jiaowu-test/update_job_levels_v2.py

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

import json
import os
import re
from datetime import datetime

# 读取岗位等级数据
def load_job_levels():
    with open('网页未导入数据/文旅产业/岗位等级.json', 'r', encoding='utf-8') as f:
        data = json.load(f)
    
    # 创建岗位名称到等级的映射
    job_levels_map = {}
    for item in data:
        job_name = item['❌岗位名称']
        level = item['前端查询名称']
        job_levels_map[job_name] = level
    
    return job_levels_map

# 更新resumeInterviewMock.js文件 - 添加level字段
def update_resume_interview_mock(job_levels_map):
    file_path = 'src/mocks/resumeInterviewMock.js'
    
    # 备份文件
    backup_path = f'{file_path}.backup_{datetime.now().strftime("%Y%m%d_%H%M%S")}_levels'
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
    with open(backup_path, 'w', encoding='utf-8') as f:
        f.write(content)
    print(f"已备份: {backup_path}")
    
    # 更新内容
    updated_count = 0
    lines = content.split('\n')
    new_lines = []
    i = 0
    
    while i < len(lines):
        line = lines[i]
        new_lines.append(line)
        
        # 查找title字段
        if 'title:' in line and 'positions' not in line:
            # 提取岗位名称
            match = re.search(r'title:\s*["\']([^"\']+)["\']', line)
            if match:
                position_name = match.group(1)
                if position_name in job_levels_map:
                    level = job_levels_map[position_name]
                    # 检查下一行是否已经有level字段
                    has_level = False
                    for j in range(i+1, min(i+5, len(lines))):
                        if 'level:' in lines[j]:
                            has_level = True
                            # 更新现有的level字段
                            lines[j] = re.sub(
                                r'level:\s*["\'][^"\']*["\']',
                                f'level: "{level}"',
                                lines[j]
                            )
                            updated_count += 1
                            print(f"更新: {position_name} -> {level}")
                            break
                    
                    # 如果没有level字段，添加一个
                    if not has_level:
                        # 在title后面添加level字段
                        indent = len(line) - len(line.lstrip())
                        new_level_line = ' ' * indent + f'level: "{level}",'
                        # 找到合适的位置插入（在title之后）
                        new_lines.append(new_level_line)
                        updated_count += 1
                        print(f"添加: {position_name} -> {level}")
        i += 1
    
    # 写回文件
    with open(file_path, 'w', encoding='utf-8') as f:
        f.write('\n'.join(new_lines))
    
    print(f"resumeInterviewMock.js 更新完成，共更新 {updated_count} 处")

# 更新companyJobsNew.json文件
def update_company_jobs(job_levels_map):
    file_path = 'src/data/companyJobsNew.json'
    
    # 备份文件
    backup_path = f'{file_path}.backup_{datetime.now().strftime("%Y%m%d_%H%M%S")}_levels'
    with open(file_path, 'r', encoding='utf-8') as f:
        data = json.load(f)
    with open(backup_path, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)
    print(f"已备份: {backup_path}")
    
    # 更新数据
    updated_count = 0
    added_count = 0
    
    for company in data:
        if 'jobs' in company:
            for job in company['jobs']:
                position_name = job.get('positionName', '')
                if position_name in job_levels_map:
                    new_level = job_levels_map[position_name]
                    if 'jobLevel' in job:
                        old_level = job['jobLevel']
                        if old_level != new_level:
                            job['jobLevel'] = new_level
                            updated_count += 1
                            print(f"更新: {position_name}: {old_level} -> {new_level}")
                    else:
                        job['jobLevel'] = new_level
                        added_count += 1
                        print(f"添加: {position_name} -> {new_level}")
    
    # 写回文件
    with open(file_path, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)
    
    print(f"companyJobsNew.json 更新完成，更新 {updated_count} 处，新增 {added_count} 处")

# 检查mockData.js中的项目库数据
def check_mock_data_projects(job_levels_map):
    file_path = 'src/data/mockData.js'
    
    print("检查mockData.js中的项目库数据...")
    
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
    
    # 查找所有引用的岗位
    found_positions = set()
    
    # 查找relatedPositions和targetPositions中的岗位
    pattern = r'["\']([^"\']+)["\']'
    
    # 查找包含positions的行
    lines = content.split('\n')
    for i, line in enumerate(lines):
        if 'relatedPositions:' in line or 'targetPositions:' in line:
            # 查找数组内容
            j = i
            bracket_count = 0
            in_array = False
            while j < len(lines):
                if '[' in lines[j]:
                    in_array = True
                    bracket_count += lines[j].count('[')
                if in_array:
                    matches = re.findall(pattern, lines[j])
                    for match in matches:
                        if match in job_levels_map:
                            found_positions.add(match)
                bracket_count -= lines[j].count(']')
                if in_array and bracket_count <= 0:
                    break
                j += 1
    
    print(f"在项目库中找到 {len(found_positions)} 个不同的岗位引用:")
    for pos in sorted(found_positions):
        print(f"  - {pos}: {job_levels_map[pos]}")

# 主函数
def main():
    print("=" * 50)
    print("开始更新岗位等级数据 V2")
    print("=" * 50)
    
    # 加载岗位等级映射
    job_levels_map = load_job_levels()
    print(f"已加载 {len(job_levels_map)} 个岗位等级映射")
    
    # 显示等级分布
    level_counts = {}
    for level in job_levels_map.values():
        level_counts[level] = level_counts.get(level, 0) + 1
    print("\n岗位等级分布:")
    for level, count in level_counts.items():
        print(f"  {level}: {count} 个岗位")
    
    print("\n" + "=" * 50)
    
    # 更新各个文件
    print("\n1. 更新简历面试题数据...")
    update_resume_interview_mock(job_levels_map)
    
    print("\n2. 更新公司岗位数据...")
    update_company_jobs(job_levels_map)
    
    print("\n3. 检查项目库数据...")
    check_mock_data_projects(job_levels_map)
    
    print("\n" + "=" * 50)
    print("所有更新完成！")
    print("=" * 50)

if __name__ == "__main__":
    main()