宜博 / lemonboss

/**
 * YouTube Crawler Benchmark Test
 * 基于 benchmark.md 的评分标准（5维度：30/25/20/15/10）
 *
 * 重要：本测试在无 yt-dlp / 无 API Key 环境下使用 Mock 模式运行
 */

const { YouTubeTrendingCrawler, getMockTrendingVideos } = require('./youtube_crawler');
const fs = require('fs');
const path = require('path');

// 强制使用 Mock 模式（无外部依赖）
const FORCE_MOCK = true;

// 测试结果
const SCORES = {
  functionality: { score: 0, max: 30, details: [] },
  code_quality: { score: 0, max: 25, details: [] },
  api_usage: { score: 0, max: 20, details: [] },
  data_completeness: { score: 0, max: 15, details: [] },
  extensibility: { score: 0, max: 10, details: [] }
};

const LOGS = [];

function log(message, level = 'info') {
  const entry = { time: new Date().toISOString(), level, message };
  LOGS.push(entry);
  console.log(`[${level.toUpperCase()}] ${message}`);
}

// ============ 维度1: 功能完整性 (30分) ============

async function testGetTrending() {
  log('\n--- 测试: get_trending() 方法 (8分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler({ useMock: true });
    const videos = await crawler.get_trending('US', 5);

    if (Array.isArray(videos) && videos.length > 0) {
      score += 4;
      log('✅ 成功返回视频数组');
    } else {
      log('❌ 未返回视频数组');
    }

    if (videos.length <= 5) {
      score += 2;
      log('✅ maxResults 参数生效');
    }

    if (videos[0]?.videoId) {
      score += 2;
      log('✅ 视频包含 videoId');
    }
  } catch (error) {
    log(`❌ get_trending 测试失败: ${error.message}`, 'error');
  }

  SCORES.functionality.details.push({ test: 'get_trending', score, max: 8 });
  SCORES.functionality.score += score;
  log(`得分: ${score}/8`);
  return score;
}

async function testGetMultiRegionTrending() {
  log('\n--- 测试: get_multi_region_trending() 方法 (7分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler({ useMock: true });
    const results = await crawler.get_multi_region_trending(['US', 'JP', 'KR'], 3);

    if (results && typeof results === 'object') {
      score += 2;
      log('✅ 返回对象结构');
    }

    if (results.US && Array.isArray(results.US)) {
      score += 2;
      log('✅ US 地区数据正确');
    }

    if (results.JP && results.KR) {
      score += 2;
      log('✅ 多地区支持正常');
    }

    if (Object.keys(results).length === 3) {
      score += 1;
      log('✅ 所有请求的地区都有结果');
    }
  } catch (error) {
    log(`❌ get_multi_region_trending 测试失败: ${error.message}`, 'error');
  }

  SCORES.functionality.details.push({ test: 'get_multi_region_trending', score, max: 7 });
  SCORES.functionality.score += score;
  log(`得分: ${score}/7`);
  return score;
}

function testExtractVideoInfo() {
  log('\n--- 测试: extract_video_info() 方法 (5分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler();

    const mockApiItem = {
      id: 'test123',
      snippet: {
        title: 'Test Video',
        channelTitle: 'Test Channel',
        publishedAt: '2024-01-01T00:00:00Z',
        thumbnails: {
          default: { url: 'http://example.com/default.jpg' },
          medium: { url: 'http://example.com/medium.jpg' },
          high: { url: 'http://example.com/high.jpg' }
        },
        categoryId: '10'
      },
      statistics: {
        viewCount: '1000000'
      }
    };

    const result = crawler.extract_video_info(mockApiItem);

