126 lines
4.3 KiB
Python
126 lines
4.3 KiB
Python
|
#!/usr/bin/env python3
|
||
|
|
# -*- coding: utf-8 -*-
|
||
|
|
import json
|
||
|
|
import re
|
||
|
|
|
||
|
|
def get_position_levels_from_resume():
|
||
|
|
"""从化工岗位简历.json获取岗位等级映射"""
|
||
|
|
with open('网页未导入数据/化工产业/化工岗位简历.json', 'r', encoding='utf-8') as f:
|
||
|
|
data = json.load(f)
|
||
|
|
|
||
|
|
position_levels = {}
|
||
|
|
for item in data:
|
||
|
|
position = item.get('岗位名称', '').strip()
|
||
|
|
level = item.get('岗位等级标签', '').strip()
|
||
|
|
if position and level:
|
||
|
|
position_levels[position] = level
|
||
|
|
|
||
|
|
return position_levels
|
||
|
|
|
||
|
|
def extract_positions_from_mock():
|
||
|
|
"""从mock文件中提取所有项目的岗位信息"""
|
||
|
|
with open('src/mocks/projectLibraryMock.js', 'r', encoding='utf-8') as f:
|
||
|
|
content = f.read()
|
||
|
|
|
||
|
|
# 查找所有项目的岗位数据
|
||
|
|
projects_positions = {}
|
||
|
|
|
||
|
|
# 用正则表达式提取项目ID和positions数组
|
||
|
|
pattern = r'"id":\s*(\d+),.*?"positions":\s*\[(.*?)\]'
|
||
|
|
matches = re.finditer(pattern, content, re.DOTALL)
|
||
|
|
|
||
|
|
for match in matches:
|
||
|
|
project_id = int(match.group(1))
|
||
|
|
positions_str = match.group(2)
|
||
|
|
|
||
|
|
# 提取每个岗位
|
||
|
|
pos_pattern = r'"level":\s*"([^"]*)".*?"position":\s*"([^"]*)"'
|
||
|
|
positions = []
|
||
|
|
for pos_match in re.finditer(pos_pattern, positions_str):
|
||
|
|
level = pos_match.group(1)
|
||
|
|
position = pos_match.group(2)
|
||
|
|
positions.append({'level': level, 'position': position})
|
||
|
|
|
||
|
|
if positions:
|
||
|
|
projects_positions[project_id] = positions
|
||
|
|
|
||
|
|
return projects_positions
|
||
|
|
|
||
|
|
def compare_and_report():
|
||
|
|
"""比较并报告差异"""
|
||
|
|
# 获取数据
|
||
|
|
resume_levels = get_position_levels_from_resume()
|
||
|
|
mock_positions = extract_positions_from_mock()
|
||
|
|
|
||
|
|
print("=" * 60)
|
||
|
|
print("岗位等级对比报告")
|
||
|
|
print("=" * 60)
|
||
|
|
|
||
|
|
# 统计信息
|
||
|
|
total_positions = 0
|
||
|
|
mismatches = []
|
||
|
|
not_found = []
|
||
|
|
|
||
|
|
# 检查每个项目的岗位
|
||
|
|
for project_id, positions in mock_positions.items():
|
||
|
|
print(f"\n项目 {project_id}:")
|
||
|
|
for pos_info in positions:
|
||
|
|
current_level = pos_info['level']
|
||
|
|
position_name = pos_info['position']
|
||
|
|
total_positions += 1
|
||
|
|
|
||
|
|
if position_name in resume_levels:
|
||
|
|
correct_level = resume_levels[position_name]
|
||
|
|
if current_level != correct_level:
|
||
|
|
print(f" ❌ {position_name}: 当前等级[{current_level}] → 应为[{correct_level}]")
|
||
|
|
mismatches.append({
|
||
|
|
'project': project_id,
|
||
|
|
'position': position_name,
|
||
|
|
'current': current_level,
|
||
|
|
'correct': correct_level
|
||
|
|
})
|
||
|
|
else:
|
||
|
|
print(f" ✅ {position_name}: {current_level}")
|
||
|
|
else:
|
||
|
|
print(f" ⚠️ {position_name}: 在简历数据中未找到")
|
||
|
|
not_found.append({
|
||
|
|
'project': project_id,
|
||
|
|
'position': position_name,
|
||
|
|
'current': current_level
|
||
|
|
})
|
||
|
|
|
||
|
|
# 汇总报告
|
||
|
|
print("\n" + "=" * 60)
|
||
|
|
print("汇总统计")
|
||
|
|
print("=" * 60)
|
||
|
|
print(f"总岗位数: {total_positions}")
|
||
|
|
print(f"等级不匹配: {len(mismatches)} 个")
|
||
|
|
print(f"未找到岗位: {len(not_found)} 个")
|
||
|
|
print(f"正确匹配: {total_positions - len(mismatches) - len(not_found)} 个")
|
||
|
|
|
||
|
|
# 显示所有需要修正的岗位
|
||
|
|
if mismatches:
|
||
|
|
print("\n需要修正的岗位等级：")
|
||
|
|
for item in mismatches:
|
||
|
|
print(f" 项目{item['project']}: {item['position']} [{item['current']}→{item['correct']}]")
|
||
|
|
|
||
|
|
if not_found:
|
||
|
|
print("\n未在简历数据中找到的岗位：")
|
||
|
|
for item in not_found:
|
||
|
|
print(f" 项目{item['project']}: {item['position']} (当前: {item['current']})")
|
||
|
|
|
||
|
|
return mismatches, not_found
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
mismatches, not_found = compare_and_report()
|
||
|
|
|
||
|
|
# 保存需要更新的数据
|
||
|
|
update_data = {
|
||
|
|
'mismatches': mismatches,
|
||
|
|
'not_found': not_found
|
||
|
|
}
|
||
|
|
|
||
|
|
with open('position_updates_needed.json', 'w', encoding='utf-8') as f:
|
||
|
|
json.dump(update_data, f, ensure_ascii=False, indent=2)
|
||
|
|
|
||
|
|
print(f"\n需要更新的数据已保存到 position_updates_needed.json")
|