Files
ALL-teach_sys/frontend_智能制造/fix_interview_sections_complete.py

185 lines
7.2 KiB
Python
Raw Permalink Normal View History

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import json
import re
from datetime import datetime
# 读取智能制造岗位简历数据
print("正在读取智能制造岗位简历.json...")
with open('网页未导入数据/智能制造产业/智能制造岗位简历.json', 'r', encoding='utf-8') as f:
smart_mfg_data = json.load(f)
# 读取当前mock文件
print("正在读取当前mock文件...")
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
mock_content = f.read()
# 备份原文件
backup_time = datetime.now().strftime('%Y%m%d_%H%M%S')
backup_file = f'src/mocks/resumeInterviewMock.js.backup_sections_fix_{backup_time}'
with open(backup_file, 'w', encoding='utf-8') as f:
f.write(mock_content)
print(f"已创建备份文件: {backup_file}")
# 解析智能制造岗位简历数据,构建完整的面试题映射
interview_data_map = {}
for item in smart_mfg_data:
job_group = item.get('简历岗位群', '')
interview_content = item.get('面试题内容', '')
if job_group and interview_content:
# 解析面试题内容
questions_data = []
# 按章节分割内容
sections = re.split(r'\n# ', interview_content)
for i, section in enumerate(sections):
if not section.strip():
continue
# 处理第一个章节(可能没有前置换行符)
if i == 0 and not section.startswith('一、'):
section = section[2:] if section.startswith('# ') else section
lines = section.split('\n')
if not lines:
continue
# 第一行是章节标题
section_title = lines[0].strip()
if not section_title:
continue
current_section_questions = []
# 解析该章节中的问题
j = 1 # 跳过标题行
while j < len(lines):
line = lines[j].strip()
if not line:
j += 1
continue
# 查找问题编号(如 1. xxx 或 1、xxx
question_match = re.match(r'^(\d+)[\.\、]\s*(.+)', line)
if question_match:
question_num = question_match.group(1)
question_text = question_match.group(2).strip()
# 查找答案
answer_lines = []
j += 1 # 移到下一行开始查找答案
while j < len(lines):
next_line = lines[j].strip()
# 如果遇到下一个问题,停止
if re.match(r'^\d+[\.\、]\s*', next_line):
j -= 1 # 回退,让外层循环处理
break
# 处理答案内容
if next_line:
# 移除答案标记
if re.match(r'^答案[:]?\s*', next_line):
answer_text = re.sub(r'^答案[:]?\s*', '', next_line)
if answer_text:
answer_lines.append(answer_text)
elif next_line.startswith('-') or not re.match(r'^答案', next_line):
# 其他内容作为答案的一部分
answer_lines.append(next_line)
j += 1
# 整理答案
answer = ' '.join(answer_lines).strip()
if not answer:
answer = "请根据实际情况回答"
current_section_questions.append({
'question': question_text,
'answer': answer
})
else:
j += 1
# 如果该章节有问题,添加到结果中
if current_section_questions:
questions_data.append({
'id': f'group_q{len(questions_data) + 1}',
'title': section_title,
'questions': current_section_questions
})
interview_data_map[job_group] = questions_data
print(f"\n共解析 {len(interview_data_map)} 个岗位群的面试题数据")
# 统计解析结果
for group, data in interview_data_map.items():
total_questions = sum(len(section['questions']) for section in data)
print(f" - {group}: {len(data)} 个章节,{total_questions} 道题")
# 更新mock文件中的面试题
def update_industry_questions(match):
full_match = match.group(0)
industry_name = match.group(1)
# 查找对应的面试题数据
if industry_name not in interview_data_map:
print(f" - {industry_name}: 保持原样(未找到对应数据)")
return full_match
questions_data = interview_data_map[industry_name]
# 构建新的questions数组
new_questions = []
for section_data in questions_data:
sub_questions = []
for idx, q in enumerate(section_data['questions']):
# 转义特殊字符
question_text = q['question'].replace('\\', '\\\\').replace('"', '\\"')
answer_text = q['answer'].replace('\\', '\\\\').replace('"', '\\"').replace('\n', '\\n')
sub_questions.append('{{\n "id": "q{}_{}", \n "question": "{}", \n "answer": "{}"\n }}'.format(section_data['id'][7:], idx+1, question_text, answer_text))
section_title = section_data['title'].replace('\\', '\\\\').replace('"', '\\"')
new_questions.append('{{\n "id": "{}", \n "question": "# {}", \n "subQuestions": [\n {}\n ]\n }}'.format(section_data['id'], section_title, ','.join(sub_questions)))
# 替换questions部分
questions_str = ',\n '.join(new_questions)
# 构建完整的替换内容
before_questions = match.group(0).split('"questions": [')[0]
result = before_questions + '"questions": [\n ' + questions_str + '\n ]'
# 统计题目数量
total_questions = sum(len(section['questions']) for section in questions_data)
print(f" - {industry_name}: 更新为 {len(questions_data)} 个章节,{total_questions} 道题")
return result
# 执行更新
print("\n正在更新面试题数据...")
pattern = r'"name":\s*"([^"]+)"[^}]*?"questions":\s*\[.*?\]\s*(?=\})'
new_content = re.sub(pattern, update_industry_questions, mock_content, flags=re.DOTALL)
# 保存更新后的文件
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
f.write(new_content)
print("\n✅ 面试题数据更新完成!")
# 验证语法
import subprocess
result = subprocess.run(['node', '-c', 'src/mocks/resumeInterviewMock.js'],
capture_output=True, text=True)
if result.returncode == 0:
print("✅ 语法检查通过!")
else:
print("❌ 语法错误:")
print(result.stderr)