    // 检查所有必需字段
    const requiredFields = ['videoId', 'url', 'title', 'channelTitle', 'viewCount', 'publishedAt', 'thumbnails'];
    const hasAllFields = requiredFields.every(f => result[f] !== undefined);

    if (hasAllFields) {
      score += 2;
      log('✅ 所有必需字段存在');
    }

    if (result.videoId === 'test123') {
      score += 1;
      log('✅ videoId 正确提取');
    }

    if (result.url === 'https://youtube.com/watch?v=test123') {
      score += 1;
      log('✅ URL 正确构建');
    }

    if (result.viewCount === 1000000) {
      score += 1;
      log('✅ viewCount 正确解析为数字');
    }
  } catch (error) {
    log(`❌ extract_video_info 测试失败: ${error.message}`, 'error');
  }

  SCORES.functionality.details.push({ test: 'extract_video_info', score, max: 5 });
  SCORES.functionality.score += score;
  log(`得分: ${score}/5`);
  return score;
}

function testSaveToJson() {
  log('\n--- 测试: save_to_json() 方法 (5分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler();
    const testData = [{ videoId: 'test1', title: 'Test' }];
    const testPath = '/tmp/test_youtube_crawler.json';

    crawler.save_to_json(testData, testPath);

    if (fs.existsSync(testPath)) {
      score += 2;
      log('✅ 文件成功创建');

      const content = fs.readFileSync(testPath, 'utf-8');
      const parsed = JSON.parse(content);

      if (Array.isArray(parsed) && parsed[0].videoId === 'test1') {
        score += 2;
        log('✅ JSON 格式正确');
      }

      // 清理
      fs.unlinkSync(testPath);
      score += 1;
      log('✅ 文件写入完整');
    }
  } catch (error) {
    log(`❌ save_to_json 测试失败: ${error.message}`, 'error');
  }

  SCORES.functionality.details.push({ test: 'save_to_json', score, max: 5 });
  SCORES.functionality.score += score;
  log(`得分: ${score}/5`);
  return score;
}

function testSaveToCsv() {
  log('\n--- 测试: save_to_csv() 方法 (5分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler();
    const testData = [
      { videoId: 'v1', title: 'Video 1', channelTitle: 'Channel A', viewCount: 1000 },
      { videoId: 'v2', title: 'Video 2', channelTitle: 'Channel B', viewCount: 2000 }
    ];
    const testPath = '/tmp/test_youtube_crawler.csv';

    crawler.save_to_csv(testData, testPath);

    if (fs.existsSync(testPath)) {
      score += 2;
      log('✅ CSV 文件成功创建');

      const content = fs.readFileSync(testPath, 'utf-8');
      const lines = content.split('\n').filter(l => l.trim());

      if (lines.length >= 2) {
        score += 2;
        log('✅ CSV 包含表头和数据行');
      }

      if (lines[0].includes('videoId') && lines[0].includes('title')) {
        score += 1;
        log('✅ CSV 表头正确');
      }

      // 清理
      fs.unlinkSync(testPath);
    }
  } catch (error) {
    log(`❌ save_to_csv 测试失败: ${error.message}`, 'error');
  }

  SCORES.functionality.details.push({ test: 'save_to_csv', score, max: 5 });
  SCORES.functionality.score += score;
  log(`得分: ${score}/5`);
  return score;
}

// ============ 维度2: 代码质量 (25分) ============

function testClassStructure() {
  log('\n--- 测试: 类结构清晰 (5分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // 类定义
    if (code.includes('class YouTubeTrendingCrawler')) {
      score += 2;
      log('✅ YouTubeTrendingCrawler 类已定义');
    }

    // 构造函数
    if (code.includes('constructor(')) {
      score += 1;
      log('✅ 构造函数存在');
    }

    // 方法定义
    const methods = ['get_trending', 'get_multi_region_trending', 'extract_video_info', 'save_to_json', 'save_to_csv'];
    const hasAllMethods = methods.every(m => code.includes(m));

    if (hasAllMethods) {
      score += 2;
      log('✅ 所有必需方法存在');
    }
  } catch (error) {
    log(`❌ 类结构测试失败: ${error.message}`, 'error');
  }

