本对齐、六类理据智能分类、标准化校勘记生成三阶段流水线。

## 功能

- **align_texts**: 多版本（2-10本）古籍文本的标点清洗与 Needleman-Wunsch / LCS 字符级对齐
- **classify_variant**: 按六类校勘学理据（音近/形近/义近/倒文/衍脱文/字形分合）对异文进行智能分类
- **generate_collation_note**: 按古籍整理标准格式生成 Markdown/LaTeX 校勘记
- **analyze_texts**: 全流水线便捷入口，一步完成从原始版本到校勘记的完整流程

## 安装

```bash
pip install dhcckb-classical-collation
```

## 使用

作为 MCP Server 启动：

```bash
uvx dhcckb-classical-collation
```

或在 MCP 客户端配置中：

```json
{
  "mcpServers": {
    "classical-collation": {
      "command": "uvx",
      "args": ["dhcckb-classical-collation"]
    }
  }
}
```

## 依赖

- Python ≥ 3.10
- fastmcp ≥ 2.0.0
- numpy ≥ 1.24.0
- pydantic ≥ 2.0.0
- openai ≥ 1.0.0 (可选，LLM 推理层)
