lzy-codec 0.1.0

package/.github/workflows/build.yml

@@ -0,0 +1,77 @@
+name: build
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '18'
+
+      - name: Install pnpm
+        run: npm install -g pnpm
+
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Compress JavaScript
+        run: |
+          pnpm run build
+
+      - name: Create Release
+        id: create_release
+        uses: actions/create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ${{ github.ref }}
+          release_name: Release ${{ github.ref }}
+          draft: false
+          prerelease: false
+
+      - name: Upload Release Asset
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }}
+          asset_path: ./dist/assets/main.js
+          asset_name: lzy-codec-${{ github.ref_name }}.min.js
+          asset_content_type: application/javascript
+
+  publish:
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '18'
+
+      - name: Install pnpm
+        run: npm install -g pnpm
+
+      - name: Install dependencies
+        run: pnpm install
+
+      - name: Login to npm
+        run: npm config set //registry.npmjs.org/:_authToken=${{ secrets.NPM_TOKEN }}
+
+      - name: Publish to npm
+        run: npm publish --access public

package/.prettierrc

@@ -0,0 +1,5 @@
+{
+  "tabWidth": 4,
+  "semi": false,
+  "singleQuote": true
+}

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2021 李宗英
+
+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 +1,59 @@
+# LZY Codec
+
+一種變長文本編解碼方案，支持對Unicode進行編解碼。編解碼效率、存儲空間全面優於UTF-8，未來會替代UTF-8成為新的世界通用編解碼標準。
+
+[lzy-codec-js](https://github.com/lizongying/lzy-codec-js)
+
+[npm](https://www.npmjs.com/package/lzy-codec-js)
+
+## Other languages
+
+[lzy-codec-go](https://github.com/lizongying/lzy-codec-go)
+[lzy-codec-py](https://github.com/lizongying/lzy-codec-py)
+
+## 引用
+
+### node
+
+install
+
+```
+npm i lzy-codec-js
+```
+
+package.json
+
+```json
+{
+  "type": "module",
+  "dependencies": {
+    "lzy-codec-js": "^0.1.0"
+  }
+}
+```
+
+example
+
+```
+import {
+    encodeFromString,
+    decodeToString,
+    encodeFromBytes,
+    decodeToBytes,
+} from 'lzy-codec-js'
+
+const testStr = 'Hello 世界！LZY编码测试😀' // 包含emoji（大于0xFFFF的字符）
+console.log(`原始字符串: ${testStr}`)
+
+// 编码流程
+const lzyBytes = encodeFromString(testStr)
+console.log(`LZY编码字节: `, lzyBytes)
+
+// 解码流程
+const decodedStr = decodeToString(lzyBytes)
+console.log(`解码后字符串: ${decodedStr}`)
+```
+
+## 讚賞
+
+![image](./screenshots/appreciate.png)

package/dist/assets/main.js

@@ -0,0 +1 @@
+var T=(n,o)=>()=>(o||n((o={exports:{}}).exports,o),o.exports);var a=T((c,l)=>{const s=new Error("invalid unicode");function R(n){return 0<=n&&n<55296||57343<n&&n<=1114111}function u(n){const o=[];for(const e of n)e<128?o.push(e&255):e<16384?(o.push(e>>7&255),o.push((128|e&127)&255)):(o.push(e>>14&255),o.push((128|e>>7&127)&255),o.push((128|e&127)&255));return new Uint8Array(o)}function x(n){const o=[];for(let e=0;e<n.length;e++){const r=n.charCodeAt(e);if(r>=55296&&r<=57343&&e+1<n.length){const d=n.charCodeAt(e+1),t=(r-55296<<10)+(d-56320)+65536;o.push(t),e++}else o.push(r)}return u(o)}function A(n){const e=new TextDecoder("utf-8").decode(n);return x(e)}function h(n){const o=n.length;if(o===0)throw s;let e=-1;for(let f=0;f<o;f++)if((n[f]&128)===0){e=f;break}if(e===-1||o-e===0)throw s;const d=[];let t=0;for(let f=e;f<o;f++){const i=n[f];if(i>>7===0){if(f>e){if(!R(t))throw s;d.push(t)}t=i}else{if(t>8703)throw s;t=t<<7|i&127}}if(!R(t))throw s;return d.push(t),d}function w(n){const o=h(n);let e="";for(const r of o)if(r<=65535)e+=String.fromCharCode(r);else{const d=r-65536,t=55296+(d>>10),f=56320+(d&1023);e+=String.fromCharCode(t,f)}return e}function S(n){const o=w(n);return new TextEncoder("utf-8").encode(o)}typeof l<"u"&&l.exports?(c.encode=u,c.encodeFromString=x,c.encodeFromBytes=A,c.decode=h,c.decodeToString=w,c.decodeToBytes=S):typeof window<"u"&&(window.encode=u,window.encodeFromString=x,window.encodeFromBytes=A,window.decode=h,window.decodeToString=w,window.decodeToBytes=S)});export default a();

