/**
 * Unifuncs API 网站覆盖能力测试脚本
 * 
 * 测试 unifuncs DeepSearch 对中国医生常用医学期刊网站的搜索能力
 * 使用异步模式（create_task + query_task）并行测试所有站点
 * 
 * 运行方式：
 *   cd backend
 *   npx tsx scripts/test-unifuncs-site-coverage.ts
 */

// ========== 配置 ==========
const API_KEY = 'sk-2fNwqUH73elGq0aDKJEM4ReqP7Ry0iqHo4OXyidDe2WpQ9XQ';
const BASE_URL = 'https://api.unifuncs.com/deepsearch/v1';
const MAX_DEPTH = 5;          // 测试用低深度，加快速度
const POLL_INTERVAL = 10000;  // 10s 轮询间隔
const MAX_WAIT = 600000;      // 单任务最长等待 10 分钟
const QUERY = '他汀类药物预防心血管疾病的随机对照试验和Meta分析，近5年高质量研究';

// ========== 测试站点列表 ==========
interface TestSite {
  id: number;
  name: string;
  url: string;
  priority: 'top7' | 'other';
  category: 'english' | 'chinese';
}

const TEST_SITES: TestSite[] = [
  // ── Top 7 最关注 ──
  { id: 1,  name: 'PubMed',                url: 'https://pubmed.ncbi.nlm.nih.gov/',  priority: 'top7', category: 'english' },
  { id: 2,  name: 'ClinicalTrials.gov',    url: 'https://clinicaltrials.gov/',        priority: 'top7', category: 'english' },
  { id: 3,  name: '中华医学期刊网',          url: 'https://medjournals.cn/',            priority: 'top7', category: 'chinese' },
  { id: 4,  name: '中国知网 CNKI',          url: 'https://www.cnki.net/',              priority: 'top7', category: 'chinese' },
  { id: 5,  name: '万方数据',               url: 'https://www.wanfangdata.com.cn/',    priority: 'top7', category: 'chinese' },
  { id: 6,  name: '维普 VIP',              url: 'https://www.cqvip.com/',             priority: 'top7', category: 'chinese' },
  { id: 7,  name: '中国临床试验注册中心',     url: 'http://www.chictr.org.cn/',          priority: 'top7', category: 'chinese' },
  // ── 其他常用 ──
  { id: 8,  name: 'CBM/SinoMed',           url: 'http://www.sinomed.ac.cn/',          priority: 'other', category: 'chinese' },
  { id: 9,  name: 'Web of Science',        url: 'https://www.webofscience.com/',      priority: 'other', category: 'english' },
  { id: 10, name: 'Embase',                url: 'http://www.embase.com/',             priority: 'other', category: 'english' },
  { id: 11, name: 'Cochrane Library',       url: 'https://www.cochranelibrary.com/',   priority: 'other', category: 'english' },
  { id: 12, name: 'Google Scholar',         url: 'https://scholar.google.com/',        priority: 'other', category: 'english' },
  { id: 13, name: 'Ovid',                  url: 'http://ovidsp.ovid.com/',            priority: 'other', category: 'english' },
  { id: 14, name: 'Scopus',                url: 'https://www.scopus.com/',            priority: 'other', category: 'english' },
  { id: 15, name: '中国中医药数据库',        url: 'https://cintmed.cintcm.cn/',         priority: 'other', category: 'chinese' },
  { id: 16, name: 'GeenMedical',           url: 'https://www.geenmedical.com/',       priority: 'other', category: 'english' },
  { id: 17, name: 'NSTL 国家科技图书文献中心', url: 'https://www.nstl.gov.cn/',         priority: 'other', category: 'chinese' },
  { id: 18, name: 'NCBI (全站)',            url: 'https://www.ncbi.nlm.nih.gov/',      priority: 'other', category: 'english' },
];

