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

# 读取化工岗位简历数据
with open('网页未导入数据/化工产业/化工岗位简历.json', 'r', encoding='utf-8') as f:
    chemical_data = json.load(f)

# 统计和收集所有岗位群的面试题
job_group_questions = {}
total_questions = 0
positions_per_group = {}

# 遍历所有岗位
for position_data in chemical_data:
    position_name = position_data.get('positionName', '')
    job_group = position_data.get('jobGroup', '')

    # 初始化岗位群数据
    if job_group not in job_group_questions:
        job_group_questions[job_group] = []
        positions_per_group[job_group] = []

    positions_per_group[job_group].append(position_name)

    # 提取该岗位的面试题
    if 'interviewQuestions' in position_data:
        interview_content = position_data['interviewQuestions']

        # 解析面试题内容
        questions = []

        # 按换行分割，每两行构成一个问答对
        lines = [line.strip() for line in interview_content.split('\n') if line.strip()]

        for i in range(0, len(lines), 2):
            if i + 1 < len(lines):
                question = lines[i]
                answer = lines[i + 1]

                # 清理问题和答案文本
                question = re.sub(r'^问题\d+[:：]\s*', '', question)
                question = re.sub(r'^问[:：]\s*', '', question)
                question = re.sub(r'^\d+[、.]\s*', '', question)

                answer = re.sub(r'^答案[:：]\s*', '', answer)
                answer = re.sub(r'^答[:：]\s*', '', answer)
                answer = re.sub(r'^解答[:：]\s*', '', answer)

                if question and answer:
                    questions.append({
                        "question": question.strip(),
                        "answer": answer.strip()
                    })
            elif i < len(lines):
                # 如果只有一行，作为问题，答案使用通用答案
                question = lines[i]
                question = re.sub(r'^问题\d+[:：]\s*', '', question)
                question = re.sub(r'^\d+[、.]\s*', '', question)

                if question.strip():
                    questions.append({
                        "question": question.strip(),
                        "answer": f"这是{position_name}岗位的重要考察点，需要根据个人经验和专业知识进行回答。"
                    })

        # 添加到岗位群的问题列表
        for q in questions:
            # 检查是否已存在完全相同的问题
            is_duplicate = False
            for existing in job_group_questions[job_group]:
                if existing['question'] == q['question']:
                    is_duplicate = True
                    break

            if not is_duplicate and q['question'] and q['answer']:
                job_group_questions[job_group].append(q)
                total_questions += 1

# 输出统计信息
print(f"\n===== 化工岗位面试题统计 =====")
print(f"总岗位数: {len(chemical_data)}")
print(f"总岗位群数: {len(job_group_questions)}")
print(f"总面试题数: {total_questions}")
print(f"\n各岗位群面试题数量：")

for job_group, questions in sorted(job_group_questions.items()):
    positions = positions_per_group[job_group]
    if len(positions) > 3:
        positions_str = ', '.join(positions[:3]) + f' 等{len(positions)}个岗位'
    else:
        positions_str = ', '.join(positions)
    print(f"  {job_group}: {len(questions)} 题 (包含: {positions_str})")

# 输出前几个岗位群的面试题示例
print(f"\n===== 面试题示例 =====")
for job_group in list(job_group_questions.keys())[:2]:
    print(f"\n【{job_group}】的前3道面试题：")
    for i, q in enumerate(job_group_questions[job_group][:3], 1):
        print(f"  {i}. 问：{q['question'][:50]}...")
        print(f"     答：{q['answer'][:50]}...")

# 保存面试题数据到JSON文件
with open('all_interview_questions.json', 'w', encoding='utf-8') as f:
    json.dump(job_group_questions, f, ensure_ascii=False, indent=2)
print(f"\n✅ 已保存所有面试题到 all_interview_questions.json")

print(f"\n下一步：生成更新脚本...")