micromark-extension-cjk-friendly-util 1.0.0

package/LICENSE

@@ -0,0 +1,28 @@
+Copyright (c) 2025 Tatsunori Uchino <tats.u@live.jp>
+
+MIT LICENSE
+
+Based on micromark's sub-packages (micromark-util-character, micromark-util-symbol, and micromark-util-classify-character)
+
+(The MIT License)
+
+Copyright (c) Titus Wormer <tituswormer@gmail.com>
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+'Software'), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

package/README.md

@@ -0,0 +1,139 @@
+# micromark-extension-cjk-friendly-util
+
+[![Version](https://img.shields.io/npm/v/micromark-extension-cjk-friendly-util)](https://npmjs.com/package/micromark-extension-cjk-friendly-util) [![NPM Downloads](https://img.shields.io/npm/dw/micromark-extension-cjk-friendly-util)](https://npmjs.com/package/micromark-extension-cjk-friendly-util) [![NPM Last Update](https://img.shields.io/npm/last-update/micromark-extension-cjk-friendly-util)](https://npmjs.com/package/micromark-extension-cjk-friendly-util)
+
+An utility library package for [micromark-extension-cjk-friendly](https://npmjs.com/package/micromark-extension-cjk-friendly), which is internally used by [remark-cjk-friendly](https://npmjs.com/package/remark-cjk-friendly), and its related packages.
+
+## Problem / <span lang="ja">問題</span> / <span lang="zh-Hans-CN">问题</span> / <span lang="ko">문제점</span>
+
+CommonMark has a problem that the following emphasis marks `**` are not recognized as emphasis marks in Japanese, Chinese, and Korean.
+
+<span lang="ja">CommonMarkには、日本語・中国語・韓国語内の次のような強調記号(`**`)が強調記号として認識されない問題があります。</span>
+
+<span lang="zh-Hans-CN">CommonMark存在以下问题：在中文、日语和韩语文本中，强调标记`**`不会被识别为强调标记。</span>
+
+<span lang="ko">CommonMark는 일본어와 중국어에서 다음과 같은 강조 표시 `**`가 강조 표시로 인식되지 않는 문제가 있습니다.</span>
+
+```md
+**このアスタリスクは強調記号として認識されず、そのまま表示されます。**この文のせいで。
+
+**该星号不会被识别，而是直接显示。**这是因为它没有被识别为强调符号。
+
+**이 별표는 강조 표시로 인식되지 않고 그대로 표시됩니다(이 괄호 때문에)**이 문장 때문에.
+```
+
+This problem occurs because the character just inside the `**` is a (Japanese or Chinese) punctuation mark (。) or parenthesis and the character just outside is not a space or punctuation mark.
+
+<span lang="ja">これが起こった原因は、終了側の`**`のすぐ内側が約物（。やカッコ）、かつ外側が約物や空白以外の文字であるためです。</span>
+
+<span lang="zh-Hans-CN">这个问题是因为在`**`的结束部分，内侧字符是标点符号（。）或括号，而外侧字符不是空格或标点符号。</span>
+
+<span lang="ko">이 문제는 `**` 바로 안쪽의 문자가 (일본어나 중국어) 문장 부호(。) 또는 괄호이고 바깥쪽 문자가 공백이나 문장 부호가 아니기 때문에 발생합니다.</span>
+
+Of course, not only the end side but also the start side has the same issue.
+
+<span lang="ja">もちろん終了側だけでなく、開始側も同様の問題が存在します。</span>
+
+<span lang="zh-Hans-CN">当然，不仅是结束侧，开始侧也存在同样的问题。</span>
+
+<span lang="ko">물론 끝나는 부분뿐만 아니라 시작하는 부분에서도 동일한 문제가 있습니다.</span>
+
+CommonMark issue: https://github.com/commonmark/commonmark-spec/issues/650
+
+## Runtime Requirements / <span lang="ja">実行環境の要件</span> / <span lang="zh-Hans-CN">运行环境要求</span> / <span lang="ko">업데이트 전략</span>
+
+This package uses the [`v` flag of the regular expression](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/RegExp/unicodeSets) introduced in ES2024 to determine whether the character is an emoji or not.
+
+<span lang="ja">本パッケージは文字が絵文字かどうかを判定するために、ES2024で導入された[正規表現の`v`フラグ](https://developer.mozilla.org/ja/docs/Web/JavaScript/Reference/Global_Objects/RegExp/unicodeSets)を使用しています。</span>
+
+<span lang="zh-CN">本包使用 ES2024 引入的[`v` 标志](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/RegExp/unicodeSets) 来判断字符是否为 emoji。</span>
+
+<span lang="ko">이 패키지는 ES2024에서 도입된 [`v` 플래그](https://developer.mozilla.org/ko/docs/Web/JavaScript/Reference/Global_Objects/RegExp/unicodeSets)를 사용하여 문자가 이모지인지 여부를 판단합니다.</span>
+
+It makes this package compatible only with relatively recent browsers and Node.js:
+
+<span lang="ja">このため、本パッケージは、次のような比較的新しいブラウザやNode.jsでしか動作しません。</span>
+
+<span lang="zh-CN">因此，本包只兼容比较新的浏览器和 Node.js:</span>
+
+<span lang="ko">따라서, 이 패키지는 비교적 최신 브라우저와 Node.js에서만 작동합니다.</span>
+
+- Chrome / Edge 112 or later
+- Firefox 116 or later
+- Safari 17 or later
+- Node.js 20 or later
+
+## Installation / <span lang="ja">インストール</span> / <span lang="zh-Hans-CN">安装</span> / <span lang="ko">설치</span>
+
+Install `micromark-extension-cjk-friendly-util` via [npm](https://www.npmjs.com/):
+
+<span lang="ja">`micromark-extension-cjk-friendly-util`を[npm](https://www.npmjs.com/)でインストールしてください。</span>
+
+<span lang="zh-Hans-CN">通过 [npm](https://www.npmjs.com/) 安装 `micromark-extension-cjk-friendly-util`。</span>
+
+<span lang="ko">`micromark-extension-cjk-friendly-util`를 [npm](https://www.npmjs.com/)으로 설치하세요.</span>
+
+```bash
+npm install micromark-extension-cjk-friendly-util
+```
+
+If you use another package manager, please replace `npm install` with the command of the package manager you use (e.g. `pnpm add` or `yarn add`).
+