// ========== 结果结构 ==========
interface TaskResult {
  site: TestSite;
  taskId: string | null;
  status: 'success' | 'failed' | 'timeout' | 'create_error';
  searchCount: number;
  readCount: number;
  iterations: number;
  contentLength: number;
  reasoningLength: number;
  referencesFound: number;    // 在 content 中找到的该站点链接数
  otherLinksFound: number;    // 找到的其他链接数
  durationSec: number;
  errorMessage: string;
  sampleLinks: string[];      // 找到的前 5 个链接
}

// ========== API 封装 ==========

async function createTask(site: TestSite): Promise<{ taskId: string } | { error: string }> {
  const payload = {
    model: 's2',
    messages: [{ role: 'user', content: QUERY }],
    introduction: '你是一名专业的临床研究文献检索专家。请在指定数据库中尽可能多地检索相关文献，输出每篇文献的标题、作者、年份、链接。',
    max_depth: MAX_DEPTH,
    domain_scope: [site.url],
    reference_style: 'link',
    generate_summary: true,
  };

  try {
    const res = await fetch(`${BASE_URL}/create_task`, {
      method: 'POST',
      headers: {
        'Authorization': `Bearer ${API_KEY}`,
        'Content-Type': 'application/json',
      },
      body: JSON.stringify(payload),
    });

    const json = await res.json() as any;
    if (json.code === 0 && json.data?.task_id) {
      return { taskId: json.data.task_id };
    }
    return { error: `API 返回错误: ${json.message || JSON.stringify(json)}` };
  } catch (err: any) {
    return { error: `请求失败: ${err.message}` };
  }
}

async function queryTask(taskId: string): Promise<any> {
  const params = new URLSearchParams({ task_id: taskId });
  const res = await fetch(`${BASE_URL}/query_task?${params.toString()}`, {
    headers: { 'Authorization': `Bearer ${API_KEY}` },
  });
  return res.json();
}

function sleep(ms: number): Promise<void> {
  return new Promise(resolve => setTimeout(resolve, ms));
}

// ========== 链接提取 ==========

function extractDomainLinks(content: string, siteUrl: string): string[] {
  const domain = new URL(siteUrl).hostname.replace('www.', '');
  const urlPattern = /https?:\/\/[^\s)\]"'>]+/gi;
  const allUrls = content.match(urlPattern) || [];
  return [...new Set(allUrls.filter(u => u.includes(domain)))];
}

function extractAllLinks(content: string): string[] {
  const urlPattern = /https?:\/\/[^\s)\]"'>]+/gi;
  return [...new Set(content.match(urlPattern) || [])];
}

// ========== 单站点完整流程 ==========

async function testSingleSite(site: TestSite): Promise<TaskResult> {
  const startTime = Date.now();
  const baseResult: TaskResult = {
    site,
    taskId: null,
    status: 'failed',
    searchCount: 0,
    readCount: 0,
    iterations: 0,
    contentLength: 0,
    reasoningLength: 0,
    referencesFound: 0,
    otherLinksFound: 0,
    durationSec: 0,
    errorMessage: '',
    sampleLinks: [],
  };

  // 1. 创建任务
  console.log(`  [${site.id.toString().padStart(2)}] ${site.name} → 创建任务...`);
  const createResult = await createTask(site);

  if ('error' in createResult) {
    baseResult.status = 'create_error';
    baseResult.errorMessage = createResult.error;
    baseResult.durationSec = (Date.now() - startTime) / 1000;
    console.log(`  [${site.id.toString().padStart(2)}] ${site.name} ✗ 创建失败: ${createResult.error}`);
    return baseResult;
  }

  baseResult.taskId = createResult.taskId;
  console.log(`  [${site.id.toString().padStart(2)}] ${site.name} → task_id: ${createResult.taskId}`);

