import json
import re

# 读取食品项目案例数据
with open('网页未导入数据/食品产业/食品项目案例.json', 'r', encoding='utf-8') as f:
    food_cases = json.load(f)

print(f"总共找到 {len(food_cases)} 个食品项目案例")

# 分析有附件的项目，并按照所属单元分类
projects_with_attachments = []
unit_mapping = {}

for case in food_cases:
    case_name = case.get('案例名称', '')
    compound_unit = case.get('对应单元名称（复合能力课）', '')
    vertical_unit = case.get('对应单元名称（垂直能力课）', '')
    attachments_str = case.get('附件', '')

    # 只处理有附件的项目
    if attachments_str and attachments_str.strip():
        # 解析附件字符串
        attachments = []
        for attachment in attachments_str.split(','):
            attachment = attachment.strip()
            if attachment:
                # 提取文件扩展名
                ext_match = re.search(r'\.([a-zA-Z0-9]+)$', attachment)
                file_type = ext_match.group(1).lower() if ext_match else 'unknown'

                attachments.append({
                    "id": f"attach_{len(attachments) + 1}",
                    "name": attachment,
                    "type": file_type,
                    "size": "2.5MB",  # 模拟文件大小
                    "url": f"https://example.com/files/{attachment}"
                })

        # 确定单元名称（优先使用复合能力课）
        unit_name = compound_unit if compound_unit else vertical_unit
        if not unit_name:
            unit_name = "其他"

        # 创建简化的项目名称（去掉"项目"后缀）
        simplified_name = case_name.replace('项目', '').strip()

        project_data = {
            "originalName": case_name,
            "simplifiedName": simplified_name,
            "unitName": unit_name,
            "attachments": attachments
        }

        projects_with_attachments.append(project_data)

        # 按单元分类
        if unit_name not in unit_mapping:
            unit_mapping[unit_name] = []
        unit_mapping[unit_name].append(project_data)

print(f"\n找到 {len(projects_with_attachments)} 个有附件的项目")
print(f"涉及 {len(unit_mapping)} 个单元")

print("\n按单元分类的有附件项目:")
for unit, projects in unit_mapping.items():
    print(f"\n【{unit}】:")
    for project in projects:
        print(f"  - {project['simplifiedName']}")
        for att in project['attachments']:
            print(f"    * {att['name']} ({att['type']})")

# 生成新的我的项目库数据，使用真实的有附件项目
new_my_projects_data = []

for unit, projects in unit_mapping.items():
    project_names = [project['simplifiedName'] for project in projects]
    new_my_projects_data.append({
        "unitName": unit,
        "projects": project_names
    })

# 生成JavaScript代码 - 我的项目库数据
my_projects_js = '''// 我的项目库数据 - 基于真实食品项目案例
const myProjectsData = [
'''

for unit_data in new_my_projects_data:
    my_projects_js += f'  {{\n'
    my_projects_js += f'    "unitName": "{unit_data["unitName"]}",\n'
    my_projects_js += f'    "projects": [\n'
    for project in unit_data["projects"]:
        my_projects_js += f'      "{project}",\n'
    my_projects_js = my_projects_js.rstrip(',\n') + '\n'
    my_projects_js += f'    ]\n'
    my_projects_js += f'  }},\n'

my_projects_js = my_projects_js.rstrip(',\n') + '\n'
my_projects_js += '];'

# 生成JavaScript代码 - 附件数据映射
attachments_js = '''// 项目附件数据映射 - 基于真实食品项目案例
const projectAttachmentsData = {
'''

for project in projects_with_attachments:
    attachments_js += f'  "{project["simplifiedName"]}": [\n'
    for att in project['attachments']:
        attachments_js += f'    {{\n'
        attachments_js += f'      "id": "{att["id"]}",\n'
        attachments_js += f'      "name": "{att["name"]}",\n'
        attachments_js += f'      "type": "{att["type"]}",\n'
        attachments_js += f'      "size": "{att["size"]}",\n'
        attachments_js += f'      "url": "{att["url"]}"\n'
        attachments_js += f'    }},\n'
    attachments_js = attachments_js.rstrip(',\n') + '\n'
    attachments_js += f'  ],\n'

attachments_js = attachments_js.rstrip(',\n') + '\n'
attachments_js += '''};

export default projectAttachmentsData;
'''

print(f"\n生成的我的项目库JavaScript代码：")
print(my_projects_js)

print(f"\n生成的附件数据JavaScript代码：")
print(attachments_js)

# 保存到文件
with open('my_projects_data_real_food.js', 'w', encoding='utf-8') as f:
    f.write(my_projects_js)

with open('project_attachments_data_real.js', 'w', encoding='utf-8') as f:
    f.write(attachments_js)

print(f"\n已保存到文件:")
print(f"  - my_projects_data_real_food.js")
print(f"  - project_attachments_data_real.js")

print(f"\n统计信息：")
print(f"  有附件的项目总数: {len(projects_with_attachments)}")
print(f"  涉及单元数: {len(unit_mapping)}")
print(f"  总项目数: {sum(len(projects) for projects in unit_mapping.values())}")

# 显示每个单元的项目数量
print(f"\n各单元项目数量:")
for unit, projects in unit_mapping.items():
    print(f"  {unit}: {len(projects)} 个项目")