LQAgentPlatform/utils_test/standard_new_Test/test_user_standards.py

"""
测试用户提供的4个标准规范
验证归一化匹配逻辑是否有效
直接使用生产代码 core.construction_review.component.standard_matching 模块
"""
import asyncio
import sys
import os

# 添加项目根目录到 Python 路径
current_dir = os.path.dirname(os.path.abspath(__file__))
project_root = os.path.dirname(os.path.dirname(current_dir))
if project_root not in sys.path:
    sys.path.insert(0, project_root)

from conftest import (
    StandardRepository,
    StandardMatcher,
    MatchResultCode,
)

# Mock 数据
MOCK_DATA = [
    {"id": 1, "standard_name": "铁路桥涵设计规范", "standard_number": "TB 10002-2017", "validity": "XH"},
    {"id": 2, "standard_name": "铁路工程抗震设计规范", "standard_number": "GB 50111-2006", "validity": "XH"},
    {"id": 3, "standard_name": "铁路混凝土工程施工质量验收标准", "standard_number": "TB 10424-2018", "validity": "XH"},
    {"id": 4, "standard_name": "公路水运危险性较大工程专项施工方案编制审查规程", "standard_number": "JT/T 1495-2024", "validity": "XH"},
]


def create_matcher():
    """创建加载了 Mock 数据的匹配器"""
    repo = StandardRepository()
    repo.load_data(MOCK_DATA)
    return StandardMatcher(repo)


def check_standards(matcher, standards):
    """批量检查（模拟 StandardMatchingService.check_standards）"""
    results = []
    for idx, std in enumerate(standards, start=1):
        result = matcher.match(
            seq_no=idx,
            input_name=std.get("standard_name", ""),
            input_number=std.get("standard_number", "")
        )
        if result is not None:
            results.append(result)
    return results


async def test_user_standards():
    """测试用户提供的4个标准"""
    matcher = create_matcher()

    # 用户提供的4个标准
    test_standards = [
        {"standard_name": "铁路桥涵设计规范", "standard_number": "TB 10002-2017"},
        {"standard_name": "铁路工程抗震设计规范", "standard_number": "GB 50111-2006"},
        {"standard_name": "铁路混凝土工程施工质量验收标准", "standard_number": "TB 10424-2018"},
        {"standard_name": "公路水运危险性较大工程专项施工方案编制审查规程", "standard_number": "JT/T 1495-2023"},
    ]

    print("=" * 80)
    print("测试用户提供的4个标准（使用生产代码归一化匹配）")
    print("=" * 80)

    results = check_standards(matcher, test_standards)

    all_passed = True
    for i, result in enumerate(results, 1):
        print(f"\n【{i}】{result.raw_name}")
        print(f"    标准号: {result.raw_number}")
        print(f"    状态码: {result.status_code}")
        print(f"    处理结果: {result.process_result}")
        print(f"    最终结果: {result.final_result}")

        # 验证预期结果
        if i <= 3:
            # 前3个应该是 OK
            if result.status_code != MatchResultCode.OK.value:
                print(f"    [失败] 期望 OK，实际 {result.status_code}")
                all_passed = False
            else:
                print(f"    [通过]")
        else:
            # 第4个应该是 MISMATCH（因为Mock数据中是2024版）
            if result.status_code != MatchResultCode.MISMATCH.value:
                print(f"    [失败] 期望 MISMATCH，实际 {result.status_code}")
                all_passed = False
            else:
                print(f"    [通过]")

    print("\n" + "=" * 80)
    if all_passed:
        print("[成功] 所有测试通过！")
    else:
        print("[失败] 部分测试失败！")
    print("=" * 80)

    return all_passed


def test_with_bookname_variations():
    """测试书名号变体（归一化匹配）"""
    print("\n" + "=" * 80)
    print("测试书名号变体匹配（生产代码归一化）")
    print("=" * 80)

    repo = StandardRepository()
    mock_data = [
        {"id": 1, "standard_name": "铁路桥涵设计规范", "standard_number": "TB 10002-2017", "validity": "XH"},
    ]
    repo.load_data(mock_data)
    matcher = StandardMatcher(repo)

    # 测试各种名称变体
    test_cases = [
        ("铁路桥涵设计规范", "TB 10002-2017", "无书名号"),
        ("《铁路桥涵设计规范》", "TB 10002-2017", "带书名号"),
        ("铁路桥涵 设计规范", "TB 10002-2017", "带空格（归一化去除后匹配）"),
        ("《铁路桥涵 设计规范》", "TB 10002-2017", "带书名号和空格（归一化去除后匹配）"),
    ]

    all_passed = True
    for name, number, desc in test_cases:
        result = matcher.match(1, name, number)
        # 归一化会去除所有空白，所以带空格的变体也应匹配成功
        if result is not None and result.status_code == MatchResultCode.OK.value:
            status = "[OK]"
        else:
            status = "[FAIL]"
            all_passed = False
        print(f"\n{status} {desc}")
        print(f"   输入名称: {name}")
        if result:
            print(f"   结果: {result.status_code}")
        else:
            print(f"   结果: None（跳过审查）")

    return all_passed


if __name__ == "__main__":
    # 运行异步测试
    result1 = asyncio.run(test_user_standards())

    # 运行书名号变体测试
    result2 = test_with_bookname_variations()

    print("\n" + "=" * 80)
    if result1 and result2:
        print("[成功] 所有测试通过！")
        sys.exit(0)
    else:
        print("[警告] 部分测试失败！")
        sys.exit(1)