@automattic/vip 4.1.4 → 4.1.6

package/node_modules/unicode-segmenter/README.md

@@ -0,0 +1,324 @@
+# unicode-segmenter
+[![NPM Package Version](https://img.shields.io/npm/v/unicode-segmenter)](https://npmx.dev/unicode-segmenter)
+[![NPM Downloads](https://img.shields.io/npm/dw/unicode-segmenter)](https://npmx.dev/unicode-segmenter)
+[![Integration](https://github.com/cometkim/unicode-segmenter/actions/workflows/ci.yml/badge.svg)](https://github.com/cometkim/unicode-segmenter/actions/workflows/ci.yml)
+[![codecov](https://codecov.io/gh/cometkim/unicode-segmenter/graph/badge.svg?token=3rA29JEH4J)](https://codecov.io/gh/cometkim/unicode-segmenter)
+[![CodSpeed Badge](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/cometkim/unicode-segmenter?utm_source=badge)
+[![LICENSE - MIT](https://img.shields.io/github/license/cometkim/unicode-segmenter)](#license)
+
+A lightweight implementation of the [Unicode Text Segmentation (UAX \#29)](https://www.unicode.org/reports/tr29)
+
+- **Spec compliant**: Up-to-date Unicode data, verified by the official Unicode test suites and fuzzed with the native `Intl.Segmenter`, and maintaining 100% test coverage.
+
+- **Excellent compatibility**: It works well on older browsers, edge runtimes, React Native (Hermes) and QuickJS.
+
+- **Zero-dependencies**: It doesn't bloat `node_modules` or the network bandwidth. Like a small minimal snippet.
+
+- **Small bundle size**: It effectively compresses the Unicode data and provides a bundler-friendly format.
+
+- **Extremely efficient**: It's carefully optimized for runtime performance, making it the fastest one in the ecosystem—outperforming even the built-in `Intl.Segmenter`. Its flat lookup tables also keep the memory footprint far smaller than other libraries.
+
+- **TypeScript**: It's fully type-checked, and provides type definitions and JSDoc.
+
+- **ESM-first**: It primarily supports ES modules, and still supports CommonJS.
+
+> [!NOTE]
+> unicode-segmenter is now **[e18e] recommendation!**
+
+## Unicode® Version
+
+Unicode® 17.0.0
+
+Unicode® Standard Annex \#29 - [Revision 47](https://www.unicode.org/reports/tr29/tr29-47.html) (2025-08-17)
+
+## APIs
+
+Entries for Unicode text segmentation.
+
+- [`unicode-segmenter/grapheme`](#export-unicode-segmentergrapheme): Segments and counts **extended grapheme clusters**
+- [`unicode-segmenter/intl-adapter`](#export-unicode-segmenterintl-adapter): [`Intl.Segmenter`] adapter
+- [`unicode-segmenter/intl-polyfill`](#export-unicode-segmenterintl-polyfill): [`Intl.Segmenter`] polyfill
+
+And matchers for extra use cases.
+
+- [`unicode-segmenter/emoji`](#export-unicode-segmenteremoji): Matches single codepoint emojis
+- [`unicode-segmenter/general`](#export-unicode-segmentergeneral): Matches single codepoint alphanumerics
+
+### Export `unicode-segmenter/grapheme`
+
+Utilities for text segmentation by extended grapheme cluster rules.
+
+#### Example: Split graphemes
+
+You can split a string into graphemes by simply consuming the `splitGraphemes()` generator.
+
+It yields substrings directly, so it allocates less than `graphemeSegments()`.
+
+```js
+import { splitGraphemes } from 'unicode-segmenter/grapheme';
+
+[...splitGraphemes('#️⃣*️⃣0️⃣1️⃣2️⃣')];
+// 0: #️⃣
+// 1: *️⃣
+// 2: 0️⃣
+// 3: 1️⃣
+// 4: 2️⃣
+```
+
+#### Example: Collect graphemes into an array
+
+If you need the result as an array, use `collectGraphemes()` for convenience.
+
+This is a fast version of `[...splitGraphemes(str)]`, 1.5-2.5x faster.
+
+```js
+import { collectGraphemes } from 'unicode-segmenter/grapheme';
+
+collectGraphemes('#️⃣*️⃣0️⃣1️⃣2️⃣'); // => ["#️⃣", "*️⃣", "0️⃣", "1️⃣", "2️⃣"]
+```
+
+However, it collects all grapheme clusters at once, so it's not good for large text or streamed input.
+
+#### Example: Count graphemes
+
+If you need only the count, use `countGraphemes()`, which is optimized to avoid allocations for segments.
+
+Mostly 2-4x faster than the full segmenter and more GC friendly, so you can call it in a hot path.
+
+```js
+import { countGraphemes } from 'unicode-segmenter/grapheme';
+
+'👋 안녕!'.length;
+// => 6
+countGraphemes('👋 안녕!');
+// => 5
+
+'a̐éö̲'.length;
+// => 7
+countGraphemes('a̐éö̲');
+// => 3
+```
+
+#### Example: Get full segment info
+
+You can retrieve all grapheme segments using the `graphemeSegments()` generator.
+
+Each segment is returned as a `GraphemeSegmentOutput` object containing the `segment` (the substring), the starting `index`, and the full `input` string. This pattern is similar to the [`Intl.Segmenter`] API, so it can be a drop-in replacement.
+
+```js
+import { graphemeSegments } from 'unicode-segmenter/grapheme';
+
+[...graphemeSegments('a̐éö̲\r\n')];
+// 0: { segment: 'a̐', index: 0, input: 'a̐éö̲\r\n' }
+// 1: { segment: 'é', index: 2, input: 'a̐éö̲\r\n' }
+// 2: { segment: 'ö̲', index: 4, input: 'a̐éö̲\r\n' }
+// 3: { segment: '\r\n', index: 7, input: 'a̐éö̲\r\n' }