+<span lang="ja">npm以外のパッケージマネージャを使う場合は、`npm install`を当該パッケージマネージャのコマンド（例：`pnpm add`・`yarn add`）に置き換えてください。</span>
+
+<span lang="zh-Hans-CN">如果使用其他包管理器，请将 `npm install` 替换为当时包管理器的命令（例如：`pnpm add`、`yarn add`）。</span>
+
+<span lang="ko">다른 패키지 매니저를 사용하는 경우 `npm install`을 해당 패키지 매니저의 명령어(예: `pnpm add`, `yarn add`)로 바꾸어 주세요.</span>
+
+## Usage / <span lang="ja">使い方</span> / <span lang="zh-Hans-CN">用法</span> / <span lang="ko">사용법</span>
+
+> [!IMPORTANT]
+> Most people do not have to use this package directly. Did you mean:
+>
+> - [remark-cjk-friendly](https://npmjs.com/package/remark-cjk-friendly)
+> - [micromark-extension-cjk-friendly](https://npmjs.com/package/micromark-extension-cjk-friendly)
+
+This package provides a function and a namespace based on the original micromark-related packages:
+
+| Name | Type | Derived from | Original Name | Description |
+| --- | --- | --- | --- | --- |
+| `classifyCharacter` | function | [micromark-util-character](https://npmjs.com/package/micromark-util-character) | (same) | Tells whether a character is not only a punctuation or whitespace but also a CJK or variation selector |
+| `constantsEx` | namespace | [micromark-util-symbol](https://npmjs.com/package/micromark-util-symbol) | `constants` | Constants meaning CJK and variation selectors; use it and the original `constants` together. |
+
+Also, this package provides some utility functions to check whether a character belongs to the category defined in the specification (e.g. CJK code point without variation selector), or to help you fetch the Unicode Code Point of a character around the emphasis mark.
+
+## Specification / <span lang="ja">規格書</span> / <span lang="zh-Hans-CN">规范</span> / <span lang="ko">규정서</span>
+
+https://github.com/tats-u/markdown-cjk-friendly/blob/main/specification.md (English)
+
+## Related packages / <span lang="ja">関連パッケージ</span> / <span lang="zh-Hans-CN">相关包</span> / <span lang="ko">관련 패키지</span>
+
+- [micromark-extension-cjk-friendly](https://npmjs.com/package/micromark-extension-cjk-friendly) [![Version](https://img.shields.io/npm/v/micromark-extension-cjk-friendly)](https://npmjs.com/package/micromark-extension-cjk-friendly) [![NPM Downloads](https://img.shields.io/npm/dw/micromark-extension-cjk-friendly)](https://npmjs.com/package/micromark-extension-cjk-friendly) [![NPM Last Update](https://img.shields.io/npm/last-update/micromark-extension-cjk-friendly)](https://npmjs.com/package/micromark-extension-cjk-friendly)
+- [remark-cjk-friendly](https://npmjs.com/package/remark-cjk-friendly) [![Version](https://img.shields.io/npm/v/remark-cjk-friendly)](https://npmjs.com/package/remark-cjk-friendly) [![NPM Downloads](https://img.shields.io/npm/dw/remark-cjk-friendly)](https://npmjs.com/package/remark-cjk-friendly) [![NPM Last Update](https://img.shields.io/npm/last-update/remark-cjk-friendly)](https://npmjs.com/package/remark-cjk-friendly)
+- [markdown-it-cjk-friendly](https://npmjs.com/package/markdown-it-cjk-friendly) [![Version](https://img.shields.io/npm/v/markdown-it-cjk-friendly)](https://npmjs.com/package/markdown-it-cjk-friendly) [![NPM Downloads](https://img.shields.io/npm/dw/markdown-it-cjk-friendly)](https://npmjs.com/package/markdown-it-cjk-friendly) [![NPM Last Update](https://img.shields.io/npm/last-update/markdown-it-cjk-friendly)](https://npmjs.com/package/markdown-it-cjk-friendly)
+- [remark-cjk-friendly](https://npmjs.com/package/remark-cjk-friendly) [![Version](https://img.shields.io/npm/v/remark-cjk-friendly)](https://npmjs.com/package/remark-cjk-friendly) [![NPM Downloads](https://img.shields.io/npm/dw/remark-cjk-friendly)](https://npmjs.com/package/remark-cjk-friendly) [![NPM Last Update](https://img.shields.io/npm/last-update/remark-cjk-friendly)](https://npmjs.com/package/remark-cjk-friendly)
+- [micromark-extension-cjk-friendly-gfm-strikethrough](https://npmjs.com/package/micromark-extension-cjk-friendly-gfm-strikethrough) [![Version](https://img.shields.io/npm/v/micromark-extension-cjk-friendly-gfm-strikethrough)](https://npmjs.com/package/micromark-extension-cjk-friendly-gfm-strikethrough) [![NPM Downloads](https://img.shields.io/npm/dw/micromark-extension-cjk-friendly-gfm-strikethrough)](https://npmjs.com/package/micromark-extension-cjk-friendly-gfm-strikethrough) [![NPM Last Update](https://img.shields.io/npm/last-update/micromark-extension-cjk-friendly-gfm-strikethrough)](https://npmjs.com/package/micromark-extension-cjk-friendly-gfm-strikethrough)
+
+## Contributing / <span lang="ja">貢献</span> / <span lang="zh-Hans-CN">贡献</span> / <span lang="ko">기여</span>
+
+### Setup
+
+Install the dependencies:
+
+```bash
+pnpm install
+```
+
+### Get Started
+
+Build the library:
+
+```bash
+pnpm build
+```
+
+Build the library in watch mode:
+
+```bash
+pnpm dev
+```

