add CodSpeed benchmark for unicode-segmenter/grapheme

Author: cometkim

.github/workflows/codspeed.yml

@@ -0,0 +1,29 @@
+name: CodSpeed
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  benchmarks:
+    name: Run benchmarks
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 24
+          cache: yarn
+
+      - name: Install Dependencies
+        run: yarn install --immutable
+
+      - name: Run benchmarks
+        uses: CodSpeedHQ/action@v3
+        with:
+          run: node benchmark/grapheme/codspeed.mjs
+          token: ${{ secrets.CODSPEED_TOKEN }}

benchmark/grapheme/codspeed.js

@@ -0,0 +1,57 @@
+import { withCodSpeed } from '@codspeed/tinybench-plugin';
+import { Bench } from 'tinybench';
+
+import { graphemeSegments } from '../../src/grapheme.js';
+
+let testcases = [
+  [
+    'Lorem ipsum (ascii)',
+    'Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.',
+  ],
+  [
+    'Emojis',
+    '🌟📚✨🎉🚀🌍🎈🌸🍀🌻🎨💖🐾🍒🔮🍕🌙🌈🐢🍉💡📅🎶🎮🔥💤💼🚲🌼🔒💧💫',
+  ],
+  [
+    'Hindi',
+    'राधा अपने बगीचे में फूलों को पानी देते हुए पक्षियों की चहचहाहट सुन रही थी, और वह सोच रही थी कि आज का दिन कितना शांत और सुंदर है।',
+  ],
+  [
+    'Demonic characters',
+    'Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘!͖̬̰̙̗̿̋ͥͥ̂ͣ̐́́͜͞',
+  ],
+  [
+    'Tweet text (combined)',
+    '🚀 새로운 유니코드 분할기 라이브러리 \'unicode-segmenter\'를 소개합니다! 🔍 각종 언어의 문자를 정확하게 구분해주는 강력한 도구입니다. Check it out! 👉 [https://github.com/cometkim/unicode-segmenter] #Unicode #Programming 🌐',
+  ],
+  [
+    'Code snippet (combined)',
+    `
+// 'unicode-segmenter' 라이브러리를 사용한 유니코드 문자 분할 예제 코드 🚀
+
+// ESM supported!
+import { graphemeSegments } from 'unicode-segmenter/grapheme';
+
+// 문자열을 유니코드 그래핌 단위로 분할하는 함수 예시
+function 문자분할테스트(문자열) {
+  const 분할된문자들 = [...graphemeSegments(문자열)].map(({ segment }) => segment);
+  console.log("분할된 유니코드 문자들:", 분할된문자들);
+}
+
+// 테스트 문자열
+const 테스트문자열 = "안녕하세요! Welcome to the unicode-segementer library 📚";
+문자분할테스트(테스트문자열);
+`,
+  ],
+];
+
+const bench = withCodSpeed(new Bench());
+
+for (const [name, input] of testcases) {
+  bench.add(name, () => {
+    void [...graphemeSegments(input)];
+  });
+}
+
+await bench.run();
+console.table(bench.table());

package.json

@@ -118,6 +118,7 @@
     "@babel/core": "^7.27.1",
     "@babel/plugin-transform-modules-commonjs": "^7.27.1",
     "@changesets/cli": "^2.29.4",
+    "@codspeed/tinybench-plugin": "^4.0.1",
     "@formatjs/intl-segmenter": "11.7.10",
     "@mitata/counters": "^0.0.8",
     "@react-native/metro-babel-transformer": "^0.79.2",
@@ -135,6 +136,7 @@
     "os-browserify": "^0.3.0",
     "pretty-bytes": "^7.0.0",
     "rimraf": "^6.0.1",
+    "tinybench": "^4.0.1",
     "typescript": "^5.8.3",
     "unicode-segmentation-wasm": "github:cometkim/unicode-segmentation-wasm#230eb74d320ea2f31f95b74ddb2567186d496587",
     "vite": "^6.3.5",