The RegExp challenge

benchmark-1-isbot.mjs

// Benchmark #1 - `isbot` tests
//
// Relevant issues:
// - https://github.com/oven-sh/bun/issues/5197
// Relevant credit:
// - https://github.com/strager for writing this benchmark
// - https://www.npmjs.com/package/isbot for `isbot`

import { run, bench } from "mitata";
import { gunzipSync } from "node:zlib";

const response = await fetch(
  "https://github.com/quick-lint/bun-vs-node/raw/17934db/bun-regexp-bug/uas.txt.gz",
);
const compressedBody = await response.arrayBuffer();
const body = gunzipSync(Buffer.from(compressedBody)).toString("utf8");

const userAgents = body.split("\n");
const regExp =
  / daum[ /]| deusu\/| yadirectfetcher|(?:^| )site|(?:^|[^g])news|@[a-z]|\(at\)[a-z]|\(github\.com\/|\[at\][a-z]|^12345|^<|^[\w \.\-\(\)]+(\/v?\d+(\.\d+)?(\.\d{1,10})?)?$|^[^ ]{50,}$|^active|^ad muncher|^amaya|^anglesharp\/|^anonymous|^avsdevicesdk\/|^axios\/|^bidtellect\/|^biglotron|^btwebclient\/|^castro|^clamav[ /]|^client\/|^cobweb\/|^coccoc|^custom|^ddg[_-]android|^discourse|^dispatch\/\d|^downcast\/|^duckduckgo|^facebook|^fdm[ /]\d|^getright\/|^gozilla\/|^hatena|^hobbit|^hotzonu|^hwcdn\/|^jeode\/|^jetty\/|^jigsaw|^linkdex|^lwp[-: ]|^metauri|^microsoft bits|^movabletype|^mozilla\/\d\.\d \(compatible;?\)$|^mozilla\/\d\.\d \w*$|^navermailapp|^netsurf|^offline explorer|^php|^postman|^postrank|^python|^read|^reed|^restsharp\/|^snapchat|^space bison|^svn|^swcd |^taringa|^test certificate info|^thumbor\/|^tumblr\/|^user-agent:mozilla|^valid|^venus\/fedoraplanet|^w3c|^webbandit\/|^webcopier|^wget|^whatsapp|^xenu link sleuth|^yahoo|^yandex|^zdm\/\d|^zoom marketplace\/|^{{.*}}$|adbeat\.com|appinsights|archive|ask jeeves\/teoma|bit\.ly\/|bluecoat drtr|(?<! cu)bot|browsex|burpcollaborator|capture|catch|check|chrome-lighthouse|chromeframe|cloud|crawl|cryptoapi|dareboost|datanyze|dataprovider|dejaclick|dmbrowser|download|evc-batch\/|feed|firephp|freesafeip|ghost|gomezagent|(?<! (?:channel\/|google\/))google(?!(app|\/google| pixel))|headlesschrome\/|(?<!(?:lib))http|httrack|hubspot marketing grader|hydra|ibisbrowser|images|iplabel|ips-agent|java(?!;)|library|mail\.ru\/|manager|monitor|morningscore\/|neustar wpm|nutch|offbyone|optimize|pageburst|pagespeed|perl|phantom|pingdom|powermarks|preview|proxy|ptst[ /]\d|reader|rexx;|rigor|rss|scan|scrape|(?<! ya(?:yandex)?)search|serp ?reputation ?management|server|sogou|sparkler\/|speedcurve|spider|splash|statuscake|stumbleupon\.com|supercleaner|synapse|synthetic|taginspector\/|torrent|tracemyfile|transcoder|trendsmapresolver|twingly recon|url|virtuoso|wappalyzer|webglance|webkit2png|websitemetadataretriever|whatcms\/|wordpress|zgrab/;

bench("isbot", () => {
  let count = 0;
  for (const userAgent of userAgents) {
    count += regExp.test(userAgent);
  }
});

await run();

benchmark-2-marked.mjs

// Benchmark #2 - Markdown parser
//
// Relevant issues:
// - https://github.com/markedjs/marked/issues/2863
// - https://github.com/oven-sh/bun/issues/3464

import { run, bench } from "mitata";
import { marked } from "marked";

const response = await fetch(
  "https://github.com/markedjs/marked/files/11911404/test.md",
);
const data = await response.text();

bench("marked (sync)", () => {
  marked(data, (error, result) => {
    if (error) throw error;
    console.log(result.length);
  });
});

bench("marked (async)", async () => {
  await marked(data, {
    async: true,
  });
});

await run();

benchmark-3-capturegroup.mjs

// Benchmark #3 - Capture groups
//
// Relevant issues:
// - https://github.com/oven-sh/bun/issues/3464#issuecomment-1774043531
// Relevant credit:
// - https://github.com/yschroe for writing this benchmark

import { run, bench } from "mitata";

const loremIpsum =
  "Lorem ipsum dolor sit amet, consectetur adipisici elit, sed eiusmod tempor incidunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquid ex ea commodi consequat. Quis aute iure reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint obcaecat cupiditat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.";
const regExps = [
  /A{1,3}B{1,3}/g,
  /A{1,3}(B){1,3}/g,
  /(A)(B){1,3}/g,
  /(A){1,3}(B){1,3}/g,
];

bench("capture groups", () => {
  let count = 0;
  for (const regExp of regExps) {
    count += loremIpsum.match(regExp)?.length;
  }
});

await run();