+```
+
+#### Example: Build an advanced grapheme matcher
+
+`graphemeSegments()` exposes some knowledge identified in the middle of the process to support some useful cases.
+
+For example, knowing the [Grapheme_Cluster_Break](https://www.unicode.org/reports/tr29/tr29-43.html#Default_Grapheme_Cluster_Table) category at the beginning and end of a segment can help approximately infer the applied boundary rule.
+
+```js
+import { graphemeSegments, GraphemeCategory } from 'unicode-segmenter/grapheme';
+
+function* matchEmoji(str) {
+  for (const { segment, _catBegin } of graphemeSegments(input)) {
+    // `_catBegin` identified as Extended_Pictographic means the segment is emoji
+    if (_catBegin === GraphemeCategory.Extended_Pictographic) {
+      yield segment;
+    }
+  }
+}
+
+[...matchEmoji('1🌷2🎁3💩4😜5👍')]
+// 0: 🌷
+// 1: 🎁
+// 2: 💩
+// 3: 😜
+// 4: 👍
+```
+
+Or build even more advanced one like an Unicode-aware [TTY string width](https://github.com/cometkim/unicode-string-width) utility.
+
+### Export `unicode-segmenter/intl-adapter`
+
+[`Intl.Segmenter`] API adapter (only `granularity: "grapheme"` available yet)
+
+```js
+import { Segmenter } from 'unicode-segmenter/intl-adapter';
+
+// Same API with the `Intl.Segmenter`
+const segmenter = new Segmenter();
+```
+
+### Export `unicode-segmenter/intl-polyfill`
+
+[`Intl.Segmenter`] API polyfill (only `granularity: "grapheme"` available yet)
+
+```js
+// Apply polyfill to the `globalThis.Intl` object.
+import 'unicode-segmenter/intl-polyfill';
+
+const segmenter = new Intl.Segmenter();
+```
+
+### Export `unicode-segmenter/emoji`
+
+Utilities for matching emoji-like characters.
+
+#### Example: Use Unicode emoji property matches
+
+```js
+import {
+  isEmojiPresentation,    // match \p{Emoji_Presentation}
+  isExtendedPictographic, // match \p{Extended_Pictographic}
+} from 'unicode-segmenter/emoji';
+
+isEmojiPresentation('😍'.codePointAt(0));
+// => true
+isEmojiPresentation('♡'.codePointAt(0));
+// => false
+
+isExtendedPictographic('😍'.codePointAt(0));
+// => true
+isExtendedPictographic('♡'.codePointAt(0));
+// => true
+```
+
+### Export `unicode-segmenter/general`
+
+Utilities for matching alphanumeric characters.
+
+#### Example: Use Unicode general property matchers
+
+```js
+import {
+  isLetter,       // match \p{L}
+  isNumeric,      // match \p{N}
+  isAlphabetic,   // match \p{Alphabetic}
+  isAlphanumeric, // match [\p{N}\p{Alphabetic}]
+} from 'unicode-segmenter/general';
+```
+
+## Runtime Compatibility
+
+`unicode-segmenter` uses only fundamental features of ES2015, making it compatible with most browsers.
+
+To ensure compatibility, the runtime should support:
+- [`String.prototype.codePointAt()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/codePointAt)
+- [Typed arrays](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Typed_arrays)
+- [Generators](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Generator)
+- [Modules](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Modules)
+
+If the runtime doesn't support these features, it can easily be fulfilled with tools like Babel.
+
+## React Native Support
+
+Since [Hermes doesn't support the `Intl.Segmenter` API](https://github.com/facebook/hermes/blob/main/doc/IntlAPIs.md) yet, `unicode-segmenter` is a good alternative.
+
+`unicode-segmenter` is compiled into small & efficient Hermes bytecode than other JavaScript libraries. See the [benchmark](#hermes-bytecode-stats) for details.
+
+## Comparison
+
+`unicode-segmenter` aims to be lighter and faster than alternatives in the ecosystem while fully spec compliant. So the benchmark is tracking several libraries' performance, bundle size, and Unicode version compliance.
+
+### `unicode-segmenter/grapheme` vs
+
+- [graphemer]@1.4.0
+- [grapheme-splitter]@1.0.4
+- [@formatjs/intl-segmenter]@12.1.0
+- WebAssembly build of [unicode-segmentation]@1.12.0 with minimum bindings
+- Built-in [`Intl.Segmenter`] API
+
+#### JS Bundle Stats
+
+| Name                                 | Unicode® | ESM? |    Size | Size (min) | Size (min+gzip) | Size (min+br) | Size (min+zstd) |
+|--------------------------------------|----------|------|--------:|-----------:|----------------:|--------------:|----------------:|
+| `unicode-segmenter/grapheme`         | 17.0.0   | ✔️   |   7,767 |      4,876 |           2,325 |         2,104 |           2,374 |
+| `unicode-segmenter/grapheme` (full*) | 17.0.0   | ✔️   |  10,173 |      5,725 |           2,607 |         2,322 |           2,668 |
+| `graphemer`                          | 15.0.0   | ✖️   | 410,435 |     95,104 |          15,752 |        10,660 |          15,911 |
+| `grapheme-splitter`                  | 10.0.0   | ✖️   | 122,254 |     23,682 |           7,852 |         4,802 |           6,753 |
+| `@formatjs/intl-segmenter`*          | 17.0.0   | ✖️   | 268,301 |    176,759 |          45,988 |        31,701 |          45,370 |
