141 lines
5.0 KiB
Python
141 lines
5.0 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
# -*- coding: utf-8 -*-
|
|||
|
|
"""
|
|||
|
|
清理面试题答案中的选项，只保留正确答案
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import re
|
|||
|
|
from datetime import datetime
|
|||
|
|
|
|||
|
|
print("=== 清理面试题答案中的选项 ===\n")
|
|||
|
|
|
|||
|
|
# 1. 读取当前mock文件
|
|||
|
|
print("1. 读取当前mock文件...")
|
|||
|
|
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
|
|||
|
|
content = f.read()
|
|||
|
|
|
|||
|
|
# 2. 备份
|
|||
|
|
backup_time = datetime.now().strftime('%Y%m%d_%H%M%S')
|
|||
|
|
backup_file = f'src/mocks/resumeInterviewMock.js.backup_clean_options_{backup_time}'
|
|||
|
|
print(f"2. 创建备份: {backup_file}")
|
|||
|
|
with open(backup_file, 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(content)
|
|||
|
|
|
|||
|
|
# 3. 处理答案中的选项
|
|||
|
|
print("\n3. 开始清理答案中的选项...")
|
|||
|
|
|
|||
|
|
def clean_answer(match):
|
|||
|
|
"""清理答案中的选项格式"""
|
|||
|
|
full_match = match.group(0)
|
|||
|
|
answer_content = match.group(1)
|
|||
|
|
|
|||
|
|
# 检查是否包含选项格式（A. B. C. 或 A、B、C、等）
|
|||
|
|
if re.search(r'[A-D][\.、]', answer_content):
|
|||
|
|
# 尝试提取正确答案
|
|||
|
|
# 模式1: "正确答案是A" 或 "答案：A"
|
|||
|
|
correct_match = re.search(r'(?:正确答案[是为：:]*|答案[是为：:]*)\s*([A-D])', answer_content)
|
|||
|
|
if correct_match:
|
|||
|
|
option_letter = correct_match.group(1)
|
|||
|
|
# 查找该选项的内容
|
|||
|
|
option_pattern = rf'{option_letter}[\.、]\s*([^A-D\n]+?)(?=[A-D][\.、]|$)'
|
|||
|
|
option_content = re.search(option_pattern, answer_content)
|
|||
|
|
if option_content:
|
|||
|
|
# 返回只包含正确答案内容的版本
|
|||
|
|
cleaned_answer = option_content.group(1).strip()
|
|||
|
|
# 去除可能的句号或其他标点
|
|||
|
|
cleaned_answer = re.sub(r'[。；;]+$', '', cleaned_answer)
|
|||
|
|
return f'"answer": "{cleaned_answer}"'
|
|||
|
|
|
|||
|
|
# 模式2: 选项列表后跟正确答案说明
|
|||
|
|
# 例如："A. 选项1 B. 选项2 C. 选项3 D. 选项4。正确答案是C"
|
|||
|
|
if '正确答案' in answer_content or '答案' in answer_content:
|
|||
|
|
# 提取所有选项
|
|||
|
|
options = {}
|
|||
|
|
option_matches = re.findall(r'([A-D])[\.、]\s*([^A-D\n]+?)(?=[A-D][\.、]|正确答案|答案|$)', answer_content)
|
|||
|
|
for letter, content in option_matches:
|
|||
|
|
options[letter] = content.strip().rstrip('。；;')
|
|||
|
|
|
|||
|
|
# 找出正确答案
|
|||
|
|
correct_match = re.search(r'(?:正确答案|答案)[是为：:]*\s*([A-D])', answer_content)
|
|||
|
|
if correct_match and correct_match.group(1) in options:
|
|||
|
|
return f'"answer": "{options[correct_match.group(1)]}"'
|
|||
|
|
|
|||
|
|
# 如果没有选项格式或无法处理，返回原始内容
|
|||
|
|
return full_match
|
|||
|
|
|
|||
|
|
# 4. 执行替换
|
|||
|
|
original_content = content
|
|||
|
|
# 匹配 "answer": "..." 模式
|
|||
|
|
pattern = r'"answer":\s*"([^"]*(?:\\.[^"]*)*)"'
|
|||
|
|
|
|||
|
|
# 统计处理的答案数量
|
|||
|
|
matches = re.findall(pattern, content)
|
|||
|
|
total_answers = len(matches)
|
|||
|
|
print(f"找到 {total_answers} 个答案")
|
|||
|
|
|
|||
|
|
# 处理包含选项的答案
|
|||
|
|
processed = 0
|
|||
|
|
for match in re.finditer(pattern, content):
|
|||
|
|
answer_text = match.group(1)
|
|||
|
|
if re.search(r'[A-D][\.、]', answer_text):
|
|||
|
|
processed += 1
|
|||
|
|
|
|||
|
|
print(f"其中 {processed} 个答案包含选项格式")
|
|||
|
|
|
|||
|
|
# 执行替换
|
|||
|
|
content = re.sub(pattern, clean_answer, content)
|
|||
|
|
|
|||
|
|
# 5. 额外的清理模式
|
|||
|
|
print("\n4. 执行额外的清理模式...")
|
|||
|
|
|
|||
|
|
# 清理常见的选项格式
|
|||
|
|
def additional_clean(text):
|
|||
|
|
"""额外的清理规则"""
|
|||
|
|
# 移除"选项："开头
|
|||
|
|
text = re.sub(r'"answer":\s*"选项[：:]\s*', '"answer": "', text)
|
|||
|
|
|
|||
|
|
# 如果答案以单个字母开头（如"A 内容"），去掉字母
|
|||
|
|
text = re.sub(r'"answer":\s*"[A-D]\s+([^"]+)"', r'"answer": "\1"', text)
|
|||
|
|
|
|||
|
|
# 如果答案以"A."或"A、"开头，去掉
|
|||
|
|
text = re.sub(r'"answer":\s*"[A-D][\.、]\s*([^"]+)"', r'"answer": "\1"', text)
|
|||
|
|
|
|||
|
|
return text
|
|||
|
|
|
|||
|
|
content = additional_clean(content)
|
|||
|
|
|
|||
|
|
# 6. 保存文件
|
|||
|
|
print("\n5. 保存更新后的文件...")
|
|||
|
|
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(content)
|
|||
|
|
|
|||
|
|
# 7. 验证语法
|
|||
|
|
print("\n6. 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！")
|
|||
|
|
|
|||
|
|
# 检查是否有变化
|
|||
|
|
if content != original_content:
|
|||
|
|
# 再次统计包含选项的答案
|
|||
|
|
remaining_options = len(re.findall(r'"answer":\s*"[^"]*[A-D][\.、]', content))
|
|||
|
|
print(f"\n清理结果：")
|
|||
|
|
print(f"- 原始包含选项的答案: {processed} 个")
|
|||
|
|
print(f"- 剩余包含选项的答案: {remaining_options} 个")
|
|||
|
|
print(f"- 成功清理: {processed - remaining_options} 个")
|
|||
|
|
else:
|
|||
|
|
print("\n未发现需要清理的选项格式")
|
|||
|
|
else:
|
|||
|
|
print("❌ 语法错误：")
|
|||
|
|
print(result.stderr)
|
|||
|
|
print("\n正在恢复备份...")
|
|||
|
|
with open(backup_file, 'r', encoding='utf-8') as f:
|
|||
|
|
content = f.read()
|
|||
|
|
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(content)
|
|||
|
|
print("已恢复到备份版本")
|
|||
|
|
|
|||
|
|
print("\n✅ 清理完成！")
|