package/dist/categoryUtil.d.ts

@@ -0,0 +1,45 @@
+import { type classifyCharacter } from "./classifyCharacter.js";
+type Category = ReturnType<typeof classifyCharacter>;
+/**
+ * `true` if the code point represents an [Unicode whitespace character](https://spec.commonmark.org/0.31.2/#unicode-whitespace-character).
+ *
+ * @param category the return value of `classifyCharacter`.
+ * @returns `true` if the code point represents an Unicode whitespace character
+ */
+export declare function isUnicodeWhitespace(category: Category): boolean;
+/**
+ * `true` if the code point represents a [non-CJK punctuation character](https://github.com/tats-u/markdown-cjk-friendly/blob/main/specification.md#non-cjk-punctuation-character).
+ *
+ * @param category the return value of `classifyCharacter`.
+ * @returns `true` if the code point represents a non-CJK punctuation character
+ */
+export declare function isNonCjkPunctuation(category: Category): boolean;
+/**
+ * `true` if the code point represents a [CJK character (CJK code point without variation selector)](https://github.com/tats-u/markdown-cjk-friendly/blob/main/specification.md#cjk-code-point-without-variation-selector).
+ *
+ * @param category the return value of `classifyCharacter`.
+ * @returns `true` if the code point represents a CJK character
+ */
+export declare function isCjk(category: Category): boolean;
+/**
+ * `true` if the code point represents an [IVS (Ideographic Variation Selector)](https://github.com/tats-u/markdown-cjk-friendly/blob/main/specification.md#ivs).
+ *
+ * @param category the return value of `classifyCharacter`.
+ * @returns `true` if the code point represents an IVS
+ */
+export declare function isIvs(category: Category): boolean;
+/**
+ * `true` if the code point represents a [SVS (Standard Variation Selector/Sequence) that can follow CJK](https://github.com/tats-u/markdown-cjk-friendly/blob/main/specification.md#svs-that-can-follow-cjk).
+ *
+ * @param category the return value of `classifyCharacter`.
+ * @returns `true` if the code point represents an SVS that can follow CJK
+ */
+export declare function isSvsFollowingCjk(category: Category): boolean;
+/**
+ * `true` if the code point represents an [Unicode whitespace character](https://spec.commonmark.org/0.31.2/#unicode-whitespace-character) or an [Unicode punctuation character](https://spec.commonmark.org/0.31.2/#unicode-punctuation-character).
+ *
+ * @param category the return value of `classifyCharacter`.
+ * @returns `true` if the code point represents a space or punctuation
+ */
+export declare function isSpaceOrPunctuation(category: Category): boolean;
+export {};

