136 lines
5.0 KiB
Python
136 lines
5.0 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文件中提取项目详情中的岗位信息"""
|
||
|
|
with open('src/mocks/projectLibraryMock.js', 'r', encoding='utf-8') as f:
|
||
|
|
lines = f.readlines()
|
||
|
|
|
||
|
|
projects_positions = {}
|
||
|
|
current_project = None
|
||
|
|
in_positions = False
|
||
|
|
current_positions = []
|
||
|
|
|
||
|
|
for i, line in enumerate(lines):
|
||
|
|
# 查找项目ID
|
||
|
|
if '"id":' in line and 'const project' not in lines[max(0, i-5):i+1]:
|
||
|
|
match = re.search(r'"id":\s*(\d+)', line)
|
||
|
|
if match:
|
||
|
|
# 如果有之前的项目数据，保存它
|
||
|
|
if current_project and current_positions:
|
||
|
|
projects_positions[current_project] = current_positions
|
||
|
|
|
||
|
|
current_project = int(match.group(1))
|
||
|
|
current_positions = []
|
||
|
|
in_positions = False
|
||
|
|
|
||
|
|
# 查找positions数组开始
|
||
|
|
if '"positions":' in line and '[' in line:
|
||
|
|
in_positions = True
|
||
|
|
|
||
|
|
# 在positions数组中查找岗位
|
||
|
|
if in_positions:
|
||
|
|
# 查找level
|
||
|
|
level_match = re.search(r'"level":\s*"([^"]*)"', line)
|
||
|
|
if level_match:
|
||
|
|
level = level_match.group(1)
|
||
|
|
|
||
|
|
# 查找下一行的position
|
||
|
|
if i + 1 < len(lines):
|
||
|
|
next_line = lines[i + 1]
|
||
|
|
pos_match = re.search(r'"position":\s*"([^"]*)"', next_line)
|
||
|
|
if pos_match:
|
||
|
|
position = pos_match.group(1)
|
||
|
|
current_positions.append({
|
||
|
|
'level': level,
|
||
|
|
'position': position
|
||
|
|
})
|
||
|
|
|
||
|
|
# 检查positions数组结束
|
||
|
|
if ']' in line:
|
||
|
|
in_positions = False
|
||
|
|
|
||
|
|
# 保存最后一个项目
|
||
|
|
if current_project and current_positions:
|
||
|
|
projects_positions[current_project] = current_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)
|
||
|
|
print(f"\n从简历数据中读取到 {len(resume_levels)} 个岗位等级")
|
||
|
|
print(f"从Mock文件中读取到 {len(mock_positions)} 个项目的岗位数据\n")
|
||
|
|
|
||
|
|
# 统计信息
|
||
|
|
total_positions = 0
|
||
|
|
mismatches = []
|
||
|
|
not_found = []
|
||
|
|
correct_matches = []
|
||
|
|
|
||
|
|
# 检查每个项目的岗位
|
||
|
|
for project_id in sorted(mock_positions.keys()):
|
||
|
|
positions = mock_positions[project_id]
|
||
|
|
if positions:
|
||
|
|
print(f"\n【项目 {project_id}】({len(positions)}个岗位)")
|
||
|
|
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[{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}")
|
||
|
|
correct_matches.append(position_name)
|
||
|
|
else:
|
||
|
|
print(f" ⚠️ {position_name}: 在简历数据中未找到 (当前: {current_level})")
|
||
|
|
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"等级正确: {len(correct_matches)} 个 ({len(correct_matches)*100/max(1,total_positions):.1f}%)")
|
||
|
|
print(f"等级错误: {len(mismatches)} 个 ({len(mismatches)*100/max(1,total_positions):.1f}%)")
|
||
|
|
print(f"未找到岗位: {len(not_found)} 个 ({len(not_found)*100/max(1,total_positions):.1f}%)")
|
||
|
|
|
||
|
|
return mismatches, not_found
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
mismatches, not_found = compare_and_report()
|