+| `unicode-segmentation`*              | 15.1.0   | -    |  56,529 |     52,439 |          24,108 |        17,343 |          24,375 |
+| `Intl.Segmenter`*                    | -        | -    |       0 |          0 |               0 |             0 |               0 |
+
+* `unicode-segmenter/grapheme` provides count/split-only API which has much less overhead than full `Segmenter` implementation, which includes some redundant codes but tree-shakable.
+* `@formatjs/intl-segmenter` handles grapheme, word, and sentence, but it's not tree-shakable.
+* `unicode-segmentation` size contains only minimum WASM binary and its bindings to execute benchmarking. It will increases to expose more features.
+* `Intl.Segmenter`'s Unicode data depends on the host, and may not be up-to-date.
+* `Intl.Segmenter` may not be available in [some old browsers](https://caniuse.com/mdn-javascript_builtins_intl_segmenter), edge runtimes, or embedded environments.
+
+#### Hermes Bytecode Stats
+
+| Name                                | Bytecode size | Bytecode size (gzip)* |
+|-------------------------------------|--------------:|----------------------:|
+| `unicode-segmenter/grapheme`        |        15,794 |                 8,916 |
+| `unicode-segmenter/grapheme` (full) |        16,003 |                 9,073 |
+| `graphemer`                         |       134,085 |                31,770 |
+| `grapheme-splitter`                 |        63,942 |                19,165 |
+| `@formatjs/intl-segmenter`          |       329,547 |               136,751 |
+
+* The installation size contains _compressed_ assets.
+
+#### Memory Stats
+
+Retained memory per library after segmenting the benchmark corpus, measured by `yarn memory-stats:grapheme` in isolated Node.js processes (median of 5, GC-stabilized deltas).
+
+
+| Name                         | JS heap | ArrayBuffers* |
+|------------------------------|--------:|--------------:|
+| `unicode-segmenter/grapheme` | 217 kB  |       19.1 kB |
+| `graphemer`                  | 2.32 MB |           0 B |
+| `grapheme-splitter`          | 570 kB  |           0 B |
+| `@formatjs/intl-segmenter`   | 1.95 MB |           0 B |
+| `unicode-segmentation`*      | 214 kB  |             - |
+| `Intl.Segmenter`*            | 86.1 kB |             - |
+
+* "ArrayBuffers" is `process.memoryUsage().arrayBuffers`: `unicode-segmenter` keeps its lookup tables in typed arrays, so they live there instead of the JS heap. No other JavaScript library here allocates any.
+* `unicode-segmentation`'s WASM linear memory and `Intl.Segmenter`'s ICU data are allocated by native code and invisible to both columns.
+
+#### Runtime Performance
+
+Here is a brief explanation, and you can see [archived benchmark results](benchmark/grapheme/_records).
+
+**Performance in Node.js/Bun/Deno**: `unicode-segmenter/grapheme` has best-in-class performance.
+- 5\~48x faster than other JavaScript libraries.
+- 3.5\~8x faster than WASM binding of the Rust's [unicode-segmentation].
+- 1.3\~2.5x faster than built-in [`Intl.Segmenter`].
+
+**Performance in Browsers**: The performance in browser environments varies greatly due to differences in browser engines, which makes benchmarking inconsistent, but:
+- Still significantly faster than other JavaScript libraries.
+- Generally outperforms the built-in in the most browser environments, except the Firefox.
+
+**Performance in React Native**: `unicode-segmenter/grapheme` is still faster than alternatives when compiled to Hermes bytecode. It's \~4x faster than `graphemer` and \~34x faster than `grapheme-splitter`.
+
+**Performance in QuickJS**: `unicode-segmenter/grapheme` is the only usable library in terms of performance.
+
+Instead of trusting these claims, you can try `yarn perf:grapheme` directly in your environment or build your own benchmark.
+
+## Acknowledgments
+
+- **The Rust Unicode team ([@unicode-rs](https://github.com/unicode-rs))**:\
+   The initial implementation was ported manually from [unicode-segmentation] library.
+
+- **Marijn Haverbeke ([@marijnh](https://github.com/marijnh))**:\
+   Inspired a technique that can greatly compress Unicode data table from [his library](https://github.com/marijnh/find-cluster-break).
+
+## LICENSE
+
+[MIT](LICENSE)
+
+[e18e]: https://e18e.dev/
+[Hermes]: https://hermesengine.dev/
+[QuickJS]: https://bellard.org/quickjs/
+[unicode-segmentation]: https://github.com/unicode-rs/unicode-segmentation
+[`Intl.Segmenter`]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Intl/Segmenter
+[graphemer]: https://github.com/flmnt/graphemer
+[grapheme-splitter]: https://github.com/orling/grapheme-splitter
+[emoji-regex]: https://github.com/mathiasbynens/emoji-regex
+[emojibase-regex]: https://emojibase.dev/docs/regex
+[XRegExp]: https://xregexp.com/
+[@formatjs/intl-segmenter]: https://formatjs.github.io/docs/polyfills/intl-segmenter/

