Initial commit: 教务系统在线平台
- 包含4个产业方向的前端项目：智能开发、智能制造、大健康、财经商贸 - 已清理node_modules、.yoyo等大文件，项目大小从2.6GB优化至631MB - 配置完善的.gitignore文件 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
KQL
210
frontend_大健康/clean_all_interview_questions.py
Normal file
210
frontend_大健康/clean_all_interview_questions.py
Normal file
@@ -0,0 +1,210 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
完全清理并重写所有面试题数据为扁平结构
|
||||
确保所有岗位都使用正确的 questions: [{ id, question, answer }] 格式
|
||||
"""
|
||||
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from datetime import datetime
|
||||
|
||||
def load_health_resume_data():
|
||||
"""加载大健康岗位简历数据"""
|
||||
try:
|
||||
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:
|
||||
return json.load(f)
|
||||
except Exception as e:
|
||||
print(f"Error loading health resume data: {e}")
|
||||
return None
|
||||
|
||||
def parse_interview_content_to_flat_array(content):
|
||||
"""解析面试题内容，转换为扁平的问答数组"""
|
||||
if not content:
|
||||
return []
|
||||
|
||||
questions = []
|
||||
|
||||
# 按大标题分割（# 一、二、三等）
|
||||
if content.startswith('# '):
|
||||
content = '\n' + content
|
||||
sections = re.split(r'\n# ([一二三四五六七八九十]+、[^#\n]+)', content)
|
||||
|
||||
if len(sections) < 2:
|
||||
return []
|
||||
|
||||
question_counter = 1
|
||||
for i in range(1, len(sections), 2):
|
||||
if i + 1 < len(sections):
|
||||
section_title = sections[i].strip()
|
||||
section_content = sections[i + 1].strip()
|
||||
|
||||
# 按问题编号分割 (1. 2. 3. 等)
|
||||
question_parts = re.split(r'\n\s*(\d+\.)\s+', section_content)
|
||||
|
||||
for j in range(1, len(question_parts), 2):
|
||||
if j + 1 < len(question_parts):
|
||||
question_block = question_parts[j + 1].strip()
|
||||
|
||||
# 提取问题和答案
|
||||
lines = question_block.split('\n')
|
||||
question_text = ""
|
||||
answer_text = ""
|
||||
in_answer = False
|
||||
|
||||
for line in lines:
|
||||
line = line.strip()
|
||||
if line.startswith('示例答案：'):
|
||||
in_answer = True
|
||||
continue
|
||||
|
||||
if not in_answer and line and not line.startswith('示例答案：'):
|
||||
if question_text:
|
||||
question_text += " "
|
||||
question_text += line
|
||||
elif in_answer and line:
|
||||
if answer_text:
|
||||
answer_text += " "
|
||||
answer_text += line
|
||||
|
||||
if question_text:
|
||||
questions.append({
|
||||
"id": f"q{question_counter}",
|
||||
"question": question_text,
|
||||
"answer": answer_text
|
||||
})
|
||||
question_counter += 1
|
||||
|
||||
return questions
|
||||
|
||||
def clean_and_update_all_questions():
|
||||
"""完全清理并更新所有面试题数据"""
|
||||
try:
|
||||
# 加载大健康数据
|
||||
health_data = load_health_resume_data()
|
||||
if not health_data:
|
||||
print("Failed to load health resume data")
|
||||
return False
|
||||
|
||||
# 创建岗位到面试题的映射
|
||||
position_to_questions = {}
|
||||
for item in health_data:
|
||||
position_name = item.get('岗位名称', '')
|
||||
interview_content = item.get('面试题内容', '')
|
||||
|
||||
if position_name and interview_content:
|
||||
questions = parse_interview_content_to_flat_array(interview_content)
|
||||
position_to_questions[position_name] = questions
|
||||
|
||||
print(f"解析了 {len(position_to_questions)} 个岗位的面试题")
|
||||
|
||||
# 读取现有文件
|
||||
