#!/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_complete_{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 = []

        lines = interview_content.split('\n')
        current_section = None
        current_section_questions = []
        section_id = 1

        for line in lines:
            line = line.strip()
            if not line:
                continue

            # 大标题（如 # 一、xxx）
            if line.startswith('# '):
                # 保存上一个section
                if current_section and current_section_questions:
                    questions_data.append({
                        'id': f'group_q{section_id}',
                        'title': current_section,
                        'questions': current_section_questions
                    })
                    section_id += 1

                current_section = line[2:].strip()
                current_section_questions = []

            # 问题编号（如 1. xxx 或 1、xxx）
            elif re.match(r'^(\d+)[\.、]\s+', line):
                # 提取问题
                question_match = re.match(r'^(\d+)[\.、]\s+(.+)', line)
                if question_match:
                    question_text = question_match.group(2).strip()

                    # 查找后续的答案
                    answer_lines = []
                    line_index = lines.index(line) + 1

                    while line_index < len(lines):
                        next_line = lines[line_index].strip()

                        # 如果遇到下一个问题或章节，停止
                        if next_line.startswith('#') or re.match(r'^(\d+)[\.、]\s+', next_line):
                            break

                        # 如果是答案标记
                        if next_line.startswith('示例答案') or next_line.startswith('答案'):
                            # 提取答案内容
                            if '：' in next_line or ':' in next_line:
                                answer_text = re.sub(r'^(示例答案|答案)[：:]?\s*', '', next_line)
                                answer_lines.append(answer_text)
                            line_index += 1
                            # 继续读取多行答案
                            while line_index < len(lines):
                                next_line = lines[line_index].strip()
                                if not next_line or next_line.startswith('#') or re.match(r'^(\d+)[\.、]\s+', next_line):
                                    break
                                answer_lines.append(next_line)
                                line_index += 1
                            break
                        elif next_line:
                            # 如果没有明确的答案标记，下一行非空内容可能就是答案
                            answer_lines.append(next_line)
                            line_index += 1
                            break
                        else:
                            line_index += 1

                    answer = ' '.join(answer_lines).strip()

                    current_section_questions.append({
                        'question': question_text,
                        'answer': answer
                    })

        # 保存最后一个section
        if current_section and current_section_questions:
            questions_data.append({
                'id': f'group_q{section_id}',
                'title': current_section,
                '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")

# 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(f'''{{
            "id": "q{section_data['id'][7:]}_{idx+1}",
            "question": "{question_text}",
            "answer": "{answer_text}"
          }}''')

        section_title = section_data['title'].replace('\\', '\\\\').replace('"', '\\"')

        new_questions.append(f'''{{
        "id": "{section_data['id']}",
        "question": "# {section_title}",
        "subQuestions": [
          {','.join(sub_questions)}
        ]
      }}''')

    # 替换questions部分
    questions_str = ',\n      '.join(new_questions)

    # 构建完整的替换内容
    result = match.group(0).split('"questions": [')[0]
    result += '"questions": [\n      '
    result += questions_str
    result += '\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)