package/eslint.config.js

@@ -0,0 +1,47 @@
+import js from "@eslint/js";
+import globals from "globals";
+import prettier from "eslint-config-prettier";
+import eslintPluginImport from "eslint-plugin-import";
+
+export default [
+    {
+        ignores: ["dist/**", "node_modules/**", "src/tests/**", "vite.config.js"],
+    },
+    {
+        files: ["src/**/*.{js}"],
+        ...js.configs.recommended,
+        languageOptions: {
+            ecmaVersion: 'latest',
+            sourceType: 'module',
+            globals: {
+                ...globals.browser,
+                ...globals.node,
+                ...globals.worker,
+            },
+        },
+        plugins: {
+            import: eslintPluginImport,
+        },
+        rules: {
+            'import/order': [
+                'error',
+                {
+                    groups: [
+                        ['builtin', 'external'],
+                        ['internal'],
+                        ['parent', 'sibling', 'index'],
+                    ],
+                    'newlines-between': 'always',
+                    alphabetize: {
+                        order: 'asc',
+                        caseInsensitive: true,
+                    },
+                },
+            ],
+            // 'no-console': 'warn',
+            // 'no-debugger': 'error',
+            // 'no-unused-vars': ['warn', {argsIgnorePattern: '^_'}],
+        },
+    },
+    prettier,
+];

package/package.json

@@ -0,0 +1,35 @@
+{
+  "name": "lzy-codec",
+  "version": "0.1.0",
+  "description": "一種變長文本編解碼方案，支持對Unicode進行編解碼。編解碼效率、存儲空間全面優於UTF-8，未來會替代UTF-8成為新的世界通用編解碼標準。",
+  "main": "dist/assets/main.js",
+  "type": "module",
+  "scripts": {
+    "test": "bun ./src/test.js",
+    "check": "npx eslint \"src/**/*.js\"",
+    "fix": "npx prettier \"src/**/*.js\" --write",
+    "build": "vite build",
+    "prepublishOnly": "pnpm run build"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/lizongying/lzy-codec-js.git"
+  },
+  "keywords": [
+    "lzy",
+    "lzy-codec",
+    "lzy codec"
+  ],
+  "author": "Li ZongYing",
+  "license": "MIT",
+  "bugs": {
+    "url": "https://github.com/lizongying/lzy-codec-js/issues"
+  },
+  "homepage": "https://github.com/lizongying/lzy-codec-js#readme",
+  "devDependencies": {
+    "terser": "^5.30.3"
+  },
+  "dependencies": {
+    "vite": "^7.3.0"
+  }
+}

