ALL-teach_sys/frontend_大健康/verify_position_levels_v2.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import json
import re

def verify_position_levels():
    """验证项目库数据中的岗位等级是否与大健康岗位简历数据一致"""
    
    # 1. 读取岗位等级映射
    position_level_map = {}
    with open('网页未导入数据/大健康产业/大健康岗位简历.json', 'r', encoding='utf-8') as f:
        resume_data = json.load(f)
    for item in resume_data:
        position_name = item.get('岗位名称', '')
        level = item.get('岗位等级标签', '')
        if position_name and level:
            position_level_map[position_name] = level
    
    # 2. 读取生成的projectLibraryMock.js文件
    with open('src/mocks/projectLibraryMock.js', 'r', encoding='utf-8') as f:
        mock_content = f.read()
    
    # 3. 提取项目详情数据
    # 查找getMockProjectDetail函数中的projects数组
    # 使用更宽松的正则表达式
    pattern = r'getMockProjectDetail[^{]*\{[^}]*const projects = (\[[^\]]+\]);'
    projects_match = re.search(pattern, mock_content, re.DOTALL)
    
    if not projects_match:
        # 尝试另一种模式
        pattern = r'const projects = (\[\s*\{[\s\S]*?\}\s*\]);'
        projects_match = re.search(pattern, mock_content)
    
    if projects_match:
        projects_json = projects_match.group(1)
        
        # 清理JavaScript格式为JSON格式
        # 移除可能的尾随逗号
        projects_json = re.sub(r',(\s*[}\]])', r'\1', projects_json)
        
        try:
            projects_data = json.loads(projects_json)
        except json.JSONDecodeError:
            # 如果JSON解析失败，尝试使用eval（不推荐但有效）
            # 先创建一个安全的执行环境
            safe_dict = {"true": True, "false": False, "null": None}
            try:
                projects_data = eval(projects_json, {"__builtins__": {}}, safe_dict)
            except:
                print("无法解析项目数据，尝试直接从文件提取...")
                
                # 直接查找所有applicablePositions
                positions_pattern = r'"applicablePositions":\s*\[(.*?)\]'
                all_positions = re.findall(positions_pattern, mock_content, re.DOTALL)
                
                print("=" * 60)
                print("项目库岗位等级验证报告")
                print("=" * 60)
                
                error_count = 0
                correct_count = 0
                
                for positions_str in all_positions:
                    # 提取每个岗位
                    pos_items = re.findall(r'\{\s*"level":\s*"([^"]+)",\s*"position":\s*"([^"]+)"\s*\}', positions_str)
                    
                    for level_in_project, position in pos_items:
                        expected_level = position_level_map.get(position, '未找到')
                        
                        if expected_level == '未找到':
                            print(f"  ⚠️  {position}: 在简历数据中未找到")
                            error_count += 1
                        elif level_in_project != expected_level:
                            print(f"  ❌ {position}: {level_in_project} → 应为 {expected_level}")
                            error_count += 1
                        else:
                            print(f"  ✅ {position}: {level_in_project}")
                            correct_count += 1
                
                print("\n" + "=" * 60)
                print("验证结果汇总：")
                print(f"✅ 正确: {correct_count} 个岗位")
                print(f"❌ 错误: {error_count} 个岗位")
                
                if error_count == 0 and correct_count > 0:
                    print("\n🎉 所有岗位等级都正确！")
                elif error_count > 0:
                    print("\n⚠️  发现岗位等级不一致，请检查！")
                else:
                    print("\n⚠️  未找到任何岗位数据！")
                
                return error_count == 0
        
        print("=" * 60)
        print("项目库岗位等级验证报告")
        print("=" * 60)
        
        error_count = 0
        correct_count = 0
        
        for project in projects_data:
            if 'applicablePositions' in project:
                print(f"\n项目: {project.get('name', 'Unknown')}")
                print("-" * 40)
                
                for pos_item in project['applicablePositions']:
                    position = pos_item['position']
                    level_in_project = pos_item['level']
                    expected_level = position_level_map.get(position, '未找到')
                    
                    if expected_level == '未找到':
                        print(f"  ⚠️  {position}: 在简历数据中未找到")
                        error_count += 1
                    elif level_in_project != expected_level:
                        print(f"  ❌ {position}: {level_in_project} → 应为 {expected_level}")
                        error_count += 1
                    else:
                        print(f"  ✅ {position}: {level_in_project}")
                        correct_count += 1
        
        print("\n" + "=" * 60)
        print("验证结果汇总：")
        print(f"✅ 正确: {correct_count} 个岗位")
        print(f"❌ 错误: {error_count} 个岗位")
        
        if error_count == 0 and correct_count > 0:
            print("\n🎉 所有岗位等级都正确！")
        else:
            print("\n⚠️  发现岗位等级不一致，请检查！")
        
        return error_count == 0
    else:
        print("无法在文件中找到项目数据")
        return False

if __name__ == "__main__":
    verify_position_levels()