  SCORES.code_quality.details.push({ test: 'class_structure', score, max: 5 });
  SCORES.code_quality.score += score;
  log(`得分: ${score}/5`);
  return score;
}

function testExceptionHandling() {
  log('\n--- 测试: 异常处理 (8分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // try-catch 块
    const tryCatchCount = (code.match(/try\s*\{/g) || []).length;
    if (tryCatchCount >= 3) {
      score += 2;
      log(`✅ 包含 ${tryCatchCount} 个 try-catch 块`);
    }

    // 输入验证
    if (code.includes('_validateRegionCode') && code.includes('_validateMaxResults')) {
      score += 2;
      log('✅ 输入验证方法存在');
    }

    // 网络异常处理
    if (code.includes('fetch') && code.includes('response.ok')) {
      score += 2;
      log('✅ 网络响应检查');
    }

    // API 错误处理
    if (code.includes('API error') || code.includes('403') || code.includes('429')) {
      score += 2;
      log('✅ API 错误码处理');
    }
  } catch (error) {
    log(`❌ 异常处理测试失败: ${error.message}`, 'error');
  }

  SCORES.code_quality.details.push({ test: 'exception_handling', score, max: 8 });
  SCORES.code_quality.score += score;
  log(`得分: ${score}/8`);
  return score;
}

function testLogging() {
  log('\n--- 测试: 日志记录 (5分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler({ useMock: true });

    // 检查日志方法
    if (typeof crawler._log === 'function' && typeof crawler.getLogs === 'function') {
      score += 2;
      log('✅ 日志方法存在');
    }

    // 执行操作产生日志
    crawler.getLogs(); // 触发可能的日志
    const logs = crawler.getLogs();

    if (logs.length > 0) {
      score += 2;
      log('✅ 日志记录工作正常');
    }

    // 日志结构
    if (logs[0]?.timestamp && logs[0]?.level) {
      score += 1;
      log('✅ 日志包含必要字段');
    }
  } catch (error) {
    log(`❌ 日志测试失败: ${error.message}`, 'error');
  }

  SCORES.code_quality.details.push({ test: 'logging', score, max: 5 });
  SCORES.code_quality.score += score;
  log(`得分: ${score}/5`);
  return score;
}

function testComments() {
  log('\n--- 测试: 代码注释 (4分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // JSDoc 注释
    const jsdocCount = (code.match(/\/\*\*/g) || []).length;
    if (jsdocCount >= 5) {
      score += 2;
      log(`✅ 包含 ${jsdocCount} 个 JSDoc 注释`);
    }

    // 方法注释
    const methods = ['get_trending', 'get_multi_region_trending', 'extract_video_info'];
    const commentedMethods = methods.filter(m => {
      const idx = code.indexOf(m);
      const before = code.slice(Math.max(0, idx - 200), idx);
      return before.includes('/**') || before.includes('//');
    });

    if (commentedMethods.length >= 2) {
      score += 2;
      log('✅ 关键方法有注释');
    }
  } catch (error) {
    log(`❌ 注释测试失败: ${error.message}`, 'error');
  }

  SCORES.code_quality.details.push({ test: 'comments', score, max: 4 });
  SCORES.code_quality.score += score;
  log(`得分: ${score}/4`);
  return score;
}

function testTypeAnnotations() {
  log('\n--- 测试: 类型提示 (3分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // JSDoc 类型注解
    if (code.includes('@param') && code.includes('@returns')) {
      score += 2;
      log('✅ 包含 JSDoc 类型注解');
    }

    // 参数类型说明
    const paramTypes = ['string', 'number', 'Object', 'Array', 'boolean'];
    const hasTypeDocs = paramTypes.some(t => code.includes(`{${t}}`) || code.includes(`{${t}[]}`));

    if (hasTypeDocs) {
      score += 1;
      log('✅ 参数类型有说明');
    }
  } catch (error) {
    log(`❌ 类型提示测试失败: ${error.message}`, 'error');
  }