package/dist/characterWithNonBmp.d.ts

@@ -0,0 +1,55 @@
+import type { Code } from "micromark-util-types";
+/**
+ * Check if `uc` is CJK or IVS
+ *
+ * @param uc code point
+ * @returns `true` if `uc` is CJK, `null` if IVS, or `false` if neither
+ */
+export declare function cjkOrIvs(uc: Code): boolean | null;
+/**
+ * Check whether the character code represents Standard Variation Sequence that can follow an ideographic character.
+ *
+ * U+FE0E is used for some CJK symbols (e.g. U+3299) that can also be
+ */
+export declare const svsFollowingCjk: (code: Code) => boolean;
+/**
+ * Check whether the character code represents Unicode punctuation.
+ *
+ * A **Unicode punctuation** is a character in the Unicode `Pc` (Punctuation,
+ * Connector), `Pd` (Punctuation, Dash), `Pe` (Punctuation, Close), `Pf`
+ * (Punctuation, Final quote), `Pi` (Punctuation, Initial quote), `Po`
+ * (Punctuation, Other), or `Ps` (Punctuation, Open) categories, or an ASCII
+ * punctuation (see `asciiPunctuation`).
+ *
+ * See:
+ * **\[UNICODE]**:
+ * [The Unicode Standard](https://www.unicode.org/versions/).
+ * Unicode Consortium.
+ *
+ * @param code
+ *   Code.
+ * @returns
+ *   Whether it matches.
+ */
+export declare const unicodePunctuation: (code: Code) => boolean;
+/**
+ * Check whether the character code represents Unicode whitespace.
+ *
+ * Note that this does handle micromark specific markdown whitespace characters.
+ * See `markdownLineEndingOrSpace` to check that.
+ *
+ * A **Unicode whitespace** is a character in the Unicode `Zs` (Separator,
+ * Space) category, or U+0009 CHARACTER TABULATION (HT), U+000A LINE FEED (LF),
+ * U+000C (FF), or U+000D CARRIAGE RETURN (CR) (**\[UNICODE]**).
+ *
+ * See:
+ * **\[UNICODE]**:
+ * [The Unicode Standard](https://www.unicode.org/versions/).
+ * Unicode Consortium.
+ *
+ * @param code
+ *   Code.
+ * @returns
+ *   Whether it matches.
+ */
+export declare const unicodeWhitespace: (code: Code) => boolean;

package/dist/classifyCharacter.d.ts

@@ -0,0 +1,26 @@
+import { constants } from "micromark-util-symbol";
+import type { Code } from "micromark-util-types";
+export declare namespace constantsEx {
+    const spaceOrPunctuation: 3;
+    const cjk: 4096;
+    const cjkPunctuation: 4098;
+    const ivs: 8192;
+    const cjkOrIvs: 12288;
+    const svsFollowingCjk: 16384;
+    const variationSelector: 28672;
+}
+/**
+ * Classify whether a code represents whitespace, punctuation, or something
+ * else.
+ *
+ * Used for attention (emphasis, strong), whose sequences can open or close
+ * based on the class of surrounding characters.
+ *
+ * > 👉 **Note**: eof (`null`) is seen as whitespace.
+ *
+ * @param code
+ *   Code.
+ * @returns
+ *   Group.
+ */
+export declare function classifyCharacter(code: Code): typeof constants.characterGroupWhitespace | typeof constants.characterGroupPunctuation | typeof constantsEx.cjk | typeof constantsEx.cjkPunctuation | typeof constantsEx.ivs | typeof constantsEx.svsFollowingCjk | 0;

