#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import json
import re
from datetime import datetime

print("=== 完整面试题更新工具 ===")
print("此工具将完整导入所有岗位群的所有章节面试题")

# 读取智能制造岗位简历数据
print("\n1. 读取源数据...")
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("2. 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_update_{backup_time}'
with open(backup_file, 'w', encoding='utf-8') as f:
    f.write(mock_content)
print(f"3. 已创建备份: {backup_file}")

# 解析智能制造岗位简历数据
interview_data_map = {}

print("\n4. 解析面试题数据...")
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:
        questions_data = []
        
        # 按 # 分割章节，但保留 # 标记
        sections = re.split(r'\n(?=# )', interview_content.strip())
        
        for section in sections:
            if not section.strip():
                continue
                
            lines = section.split('\n')
            if not lines:
                continue
                
            # 第一行是章节标题
            section_title = lines[0].strip()
            if section_title.startswith('# '):
                section_title = section_title[2:].strip()
            
            if not section_title:
                continue
                
            current_section_questions = []
            
            # 解析该章节中的问题
            i = 1  # 跳过标题行
            while i < len(lines):
                line = lines[i].strip()
                if not line:
                    i += 1
                    continue
                
                # 查找问题编号（如 1. xxx 或 1、xxx）
                question_match = re.match(r'^(\d+)[\.\、]\s*(.+)', line)
                if question_match:
                    question_text = question_match.group(2).strip()
                    
                    # 查找答案
                    answer_lines = []
                    i += 1  # 移到下一行开始查找答案
                    
                    while i < len(lines):
                        next_line = lines[i].strip()
                        
                        # 如果遇到下一个问题，停止
                        if re.match(r'^\d+[\.\、]\s*', next_line):
                            i -= 1  # 回退，让外层循环处理
                            break
                            
                        # 处理答案内容
                        if next_line:
                            # 移除答案标记
                            if re.match(r'^答案[：:]?\s*', next_line):
                                answer_text = re.sub(r'^答案[：:]?\s*', '', next_line)
                                if answer_text:
                                    answer_lines.append(answer_text)
                            elif not re.match(r'^答案', next_line):
                                # 其他内容作为答案的一部分
                                answer_lines.append(next_line)
                        
                        i += 1
                    
                    # 整理答案
                    answer = ' '.join(answer_lines).strip()
                    if not answer:
                        answer = "请根据实际情况回答"
                    
                    current_section_questions.append({
                        'question': question_text,
                        'answer': answer
                    })
                else:
                    i += 1
            
            # 如果该章节有问题，添加到结果中
            if current_section_questions:
                questions_data.append({
                    'id': f'group_q{len(questions_data) + 1}',
                    'title': section_title,
                    'questions': current_section_questions
                })
        
        interview_data_map[job_group] = questions_data

print(f"\n解析结果:")
total_sections = 0
total_questions = 0
for group, data in interview_data_map.items():
    section_count = len(data)
    question_count = sum(len(section['questions']) for section in data)
    total_sections += section_count
    total_questions += question_count
    print(f"  - {group}: {section_count} 个章节，{question_count} 道题")

print(f"\n总计: {len(interview_data_map)} 个岗位群，{total_sections} 个章节，{total_questions} 道题")

# 更新mock文件中的面试题
def update_industry_questions(match):
    industry_name = match.group(1)

    # 查找对应的面试题数据
    if industry_name not in interview_data_map:
        return match.group(0)  # 保持原样

    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('{\\n            "id": "q{}_{}", \\n            "question": "{}", \\n            "answer": "{}"\\n          }'.format(
                section_data['id'][7:], idx+1, question_text, answer_text))

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

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

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

    # 构建完整的替换内容
    before_questions = match.group(0).split('"questions": [')[0]
    result = before_questions + '"questions": [\\n      ' + questions_str + '\\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("\n5. 正在更新面试题数据...")
pattern = r'"name":\s*"([^"]+)"[^}]*?"questions":\s*\[.*?\]\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("\n6. ✅ 面试题数据更新完成！")

# 验证语法
print("7. 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！")
    
    # 统计最终结果
    with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
        final_content = f.read()
    
    final_questions = len(re.findall(r'"id": "q[0-9]', final_content))
    final_sections = len(re.findall(r'"question": "# ', final_content))
    
    print(f"\n=== 最终统计 ===")
    print(f"总章节数: {final_sections}")
    print(f"总题目数: {final_questions}")
    print(f"\n现在用户可以在页面看到完整的面试题了！")
    
else:
    print("❌ 语法错误：")
    print(result.stderr)