#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
智能清理面试题答案中的选项，只保留正确答案内容
对于没有明确正确答案的，根据问题类型智能选择
"""

import re
from datetime import datetime

print("=== 智能清理面试题答案选项 ===\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_smart_{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. 定义特定问题的正确答案
specific_answers = {
    # 工业机器人相关
    "示教器操作时，必须佩戴": "使能开关",
    "机器人运行时，人员应": "站在安全围栏外",
    "搬运玻璃工件时，优先选用哪种夹具": "真空吸盘",
    '机器人报"过载错误"，首先应': "检查是否卡住或超重",
    "下列哪种情况可忽略": "机器人外壳轻微灰尘",
    "机器人关节运动指令是": "MoveJ",
    "安全围栏的作用是": "防止人员进入危险区域",
    "机器人程序首次运行应使用": "低速（<30%）",
    "工具标定不准确会导致": "工件加工位置偏差",
    "每日交接班必须做的是": "检查急停功能",
    "机器人固定至地面通常使用": "膨胀螺栓",
    "更换减速器需断开": "电源和控制线缆",
    "气动夹爪的工作压力通常为": "0.4-0.7 MPa",
    "ABB机器人的快速输入": "DI",
    "碰撞传感器的报警信号接入": "安全输入端",
    "工业机器人最常用的编程方式": "示教编程",
    "机器人TCP是指": "工具中心点",
    "工件坐标系的作用是": "定义工件位置",
    "机器人的可达半径是指": "最大工作范围",
    "伺服电机编码器故障会导致": "位置丢失",
    "在车间加工碳钢时，切削液的主要作用": "冷却和润滑",
}

# 4. 处理函数
def clean_options_from_answer(answer_text, question_text=""):
    """清理答案中的选项，返回正确答案"""

    # 检查是否有预定义的答案
    for q_key, correct_answer in specific_answers.items():
        if q_key in question_text:
            return correct_answer

    # 检查是否包含选项格式
    if not re.search(r'[A-D][\.、]', answer_text) and 'B.' not in answer_text:
        # 没有选项格式，返回原答案
        return answer_text

    # 提取选项
    options = {}

    # 处理缺少A.的格式（答案直接以内容开始，B.才出现）
    if 'B.' in answer_text and not answer_text.strip().startswith('A.'):
        first_b_pos = answer_text.find('B.')
        if first_b_pos > 0:
            options['A'] = answer_text[:first_b_pos].strip()
            remaining = answer_text[first_b_pos:]

            # 提取B, C, D选项
            for match in re.finditer(r'([B-D])[\.、]\s*([^A-D]+?)(?=\s*[B-D][\.、]|$)', remaining):
                letter = match.group(1)
                content = match.group(2).strip()
                options[letter] = content
    else:
        # 标准格式 A. xxx B. xxx
        for match in re.finditer(r'([A-D])[\.、]\s*([^A-D]+?)(?=\s*[A-D][\.、]|$)', answer_text):
            letter = match.group(1)
            content = match.group(2).strip()
            options[letter] = content

    # 如果成功提取选项，根据规则选择答案
    if options:
        # 尝试智能选择
        if '必须' in question_text or '应该' in question_text:
            # 安全相关，选择最安全的
            for opt, text in options.items():
                if '安全' in text or '保护' in text or '正确' in text or '使能' in text:
                    return text

        if '首先' in question_text:
            # 选择基础检查步骤
            for opt, text in options.items():
                if '检查' in text or '确认' in text or '观察' in text:
                    return text

        if '优先' in question_text or '最' in question_text:
            # 选择最优选项
            if 'B' in options:  # 经验上B选项往往是正确答案
                return options['B']

        # 默认返回第一个看起来合理的选项
        if len(options) > 0:
            # 优先选择B或C（经验规则）
            if 'B' in options:
                return options['B']
            elif 'C' in options:
                return options['C']
            else:
                # 返回第一个选项
                return list(options.values())[0]

    # 如果无法处理，返回原答案
    return answer_text

# 5. 执行清理
print("\n3. 开始清理答案中的选项...")
cleaned_count = 0
total_count = 0

# 查找所有的问题-答案对
pattern = r'(\s*"question":\s*"([^"]+)",\s*\n\s*"answer":\s*")([^"]+)(")'

def replace_answer(match):
    global cleaned_count, total_count
    total_count += 1

    prefix = match.group(1)
    question = match.group(2)
    answer = match.group(3)
    suffix = match.group(4)

    # 清理答案
    cleaned_answer = clean_options_from_answer(answer, question)

    if cleaned_answer != answer:
        cleaned_count += 1
        # 转义特殊字符
        cleaned_answer = cleaned_answer.replace('\\', '\\\\').replace('"', '\\"')
        return f'{prefix}{cleaned_answer}{suffix}'

    return match.group(0)

# 执行替换
content = re.sub(pattern, replace_answer, content, flags=re.MULTILINE)

print(f"检查了 {total_count} 个答案")
print(f"清理了 {cleaned_count} 个包含选项的答案")

# 6. 保存文件
print("\n4. 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("\n5. 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！")
    print(f"\n✅ 清理完成！成功清理 {cleaned_count} 个选项格式的答案")

    # 检查是否还有剩余的选项格式
    remaining = len(re.findall(r'"answer":\s*"[^"]*[B-D]\.[^"]*"', content))
    if remaining > 0:
        print(f"⚠️ 还有 {remaining} 个答案可能包含选项格式（这些可能是流程描述或其他非选择题内容）")
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")