package/dist/codeUtil.d.ts

@@ -0,0 +1,45 @@
+import type { Code, Point, TokenizeContext } from "micromark-util-types";
+/**
+ * Check if the given code is a [High-Surrogate Code Unit](https://www.unicode.org/glossary/#high_surrogate_code_unit).
+ *
+ * A High-Surrogate Code Unit is the _first_ half of a [Surrogate Pair](https://www.unicode.org/glossary/#surrogate_pair).
+ *
+ * @param code Code.
+ * @returns `true` if the code is a High-Surrogate Code Unit, `false` otherwise.
+ */
+export declare function isCodeHighSurrogate(code: Code): code is Exclude<Code, null>;
+/**
+ * Check if the given code is a [Low-Surrogate Code Unit](https://www.unicode.org/glossary/#low_surrogate_code_unit).
+ *
+ * A Low-Surrogate Code Unit is the _second_ half of a [Surrogate Pair](https://www.unicode.org/glossary/#surrogate_pair).
+ * @param code
+ *   The character code to check.
+ * @returns
+ *   True if the code is a Low-Surrogate Code Unit, false otherwise.
+ */
+export declare function isCodeLowSurrogate(code: Code): code is Exclude<Code, null>;
+/**
+ * If `code` is a [Low-Surrogate Code Unit](https://www.unicode.org/glossary/#low_surrogate_code_unit), try to get a genuine previous [Unicode Scalar Value](https://www.unicode.org/glossary/#unicode_scalar_value) corresponding to the Low-Surrogate Code Unit.
+ * @param code a tentative previous [code unit](https://www.unicode.org/glossary/#code_unit) less than 65,536, including a Low-Surrogate one
+ * @param nowPoint `this.now()` (`this` = `TokenizeContext`)
+ * @param sliceSerialize `this.sliceSerialize` (`this` = `TokenizeContext`)
+ * @returns a value greater than 65,535 if the previous code point represents a [Supplementary Character](https://www.unicode.org/glossary/#supplementary_character), or `code` otherwise
+ */
+export declare function tryGetGenuinePreviousCode(code: Exclude<Code, null>, nowPoint: Point, sliceSerialize: TokenizeContext["sliceSerialize"]): Exclude<Code, null>;
+/**
+ * Try to get the [Unicode Code Point](https://www.unicode.org/glossary/#code_point) two positions before the current position.
+ *
+ * @param previousCode a previous code point. Should be greater than 65,535 if it represents a [Supplementary Character](https://www.unicode.org/glossary/#supplementary_character).
+ * @param nowPoint `this.now()` (`this` = `TokenizeContext`)
+ * @param sliceSerialize `this.sliceSerialize` (`this` = `TokenizeContext`)
+ * @returns a value greater than 65,535 if the code point two positions before represents a [Supplementary Character](https://www.unicode.org/glossary/#supplementary_character), a value less than 65,536 for a [BMP Character](https://www.unicode.org/glossary/#bmp_character), or `null` if not found
+ */
+export declare function tryGetCodeTwoBefore(previousCode: Exclude<Code, null>, nowPoint: Point, sliceSerialize: TokenizeContext["sliceSerialize"]): Code;
+/**
+ * If `code` is a [High-Surrogate Code Unit](https://www.unicode.org/glossary/#high_surrogate_code_unit), try to get a genuine next [Unicode Scalar Value](https://www.unicode.org/glossary/#unicode_scalar_value) corresponding to the High-Surrogate Code Unit.
+ * @param code a tentative next [code unit](https://www.unicode.org/glossary/#code_unit) less than 65,536, including a High-Surrogate one
+ * @param nowPoint `this.now()` (`this` = `TokenizeContext`)
+ * @param sliceSerialize `this.sliceSerialize` (`this` = `TokenizeContext`)
+ * @returns a value greater than 65,535 if the next code point represents a [Supplementary Character](https://www.unicode.org/glossary/#supplementary_character), or `code` otherwise
+ */
+export declare function tryGetGenuineNextCode(code: Exclude<Code, null>, nowPoint: Point, sliceSerialize: TokenizeContext["sliceSerialize"]): Exclude<Code, null>;