  // 2. 轮询直到完成
  const deadline = Date.now() + MAX_WAIT;
  let lastStatus = '';

  while (Date.now() < deadline) {
    await sleep(POLL_INTERVAL);

    try {
      const json = await queryTask(createResult.taskId) as any;
      const data = json.data;

      if (!data) {
        continue;
      }

      const currentStatus = data.status;
      if (currentStatus !== lastStatus) {
        const progress = data.progress ? `${data.progress.current}/${data.progress.total}` : '?';
        const stats = data.statistics
          ? `搜索${data.statistics.search_count || 0} 阅读${data.statistics.read_count || 0}`
          : '';
        console.log(`  [${site.id.toString().padStart(2)}] ${site.name} → ${currentStatus} (${progress}) ${stats}`);
        lastStatus = currentStatus;
      }

      if (currentStatus === 'completed') {
        const content = data.result?.content || '';
        const reasoning = data.result?.reasoning_content || '';
        const stats = data.statistics || {};

        const siteLinks = extractDomainLinks(content, site.url);
        const allLinks = extractAllLinks(content);

        baseResult.status = 'success';
        baseResult.contentLength = content.length;
        baseResult.reasoningLength = reasoning.length;
        baseResult.searchCount = stats.search_count || 0;
        baseResult.readCount = stats.read_count || 0;
        baseResult.iterations = stats.iterations || 0;
        baseResult.referencesFound = siteLinks.length;
        baseResult.otherLinksFound = allLinks.length - siteLinks.length;
        baseResult.sampleLinks = siteLinks.slice(0, 5);
        baseResult.durationSec = (Date.now() - startTime) / 1000;

        console.log(`  [${site.id.toString().padStart(2)}] ${site.name} ✓ 完成 | 站内链接:${siteLinks.length} 其他链接:${allLinks.length - siteLinks.length} | ${baseResult.durationSec.toFixed(0)}s`);
        return baseResult;
      }

      if (currentStatus === 'failed') {
        baseResult.status = 'failed';
        baseResult.errorMessage = data.result?.content || '任务失败';
        baseResult.durationSec = (Date.now() - startTime) / 1000;
        console.log(`  [${site.id.toString().padStart(2)}] ${site.name} ✗ 失败: ${baseResult.errorMessage.slice(0, 80)}`);
        return baseResult;
      }
    } catch (err: any) {
      // 轮询中的网络错误，继续重试
    }
  }

  // 超时
  baseResult.status = 'timeout';
  baseResult.errorMessage = `超时（${MAX_WAIT / 1000}s）`;
  baseResult.durationSec = (Date.now() - startTime) / 1000;
  console.log(`  [${site.id.toString().padStart(2)}] ${site.name} ⏰ 超时`);
  return baseResult;
}

// ========== 结果报告 ==========

function printReport(results: TaskResult[]) {
  console.log('\n');
  console.log('='.repeat(100));
  console.log('                    Unifuncs DeepSearch API 网站覆盖能力测试报告');
  console.log('='.repeat(100));
  console.log(`测试时间: ${new Date().toISOString()}`);
  console.log(`测试查询: "${QUERY}"`);
  console.log(`配置: max_depth=${MAX_DEPTH}, poll_interval=${POLL_INTERVAL / 1000}s`);
  console.log('');

  // ── Top 7 结果 ──
  console.log('━'.repeat(100));
  console.log('  ★ Top 7 最关注站点');
  console.log('━'.repeat(100));
  printTable(results.filter(r => r.site.priority === 'top7'));

  // ── 其他结果 ──
  console.log('');
  console.log('━'.repeat(100));
  console.log('  其他常用站点');
  console.log('━'.repeat(100));
  printTable(results.filter(r => r.site.priority === 'other'));

  // ── 汇总 ──
  console.log('');
  console.log('━'.repeat(100));
  console.log('  汇总统计');
  console.log('━'.repeat(100));

  const successSites = results.filter(r => r.status === 'success' && r.referencesFound > 0);
  const reachableSites = results.filter(r => r.status === 'success');
  const failedSites = results.filter(r => r.status !== 'success');

  console.log(`  可搜索并返回站内链接: ${successSites.length}/${results.length} 个站点`);
  console.log(`  可到达但无站内链接:   ${reachableSites.length - successSites.length} 个站点`);
  console.log(`  不可用/失败/超时:     ${failedSites.length} 个站点`);
  console.log('');

