Files
online_sys/frontend_智能制造/update_all_clean.py

258 lines
8.5 KiB
Python
Raw Permalink Normal View History

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
清洁版本完整更新所有岗位群的面试题
从智能制造岗位简历.json中提取完整数据
"""
import json
import re
from datetime import datetime
print("=== 完整更新所有岗位群面试题(清洁版) ===\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(只保留每个岗位群的第一个)
print("2. 解析面试题数据...")
interview_questions_map = {}
processed_groups = set()
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 processed_groups:
continue
processed_groups.add(job_group)
# 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_clean_{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. 处理每个岗位群
print("\n5. 开始更新各岗位群...")
successful_updates = []
failed_updates = []
# 处理顺序(按在文件中出现的顺序)
job_order = [
"3D打印工艺", "CNC加工工艺", "PLC", "钣金工程", "产品测试",
"产品设计", "电气设计", "非标自动化设计", "工业机器人", "焊接工艺",
"机加工工艺", "机器视觉", "模具工程", "塑性成形工艺", "特种加工工艺", "自动化控制"
]
for job_group in job_order:
if job_group not in interview_questions_map:
print(f" ⚠️ {job_group} 没有面试题数据")
continue
questions = interview_questions_map[job_group]
print(f"\n处理 {job_group} ({len(questions)} 道题)...")
# 构建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}"
}}''')
new_questions_str = f'''[
{{
"id": "group_q1",
"question": "# {job_group}岗位面试题",
"subQuestions": [
{','.join(sub_questions_list)}
]
}}
]'''
# 查找并替换
# 查找该岗位群的起始位置
pattern = f'"name": "{job_group}"'
start_pos = mock_content.find(pattern)
if start_pos == -1:
print(f" ❌ 未找到岗位群: {job_group}")
failed_updates.append(job_group)
continue
# 找到后面的questions字段
questions_pos = mock_content.find('"questions":', start_pos)
# 检查是否在合理范围内避免找到其他岗位群的questions
next_name_pos = mock_content.find('"name":', start_pos + len(pattern))
if next_name_pos != -1 and questions_pos > next_name_pos:
print(f"{job_group} 的questions字段超出范围")
failed_updates.append(job_group)
continue
if questions_pos == -1 or questions_pos - start_pos > 5000:
print(f" ❌ 未找到 {job_group} 的questions字段")
failed_updates.append(job_group)
continue
# 找到questions数组的起始[
array_start = mock_content.find('[', questions_pos)
if array_start == -1:
print(f" ❌ 未找到 {job_group} 的数组起始")
failed_updates.append(job_group)
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} 的数组结束")
failed_updates.append(job_group)
continue
# 执行替换
before = mock_content[:array_start]
after = mock_content[array_end + 1:]
mock_content = before + new_questions_str + after
print(f" ✅ 成功更新 {job_group}: {len(questions)} 道题")
successful_updates.append((job_group, len(questions)))
# 6. 保存文件
print(f"\n6. 保存更新后的文件...")
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: {len(successful_updates)} 个岗位群")
print(f"失败: {len(failed_updates)} 个岗位群")
if successful_updates:
print("\n✅ 成功更新的岗位群:")
for group, count in successful_updates:
print(f" - {group}: {count} 道题")
if failed_updates:
print("\n❌ 更新失败的岗位群:")
for group in failed_updates:
print(f" - {group}")
# 验证最终结果
print("\n=== 验证最终结果 ===")
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
final_content = f.read()
for group, expected_count in successful_updates:
# 查找该岗位群
group_pos = final_content.find(f'"name": "{group}"')
if group_pos != -1:
# 向后查找最近的questions
questions_pos = final_content.find('"questions":', group_pos)
if questions_pos != -1:
# 统计该区域内的题目数量
search_area = final_content[questions_pos:questions_pos + 20000]
# 找到下一个name或文件结束
next_name = search_area.find('"name":')
if next_name != -1:
search_area = search_area[:next_name]
actual_count = len(re.findall(r'"id": "q1_\d+"', search_area))
status = "" if actual_count == expected_count else f"⚠️"
print(f" {status} {group}: {actual_count}/{expected_count} 道题")
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")