package/dist/index.cjs

@@ -0,0 +1,169 @@
+"use strict";
+var __webpack_require__ = {};
+(()=>{
+    __webpack_require__.d = function(exports1, definition) {
+        for(var key in definition)if (__webpack_require__.o(definition, key) && !__webpack_require__.o(exports1, key)) Object.defineProperty(exports1, key, {
+            enumerable: true,
+            get: definition[key]
+        });
+    };
+})();
+(()=>{
+    __webpack_require__.o = function(obj, prop) {
+        return Object.prototype.hasOwnProperty.call(obj, prop);
+    };
+})();
+(()=>{
+    __webpack_require__.r = function(exports1) {
+        if ('undefined' != typeof Symbol && Symbol.toStringTag) Object.defineProperty(exports1, Symbol.toStringTag, {
+            value: 'Module'
+        });
+        Object.defineProperty(exports1, '__esModule', {
+            value: true
+        });
+    };
+})();
+var __webpack_exports__ = {};
+__webpack_require__.r(__webpack_exports__);
+__webpack_require__.d(__webpack_exports__, {
+    constantsEx: ()=>classifyCharacter_constantsEx,
+    isCjk: ()=>isCjk,
+    isSpaceOrPunctuation: ()=>isSpaceOrPunctuation,
+    isNonCjkPunctuation: ()=>isNonCjkPunctuation,
+    isSvsFollowingCjk: ()=>isSvsFollowingCjk,
+    tryGetGenuinePreviousCode: ()=>tryGetGenuinePreviousCode,
+    isUnicodeWhitespace: ()=>isUnicodeWhitespace,
+    isCodeHighSurrogate: ()=>isCodeHighSurrogate,
+    isIvs: ()=>isIvs,
+    tryGetCodeTwoBefore: ()=>tryGetCodeTwoBefore,
+    classifyCharacter: ()=>classifyCharacter,
+    isCodeLowSurrogate: ()=>isCodeLowSurrogate,
+    tryGetGenuineNextCode: ()=>tryGetGenuineNextCode
+});
+const external_micromark_util_symbol_namespaceObject = require("micromark-util-symbol");
+const external_micromark_util_character_namespaceObject = require("micromark-util-character");
+const external_get_east_asian_width_namespaceObject = require("get-east-asian-width");
+function cjkOrIvs(uc) {
+    if (!uc || uc < 0) return false;
+    const eaw = (0, external_get_east_asian_width_namespaceObject.eastAsianWidthType)(uc);
+    switch(eaw){
+        case "fullwidth":
+        case "halfwidth":
+            return true;
+        case "wide":
+            return !/^\p{RGI_Emoji}/v.test(String.fromCodePoint(uc));
+        case "narrow":
+            return false;
+        case "ambiguous":
+            return 0xe0100 <= uc && uc <= 0xe01ef && null;
+        case "neutral":
+            return /^\p{sc=Hangul}/u.test(String.fromCodePoint(uc));
+    }
+}
+const svsFollowingCjk = regexCheck(/[\uFE00-\uFE02\uFE0E]/u);
+const unicodePunctuation = regexCheck(/\p{P}|\p{S}/u);
+const unicodeWhitespace = regexCheck(/\s/);
+function regexCheck(regex) {
+    return check;
+    function check(code) {
+        return null !== code && code > -1 && regex.test(String.fromCodePoint(code));
+    }
+}
+(function(constantsEx) {
+    constantsEx.spaceOrPunctuation = 3;
+    constantsEx.cjk = 0x1000;
+    constantsEx.cjkPunctuation = 0x1002;
+    constantsEx.ivs = 0x2000;
+    constantsEx.cjkOrIvs = 0x3000;
+    constantsEx.svsFollowingCjk = 0x4000;
+    constantsEx.variationSelector = 0x7000;
+})(classifyCharacter_constantsEx || (classifyCharacter_constantsEx = {}));
+function classifyCharacter(code) {
+    if (code === external_micromark_util_symbol_namespaceObject.codes.eof || (0, external_micromark_util_character_namespaceObject.markdownLineEndingOrSpace)(code) || unicodeWhitespace(code)) return external_micromark_util_symbol_namespaceObject.constants.characterGroupWhitespace;
+    let value = 0;
+    if (code >= 0x1100) {
+        if (svsFollowingCjk(code)) return classifyCharacter_constantsEx.svsFollowingCjk;
+        switch(cjkOrIvs(code)){
+            case null:
+                return classifyCharacter_constantsEx.ivs;
+            case true:
+                value |= classifyCharacter_constantsEx.cjk;
+                break;
+        }
+    }
+    if (unicodePunctuation(code)) value |= external_micromark_util_symbol_namespaceObject.constants.characterGroupPunctuation;
+    return value;
+}
+var classifyCharacter_constantsEx;
+function isUnicodeWhitespace(category) {
+    return Boolean(category & external_micromark_util_symbol_namespaceObject.constants.characterGroupWhitespace);
+}
+function isNonCjkPunctuation(category) {
+    return (category & classifyCharacter_constantsEx.cjkPunctuation) === external_micromark_util_symbol_namespaceObject.constants.characterGroupPunctuation;
+}
+function isCjk(category) {
+    return Boolean(category & classifyCharacter_constantsEx.cjk);
+}
+function isIvs(category) {
+    return category === classifyCharacter_constantsEx.ivs;
+}
+function isSvsFollowingCjk(category) {
+    return category === classifyCharacter_constantsEx.svsFollowingCjk;
+}
+function isSpaceOrPunctuation(category) {
+    return Boolean(category & classifyCharacter_constantsEx.spaceOrPunctuation);
+}
+function isCodeHighSurrogate(code) {
+    return Boolean(code && code >= 0xd800 && code <= 0xdbff);
+}
+function isCodeLowSurrogate(code) {
+    return Boolean(code && code >= 0xdc00 && code <= 0xdfff);
+}
+function tryGetGenuinePreviousCode(code, nowPoint, sliceSerialize) {
+    if (nowPoint._bufferIndex < 2) return code;
+    const previousBuffer = sliceSerialize({
+        start: {
+            ...nowPoint,
+            _bufferIndex: nowPoint._bufferIndex - 2
+        },
+        end: nowPoint
+    });
+    const previousCandidate = previousBuffer.codePointAt(0);
+    return previousCandidate && previousCandidate >= 65536 ? previousCandidate : code;
+}
+function tryGetCodeTwoBefore(previousCode, nowPoint, sliceSerialize) {
+    const previousWidth = previousCode >= 65536 ? 2 : 1;
+    if (nowPoint._bufferIndex < 1 + previousWidth) return null;
+    const idealStart = nowPoint._bufferIndex - previousWidth - 2;
+    const twoPreviousBuffer = sliceSerialize({
+        start: {
+            ...nowPoint,
+            _bufferIndex: idealStart >= 0 ? idealStart : 0
+        },
+        end: {
+            ...nowPoint,
+            _bufferIndex: nowPoint._bufferIndex - previousWidth
+        }
+    });
+    const twoPreviousLast = twoPreviousBuffer.charCodeAt(twoPreviousBuffer.length - 1);
+    if (Number.isNaN(twoPreviousLast)) return null;
+    if (twoPreviousBuffer.length < 2 || twoPreviousLast < 0xdc00 || 0xdfff < twoPreviousLast) return twoPreviousLast;
+    const twoPreviousCandidate = twoPreviousBuffer.codePointAt(0);
+    if (twoPreviousCandidate && twoPreviousCandidate >= 65536) return twoPreviousCandidate;
+    return twoPreviousLast;
+}
+function tryGetGenuineNextCode(code, nowPoint, sliceSerialize) {
+    const nextCandidate = sliceSerialize({
+        start: nowPoint,
+        end: {
+            ...nowPoint,
+            _bufferIndex: nowPoint._bufferIndex + 2
+        }
+    }).codePointAt(0);
+    return nextCandidate && nextCandidate >= 65536 ? nextCandidate : code;
+}
+var __webpack_export_target__ = exports;
+for(var __webpack_i__ in __webpack_exports__)__webpack_export_target__[__webpack_i__] = __webpack_exports__[__webpack_i__];
+if (__webpack_exports__.__esModule) Object.defineProperty(__webpack_export_target__, '__esModule', {
+    value: true
+});