package/node_modules/unicode-segmenter/_emoji_data.cjs

@@ -0,0 +1,24 @@
+"use strict";
+
+exports.extended_pictographic_table = exports.emoji_presentation_table = void 0;
+var _core = require("./core.cjs");
+// The following code was generated by "scripts/unicode.js",
+// DO NOT EDIT DIRECTLY.
+//
+// @ts-check
+
+/**
+ * @typedef {import('./core.js').UnicodeDataEncoding} UnicodeDataEncoding
+ */
+
+/**
+ * The Unicode `Emoji_Presentation` properties table
+ */
+const emoji_presentation_table = exports.emoji_presentation_table = (0, _core.decodeUnicodeFlatData)(/** @type {UnicodeDataEncoding} */
+'qhj21tc33020pg21l11i3br20j10d081h11518050l10711040207041s10j20104210t32o10e0rl31j3040uqks10qc0ub029r4p110o10k102412l11uag2c81l41l1cq244cg1303m4101qb2u3d31n1i10q11d0m5k5g3l460322333b178jeb40rh1u2191obg7c3a3o3104f2b49');
+
+/**
+ * The Unicode `Extended_Pictographic` properties table
+ */
+const extended_pictographic_table = exports.extended_pictographic_table = (0, _core.decodeUnicodeFlatData)(/** @type {UnicodeDataEncoding} */
+'pa040tov10c0od0m10q55f1vm11c0ma0p1a42nc0ne1a090q3314902021204020112030318250105bb1201110i1021i15101131502141b15120511011k1155132040202510201010603060a1f02040104210b1g3290e0e0kn11vs12j11j3040qt40c0pl2010qmtr10n23k6bf1f0e1l29g71c1e029j1n3r1ea0k1028139m16rb2v621122i522135tf1u3b51n17127c0232041d120819052c28220104060306l5g3l4572g130152cqdl2c3o37a5o27u11c32d9m2cu2191obo57eh9gg1tv3');