  SCORES.code_quality.details.push({ test: 'type_annotations', score, max: 3 });
  SCORES.code_quality.score += score;
  log(`得分: ${score}/3`);
  return score;
}

// ============ 维度3: API 使用规范 (20分) ============

function testEnvironmentVariables() {
  log('\n--- 测试: 环境变量读取 (5分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // 检查环境变量读取
    if (code.includes('process.env.YOUTUBE_API_KEY')) {
      score += 3;
      log('✅ 从环境变量读取 API Key');
    }

    if (code.includes('YOUTUBE_CRAWLER_MOCK')) {
      score += 2;
      log('✅ 支持 Mock 环境变量');
    }
  } catch (error) {
    log(`❌ 环境变量测试失败: ${error.message}`, 'error');
  }

  SCORES.api_usage.details.push({ test: 'environment_variables', score, max: 5 });
  SCORES.api_usage.score += score;
  log(`得分: ${score}/5`);
  return score;
}

function testQuotaAwareness() {
  log('\n--- 测试: 配额意识 (5分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler();

    // 配额追踪属性
    if (crawler.quotaUsed !== undefined && crawler.quotaLimit !== undefined) {
      score += 2;
      log('✅ 配额追踪属性存在');
    }

    // 配额检查方法
    if (typeof crawler.getRemainingQuota === 'function') {
      score += 2;
      log('✅ 配额检查方法存在');
    }

    // 配额使用说明
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');
    if (code.includes('quota') && code.includes('10000')) {
      score += 1;
      log('✅ 配额限制说明');
    }
  } catch (error) {
    log(`❌ 配额意识测试失败: ${error.message}`, 'error');
  }

  SCORES.api_usage.details.push({ test: 'quota_awareness', score, max: 5 });
  SCORES.api_usage.score += score;
  log(`得分: ${score}/5`);
  return score;
}

function testPagination() {
  log('\n--- 测试: 分页处理 (5分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // 检查 pageToken 或类似的分页支持
    if (code.includes('pageToken') || code.includes('nextPageToken')) {
      score += 3;
      log('✅ 分页参数支持');
    } else {
      // 或者检查是否有 maxResults 限制处理
      if (code.includes('maxResults') && code.includes('50')) {
        score += 2;
        log('✅ maxResults 范围限制（分页相关）');
      }
    }

    // 支持多次调用获取更多结果
    if (code.includes('maxResults') && code.includes('Math.min')) {
      score += 2;
      log('✅ 结果数量控制');
    }
  } catch (error) {
    log(`❌ 分页测试失败: ${error.message}`, 'error');
  }

  SCORES.api_usage.details.push({ test: 'pagination', score, max: 5 });
  SCORES.api_usage.score += score;
  log(`得分: ${score}/5`);
  return score;
}

function testErrorCodeHandling() {
  log('\n--- 测试: 错误码处理 (5分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // 403 错误
    if (code.includes('403')) {
      score += 2;
      log('✅ 403 错误处理');
    }

    // 429 错误
    if (code.includes('429')) {
      score += 2;
      log('✅ 429 错误处理');
    }

    // 400 错误
    if (code.includes('400')) {
      score += 1;
      log('✅ 400 错误处理');
    }
  } catch (error) {
    log(`❌ 错误码处理测试失败: ${error.message}`, 'error');
  }

  SCORES.api_usage.details.push({ test: 'error_code_handling', score, max: 5 });
  SCORES.api_usage.score += score;
  log(`得分: ${score}/5`);
  return score;
}

