online_sys/frontend_智能制造/update_all_interviews_direct.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
直接更新所有岗位群的面试题
使用更精确的文本处理方法
"""

import json
import re
from datetime import datetime

print("=== 直接更新所有岗位群面试题 ===\n")

# 1. 读取源数据
print("1. 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:
    source_data = json.load(f)

# 2. 解析所有面试题（只保留唯一的岗位群）
print("2. 解析面试题数据...")
interview_questions_map = {}

for item in source_data:
    job_group = item.get('简历岗位群', '')
    interview_content = item.get('面试题内容', '')

    if not job_group or not interview_content or job_group in interview_questions_map:
        continue  # 跳过已处理的岗位群

    # 收集所有问题
    all_questions = []

    lines = interview_content.split('\n')
    i = 0
    while i < len(lines):
        line = lines[i].strip()

        # 匹配问题编号
        question_match = re.match(r'^(\d+)[\.、]\s*(.+)', line)
        if question_match:
            question_text = question_match.group(2).strip()

            # 查找答案
            answer = ""
            i += 1

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

                if re.match(r'^\d+[\.、]\s*', next_line) or next_line.startswith('#'):
                    i -= 1
                    break

                if next_line and (next_line.startswith('答案') or next_line.startswith('示例答案')):
                    answer = re.sub(r'^(答案|示例答案)[：:]?\s*', '', next_line).strip()
                    if not answer:
                        i += 1
                        if i < len(lines):
                            answer = lines[i].strip()
                    break
                elif next_line and not answer:
                    answer = next_line
                    break

                i += 1

            if not answer:
                answer = "请根据实际情况回答"

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

        i += 1

    if all_questions:
        interview_questions_map[job_group] = all_questions
        print(f"  - {job_group}: {len(all_questions)} 道题")

print(f"\n共解析 {len(interview_questions_map)} 个岗位群")

# 3. 读取当前mock文件
print("\n3. 读取当前mock文件...")
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    mock_content = f.read()

# 4. 备份
backup_time = datetime.now().strftime('%Y%m%d_%H%M%S')
backup_file = f'src/mocks/resumeInterviewMock.js.backup_direct_{backup_time}'
print(f"4. 创建备份: {backup_file}")
with open(backup_file, 'w', encoding='utf-8') as f:
    f.write(mock_content)

# 5. 逐个岗位群更新
print("\n5. 开始更新各岗位群...")
updated_count = 0

for job_group, questions in interview_questions_map.items():
    print(f"\n处理 {job_group}...")

    # 构建新的questions数组
    sub_questions_list = []
    for idx, q in enumerate(questions, 1):
        question_text = q['question'].replace('\\', '\\\\').replace('"', '\\"')
        answer_text = q['answer'].replace('\\', '\\\\').replace('"', '\\"').replace('\n', ' ')

        sub_questions_list.append(f'''{{
            "id": "q1_{idx}",
            "question": "{question_text}",
            "answer": "{answer_text}"
          }}''')

    # 构建完整的questions结构
    new_questions_str = f'''[
      {{
        "id": "group_q1",
        "question": "# {job_group}岗位面试题",
        "subQuestions": [
          {','.join(sub_questions_list)}
        ]
      }}
    ]'''

    # 使用更精确的查找和替换
    # 先找到岗位群的位置
    job_group_pattern = f'"name": "{job_group}"'
    job_group_pos = mock_content.find(job_group_pattern)

    if job_group_pos == -1:
        print(f"  ⚠️ 未找到 {job_group}")
        continue

    # 从该位置开始查找 questions 字段
    search_start = job_group_pos
    questions_start = mock_content.find('"questions":', search_start)

    if questions_start == -1 or questions_start - job_group_pos > 5000:  # 限制搜索范围
        print(f"  ⚠️ 未找到 {job_group} 的questions字段")
        continue

    # 找到 questions 数组的开始 [
    array_start = mock_content.find('[', questions_start)
    if array_start == -1:
        print(f"  ⚠️ 未找到 {job_group} 的questions数组开始")
        continue

    # 找到对应的结束 ]
    bracket_count = 1
    pos = array_start + 1
    array_end = -1

    while pos < len(mock_content) and bracket_count > 0:
        if mock_content[pos] == '[':
            bracket_count += 1
        elif mock_content[pos] == ']':
            bracket_count -= 1
            if bracket_count == 0:
                array_end = pos
                break
        pos += 1

    if array_end == -1:
        print(f"  ⚠️ 未找到 {job_group} 的questions数组结束")
        continue

    # 替换questions数组
    before = mock_content[:array_start]
    after = mock_content[array_end + 1:]
    mock_content = before + new_questions_str + after

    print(f"  ✅ {job_group} 已更新为 {len(questions)} 道题")
    updated_count += 1

# 6. 保存文件
print(f"\n6. 保存更新后的文件...")
print(f"   共更新 {updated_count} 个岗位群")
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(mock_content)

# 7. 验证语法
print("\n7. 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=== 更新完成 ===")
    print(f"成功更新 {updated_count}/{len(interview_questions_map)} 个岗位群")

    # 统计最终结果
    print("\n=== 最终统计 ===")
    with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
        final_content = f.read()

    for group in interview_questions_map.keys():
        # 查找该岗位群的questions
        group_pos = final_content.find(f'"name": "{group}"')
        if group_pos != -1:
            # 从该位置向后查找questions
            questions_pos = final_content.find('"questions":', group_pos)
            if questions_pos != -1 and questions_pos - group_pos < 5000:
                # 统计该区域的题目数量
                search_end = questions_pos + 10000  # 限制搜索范围
                section = final_content[questions_pos:min(search_end, len(final_content))]
                count = len(re.findall(r'"id": "q1_\d+"', section))
                expected = len(interview_questions_map[group])
                status = "✅" if count == expected else f"⚠️ ({count}/{expected})"
                print(f"  {status} {group}: {count} 道题")
            else:
                print(f"  ❌ {group}: 未找到questions")
        else:
            print(f"  ❌ {group}: 未找到岗位群")
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:
        mock_content = f.read()
    with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
        f.write(mock_content)
    print("已恢复到备份版本")