package/node_modules/unicode-segmenter/_emoji_data.d.cts

@@ -0,0 +1 @@
+export * from "./_emoji_data.js";

package/node_modules/unicode-segmenter/_emoji_data.d.ts

@@ -0,0 +1,12 @@
+/**
+ * @typedef {import('./core.js').UnicodeDataEncoding} UnicodeDataEncoding
+ */
+/**
+ * The Unicode `Emoji_Presentation` properties table
+ */
+export const emoji_presentation_table: import("./core.js").UnicodeRangeTable;
+/**
+ * The Unicode `Extended_Pictographic` properties table
+ */
+export const extended_pictographic_table: import("./core.js").UnicodeRangeTable;
+export type UnicodeDataEncoding = import("./core.js").UnicodeDataEncoding;

package/node_modules/unicode-segmenter/_emoji_data.js

@@ -0,0 +1,26 @@
+// The following code was generated by "scripts/unicode.js",
+// DO NOT EDIT DIRECTLY.
+//
+// @ts-check
+
+import { decodeUnicodeFlatData } from './core.js';
+
+/**
+ * @typedef {import('./core.js').UnicodeDataEncoding} UnicodeDataEncoding
+ */
+
+/**
+ * The Unicode `Emoji_Presentation` properties table
+ */
+export const emoji_presentation_table = decodeUnicodeFlatData(
+  /** @type {UnicodeDataEncoding} */
+  ('qhj21tc33020pg21l11i3br20j10d081h11518050l10711040207041s10j20104210t32o10e0rl31j3040uqks10qc0ub029r4p110o10k102412l11uag2c81l41l1cq244cg1303m4101qb2u3d31n1i10q11d0m5k5g3l460322333b178jeb40rh1u2191obg7c3a3o3104f2b49')
+);
+
+/**
+ * The Unicode `Extended_Pictographic` properties table
+ */
+export const extended_pictographic_table = decodeUnicodeFlatData(
+  /** @type {UnicodeDataEncoding} */
+  ('pa040tov10c0od0m10q55f1vm11c0ma0p1a42nc0ne1a090q3314902021204020112030318250105bb1201110i1021i15101131502141b15120511011k1155132040202510201010603060a1f02040104210b1g3290e0e0kn11vs12j11j3040qt40c0pl2010qmtr10n23k6bf1f0e1l29g71c1e029j1n3r1ea0k1028139m16rb2v621122i522135tf1u3b51n17127c0232041d120819052c28220104060306l5g3l4572g130152cqdl2c3o37a5o27u11c32d9m2cu2191obo57eh9gg1tv3')
+);