package/src/main.js

@@ -0,0 +1,220 @@
+/*
+https://github.com/lizongying/lzy-codec-js
+*/
+
+// 定义常量
+const SURROGATE_MIN = 0xd800
+const SURROGATE_MAX = 0xdfff
+const UNICODE_MAX = 0x10ffff
+const ERROR_UNICODE = new Error('invalid unicode')
+
+/**
+ * 验证一个Unicode码点是否有效（排除代理区字符）
+ * @param {number} r - Unicode码点
+ * @returns {boolean} 有效性标识
+ */
+function validUnicode(r) {
+    return (
+        (0 <= r && r < SURROGATE_MIN) || (SURROGATE_MAX < r && r <= UNICODE_MAX)
+    )
+}
+
+/**
+ * 将Unicode码点数组（对应Go的rune切片）转换为LZY编码的Uint8Array
+ * @param {number[]} inputRunes - 整数数组，每个元素是有效的Unicode码点
+ * @returns {Uint8Array} LZY编码的字节序列
+ */
+function encode(inputRunes) {
+    // 先创建临时数组存储字节，最后转换为Uint8Array
+    const outputArr = []
+
+    for (const r of inputRunes) {
+        if (r < 0x80) {
+            // 单字节编码：0xxxxxxx
+            outputArr.push(r & 0xff)
+        } else if (r < 0x4000) {
+            // 双字节编码：高7位 + 0x80 | 低7位
+            outputArr.push((r >> 7) & 0xff)
+            outputArr.push((0x80 | (r & 0x7f)) & 0xff)
+        } else {
+            // 三字节编码：高7位 + 0x80|中间7位 + 0x80|低7位
+            outputArr.push((r >> 14) & 0xff)
+            outputArr.push((0x80 | ((r >> 7) & 0x7f)) & 0xff)
+            outputArr.push((0x80 | (r & 0x7f)) & 0xff)
+        }
+    }
+
+    // 转换为Uint8Array（JS中对应Go的[]byte和Python的bytes）
+    return new Uint8Array(outputArr)
+}
+
+/**
+ * 将UTF-16字符串（JS原生字符串）转换为LZY编码的Uint8Array
+ * @param {string} inputStr - JS原生字符串（UTF-16编码，自动兼容Unicode字符）
+ * @returns {Uint8Array} LZY编码的字节序列
+ */
+function encodeFromString(inputStr) {
+    // 将JS字符串转换为Unicode码点数组（对应Go的[]rune和Python的ord列表）
+    // 处理大于0xFFFF的字符（代理对），确保完整获取码点
+    const runes = []
+    for (let i = 0; i < inputStr.length; i++) {
+        const charCode = inputStr.charCodeAt(i)
+        // 检测代理对（高代理）
+        if (
+            charCode >= SURROGATE_MIN &&
+            charCode <= SURROGATE_MAX &&
+            i + 1 < inputStr.length
+        ) {
+            const lowCharCode = inputStr.charCodeAt(i + 1)
+            // 计算完整Unicode码点
+            const fullRune =
+                ((charCode - SURROGATE_MIN) << 10) +
+                (lowCharCode - 0xdc00) +
+                0x10000
+            runes.push(fullRune)
+            i++ // 跳过低代理
+        } else {
+            runes.push(charCode)
+        }
+    }
+    return encode(runes)
+}
+
+/**
+ * 将UTF-8字节序列（Uint8Array）转换为LZY编码的Uint8Array
+ * @param {Uint8Array} inputBytes - UTF-8编码的字节序列
+ * @returns {Uint8Array} LZY编码的字节序列
+ */
+function encodeFromBytes(inputBytes) {
+    // 先将UTF-8 Uint8Array解码为JS原生字符串
+    // 使用TextDecoder（浏览器/Node.js均支持）
+    const decoder = new TextDecoder('utf-8')
+    const inputStr = decoder.decode(inputBytes)
+    return encodeFromString(inputStr)
+}
+
+/**
+ * 将LZY编码的Uint8Array解码为Unicode码点数组
+ * @param {Uint8Array} inputBytes - LZY编码的字节序列
+ * @returns {number[]} Unicode码点数组
+ * @throws {Error} 无效LZY编码或Unicode码点时抛出错误
+ */
+function decode(inputBytes) {
+    const l = inputBytes.length
+    if (l === 0) {
+        throw ERROR_UNICODE
+    }
+
+    // 寻找第一个最高位为0的字节（有效起始位置）
+    let startIdx = -1
+    for (let i = 0; i < l; i++) {
+        if ((inputBytes[i] & 0x80) === 0) {
+            startIdx = i
+            break
+        }
+    }
+
+    if (startIdx === -1) {
+        throw ERROR_UNICODE
+    }
+
+    const validLen = l - startIdx
+    if (validLen === 0) {
+        throw ERROR_UNICODE
+    }
+
+    const output = []
+    // JS数组无需手动预分配，push自动扩容，此处保持逻辑对齐
+
+    let r = 0
+    for (let i = startIdx; i < l; i++) {
+        const b = inputBytes[i]
+        if (b >> 7 === 0) {
+            // 遇到单字节标记，处理上一个累积的码点（非起始位置）
+            if (i > startIdx) {
+                if (!validUnicode(r)) {
+                    throw ERROR_UNICODE
+                }
+                output.push(r)
+            }
+            // 重置为当前单字节值
+            r = b
+        } else {
+            // 累积码点：左移7位 + 低7位（排除0x80标记位）
+            if (r > UNICODE_MAX >> 7) {
+                throw ERROR_UNICODE
+            }
+            r = (r << 7) | (b & 0x7f)
+        }
+    }
+
+    // 处理最后一个累积的码点
+    if (!validUnicode(r)) {
+        throw ERROR_UNICODE
+    }
+    output.push(r)
+
+    return output
+}
+
+/**
+ * 将LZY编码的Uint8Array解码为JS原生字符串（UTF-16）
+ * @param {Uint8Array} inputBytes - LZY编码的字节序列
+ * @returns {string} JS原生字符串
+ * @throws {Error} 无效LZY编码或Unicode码点时抛出错误
+ */
+function decodeToString(inputBytes) {
+    const runes = decode(inputBytes)
+    // 将Unicode码点数组转换为JS字符串（处理代理对）
+    let outputStr = ''
+    for (const r of runes) {
+        if (r <= 0xffff) {
+            // 普通字符，直接转换
+            outputStr += String.fromCharCode(r)
+        } else {
+            // 大于0xFFFF的字符，需要转换为代理对
+            const offset = r - 0x10000
+            const highSurrogate = SURROGATE_MIN + (offset >> 10)
+            const lowSurrogate = 0xdc00 + (offset & 0x3ff)
+            outputStr += String.fromCharCode(highSurrogate, lowSurrogate)
+        }
+    }
+    return outputStr
+}
+
+/**
+ * 将LZY编码的Uint8Array解码为UTF-8字节序列（Uint8Array）
+ * @param {Uint8Array} inputBytes - LZY编码的字节序列
+ * @returns {Uint8Array} UTF-8编码的字节序列
+ * @throws {Error} 无效LZY编码或Unicode码点时抛出错误
+ */
+function decodeToBytes(inputBytes) {
+    const outputStr = decodeToString(inputBytes)
+    const encoder = new TextEncoder('utf-8')
+    return encoder.encode(outputStr)
+}
+
+if (typeof module !== 'undefined' && module.exports) {
+    exports.encode = encode
+    exports.encodeFromString = encodeFromString
+    exports.encodeFromBytes = encodeFromBytes
+    exports.decode = decode
+    exports.decodeToString = decodeToString
+    exports.decodeToBytes = decodeToBytes
+} else if (typeof window !== 'undefined') {
+    window.encode = encode
+    window.encodeFromString = encodeFromString
+    window.encodeFromBytes = encodeFromBytes
+    window.decode = decode
+    window.decodeToString = decodeToString
+    window.decodeToBytes = decodeToBytes
+}
+
+export {
+    encode,
+    encodeFromString,
+    encodeFromBytes,
+    decode,
+    decodeToString,
+    decodeToBytes,
+}

