ai_la/base7/check_difficulty_direct.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
直接通过HTTP请求检查H2控制台中的difficulty字段
"""

import requests
import re
from urllib.parse import urlencode

def check_difficulty_in_h2():
    """通过H2控制台检查difficulty字段"""
    print("=== 直接检查H2数据库中的difficulty字段 ===")
    
    session = requests.Session()
    
    try:
        # 1. 访问H2控制台
        console_url = "http://localhost:8080/h2-console"
        response = session.get(console_url)
        
        if response.status_code != 200:
            print(f"✗ 无法访问H2控制台: {response.status_code}")
            return False
        
        print("✓ H2控制台可访问")
        
        # 2. 提取JSESSIONID
        jsessionid = None
        for cookie in session.cookies:
            if cookie.name == 'JSESSIONID':
                jsessionid = cookie.value
                break
        
        if not jsessionid:
            print("✗ 无法获取JSESSIONID")
            return False
        
        print(f"✓ 获取到JSESSIONID: {jsessionid[:10]}...")
        
        # 3. 登录H2数据库
        login_url = "http://localhost:8080/h2-console/login.do"
        login_data = {
            'language': 'en',
            'setting': 'Generic H2 (Embedded)',
            'name': 'Generic H2 (Embedded)',
            'driver': 'org.h2.Driver',
            'url': 'jdbc:h2:mem:testdb',
            'user': 'sa',
            'password': '',
            'jsessionid': jsessionid
        }
        
        headers = {
            'Content-Type': 'application/x-www-form-urlencoded',
            'Referer': console_url
        }
        
        response = session.post(login_url, data=login_data, headers=headers)
        
        if response.status_code != 200:
            print(f"✗ 登录请求失败: {response.status_code}")
            return False
        
        # 检查是否登录成功
        if 'query.do' not in response.text and 'Query' not in response.text:
            print("✗ H2数据库登录失败")
            print("响应内容片段:", response.text[:200])
            return False
        
        print("✓ H2数据库登录成功")
        
        # 4. 执行查询
        query_url = "http://localhost:8080/h2-console/query.do"
        
        # 查询表结构
        print("\n--- 查询goal_detail表结构 ---")
        structure_query = "SHOW COLUMNS FROM goal_detail"
        query_data = {
            'sql': structure_query,
            'jsessionid': jsessionid
        }
        
        response = session.post(query_url, data=query_data, headers=headers)
        if response.status_code == 200:
            print("✓ 表结构查询成功")
            if 'DIFFICULTY' in response.text.upper():
                print("✓ 发现DIFFICULTY字段")
            else:
                print("✗ 未发现DIFFICULTY字段")
                print("响应内容片段:", response.text[:500])
        
        # 查询数据
        print("\n--- 查询goal_detail表数据 ---")
        data_query = "SELECT id, goal_id, question, difficulty, created_at FROM goal_detail ORDER BY created_at DESC LIMIT 5"
        query_data = {
            'sql': data_query,
            'jsessionid': jsessionid
        }
        
        response = session.post(query_url, data=query_data, headers=headers)
        if response.status_code == 200:
            print("✓ 数据查询成功")
            
            # 尝试解析HTML响应中的数据
            response_text = response.text
            
            # 查找表格数据
            if '<table' in response_text and '</table>' in response_text:
                print("✓ 找到查询结果表格")
                
                # 简单解析表格内容
                table_match = re.search(r'<table[^>]*>(.*?)</table>', response_text, re.DOTALL)
                if table_match:
                    table_content = table_match.group(1)
                    
                    # 查找difficulty列的值
                    if 'null' in table_content.lower():
                        print("⚠️  发现null值，可能存在difficulty字段为null的情况")
                    
                    # 查找具体的difficulty值
                    difficulty_pattern = r'<td[^>]*>([^<]*)</td>'
                    cells = re.findall(difficulty_pattern, table_content)
                    
                    print(f"  表格单元格数量: {len(cells)}")
                    
                    # 假设列顺序是: id, goal_id, question, difficulty, created_at
                    if len(cells) >= 5:
                        for i in range(0, len(cells), 5):
                            if i + 4 < len(cells):
                                id_val = cells[i].strip()
                                goal_id = cells[i+1].strip()
                                question = cells[i+2].strip()[:30] + "..." if len(cells[i+2]) > 30 else cells[i+2].strip()
                                difficulty = cells[i+3].strip()
                                created_at = cells[i+4].strip()
                                
                                print(f"  记录 {id_val}: difficulty = '{difficulty}'")
                                
                                if difficulty == '' or difficulty.lower() == 'null':
                                    print(f"    ⚠️  记录 {id_val} 的difficulty字段为空或null")
                                else:
                                    print(f"    ✓ 记录 {id_val} 的difficulty字段有值: {difficulty}")
                else:
                    print("✗ 无法解析表格内容")
            else:
                print("✗ 响应中未找到表格")
                if 'No data available' in response_text:
                    print("  表中暂无数据")
                else:
                    print("  响应内容片段:", response_text[:300])
        
        # 统计difficulty字段分布
        print("\n--- 统计difficulty字段分布 ---")
        stats_query = "SELECT difficulty, COUNT(*) as count FROM goal_detail GROUP BY difficulty"
        query_data = {
            'sql': stats_query,
            'jsessionid': jsessionid
        }
        
        response = session.post(query_url, data=query_data, headers=headers)
        if response.status_code == 200:
            print("✓ 统计查询成功")
            
            response_text = response.text
            if '<table' in response_text:
                table_match = re.search(r'<table[^>]*>(.*?)</table>', response_text, re.DOTALL)
                if table_match:
                    table_content = table_match.group(1)
                    cells = re.findall(r'<td[^>]*>([^<]*)</td>', table_content)
                    
                    print("  difficulty字段分布:")
                    for i in range(0, len(cells), 2):
                        if i + 1 < len(cells):
                            difficulty_val = cells[i].strip()
                            count_val = cells[i+1].strip()
                            
                            if difficulty_val == '' or difficulty_val.lower() == 'null':
                                print(f"    NULL: {count_val} 条记录")
                            else:
                                print(f"    '{difficulty_val}': {count_val} 条记录")
        
        return True
        
    except Exception as e:
        print(f"✗ 检查过程出错: {e}")
        import traceback
        traceback.print_exc()
        return False

def main():
    """主函数"""
    print("开始直接检查H2数据库中的difficulty字段...")
    
    if check_difficulty_in_h2():
        print("\n=== 检查完成 ===")
    else:
        print("\n=== 检查失败 ===")
        print("请手动访问H2控制台进行检查:")
        print("访问地址: http://localhost:8080/h2-console")
        print("连接信息: jdbc:h2:mem:testdb, 用户名: sa, 密码: (空)")

if __name__ == "__main__":
    main()