package/node_modules/unicode-segmenter/_general_data.cjs

@@ -0,0 +1,30 @@
+"use strict";
+
+exports.numeric_table = exports.letter_table = exports.alphabetic_table = void 0;
+var _core = require("./core.cjs");
+// The following code was generated by "scripts/unicode.js",
+// DO NOT EDIT DIRECTLY.
+//
+// @ts-check
+
+/**
+ * @typedef {import('./core.js').UnicodeDataEncoding} UnicodeDataEncoding
+ */
+
+/**
+ * The Unicode `L` (Letter) properties table
+ */
+const letter_table = exports.letter_table = (0, _core.decodeUnicodeFlatData)(/** @type {UnicodeDataEncoding} */
+'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');
+
+/**
+ * The Unicode `N` (Numeric) properties table
+ */
+const numeric_table = exports.numeric_table = (0, _core.decodeUnicodeFlatData)(/** @type {UnicodeDataEncoding} */
+'g39o715022hq59m89mc9sp19m7945s69m79m7925u6cj7986n69o667i1t69g69m79m4j1sg19m49vs2j1hn32ve969m19si19g8ala969mb9m59m8969mh403569mci324mt2r3u4l1mn2t1pm50pg30p18e2nl13q89u171eg29n2egmj79sb9gk15q99m29mc9m19m59mp19mhj59tu1s2co3h11ll1q1k23t1080m84qc9uq37p16n28r44m15ga12f2t2g48k31u12r44o67o17p26qk15g3969mh1u1u99q23g76m8t1g89s39g997j1rf9ml19m79mn19m696j1s4bkq1i1t59mp29m5s1je9m49m39mm19m6k1ri4u6hss39mi99m59m8916ug29mg1m1tl12pvs59ms5j1cj1s6o1ll4h3gk99mq19mv19nf9ss28g89nh3q31213s4s21eis3cjua9');
+
+/**
+ * The Unicode `Alphabetic` properties table
+ */
+const alphabetic_table = exports.alphabetic_table = (0, _core.decodeUnicodeFlatData)(/** @type {UnicodeDataEncoding} */
+'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');

package/node_modules/unicode-segmenter/_general_data.d.cts

@@ -0,0 +1 @@
+export * from "./_general_data.js";

package/node_modules/unicode-segmenter/_general_data.d.ts

@@ -0,0 +1,16 @@
+/**
+ * @typedef {import('./core.js').UnicodeDataEncoding} UnicodeDataEncoding
+ */
+/**
+ * The Unicode `L` (Letter) properties table
+ */
+export const letter_table: import("./core.js").UnicodeRangeTable;
+/**
+ * The Unicode `N` (Numeric) properties table
+ */
+export const numeric_table: import("./core.js").UnicodeRangeTable;
+/**
+ * The Unicode `Alphabetic` properties table
+ */
+export const alphabetic_table: import("./core.js").UnicodeRangeTable;
+export type UnicodeDataEncoding = import("./core.js").UnicodeDataEncoding;

package/node_modules/unicode-segmenter/_general_data.js

@@ -0,0 +1,34 @@
+// The following code was generated by "scripts/unicode.js",
+// DO NOT EDIT DIRECTLY.
+//
+// @ts-check
+
+import { decodeUnicodeFlatData } from './core.js';
+
+/**
+ * @typedef {import('./core.js').UnicodeDataEncoding} UnicodeDataEncoding
+ */
+
+/**
+ * The Unicode `L` (Letter) properties table
+ */
+export const letter_table = decodeUnicodeFlatData(
+  /** @type {UnicodeDataEncoding} */
+  ('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')
+);
+
+/**
+ * The Unicode `N` (Numeric) properties table
+ */
+export const numeric_table = decodeUnicodeFlatData(
+  /** @type {UnicodeDataEncoding} */
+  ('g39o715022hq59m89mc9sp19m7945s69m79m7925u6cj7986n69o667i1t69g69m79m4j1sg19m49vs2j1hn32ve969m19si19g8ala969mb9m59m8969mh403569mci324mt2r3u4l1mn2t1pm50pg30p18e2nl13q89u171eg29n2egmj79sb9gk15q99m29mc9m19m59mp19mhj59tu1s2co3h11ll1q1k23t1080m84qc9uq37p16n28r44m15ga12f2t2g48k31u12r44o67o17p26qk15g3969mh1u1u99q23g76m8t1g89s39g997j1rf9ml19m79mn19m696j1s4bkq1i1t59mp29m5s1je9m49m39mm19m6k1ri4u6hss39mi99m59m8916ug29mg1m1tl12pvs59ms5j1cj1s6o1ll4h3gk99mq19mv19nf9ss28g89nh3q31213s4s21eis3cjua9')
+);
+
+/**
+ * The Unicode `Alphabetic` properties table
+ */
+export const alphabetic_table = decodeUnicodeFlatData(
+  /** @type {UnicodeDataEncoding} */
+  ('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')
+);