package/src/test.js

@@ -0,0 +1,54 @@
+import {
+    encodeFromString,
+    decodeToString,
+    encodeFromBytes,
+    decodeToBytes,
+} from './main.js'
+
+// 测试代码（可选，验证功能正确性）
+if (typeof window !== 'undefined' || typeof process !== 'undefined') {
+    // 浏览器/Node.js环境均可运行测试
+    ;(function testLZY() {
+        const testStr = 'Hello 世界！LZY编码测试😀' // 包含emoji（大于0xFFFF的字符）
+        console.log(`原始字符串: ${testStr}`)
+
+        // 编码流程
+        const lzyBytes = encodeFromString(testStr)
+        console.log(`LZY编码字节: `, lzyBytes)
+
+        // 解码流程
+        const decodedStr = decodeToString(lzyBytes)
+        console.log(`解码后字符串: ${decodedStr}`)
+
+        // 验证一致性
+        if (testStr === decodedStr) {
+            console.log('✅ 编码解码一致性验证通过')
+        } else {
+            console.error('❌ 编码解码一致性验证失败')
+        }
+
+        // 测试字节流编码解码
+        const utf8Bytes = new TextEncoder().encode(testStr)
+        const lzyBytes2 = encodeFromBytes(utf8Bytes)
+        const decodedUtf8Bytes = decodeToBytes(lzyBytes2)
+
+        // 比较Uint8Array是否相等
+        let isEqual = true
+        if (utf8Bytes.length !== decodedUtf8Bytes.length) {
+            isEqual = false
+        } else {
+            for (let i = 0; i < utf8Bytes.length; i++) {
+                if (utf8Bytes[i] !== decodedUtf8Bytes[i]) {
+                    isEqual = false
+                    break
+                }
+            }
+        }
+
+        if (isEqual) {
+            console.log('✅ 字节流编码解码一致性验证通过')
+        } else {
+            console.error('❌ 字节流编码解码一致性验证失败')
+        }
+    })()
+}

package/vite.config.js

@@ -0,0 +1,20 @@
+import {resolve} from 'path'
+import {defineConfig} from 'vite'
+
+export default defineConfig({
+    build: {
+        rollupOptions: {
+            input: {
+                main: resolve(__dirname, './src/main.js'),
+            },
+            output: {
+                entryFileNames: (chunkInfo) => {
+                    return chunkInfo.name === 'main'
+                        ? 'assets/main.js'
+                        : 'assets/[name]-[hash].js'
+                },
+            },
+        },
+        outDir: 'dist',
+    },
+})