# -*- coding: utf-8 -*-
"""
测试项目名称提取逻辑
"""
import logging
import sys
import os

# 添加当前目录到模块搜索路径
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))

# 配置日志
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)

def test_project_name_extraction():
    """测试项目名称提取逻辑"""
    logger.info("开始测试项目名称提取逻辑")
    
    # 测试用例
    test_titles = [
        "[招标文件]（测-试）临海市房建施工0212-2招标文件公示[A3300000090000695005001]",
        "[招标文件]通途路（大闸路-湖西路）拓宽改造工程（监理）项目招标文件预公示[A3302010220026373001001]",
        "[招标文件]集成电路链主企业配套产业园（南片）B、H、F～G地块及配套项目-B地块建设工程（01地块）施工招标文件公示[A3306021280001738001001]",
        "[招标文件]临海市副中心城市片区基础设施更新改造工程—沿河路、前王路及镇政府停车场改造提升招标文件公示[A3300000090000689001001]",
        "[招标文件]宁波市海曙绿道提升工程（施工）招标文件预公示[A3302030230026386001001]",
        "[招标文件]嘉科微二号园一号楼改造提升工程设计采购施工总承包(EPC)招标文件公示[A3304010550007317001001]",
    ]
    
    # 导入正则表达式
    import re
    
    for title in test_titles:
        logger.info(f"\n测试标题: {title}")
        
        # 使用修改后的标题解析逻辑
        title_pattern = r"\[(?:招标文件|招标公告)\]\s*(.*?)\s*\[([A-Z0-9]+)\]\s*$"
        match = re.search(title_pattern, title)
        if match:
            project_name = match.group(1).strip()
            # 删除结尾的"招标文件公示"、"招标文件预公示"等后缀
            suffixes = ["招标文件公示", "招标文件预公示", "招标公告", "招标预公告"]
            for suffix in suffixes:
                if project_name.endswith(suffix):
                    project_name = project_name[:-len(suffix)].strip()
            project_approval = match.group(2).strip()
            logger.info(f"  提取结果:")
            logger.info(f"  项目名称: {project_name}")
            logger.info(f"  项目批准文号: {project_approval}")
        else:
            logger.warning("  标题解析失败")

def main():
    """主函数"""
    test_project_name_extraction()

if __name__ == "__main__":
    main()