peoplelib/src/sources/http.js

const UA = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0 Safari/537.36 PeopleLib/2.1.3 (+https://github.com/lofyer/peoplelib)';
const { fetch: undiciFetch, ProxyAgent } = require('undici');

// 代理配置：默认直连（空字符串）。一旦设置，所有 HTTP 请求统一走该代理。
// 持久化存储在 userData/settings.json 的 "proxy" 字段。
let proxyUrl = '';
let dispatcher = null;

function setProxy(url) {
  const nextUrl = String(url || '').trim();
  if (nextUrl === proxyUrl) return;
  let nextDispatcher = null;
  if (nextUrl) {
    const parsed = new URL(nextUrl);
    if (!/^https?:$/.test(parsed.protocol)) throw new Error('代理地址仅支持 http:// 或 https://');
    nextDispatcher = new ProxyAgent({ uri: nextUrl, connectTimeout: 30000 });
  }
  if (dispatcher) {
    dispatcher.close().catch(() => {});
  }
  proxyUrl = nextUrl;
  dispatcher = nextDispatcher;
}

function getProxy() { return proxyUrl; }

function fetchWithProxy(url, options = {}) {
  return undiciFetch(url, dispatcher ? { ...options, dispatcher } : options);
}

function fetchWithElectron(url, options = {}) {
  try {
    const electron = require('electron');
    if (electron && electron.net && typeof electron.net.fetch === 'function') {
      return electron.net.fetch(url, options);
    }
  } catch (e) { /* Node 测试环境没有 Electron 网络栈 */ }
  return fetchWithProxy(url, options);
}

async function responseBytes(res, maxBytes) {
  const declared = Number(res.headers && res.headers.get && res.headers.get('content-length'));
  if (Number.isFinite(declared) && declared > maxBytes) {
    try { if (res.body && res.body.cancel) await res.body.cancel(); } catch (e) { /* ignore */ }
    return null;
  }
  if (!res.body || typeof res.body.getReader !== 'function') {
    const bytes = Buffer.from(await res.arrayBuffer());
    return bytes.length <= maxBytes ? bytes : null;
  }
  const reader = res.body.getReader();
  const chunks = [];
  let size = 0;
  try {
    for (;;) {
      const { done, value } = await reader.read();
      if (done) break;
      const chunk = Buffer.from(value);
      size += chunk.length;
      if (size > maxBytes) {
        await reader.cancel();
        return null;
      }
      chunks.push(chunk);
    }
  } finally {
    try { reader.releaseLock(); } catch (e) { /* ignore */ }
  }
  return Buffer.concat(chunks, size);
}

// 简易 cookie jar: Map<domain, Map<name, value>>
const cookieJar = new Map();

function domainOf(url) {
  try { return new URL(url).hostname; } catch (e) { return ''; }
}

function getCookies(url) {
  const d = domainOf(url);
  const m = cookieJar.get(d);
  if (!m) return '';
  return Array.from(m.entries()).map(([k, v]) => `${k}=${v}`).join('; ');
}

function setCookies(url, setCookieHeaders) {
  if (!setCookieHeaders || !setCookieHeaders.length) return;
  const d = domainOf(url);
  if (!d) return;
  let m = cookieJar.get(d);
  if (!m) { m = new Map(); cookieJar.set(d, m); }
  for (const sc of setCookieHeaders) {
    const pair = String(sc).split(';')[0];
    const eq = pair.indexOf('=');
    if (eq > 0) m.set(pair.slice(0, eq).trim(), pair.slice(eq + 1).trim());
  }
}

// target 可以是完整 URL 或裸主机名；jar 以主机名为键，
// 传 URL 时要先取出 hostname，否则永远匹配不到。
function clearCookies(target) {
  if (!target) { cookieJar.clear(); return; }
  const host = domainOf(target) || String(target);
  for (const k of [...cookieJar.keys()]) {
    if (k === host || k.endsWith(`.${host}`)) cookieJar.delete(k);
  }
}

// 默认请求超时（毫秒）。没有超时时，单个卡死的镜像会拖死整次搜索。
const DEFAULT_TIMEOUT = 15000;

async function fetchRaw(url, options = {}) {
  const cookie = getCookies(url);
  const headers = {
    'User-Agent': UA,
    'Accept': 'application/json, application/atom+xml, application/xml, text/xml, text/html, */*',
    ...(options.headers || {})
  };
  if (cookie && !headers.Cookie) headers.Cookie = cookie;

  const { timeout, signal: outerSignal, useElectronNet, ...rest } = options;
  const ms = timeout === undefined ? DEFAULT_TIMEOUT : timeout;