package/dist/index.d.ts

@@ -0,0 +1,3 @@
+export { isCjk, isIvs, isNonCjkPunctuation, isSpaceOrPunctuation, isSvsFollowingCjk, isUnicodeWhitespace, } from "./categoryUtil.js";
+export { classifyCharacter, constantsEx } from "./classifyCharacter.js";
+export { isCodeHighSurrogate, isCodeLowSurrogate, tryGetGenuineNextCode, tryGetGenuinePreviousCode, tryGetCodeTwoBefore, } from "./codeUtil.js";

package/dist/index.js

@@ -0,0 +1,123 @@
+import * as __WEBPACK_EXTERNAL_MODULE_micromark_util_symbol_0f33a452__ from "micromark-util-symbol";
+import * as __WEBPACK_EXTERNAL_MODULE_micromark_util_character_bdee8a5c__ from "micromark-util-character";
+import * as __WEBPACK_EXTERNAL_MODULE_get_east_asian_width_c890dec0__ from "get-east-asian-width";
+function cjkOrIvs(uc) {
+    if (!uc || uc < 0) return false;
+    const eaw = (0, __WEBPACK_EXTERNAL_MODULE_get_east_asian_width_c890dec0__.eastAsianWidthType)(uc);
+    switch(eaw){
+        case "fullwidth":
+        case "halfwidth":
+            return true;
+        case "wide":
+            return !/^\p{RGI_Emoji}/v.test(String.fromCodePoint(uc));
+        case "narrow":
+            return false;
+        case "ambiguous":
+            return 0xe0100 <= uc && uc <= 0xe01ef && null;
+        case "neutral":
+            return /^\p{sc=Hangul}/u.test(String.fromCodePoint(uc));
+    }
+}
+const svsFollowingCjk = regexCheck(/[\uFE00-\uFE02\uFE0E]/u);
+const unicodePunctuation = regexCheck(/\p{P}|\p{S}/u);
+const unicodeWhitespace = regexCheck(/\s/);
+function regexCheck(regex) {
+    return check;
+    function check(code) {
+        return null !== code && code > -1 && regex.test(String.fromCodePoint(code));
+    }
+}
+(function(constantsEx) {
+    constantsEx.spaceOrPunctuation = 3;
+    constantsEx.cjk = 0x1000;
+    constantsEx.cjkPunctuation = 0x1002;
+    constantsEx.ivs = 0x2000;
+    constantsEx.cjkOrIvs = 0x3000;
+    constantsEx.svsFollowingCjk = 0x4000;
+    constantsEx.variationSelector = 0x7000;
+})(classifyCharacter_constantsEx || (classifyCharacter_constantsEx = {}));
+function classifyCharacter(code) {
+    if (code === __WEBPACK_EXTERNAL_MODULE_micromark_util_symbol_0f33a452__.codes.eof || (0, __WEBPACK_EXTERNAL_MODULE_micromark_util_character_bdee8a5c__.markdownLineEndingOrSpace)(code) || unicodeWhitespace(code)) return __WEBPACK_EXTERNAL_MODULE_micromark_util_symbol_0f33a452__.constants.characterGroupWhitespace;
+    let value = 0;
+    if (code >= 0x1100) {
+        if (svsFollowingCjk(code)) return classifyCharacter_constantsEx.svsFollowingCjk;
+        switch(cjkOrIvs(code)){
+            case null:
+                return classifyCharacter_constantsEx.ivs;
+            case true:
+                value |= classifyCharacter_constantsEx.cjk;
+                break;
+        }
+    }
+    if (unicodePunctuation(code)) value |= __WEBPACK_EXTERNAL_MODULE_micromark_util_symbol_0f33a452__.constants.characterGroupPunctuation;
+    return value;
+}
+var classifyCharacter_constantsEx;
+function isUnicodeWhitespace(category) {
+    return Boolean(category & __WEBPACK_EXTERNAL_MODULE_micromark_util_symbol_0f33a452__.constants.characterGroupWhitespace);
+}
+function isNonCjkPunctuation(category) {
+    return (category & classifyCharacter_constantsEx.cjkPunctuation) === __WEBPACK_EXTERNAL_MODULE_micromark_util_symbol_0f33a452__.constants.characterGroupPunctuation;
+}
+function isCjk(category) {
+    return Boolean(category & classifyCharacter_constantsEx.cjk);
+}
+function isIvs(category) {
+    return category === classifyCharacter_constantsEx.ivs;
+}
+function isSvsFollowingCjk(category) {
+    return category === classifyCharacter_constantsEx.svsFollowingCjk;
+}
+function isSpaceOrPunctuation(category) {
+    return Boolean(category & classifyCharacter_constantsEx.spaceOrPunctuation);
+}
+function isCodeHighSurrogate(code) {
+    return Boolean(code && code >= 0xd800 && code <= 0xdbff);
+}
+function isCodeLowSurrogate(code) {
+    return Boolean(code && code >= 0xdc00 && code <= 0xdfff);
+}
+function tryGetGenuinePreviousCode(code, nowPoint, sliceSerialize) {
+    if (nowPoint._bufferIndex < 2) return code;
+    const previousBuffer = sliceSerialize({
+        start: {
+            ...nowPoint,
+            _bufferIndex: nowPoint._bufferIndex - 2
+        },
+        end: nowPoint
+    });
+    const previousCandidate = previousBuffer.codePointAt(0);
+    return previousCandidate && previousCandidate >= 65536 ? previousCandidate : code;
+}
+function tryGetCodeTwoBefore(previousCode, nowPoint, sliceSerialize) {
+    const previousWidth = previousCode >= 65536 ? 2 : 1;
+    if (nowPoint._bufferIndex < 1 + previousWidth) return null;
+    const idealStart = nowPoint._bufferIndex - previousWidth - 2;
+    const twoPreviousBuffer = sliceSerialize({
+        start: {
+            ...nowPoint,
+            _bufferIndex: idealStart >= 0 ? idealStart : 0
+        },
+        end: {
+            ...nowPoint,
+            _bufferIndex: nowPoint._bufferIndex - previousWidth
+        }
+    });
+    const twoPreviousLast = twoPreviousBuffer.charCodeAt(twoPreviousBuffer.length - 1);
+    if (Number.isNaN(twoPreviousLast)) return null;
+    if (twoPreviousBuffer.length < 2 || twoPreviousLast < 0xdc00 || 0xdfff < twoPreviousLast) return twoPreviousLast;
+    const twoPreviousCandidate = twoPreviousBuffer.codePointAt(0);
+    if (twoPreviousCandidate && twoPreviousCandidate >= 65536) return twoPreviousCandidate;
+    return twoPreviousLast;
+}
+function tryGetGenuineNextCode(code, nowPoint, sliceSerialize) {
+    const nextCandidate = sliceSerialize({
+        start: nowPoint,
+        end: {
+            ...nowPoint,
+            _bufferIndex: nowPoint._bufferIndex + 2
+        }
+    }).codePointAt(0);
+    return nextCandidate && nextCandidate >= 65536 ? nextCandidate : code;
+}
+export { classifyCharacter, classifyCharacter_constantsEx as constantsEx, isCjk, isCodeHighSurrogate, isCodeLowSurrogate, isIvs, isNonCjkPunctuation, isSpaceOrPunctuation, isSvsFollowingCjk, isUnicodeWhitespace, tryGetCodeTwoBefore, tryGetGenuineNextCode, tryGetGenuinePreviousCode };