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
# 找到所有岗位并完全重写questions字段
|
||||
updated_content = content
|
||||
update_count = 0
|
||||
|
||||
for position_name, questions in position_to_questions.items():
|
||||
if not questions:
|
||||
continue
|
||||
|
||||
# 将questions数组转换为JavaScript格式的字符串
|
||||
questions_js_parts = []
|
||||
for q in questions:
|
||||
q_text = q['question'].replace('"', '\\"').replace('\n', '\\n')
|
||||
a_text = q['answer'].replace('"', '\\"').replace('\n', '\\n')
|
||||
question_js = ''' {
|
||||
"id": "%s",
|
||||
"question": "%s",
|
||||
"answer": "%s"
|
||||
}''' % (q['id'], q_text, a_text)
|
||||
questions_js_parts.append(question_js)
|
||||
|
||||
questions_js = '''[
|
||||
%s
|
||||
]''' % ',\n'.join(questions_js_parts)
|
||||
|
||||
# 使用更宽泛的正则表达式来匹配岗位
|
||||
# 匹配从"title"开始到下一个position或结束的整个岗位定义
|
||||
position_pattern = rf'"title": "{re.escape(position_name)}"[\s\S]*?(?="title":|^\]\s*;\s*$|^const\s+)'
|
||||
|
||||
def replace_position_questions(match):
|
||||
matched_text = match.group(0)
|
||||
# 删除现有的questions字段（不管是什么格式）
|
||||
cleaned_text = re.sub(r',?\s*"questions": \[[^\]]*?\](?:\s*,\s*)?\s*(?=\]|\})', '', matched_text, flags=re.DOTALL)
|
||||
cleaned_text = re.sub(r',?\s*"questions": \[[\s\S]*?\](?:\s*,\s*)?\s*(?=\]|\})', '', cleaned_text, flags=re.DOTALL)
|
||||
|
||||
# 在requirements后添加新的questions字段
|
||||
if '"requirements":' in cleaned_text:
|
||||
cleaned_text = re.sub(
|
||||
r'("requirements": \[[^\]]*?\])',
|
||||
r'\1,\n "questions": ' + questions_js,
|
||||
cleaned_text,
|
||||
flags=re.DOTALL
|
||||
)
|
||||
else:
|
||||
# 如果没有requirements字段，在最后一个字段后添加
|
||||
cleaned_text = re.sub(
|
||||
r'(\s+)(\]|\})\s*$',
|
||||
r',\n "questions": ' + questions_js + r'\1\2',
|
||||
cleaned_text,
|
||||
flags=re.DOTALL
|
||||
)
|
||||
|
||||
return cleaned_text
|
||||
|
||||
new_content = re.sub(position_pattern, replace_position_questions, updated_content, flags=re.MULTILINE)
|
||||
|
||||
if new_content != updated_content:
|
||||
updated_content = new_content
|
||||
update_count += 1
|
||||
print(f"✅ 重写 {position_name} 的面试题 ({len(questions)} 个问题)")
|
||||
|
||||
# 最后清理任何残留的旧格式问题
|
||||
# 删除任何包含subQuestions的问题结构
|
||||
updated_content = re.sub(
|
||||
r'"questions": \[\s*\{[^}]*"subQuestions"[\s\S]*?\}\s*\]',
|
||||
'"questions": []',
|
||||
updated_content,
|
||||
flags=re.DOTALL
|
||||
)
|
||||
|
||||
# 删除任何独立的subQuestions结构
|
||||
updated_content = re.sub(
|
||||
r'"subQuestions": \[[\s\S]*?\][\s,]*',
|
||||
'',
|
||||
updated_content,
|
||||
flags=re.DOTALL
|
||||
)
|
||||
|
||||
# 写回文件
|
||||
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
|
||||
f.write(updated_content)
|
||||
|
||||
print(f"\n🎉 成功清理并重写 {update_count} 个岗位的面试题数据！")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error cleaning interview questions: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return False
|
||||
|
||||
def main():
|
||||
"""主函数"""
|
||||
print("开始完全清理并重写面试题数据...")
|
||||
|
||||
success = clean_and_update_all_questions()
|
||||
|
||||
if success:
|
||||
print("面试题数据清理和重写完成！")
|
||||
else:
|
||||
print("面试题数据清理失败！")
|
||||
|
||||
return success
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user