  // 调用方传入的 signal 不能顶替超时，否则外部取消一旦启用就再也没有超时保护
  const ac = new AbortController();
  const abort = () => ac.abort();
  if (outerSignal) {
    if (outerSignal.aborted) ac.abort();
    else outerSignal.addEventListener('abort', abort, { once: true });
  }
  const timer = ms > 0 ? setTimeout(abort, ms) : null;

  try {
    const request = useElectronNet ? fetchWithElectron : fetchWithProxy;
    const res = await request(url, { redirect: 'follow', ...rest, headers, signal: ac.signal });
    const setCookie = res.headers.getSetCookie ? res.headers.getSetCookie() : [];
    setCookies(url, setCookie);
    return res;
  } catch (e) {
    if (e && (e.name === 'AbortError' || /abort/i.test(e.message || ''))) {
      if (outerSignal && outerSignal.aborted) throw new Error('请求已取消');
      throw new Error('请求超时，站点无响应');
    }
    // undici / Chromium 的底层网络错误信息很不友好，统一换成可读文案
    const msg = (e && e.message) || String(e);
    if (/fetch failed|ERR_|ENOTFOUND|ECONNREFUSED|ECONNRESET|EAI_AGAIN|socket hang up/i.test(msg)) {
      throw new Error('网络连接失败，请检查网络或代理设置');
    }
    throw e;
  } finally {
    if (timer) clearTimeout(timer);
    if (outerSignal) outerSignal.removeEventListener('abort', abort);
  }
}

const STATUS_HINT = {
  403: '站点拒绝访问（403）',
  404: '资源不存在（404）',
  422: '查询条件不被接受（422）',
  429: '请求过于频繁，请稍后再试（429）',
  500: '站点内部错误（500）',
  502: '站点网关错误（502）',
  503: '站点暂时不可用（503）',
  504: '站点网关超时（504）'
};

async function fetchOnce(url, options) {
  const res = await fetchRaw(url, options);
  if (!res.ok) throw new Error(STATUS_HINT[res.status] || `请求失败（HTTP ${res.status}）`);
  return res.text();
}

// 默认对瞬时故障（超时/网络抖动/5xx/限流）自动重试一次。
// 镜像轮询类数据源（LibGen / Sci-Hub / Z-Library）应传 retries: 0，
// 由上层的 tryMirrors / raceMirrors 负责换镜像，避免重试叠加放大耗时。
//
// 重试会把最坏耗时翻倍（超时 15s -> 30s），聚合搜索下体感很差。
// 因此重试时缩短单次超时：宁可放弃这次重试，也不要让整组结果一直转圈。
function fetchText(url, options = {}) {
  const { retries, retryDelay, ...rest } = options;
  const tries = (retries === undefined ? 1 : retries) + 1;
  if (tries <= 1) return fetchOnce(url, rest);

  const baseTimeout = rest.timeout === undefined ? DEFAULT_TIMEOUT : rest.timeout;
  return withRetry(
    (attempt) => fetchOnce(url, attempt === 0
      ? rest
      : { ...rest, timeout: Math.max(3000, Math.round(baseTimeout / 2)) }),
    { tries, delay: retryDelay || 800 }
  );
}

async function fetchJson(url, options = {}) {
  const text = await fetchText(url, options);
  try {
    return JSON.parse(text);
  } catch (e) {
    throw new Error('返回内容不是有效 JSON');
  }
}

function decodeEntities(s) {
  if (s == null) return '';
  return String(s)
    .replace(/&lt;/g, '<')
    .replace(/&gt;/g, '>')
    .replace(/&quot;/g, '"')
    .replace(/&#39;|&apos;/g, "'")
    .replace(/&#(\d+);/g, (_, n) => String.fromCodePoint(parseInt(n, 10)))
    .replace(/&amp;/g, '&');
}

function stripTags(s) {
  return decodeEntities(String(s == null ? '' : s).replace(/<[^>]*>/g, ' ')).replace(/\s+/g, ' ').trim();
}

function clampPage(n, min) {
  n = parseInt(n, 10);
  if (!Number.isFinite(n) || n < (min || 1)) return min || 1;
  return n;
}

// 部分站点（OpenLibrary / LibGen）对过短的关键词直接返回 422。
// 与其把 HTTP 错误抛给用户，不如提前返回空结果并带上说明。
function tooShort(keyword, min = 3) {
  const kw = String(keyword || '').trim();
  if (kw.length >= min) return null;
  return { items: [], maxPage: 1, page: 1, note: `关键词太短，该源要求至少 ${min} 个字符` };
}

// 可自愈的错误：超时、网络抖动、5xx、限流。4xx 属请求本身的问题，重试无意义。
// 主动取消（竞速败者、切换页面）不是故障，重试只会浪费一次请求。
function isRetryable(e) {
  const msg = (e && e.message) || '';
  if (/请求已取消/.test(msg)) return false;
  return /超时|网络连接失败|站点内部错误|站点网关|暂时不可用|过于频繁/.test(msg);
}

// 带退避的重试包装。仅在错误可自愈时重试，避免为 4xx 白等几秒。
// fn 会收到当前尝试序号（0 起），便于按次调整超时等参数。
async function withRetry(fn, { tries = 2, delay = 1000 } = {}) {
  for (let i = 0; ; i++) {
    try {
      return await fn(i);
    } catch (e) {
      if (i >= tries - 1 || !isRetryable(e)) throw e;
      await new Promise((r) => setTimeout(r, delay * (i + 1)));
    }
  }
}

module.exports = {
  UA, fetchRaw, fetchText, fetchJson, responseBytes, decodeEntities, stripTags,
  clampPage, tooShort, isRetryable, withRetry, getCookies, setCookies, clearCookies,
  setProxy, getProxy, fetchWithProxy
};