#!/usr/bin/env python3
import json
import re
from datetime import datetime

print("正在更新所有面试题数据（最终版）...")

# 读取提取好的面试题数据
with open('all_interview_questions_complete.json', 'r', encoding='utf-8') as f:
    job_group_questions = json.load(f)

# 统计信息
total_questions = sum(len(qs) for qs in job_group_questions.values())
print(f"准备更新 {len(job_group_questions)} 个岗位群，共 {total_questions} 道面试题")

# 读取现有mock文件
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    content = f.read()

# 备份
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
backup_file = f'src/mocks/resumeInterviewMock.js.backup_final_{timestamp}'
with open(backup_file, 'w', encoding='utf-8') as f:
    f.write(content)
print(f"已创建备份: {backup_file}")

# 更新每个岗位群
updated_count = 0
for job_group, questions in job_group_questions.items():
    if not questions:
        continue

    # 为每个问题创建正确的格式
    formatted_questions = []
    for i, q in enumerate(questions, 1):
        # 清理答案中的特殊字符
        answer = q['answer']
        # 将多个连续换行符替换为单个
        answer = re.sub(r'\n+', ' ', answer)
        # 将列表符号后的换行替换为空格
        answer = re.sub(r'[-•]\s*', '• ', answer)
        # 清理多余空格
        answer = re.sub(r'\s+', ' ', answer).strip()

        formatted_questions.append({
            "id": f"q{i}",
            "question": q['question'].strip(),
            "answer": answer
        })

    # 手动构建JSON字符串以确保格式正确
    sub_questions_parts = []
    for q in formatted_questions:
        # 使用json.dumps确保字符串正确转义
        q_str = json.dumps(q['question'], ensure_ascii=False)
        a_str = json.dumps(q['answer'], ensure_ascii=False)

        sub_questions_parts.append(f'''        {{
                "id": "{q['id']}",
                "question": {q_str},
                "answer": {a_str}
        }}''')

    sub_questions_str = ',\n'.join(sub_questions_parts)
    sub_questions_array = f"[\n{sub_questions_str}\n        ]"

    # 替换对应岗位群的subQuestions
    # 使用更精确的模式匹配
    pattern = rf'("question"\s*:\s*"{re.escape(job_group)}岗位群面试题"\s*,\s*"subQuestions"\s*:\s*)\[[^\]]*?\]'

    def replacement_func(match):
        return match.group(1) + sub_questions_array

    new_content = re.sub(pattern, replacement_func, content, flags=re.DOTALL)

    if new_content != content:
        content = new_content
        updated_count += 1
        print(f"✓ 已更新 {job_group}: {len(questions)} 道题")

# 保存更新后的文件
if updated_count > 0:
    with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
        f.write(content)
    print(f"\n✅ 成功更新了 {updated_count} 个岗位群")

# 验证语法
import subprocess
try:
    result = subprocess.run(['node', '-c', 'src/mocks/resumeInterviewMock.js'],
                          capture_output=True, text=True, encoding='utf-8')
    if result.returncode == 0:
        print("✓ 语法检查通过")
        print(f"\n🎉 所有面试题更新成功！共 {total_questions} 道题")

        # 显示各岗位群题目数量
        print("\n各岗位群题目数量：")
        for group, qs in sorted(job_group_questions.items()):
            print(f"  {group}: {len(qs)} 道题")

    else:
        print(f"✗ 语法检查失败: {result.stderr}")
        # 恢复备份
        with open(backup_file, 'r', encoding='utf-8') as f:
            backup_content = f.read()
        with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
            f.write(backup_content)
        print("已从备份恢复")
except Exception as e:
    print(f"错误: {e}")