package/package.json

@@ -0,0 +1,57 @@
+{
+  "name": "micromark-extension-cjk-friendly-util",
+  "version": "1.0.0",
+  "type": "module",
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "default": "./dist/index.js"
+    }
+  },
+  "files": [
+    "dist",
+    "LICENSE",
+    "README.md"
+  ],
+  "repository": {
+    "url": "https://github.com/tats-u/markdown-cjk-friendly"
+  },
+  "license": "MIT",
+  "author": "Tatsunori Uchino <tats.u@live.jp> (https://github.com/tats-u)",
+  "bugs": "https://github.com/tats-u/markdown-cjk-friendly/issues",
+  "keywords": [
+    "micromark-extension",
+    "micromark",
+    "markdown",
+    "japanese",
+    "chinese",
+    "korean",
+    "cjk"
+  ],
+  "description": "common library for micromark-extension-cjk-friendly and its related packages",
+  "sideEffects": false,
+  "dependencies": {
+    "get-east-asian-width": "^1.3.0",
+    "micromark-util-character": "^2.0.0",
+    "micromark-util-symbol": "^2.0.0"
+  },
+  "devDependencies": {
+    "micromark-util-types": "^2.0.0"
+  },
+  "peerDependenciesMeta": {
+    "micromark-util-types": {
+      "optional": true
+    }
+  },
+  "engines": {
+    "node": ">=20"
+  },
+  "scripts": {
+    "build": "rslib build",
+    "dev": "rslib build --watch",
+    "test": "vitest --run",
+    "test:up": "vitest -u",
+    "test:watch": "vitest watch",
+    "lint:type": "tsc --noEmit"
+  }
+}