// ============ 维度4: 数据完整性 (15分) ============

async function testRequiredFields() {
  log('\n--- 测试: 必需字段 (8分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler({ useMock: true });
    const videos = await crawler.get_trending('US', 3);

    if (!videos || videos.length === 0) {
      throw new Error('No videos returned');
    }

    const requiredFields = ['videoId', 'title', 'viewCount', 'channelTitle', 'thumbnails'];

    for (const video of videos) {
      const hasAllFields = requiredFields.every(f => video[f] !== undefined);
      if (hasAllFields) {
        score += 2;
        log('✅ 视频包含所有必需字段');
        break;
      }
    }

    // videoId 格式
    const validVideoId = videos[0].videoId && typeof videos[0].videoId === 'string';
    if (validVideoId) {
      score += 2;
      log('✅ videoId 格式正确');
    }

    // viewCount 数字
    if (typeof videos[0].viewCount === 'number') {
      score += 2;
      log('✅ viewCount 是数字类型');
    }

    // thumbnails 结构
    if (videos[0].thumbnails && typeof videos[0].thumbnails === 'object') {
      score += 2;
      log('✅ thumbnails 结构正确');
    }
  } catch (error) {
    log(`❌ 必需字段测试失败: ${error.message}`, 'error');
  }

  SCORES.data_completeness.details.push({ test: 'required_fields', score, max: 8 });
  SCORES.data_completeness.score += score;
  log(`得分: ${score}/8`);
  return score;
}

async function testDataFormat() {
  log('\n--- 测试: 数据格式 (4分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler({ useMock: true });
    const videos = await crawler.get_trending('JP', 2);

    // JSON 结构验证
    const jsonStr = JSON.stringify(videos);
    const parsed = JSON.parse(jsonStr);

    if (Array.isArray(parsed) && parsed.length > 0) {
      score += 2;
      log('✅ JSON 结构可序列化');
    }

    // URL 格式
    const validUrl = videos[0]?.url?.includes('youtube.com/watch');
    if (validUrl) {
      score += 2;
      log('✅ URL 格式正确');
    }
  } catch (error) {
    log(`❌ 数据格式测试失败: ${error.message}`, 'error');
  }

  SCORES.data_completeness.details.push({ test: 'data_format', score, max: 4 });
  SCORES.data_completeness.score += score;
  log(`得分: ${score}/4`);
  return score;
}

async function testDataCleaning() {
  log('\n--- 测试: 数据清洗 (3分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // 空值处理
    if (code.includes('_cleanString') || code.includes('null') || code.includes('undefined')) {
      score += 1;
      log('✅ 空值处理逻辑');
    }

    // 字符串清理
    if (code.includes('_cleanString') || code.includes('trim()')) {
      score += 1;
      log('✅ 字符串清理');
    }

    // 数字解析容错
    if (code.includes('_parseViewCount') || code.includes('parseInt')) {
      score += 1;
      log('✅ 数字解析容错');
    }
  } catch (error) {
    log(`❌ 数据清洗测试失败: ${error.message}`, 'error');
  }

  SCORES.data_completeness.details.push({ test: 'data_cleaning', score, max: 3 });
  SCORES.data_completeness.score += score;
  log(`得分: ${score}/3`);
  return score;
}

// ============ 维度5: 扩展性 (10分) ============

function testMultiRegionSupport() {
  log('\n--- 测试: 多地区支持 (4分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler({ useMock: true });

    // 测试多个地区代码
    const regions = ['US', 'JP', 'KR', 'GB', 'DE'];

    for (const region of regions.slice(0, 3)) {
      try {
        const videos = crawler._getMockData(region, 2);
        if (videos.length > 0) {
          score += 1;
          log(`✅ 支持地区: ${region}`);
        }
        if (score >= 4) break;
      } catch (e) {
        // 继续测试其他地区
      }
    }
  } catch (error) {
    log(`❌ 多地区支持测试失败: ${error.message}`, 'error');
  }

