"""
数据治理功能演示脚本
展示如何使用数据治理功能
"""

from pathlib import Path
from history.manager import get_history_manager
from history.data_sanitizer import get_sanitizer


def demo_basic_usage():
    """演示基础使用"""
    print("=" * 60)
    print("演示 1: 基础使用 - 自动治理")
    print("=" * 60)
    
    # 获取历史管理器（自动启用治理）
    manager = get_history_manager(Path("./workspace"))
    
    # 添加一条包含敏感信息的记录
    record = manager.add_record(
        task_id='demo-001',
        user_input='读取配置文件 C:\\Users\\admin\\config.json，邮箱: admin@company.com',
        intent_label='file_operation',
        intent_confidence=0.95,
        execution_plan='读取并解析配置文件',
        code='with open("C:\\\\Users\\\\admin\\\\config.json") as f:\n    config = json.load(f)',
        success=True,
        duration_ms=150,
        stdout='配置加载成功',
        stderr='',
        log_path='./logs/demo-001.log',
        task_summary='读取配置文件'
    )
    
    print(f"\n[OK] 已添加记录: {record.task_id}")
    
    # 检查治理元数据
    if record._governance:
        print(f"  - 数据级别: {record._governance['level']}")
        print(f"  - 敏感度评分: {record._governance['sensitivity_score']:.2f}")
        print(f"  - 保留期: {record._governance['retention_days']} 天")
        print(f"  - 敏感字段: {', '.join(record._governance['sensitive_fields'])}")
    
    print("\n")


def demo_sanitizer():
    """演示脱敏功能"""
    print("=" * 60)
    print("演示 2: 数据脱敏")
    print("=" * 60)
    
    sanitizer = get_sanitizer()
    
    # 测试文本
    test_text = """
    用户信息：
    - 邮箱: zhang.san@company.com
    - 手机: 13812345678
    - 配置文件: C:\\Users\\zhangsan\\Documents\\config.json
    - API密钥: sk-1234567890abcdefghijklmnopqrstuvwxyz123456789012
    - 服务器IP: 192.168.1.100
    """
    
    print("\n原始文本:")
    print(test_text)
    
    # 执行脱敏
    sanitized_text, matches = sanitizer.sanitize(test_text)
    
    print("\n脱敏后文本:")
    print(sanitized_text)
    
    print(f"\n检测到 {len(matches)} 处敏感信息:")
    for match in matches:
        print(f"  - {match.type.value}: {match.value[:20]}... → {match.masked_value}")
    
    # 敏感度评分
    score = sanitizer.get_sensitivity_score(test_text)
    print(f"\n敏感度评分: {score:.2f}")
    
    print("\n")


def demo_governance_metrics():
    """演示治理指标"""
    print("=" * 60)
    print("演示 3: 治理指标")
    print("=" * 60)
    
    manager = get_history_manager(Path("./workspace"))
    
    # 添加几条不同敏感度的记录
    test_records = [
        {
            'task_id': 'demo-low',
            'user_input': '计算 1 + 1',
            'code': 'print(1 + 1)',
            'stdout': '2',
            'summary': '简单计算'
        },
        {
            'task_id': 'demo-medium',
            'user_input': '列出文件 C:\\Users\\test\\documents',
            'code': 'os.listdir("C:\\\\Users\\\\test\\\\documents")',
            'stdout': '["file1.txt", "file2.txt"]',
            'summary': '列出文件'
        },
        {
            'task_id': 'demo-high',
            'user_input': '连接数据库',
            'code': 'conn = psycopg2.connect("postgresql://user:pass123@192.168.1.100/db")',
            'stdout': 'Connected',
            'summary': '数据库连接'
        }
    ]
    
    for rec in test_records:
        manager.add_record(
            task_id=rec['task_id'],
            user_input=rec['user_input'],
            intent_label='test',
            intent_confidence=0.9,
            execution_plan='测试',
            code=rec['code'],
            success=True,
            duration_ms=100,
            stdout=rec['stdout'],
            stderr='',
            log_path='',
            task_summary=rec['summary']
        )
    
    # 获取治理指标
    metrics = manager.get_governance_metrics()
    
    if metrics:
        print(f"\n[治理指标统计]:")
        print(f"  - 总记录数: {metrics.total_records}")
        print(f"  - 完整保存: {metrics.full_records}")
        print(f"  - 脱敏保存: {metrics.sanitized_records}")
        print(f"  - 最小化保存: {metrics.minimal_records}")
        print(f"  - 存储占用: {metrics.total_size_bytes / 1024:.2f} KB")
        
        if metrics.sensitive_field_hits:
            print(f"\n  敏感字段命中:")
            for field, count in metrics.sensitive_field_hits.items():
                print(f"    * {field}: {count} 次")
    
    print("\n")


def demo_cleanup():
    """演示数据清理"""
    print("=" * 60)
    print("演示 4: 数据清理")
    print("=" * 60)
    
    manager = get_history_manager(Path("./workspace"))
    
    print(f"\n清理前记录数: {len(manager.get_all())}")
    
    # 执行清理
    stats = manager.manual_cleanup()
    
    print(f"\n清理统计:")
    print(f"  - 归档: {stats['archived']} 条")
    print(f"  - 删除: {stats['deleted']} 条")
    print(f"  - 保留: {stats['remaining']} 条")
    
    print("\n")


def demo_export():
    """演示导出脱敏数据"""
    print("=" * 60)
    print("演示 5: 导出脱敏数据")
    print("=" * 60)
    
    manager = get_history_manager(Path("./workspace"))
    
    export_path = Path("./workspace/history_sanitized_export.json")
    count = manager.export_sanitized(export_path)
    
    print(f"\n[OK] 已导出 {count} 条脱敏记录")
    print(f"  文件位置: {export_path.absolute()}")
    
    print("\n")


if __name__ == '__main__':
    print("\n")
    print("=" * 60)
    print(" " * 15 + "数据治理功能演示")
    print("=" * 60)
    print("\n")
    
    try:
        # 运行所有演示
        demo_basic_usage()
        demo_sanitizer()
        demo_governance_metrics()
        demo_cleanup()
        demo_export()
        
        print("=" * 60)
        print("[OK] 所有演示完成")
        print("=" * 60)
        print("\n提示: 可以在 ./workspace 目录查看生成的文件")
        print("  - history.json: 治理后的历史记录")
        print("  - governance_metrics.json: 治理指标")
        print("  - archive/: 归档目录")
        print("  - history_sanitized_export.json: 导出的脱敏数据")
        print("\n")
        
    except Exception as e:
        print(f"\n[ERROR] 演示过程中出错: {e}")
        import traceback
        traceback.print_exc()