package/node_modules/unicode-segmenter/_grapheme_data.cjs

@@ -0,0 +1,125 @@
+"use strict";
+
+exports.grapheme_pairs = exports.grapheme_data = exports.grapheme_cats = exports.GraphemeCategory = void 0;
+// The following code was generated by "scripts/unicode.js",
+// DO NOT EDIT DIRECTLY.
+//
+// @ts-check
+
+/**
+ * @typedef {import('./core.js').UnicodeDataEncoding} UnicodeDataEncoding
+ */
+
+/**
+ * @typedef {0} GC_Any
+ * @typedef {1} GC_CR
+ * @typedef {2} GC_Control
+ * @typedef {3} GC_Extend
+ * @typedef {4} GC_Extended_Pictographic
+ * @typedef {5} GC_L
+ * @typedef {6} GC_LF
+ * @typedef {7} GC_LV
+ * @typedef {8} GC_LVT
+ * @typedef {9} GC_Prepend
+ * @typedef {10} GC_Regional_Indicator
+ * @typedef {11} GC_SpacingMark
+ * @typedef {12} GC_T
+ * @typedef {13} GC_V
+ * @typedef {14} GC_ZWJ
+ * @typedef {(
+ *   | GC_Any
+ *   | GC_CR
+ *   | GC_Control
+ *   | GC_Extend
+ *   | GC_Extended_Pictographic
+ *   | GC_L
+ *   | GC_LF
+ *   | GC_LV
+ *   | GC_LVT
+ *   | GC_Prepend
+ *   | GC_Regional_Indicator
+ *   | GC_SpacingMark
+ *   | GC_T
+ *   | GC_V
+ *   | GC_ZWJ
+ * )} GraphemeCategoryNum
+ */
+
+/**
+ * @typedef {(
+ *   | 'Any'
+ *   | 'CR'
+ *   | 'Control'
+ *   | 'Extend'
+ *   | 'Extended_Pictographic'
+ *   | 'L'
+ *   | 'LF'
+ *   | 'LV'
+ *   | 'LVT'
+ *   | 'Prepend'
+ *   | 'Regional_Indicator'
+ *   | 'SpacingMark'
+ *   | 'T'
+ *   | 'V'
+ *   | 'ZWJ'
+ * )} GraphemeCategoryKey
+ */
+
+/**
+ * Grapheme category enum
+ *
+ * Note:
+ *   The object isn't actually frozen
+ *   because using `Object.freeze` increases 800 bytes on Brotli compression.
+ *
+ * @type {Readonly<Record<GraphemeCategoryKey, GraphemeCategoryNum>>}
+ */
+const GraphemeCategory = exports.GraphemeCategory = {
+  Any: 0,
+  CR: 1,
+  Control: 2,
+  Extend: 3,
+  Extended_Pictographic: 4,
+  L: 5,
+  LF: 6,
+  LV: 7,
+  LVT: 8,
+  Prepend: 9,
+  Regional_Indicator: 10,
+  SpacingMark: 11,
+  T: 12,
+  V: 13,
+  ZWJ: 14
+};
+
+/**
+ * Encoded `Grapheme_Cluster_Break` property ranges.
+ *
+ * Internal categories (never exposed through the public API):
+ *   - 15: InCB_Consonant
+ *
+ * @type {UnicodeDataEncoding}
+ */
+const grapheme_data = exports.grapheme_data = /** @type {UnicodeDataEncoding} */
+'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';
+
+/**
+ * Category of each range in {@link grapheme_data}, base36 digit per range.
+ */
+const grapheme_cats = exports.grapheme_cats = '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';
+
+/**
+ * UAX #29 pair-wise rules for extended grapheme cluster boundaries,
+ * evaluated into a 16x16 mask table indexed by `catBefore << 4 | catAfter`.
+ *
+ * A boundary exists iff the mask shares no bit with the runtime's packed sequence state.
+ *
+ * - 0: boundary (GB999 and friends), no state bit can match
+ * - 1: no boundary; bit 0 is always set in the state
+ * - 2: GB12/GB13, no boundary iff odd run of RI precedes
+ * - 4: GB11, no boundary iff the ZWJ was preceded by ExtPic Extend*
+ * - 8: GB9c, no boundary iff InCB Consonant [Extend Linker]* Linker [Extend Linker]* precedes
+ *
+ * See `buildGraphemePairTable` in scripts/unicode.js for the rules.
+ */
+const grapheme_pairs = exports.grapheme_pairs = '0001000000010010000000100000000000000000000000000001000000010018000100000001001000010101100101100000000000000000000100000001111000010000000110101001110111111111000100000021001000010000000100100001000000011010000100000001111000014000000100180001000000010010';

package/node_modules/unicode-segmenter/_grapheme_data.d.cts

@@ -0,0 +1 @@
+export * from "./_grapheme_data.js";