  SCORES.extensibility.details.push({ test: 'multi_region_support', score, max: 4 });
  SCORES.extensibility.score += score;
  log(`得分: ${score}/4`);
  return score;
}

async function testCategoryFilter() {
  log('\n--- 测试: 分类过滤 (3分) ---');
  let score = 0;

  try {
    const crawler = new YouTubeTrendingCrawler({ useMock: true });

    // 检查 videoCategoryId 参数支持
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    if (code.includes('videoCategoryId') && code.includes('categoryId')) {
      score += 2;
      log('✅ videoCategoryId 参数支持');
    }

    // 测试分类过滤
    try {
      const videos = await crawler.get_trending('US', 5, '10'); // Music category
      if (videos && videos.length > 0) {
        score += 1;
        log('✅ 分类过滤功能可用');
      }
    } catch (e) {
      // 即使失败也给部分分，因为参数已支持
    }
  } catch (error) {
    log(`❌ 分类过滤测试失败: ${error.message}`, 'error');
  }

  SCORES.extensibility.details.push({ test: 'category_filter', score, max: 3 });
  SCORES.extensibility.score += score;
  log(`得分: ${score}/3`);
  return score;
}

function testConfigurability() {
  log('\n--- 测试: 可配置性 (3分) ---');
  let score = 0;

  try {
    const code = fs.readFileSync(path.join(__dirname, 'youtube_crawler.js'), 'utf-8');

    // 构造函数配置
    if (code.includes('constructor(options') || code.includes('constructor({')) {
      score += 1;
      log('✅ 构造函数接受配置选项');
    }

    // 可配置参数
    const configParams = ['apiKey', 'useMock', 'timeout', 'maxRetries', 'enableFallback'];
    const hasConfigParams = configParams.filter(p => code.includes(p)).length;

    if (hasConfigParams >= 3) {
      score += 1;
      log('✅ 丰富的配置参数');
    }

    // 方法参数可配置
    if (code.includes('maxResults') && code.includes('regionCode')) {
      score += 1;
      log('✅ 方法参数可配置');
    }
  } catch (error) {
    log(`❌ 可配置性测试失败: ${error.message}`, 'error');
  }

  SCORES.extensibility.details.push({ test: 'configurability', score, max: 3 });
  SCORES.extensibility.score += score;
  log(`得分: ${score}/3`);
  return score;
}

// ============ 负例测试 ============

async function testNegativeCases() {
  log('\n========================================');
  log('负例测试 (错误处理)');
  log('========================================');

  const crawler = new YouTubeTrendingCrawler({ useMock: false });

  // 无效地区代码
  try {
    await crawler.get_trending('INVALID');
    log('❌ 未拒绝无效地区代码');
  } catch (error) {
    log('✅ 正确处理无效地区代码');
  }

  // 无效 maxResults
  try {
    await crawler.get_trending('US', 100);
    log('❌ 未拒绝无效 maxResults');
  } catch (error) {
    log('✅ 正确处理无效 maxResults');
  }

  // 无效 videoId 提取
  try {
    crawler.extract_video_info({});
    log('❌ 未拒绝无效视频数据');
  } catch (error) {
    log('✅ 正确处理无效视频数据');
  }
}

// ============ 主测试流程 ============

async function runBenchmark() {
  log('========================================');
  log('YouTube Crawler Benchmark Test');
  log('基于 benchmark.md 评分标准');
  log('========================================');
  log(`开始时间: ${new Date().toISOString()}`);
  log(`强制 Mock 模式: ${FORCE_MOCK}`);
  log('');

  // 维度1: 功能完整性 (30分)
  log('╔══════════════════════════════════════╗');
  log('║  维度1: 功能完整性 (30分)            ║');
  log('╚══════════════════════════════════════╝');
  await testGetTrending();
  await testGetMultiRegionTrending();
  testExtractVideoInfo();
  testSaveToJson();
  testSaveToCsv();