  if (successSites.length > 0) {
    console.log('  ✅ 确认可搜索的站点:');
    for (const r of successSites) {
      console.log(`     - ${r.site.name} (${r.site.url}) → ${r.referencesFound} 个站内链接`);
    }
  }

  console.log('');

  const noLinkSites = reachableSites.filter(r => r.referencesFound === 0);
  if (noLinkSites.length > 0) {
    console.log('  ⚠️ 任务完成但无站内链接（可能搜索到了但链接指向其他站点）:');
    for (const r of noLinkSites) {
      console.log(`     - ${r.site.name} (${r.site.url}) → 其他链接 ${r.otherLinksFound} 个`);
      if (r.sampleLinks.length === 0) {
        const allLinks = r.otherLinksFound;
        console.log(`       内容长度: ${r.contentLength} 字符, 搜索${r.searchCount}次, 阅读${r.readCount}次`);
      }
    }
  }

  console.log('');

  if (failedSites.length > 0) {
    console.log('  ❌ 不可用站点:');
    for (const r of failedSites) {
      console.log(`     - ${r.site.name} (${r.site.url}) → ${r.status}: ${r.errorMessage.slice(0, 100)}`);
    }
  }

  console.log('');
  console.log('='.repeat(100));

  // ── 输出可用于前端配置的 JSON ──
  console.log('');
  console.log('前端可用数据源配置（可直接用于 V2.0 数据源选择）:');
  console.log('');
  const configList = results.map(r => ({
    name: r.site.name,
    url: r.site.url,
    category: r.site.category,
    available: r.status === 'success' && r.referencesFound > 0,
    reachable: r.status === 'success',
    siteLinksFound: r.referencesFound,
    searchCount: r.searchCount,
    readCount: r.readCount,
  }));
  console.log(JSON.stringify(configList, null, 2));
}

function printTable(results: TaskResult[]) {
  const header = '  序号 | 状态 | 站点名称                  | 站内链接 | 其他链接 | 搜索/阅读 | 耗时    | 说明';
  console.log(header);
  console.log('  ' + '-'.repeat(header.length - 2));

  for (const r of results) {
    const statusIcon =
      r.status === 'success' && r.referencesFound > 0 ? '✅' :
      r.status === 'success' ? '⚠️' :
      r.status === 'timeout' ? '⏰' : '❌';

    const note = r.status !== 'success'
      ? r.errorMessage.slice(0, 25)
      : r.referencesFound > 0
        ? r.sampleLinks[0]?.slice(0, 35) || ''
        : `内容${r.contentLength}字`;

    console.log(
      `  ${r.site.id.toString().padStart(4)} | ${statusIcon}  | ` +
      `${(r.site.name).padEnd(24)} | ` +
      `${r.referencesFound.toString().padStart(8)} | ` +
      `${r.otherLinksFound.toString().padStart(8)} | ` +
      `${r.searchCount}/${r.readCount}`.padStart(9) + ' | ' +
      `${r.durationSec.toFixed(0).padStart(5)}s | ` +
      note
    );
  }
}

// ========== 主入口 ==========

async function main() {
  console.log('╔════════════════════════════════════════════════════════════╗');
  console.log('║   Unifuncs DeepSearch API — 医学网站覆盖能力测试           ║');
  console.log('╚════════════════════════════════════════════════════════════╝');
  console.log('');
  console.log(`查询: "${QUERY}"`);
  console.log(`站点数: ${TEST_SITES.length} | max_depth: ${MAX_DEPTH} | 超时: ${MAX_WAIT / 1000}s`);
  console.log(`API: ${BASE_URL}`);
  console.log('');
  console.log('并行创建所有任务...\n');

  // 并行创建所有任务并执行
  const promises = TEST_SITES.map(site => testSingleSite(site));
  const results = await Promise.all(promises);

  // 输出报告
  printReport(results);
}

main().catch(err => {
  console.error('脚本执行失败:', err);
  process.exit(1);
});