Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/early-cats-exercise.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"unicode-segmenter": patch
---

grapheme: rename `countGrapheme()` to `countGraphemes()`. existing name is deprecated alias.
12 changes: 6 additions & 6 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -74,21 +74,21 @@ import { splitGraphemes } from 'unicode-segmenter/grapheme';
#### Example: Count graphemes

```js
import { countGrapheme } from 'unicode-segmenter/grapheme';
import { countGraphemes } from 'unicode-segmenter/grapheme';

'👋 안녕!'.length;
// => 6
countGrapheme('👋 안녕!');
countGraphemes('👋 안녕!');
// => 5

'a̐éö̲'.length;
// => 7
countGrapheme('a̐éö̲');
countGraphemes('a̐éö̲');
// => 3
```

> [!NOTE]
> `countGrapheme()` is a small wrapper around `graphemeSegments()`.
> `countGraphemes()` is a small wrapper around `graphemeSegments()`.
>
> If you need it more than once at a time, consider memoization or use `graphemeSegments()` or `splitSegments()` once instead.

Expand Down Expand Up @@ -251,7 +251,7 @@ Since [Hermes doesn't support the `Intl.Segmenter` API](https://github.com/faceb

| Name | Unicode® | ESM? | Size | Size (min) | Size (min+gzip) | Size (min+br) |
|------------------------------|----------|------|----------:|-----------:|----------------:|--------------:|
| `unicode-segmenter/grapheme` | 16.0.0 | ✔️ | 17,347 | 12,822 | 5,307 | 4,093 |
| `unicode-segmenter/grapheme` | 16.0.0 | ✔️ | 17,348 | 12,822 | 5,307 | 4,089 |
| `graphemer` | 15.0.0 | ✖️ ️| 410,435 | 95,104 | 15,752 | 10,660 |
| `grapheme-splitter` | 10.0.0 | ✖️ | 122,252 | 23,680 | 7,852 | 4,841 |
| `@formatjs/intl-segmenter`* | 15.0.0 | ✖️ | 491,043 | 318,721 | 54,248 | 34,380 |
Expand All @@ -267,7 +267,7 @@ Since [Hermes doesn't support the `Intl.Segmenter` API](https://github.com/faceb

| Name | Bytecode size | Bytecode size (gzip)* |
|------------------------------|--------------:|----------------------:|
| `unicode-segmenter/grapheme` | 24,521 | 12,773 |
| `unicode-segmenter/grapheme` | 24,538 | 12,788 |
| `graphemer` | 133,949 | 31,710 |
| `grapheme-splitter` | 63,810 | 19,125 |
| `@formatjs/intl-segmenter`* | 315,865 | 99,063 |
Expand Down
2 changes: 1 addition & 1 deletion benchmark/grapheme/bundle-entries/unicode-segmenter.js
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
export {
graphemeSegments,
countGrapheme,
splitGraphemes,
countGraphemes,
} from '../../../src/grapheme.js';
9 changes: 8 additions & 1 deletion src/grapheme.js
Original file line number Diff line number Diff line change
Expand Up @@ -189,12 +189,19 @@ export function* graphemeSegments(input) {
* @param {string} str
* @return number count of graphemes
*/
export function countGrapheme(str) {
export function countGraphemes(str) {
let count = 0;
for (let _ of graphemeSegments(str)) count += 1;
return count;
}

export {
/**
* @deprecated use {@link countGraphemes}
*/
countGraphemes as countGrapheme,
};

/**
* @param {string} str
* @return {IterableIterator<string>}
Expand Down
20 changes: 10 additions & 10 deletions test/grapheme.js
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,8 @@ import fc from 'fast-check';
import {
GraphemeCategory,
graphemeSegments,
countGrapheme,
splitGraphemes,
countGraphemes,
} from 'unicode-segmenter/grapheme';
import { assertObjectContaining } from './_helper.js';

Expand Down Expand Up @@ -74,34 +74,34 @@ test('graphemeSegments', async t => {
});
});

test('countGrapheme', async t => {
test('countGraphemes', async t => {
await t.test('latin', () => {
assert.equal(countGrapheme('abcd'), 4);
assert.equal(countGraphemes('abcd'), 4);
});

await t.test('flags', () => {
assert.equal(countGrapheme('🇷🇸🇮🇴'), 2);
assert.equal(countGraphemes('🇷🇸🇮🇴'), 2);
});

await t.test('emoji', () => {
assert.equal(countGrapheme('👻👩‍👩‍👦‍👦'), 2);
assert.equal(countGrapheme('🌷🎁💩😜👍🏳️‍🌈'), 6);
assert.equal(countGraphemes('👻👩‍👩‍👦‍👦'), 2);
assert.equal(countGraphemes('🌷🎁💩😜👍🏳️‍🌈'), 6);
});

await t.test('diacritics as combining marks', () => {
assert.equal(countGrapheme('Ĺo͂řȩm̅'), 5);
assert.equal(countGraphemes('Ĺo͂řȩm̅'), 5);
});

await t.test('Jamo', () => {
assert.equal(countGrapheme('뎌쉐'), 2);
assert.equal(countGraphemes('뎌쉐'), 2);
});

await t.test('Hindi', () => {
assert.equal(countGrapheme('अनुच्छेद'), 4);
assert.equal(countGraphemes('अनुच्छेद'), 4);
});

await t.test('demonic', () => {
assert.equal(countGrapheme('Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘!͖̬̰̙̗̿̋ͥͥ̂ͣ̐́́͜͞'), 6);
assert.equal(countGraphemes('Z͑ͫ̓ͪ̂ͫ̽͏̴̙̤̞͉͚̯̞̠͍A̴̵̜̰͔ͫ͗͢L̠ͨͧͩ͘G̴̻͈͍͔̹̑͗̎̅͛́Ǫ̵̹̻̝̳͂̌̌͘!͖̬̰̙̗̿̋ͥͥ̂ͣ̐́́͜͞'), 6);
});
});

Expand Down