  // 维度2: 代码质量 (25分)
  log('\n╔══════════════════════════════════════╗');
  log('║  维度2: 代码质量 (25分)              ║');
  log('╚══════════════════════════════════════╝');
  testClassStructure();
  testExceptionHandling();
  testLogging();
  testComments();
  testTypeAnnotations();

  // 维度3: API 使用规范 (20分)
  log('\n╔══════════════════════════════════════╗');
  log('║  维度3: API 使用规范 (20分)          ║');
  log('╚══════════════════════════════════════╝');
  testEnvironmentVariables();
  testQuotaAwareness();
  testPagination();
  testErrorCodeHandling();

  // 维度4: 数据完整性 (15分)
  log('\n╔══════════════════════════════════════╗');
  log('║  维度4: 数据完整性 (15分)            ║');
  log('╚══════════════════════════════════════╝');
  await testRequiredFields();
  await testDataFormat();
  await testDataCleaning();

  // 维度5: 扩展性 (10分)
  log('\n╔══════════════════════════════════════╗');
  log('║  维度5: 扩展性 (10分)                ║');
  log('╚══════════════════════════════════════╝');
  testMultiRegionSupport();
  await testCategoryFilter();
  testConfigurability();

  // 负例测试
  await testNegativeCases();

  // 总分计算
  const total = SCORES.functionality.score +
                SCORES.code_quality.score +
                SCORES.api_usage.score +
                SCORES.data_completeness.score +
                SCORES.extensibility.score;

  const maxTotal = 100;

  log('\n========================================');
  log('评分汇总');
  log('========================================');
  log(`功能完整性:    ${SCORES.functionality.score.toString().padStart(2)}/${SCORES.functionality.max}`);
  log(`代码质量:      ${SCORES.code_quality.score.toString().padStart(2)}/${SCORES.code_quality.max}`);
  log(`API 使用规范:  ${SCORES.api_usage.score.toString().padStart(2)}/${SCORES.api_usage.max}`);
  log(`数据完整性:    ${SCORES.data_completeness.score.toString().padStart(2)}/${SCORES.data_completeness.max}`);
  log(`扩展性:        ${SCORES.extensibility.score.toString().padStart(2)}/${SCORES.extensibility.max}`);
  log('----------------------------------------');
  log(`总分:          ${total}/${maxTotal}`);
  log(`目标:          ≥ 95`);
  log(`结果:          ${total >= 95 ? '✅ 通过' : total >= 75 ? '⚠️ 需改进' : '❌ 未通过'}`);
  log('========================================');

  // 输出 JSON 结果
  const result = {
    total_score: total,
    max_score: maxTotal,
    passed: total >= 95,
    target: 95,
    dimensions: {
      functionality: {
        score: SCORES.functionality.score,
        max: SCORES.functionality.max,
        details: SCORES.functionality.details
      },
      code_quality: {
        score: SCORES.code_quality.score,
        max: SCORES.code_quality.max,
        details: SCORES.code_quality.details
      },
      api_usage: {
        score: SCORES.api_usage.score,
        max: SCORES.api_usage.max,
        details: SCORES.api_usage.details
      },
      data_completeness: {
        score: SCORES.data_completeness.score,
        max: SCORES.data_completeness.max,
        details: SCORES.data_completeness.details
      },
      extensibility: {
        score: SCORES.extensibility.score,
        max: SCORES.extensibility.max,
        details: SCORES.extensibility.details
      }
    },
    timestamp: new Date().toISOString(),
    logs: LOGS,
    weak_dimensions: total >= 95 ? [] : Object.entries(SCORES)
      .filter(([_, v]) => v.score < v.max * 0.8)
      .map(([k, _]) => k)
  };

  fs.writeFileSync(
    path.join(__dirname, 'benchmark_result.json'),
    JSON.stringify(result, null, 2)
  );

  return result;
}

// 运行测试
runBenchmark().then(result => {
  process.exit(result.passed ? 0 : 1);
}).catch(error => {
  console.error('Benchmark failed:', error);
  process.exit(1);
});