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

# 读取源数据
with open('网页未导入数据/交通物流产业/交通物流项目案例.json', 'r', encoding='utf-8') as f:
    source_data = json.load(f)

# 读取现有的mock文件
with open('src/mocks/projectLibraryMock.js', 'r', encoding='utf-8') as f:
    mock_content = f.read()

# 准备所有项目的详细内容
project_details = []
for idx, project in enumerate(source_data, 1):
    name = project['案例名称']
    content = project['项目案例内容']
    
    # 分割内容为不同部分
    # 提取项目概述
    overview_match = re.search(r'(.*?)(?=## 项目整体流程介绍|$)', content, re.DOTALL)
    overview = overview_match.group(1).strip() if overview_match else content[:1000]
    
    # 提取流程介绍
    process_match = re.search(r'## 项目整体流程介绍(.*?)(?=## 项目案例关键技术点|$)', content, re.DOTALL)
    process = process_match.group(1).strip() if process_match else ''
    if not process:
        process_match = re.search(r'### 流程.*?(?=### |## |$)', content, re.DOTALL)
        process = process_match.group(0) if process_match else '流程内容待补充'
    
    # 提取关键技术点
    keypoints_match = re.search(r'## 项目案例关键技术点(.*?)$', content, re.DOTALL)
    keypoints = keypoints_match.group(1).strip() if keypoints_match else ''
    if not keypoints:
        keypoints_match = re.search(r'### .*?技术.*?(?=### |## |$)', content, re.DOTALL)
        keypoints = keypoints_match.group(0) if keypoints_match else '技术点待补充'
    
    # 处理转义字符
    overview = overview.replace('\\', '\\\\').replace('`', '\\`').replace('${', '\\${')
    process = '## 项目整体流程介绍\\n' + process if not process.startswith('##') else process
    process = process.replace('\\', '\\\\').replace('`', '\\`').replace('${', '\\${')
    keypoints = '## 项目案例关键技术点\\n' + keypoints if not keypoints.startswith('##') else keypoints
    keypoints = keypoints.replace('\\', '\\\\').replace('`', '\\`').replace('${', '\\${')
    
    project_details.append({
        'id': idx,
        'name': name,
        'overview': overview,
        'process': process,
        'keypoints': keypoints,
        'positions': project.get('对应岗位', []),
        'attachments': project.get('附件', [])
    })

# 输出前5个项目的详细内容供更新
print("=== 项目3-5的详细内容 ===")
for i in range(2, min(5, len(project_details))):
    p = project_details[i]
    print(f"\n项目{p['id']}: {p['name']}")
    print(f"概述长度: {len(p['overview'])} 字符")
    print(f"流程长度: {len(p['process'])} 字符")
    print(f"技术点长度: {len(p['keypoints'])} 字符")
    print("---")

# 保存为JSON以便后续使用
with open('project_details_extracted.json', 'w', encoding='utf-8') as f:
    json.dump(project_details, f, ensure_ascii=False, indent=2)

print("\n详细内容已保存到 project_details_extracted.json")