Add codePointLength() and graphemeLength()

.eslintrc.json

@@ -56,14 +56,7 @@
           "caseInsensitive": true
         },
         "groups": ["builtin", "external", "internal", "parent", ["sibling", "index"], "type"],
-        "newlines-between": "always",
-        "pathGroups": [
-          {
-            "pattern": "@{src,commands}/**",
-            "group": "internal",
-            "position": "after"
-          }
-        ]
+        "newlines-between": "always"
       }
     ],
     "sort-imports": "off"

package.json

@@ -107,7 +107,7 @@
     "lint-staged": "^17.0.8",
     "prettier": "^3.9.5",
     "rimraf": "^6.1.3",
-    "semantic-release": "^25.0.5",
+    "semantic-release": "^25.0.6",
     "typedoc": "^0.28.20",
     "validate-package-exports": "^1.2.1",
     "vitest": "^4.1.10"

src/codePointLength.ts

@@ -0,0 +1,13 @@
+/**
+ * Get the number of Unicode code points in `input`, unlike `string.length` which counts UTF-16 code units.
+ *
+ * @example
+ * ```ts
+ * codePointLength('hello'); // 5
+ * codePointLength('😀'); // 1
+ * '😀'.length; // 2
+ * ```
+ */
+export function codePointLength(input: string): number {
+  return [...input].length;
+}

src/graphemeLength.ts

@@ -0,0 +1,22 @@
+const segmenter = new Intl.Segmenter(undefined, { granularity: 'grapheme' });
+
+/**
+ * Get the number of grapheme clusters (user-perceived characters) in `input`, unlike `string.length` which counts UTF-16 code units.
+ *
+ * @example
+ * ```ts
+ * graphemeLength('hello'); // 5
+ * graphemeLength('👨‍👩‍👧‍👦'); // 1
+ * '👨‍👩‍👧‍👦'.length; // 11
+ * ```
+ */
+export function graphemeLength(input: string): number {
+  let count = 0;
+
+  // eslint-disable-next-line @typescript-eslint/naming-convention,@typescript-eslint/no-unused-vars
+  for (const _ of segmenter.segment(input)) {
+    count++;
+  }
+
+  return count;
+}

src/index.ts

@@ -11,6 +11,7 @@ export * from './capitalize.js';
 export * from './cartesian.js';
 export * from './chunk.js';
 export * from './clamp.js';
+export * from './codePointLength.js';
 export * from './combinations.js';
 export * from './comment.js';
 export * from './compose.js';
@@ -41,6 +42,7 @@ export * from './getPaths.js';
 export * from './getRandomItem.js';
 export * from './getSortedObject.js';
 export * from './getType.js';
+export * from './graphemeLength.js';
 export * from './has.js';
 export * from './hasAdditionalProperties.js';
 export * from './inRange.js';

test/codePointLength.test.ts

@@ -0,0 +1,23 @@
+import { describe, expect, it } from 'vitest';
+
+import { codePointLength } from '../src/codePointLength.js';
+
+describe('codePointLength()', () => {
+  it('Empty input returns 0', () => {
+    expect(codePointLength('')).toBe(0);
+  });
+
+  it('Counts ASCII characters', () => {
+    expect(codePointLength('hello')).toBe(5);
+  });
+
+  it('Counts a single character made of a surrogate pair as 1', () => {
+    expect(codePointLength('😀')).toBe(1);
+    expect('😀'.length).toBe(2);
+  });
+
+  it('Counts a mix of ASCII and surrogate pair characters', () => {
+    expect(codePointLength('a😀b😀c')).toBe(5);
+    expect('a😀b😀c'.length).toBe(7);
+  });
+});

test/graphemeLength.test.ts

@@ -0,0 +1,32 @@
+import { describe, expect, it } from 'vitest';
+
+import { graphemeLength } from '../src/graphemeLength.js';
+
+describe('graphemeLength()', () => {
+  it('Empty input returns 0', () => {
+    expect(graphemeLength('')).toBe(0);
+  });
+
+  it('Counts ASCII characters', () => {
+    expect(graphemeLength('hello')).toBe(5);
+  });
+
+  it('Counts a single character made of a surrogate pair as 1', () => {
+    expect(graphemeLength('😀')).toBe(1);
+    expect('😀'.length).toBe(2);
+  });
+
+  it('Counts a ZWJ emoji sequence as a single grapheme', () => {
+    expect(graphemeLength('👨‍👩‍👧‍👦')).toBe(1);
+    expect('👨‍👩‍👧‍👦'.length).toBe(11);
+  });
+
+  it('Counts a combining character sequence as a single grapheme', () => {
+    expect(graphemeLength('é')).toBe(1);
+    expect('é'.length).toBe(2);
+  });
+
+  it('Counts a mix of ASCII and multi-code-unit graphemes', () => {
+    expect(graphemeLength('a😀b👨‍👩‍👧‍👦c')).toBe(5);
+  });
+});