pax_global_header00006660000000000000000000000064145177726610014532gustar00rootroot0000000000000052 comment=9e1b2cda98d215d3a73fcbfe93c62e021f4ba768 punycode.js-2.3.1/000077500000000000000000000000001451777266100137765ustar00rootroot00000000000000punycode.js-2.3.1/.editorconfig000066400000000000000000000003161451777266100164530ustar00rootroot00000000000000root = true [*] charset = utf-8 indent_style = tab end_of_line = lf insert_final_newline = true trim_trailing_whitespace = true [{README.md,package.json,.travis.yml}] indent_style = space indent_size = 2 punycode.js-2.3.1/.gitattributes000066400000000000000000000000141451777266100166640ustar00rootroot00000000000000* text=auto punycode.js-2.3.1/.github/000077500000000000000000000000001451777266100153365ustar00rootroot00000000000000punycode.js-2.3.1/.github/workflows/000077500000000000000000000000001451777266100173735ustar00rootroot00000000000000punycode.js-2.3.1/.github/workflows/main.yml000066400000000000000000000007341451777266100210460ustar00rootroot00000000000000name: run-checks on: push: branches: - main pull_request: branches: - main jobs: build: runs-on: ubuntu-latest steps: - name: Checkout uses: actions/checkout@v4 - name: Set up Node.js uses: actions/setup-node@v4 with: node-version-file: '.nvmrc' - name: Install dependencies run: npm install - name: Build run: npm run build - name: Test run: npm test punycode.js-2.3.1/.github/workflows/publish-on-tag.yml000066400000000000000000000021541451777266100227510ustar00rootroot00000000000000name: publish-on-tag on: push: tags: - '*' jobs: publish: runs-on: ubuntu-latest steps: - name: Checkout uses: actions/checkout@v4 - name: Set up Node.js uses: actions/setup-node@v4 with: node-version-file: '.nvmrc' - name: Install dependencies run: npm install - name: Build run: npm run build - name: Test run: npm test - name: Publish punycode package env: NPM_TOKEN: ${{secrets.NPM_TOKEN_PUNYCODE}} run: | npm config set registry 'https://wombat-dressing-room.appspot.com/' npm config set '//wombat-dressing-room.appspot.com/:_authToken' '${NPM_TOKEN}' npm publish - name: Publish punycode.js package env: NPM_TOKEN: ${{secrets.NPM_TOKEN_PUNYCODE_JS}} run: | sed -i 's/"name": "punycode"/"name": "punycode.js"/' package.json npm config set registry 'https://wombat-dressing-room.appspot.com/' npm config set '//wombat-dressing-room.appspot.com/:_authToken' '${NPM_TOKEN}' npm publish punycode.js-2.3.1/.gitignore000066400000000000000000000004121451777266100157630ustar00rootroot00000000000000# Generated files punycode.es6.js # Coverage report coverage # Installed npm modules node_modules # Folder view configuration files .DS_Store Desktop.ini # Thumbnail cache files ._* Thumbs.db # Files that might appear on external disks .Spotlight-V100 .Trashes punycode.js-2.3.1/.nvmrc000066400000000000000000000000031451777266100151150ustar00rootroot0000000000000020 punycode.js-2.3.1/LICENSE-MIT.txt000066400000000000000000000020651451777266100162530ustar00rootroot00000000000000Copyright Mathias Bynens 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. punycode.js-2.3.1/README.md000066400000000000000000000131271451777266100152610ustar00rootroot00000000000000# Punycode.js [![punycode on npm](https://img.shields.io/npm/v/punycode)](https://www.npmjs.com/package/punycode) [![](https://data.jsdelivr.com/v1/package/npm/punycode/badge)](https://www.jsdelivr.com/package/npm/punycode) Punycode.js is a robust Punycode converter that fully complies to [RFC 3492](https://tools.ietf.org/html/rfc3492) and [RFC 5891](https://tools.ietf.org/html/rfc5891). This JavaScript library is the result of comparing, optimizing and documenting different open-source implementations of the Punycode algorithm: * [The C example code from RFC 3492](https://tools.ietf.org/html/rfc3492#appendix-C) * [`punycode.c` by _Markus W. Scherer_ (IBM)](http://opensource.apple.com/source/ICU/ICU-400.42/icuSources/common/punycode.c) * [`punycode.c` by _Ben Noordhuis_](https://github.com/bnoordhuis/punycode/blob/master/punycode.c) * [JavaScript implementation by _some_](http://stackoverflow.com/questions/183485/can-anyone-recommend-a-good-free-javascript-for-punycode-to-unicode-conversion/301287#301287) * [`punycode.js` by _Ben Noordhuis_](https://github.com/joyent/node/blob/426298c8c1c0d5b5224ac3658c41e7c2a3fe9377/lib/punycode.js) (note: [not fully compliant](https://github.com/joyent/node/issues/2072)) This project was [bundled](https://github.com/joyent/node/blob/master/lib/punycode.js) with Node.js from [v0.6.2+](https://github.com/joyent/node/compare/975f1930b1...61e796decc) until [v7](https://github.com/nodejs/node/pull/7941) (soft-deprecated). This project provides a CommonJS module that uses ES2015+ features and JavaScript module, which work in modern Node.js versions and browsers. For the old Punycode.js version that offers the same functionality in a UMD build with support for older pre-ES2015 runtimes, including Rhino, Ringo, and Narwhal, see [v1.4.1](https://github.com/mathiasbynens/punycode.js/releases/tag/v1.4.1). ## Installation Via [npm](https://www.npmjs.com/): ```bash npm install punycode --save ``` In [Node.js](https://nodejs.org/): > ⚠️ Note that userland modules don't hide core modules. > For example, `require('punycode')` still imports the deprecated core module even if you executed `npm install punycode`. > Use `require('punycode/')` to import userland modules rather than core modules. ```js const punycode = require('punycode/'); ``` ## API ### `punycode.decode(string)` Converts a Punycode string of ASCII symbols to a string of Unicode symbols. ```js // decode domain name parts punycode.decode('maana-pta'); // 'mañana' punycode.decode('--dqo34k'); // '☃-⌘' ``` ### `punycode.encode(string)` Converts a string of Unicode symbols to a Punycode string of ASCII symbols. ```js // encode domain name parts punycode.encode('mañana'); // 'maana-pta' punycode.encode('☃-⌘'); // '--dqo34k' ``` ### `punycode.toUnicode(input)` Converts a Punycode string representing a domain name or an email address to Unicode. Only the Punycoded parts of the input will be converted, i.e. it doesn’t matter if you call it on a string that has already been converted to Unicode. ```js // decode domain names punycode.toUnicode('xn--maana-pta.com'); // → 'mañana.com' punycode.toUnicode('xn----dqo34k.com'); // → '☃-⌘.com' // decode email addresses punycode.toUnicode('джумла@xn--p-8sbkgc5ag7bhce.xn--ba-lmcq'); // → 'джумла@джpумлатест.bрфa' ``` ### `punycode.toASCII(input)` Converts a lowercased Unicode string representing a domain name or an email address to Punycode. Only the non-ASCII parts of the input will be converted, i.e. it doesn’t matter if you call it with a domain that’s already in ASCII. ```js // encode domain names punycode.toASCII('mañana.com'); // → 'xn--maana-pta.com' punycode.toASCII('☃-⌘.com'); // → 'xn----dqo34k.com' // encode email addresses punycode.toASCII('джумла@джpумлатест.bрфa'); // → 'джумла@xn--p-8sbkgc5ag7bhce.xn--ba-lmcq' ``` ### `punycode.ucs2` #### `punycode.ucs2.decode(string)` Creates an array containing the numeric code point values of each Unicode symbol in the string. While [JavaScript uses UCS-2 internally](https://mathiasbynens.be/notes/javascript-encoding), this function will convert a pair of surrogate halves (each of which UCS-2 exposes as separate characters) into a single code point, matching UTF-16. ```js punycode.ucs2.decode('abc'); // → [0x61, 0x62, 0x63] // surrogate pair for U+1D306 TETRAGRAM FOR CENTRE: punycode.ucs2.decode('\uD834\uDF06'); // → [0x1D306] ``` #### `punycode.ucs2.encode(codePoints)` Creates a string based on an array of numeric code point values. ```js punycode.ucs2.encode([0x61, 0x62, 0x63]); // → 'abc' punycode.ucs2.encode([0x1D306]); // → '\uD834\uDF06' ``` ### `punycode.version` A string representing the current Punycode.js version number. ## For maintainers ### How to publish a new release 1. On the `main` branch, bump the version number in `package.json`: ```sh npm version patch -m 'Release v%s' ``` Instead of `patch`, use `minor` or `major` [as needed](https://semver.org/). Note that this produces a Git commit + tag. 1. Push the release commit and tag: ```sh git push && git push --tags ``` Our CI then automatically publishes the new release to npm, under both the [`punycode`](https://www.npmjs.com/package/punycode) and [`punycode.js`](https://www.npmjs.com/package/punycode.js) names. ## Author | [![twitter/mathias](https://gravatar.com/avatar/24e08a9ea84deb17ae121074d0f17125?s=70)](https://twitter.com/mathias "Follow @mathias on Twitter") | |---| | [Mathias Bynens](https://mathiasbynens.be/) | ## License Punycode.js is available under the [MIT](https://mths.be/mit) license. punycode.js-2.3.1/package.json000066400000000000000000000023131451777266100162630ustar00rootroot00000000000000{ "name": "punycode", "version": "2.3.1", "description": "A robust Punycode converter that fully complies to RFC 3492 and RFC 5891, and works on nearly all JavaScript platforms.", "homepage": "https://mths.be/punycode", "main": "punycode.js", "jsnext:main": "punycode.es6.js", "module": "punycode.es6.js", "engines": { "node": ">=6" }, "keywords": [ "punycode", "unicode", "idn", "idna", "dns", "url", "domain" ], "license": "MIT", "author": { "name": "Mathias Bynens", "url": "https://mathiasbynens.be/" }, "contributors": [ { "name": "Mathias Bynens", "url": "https://mathiasbynens.be/" } ], "repository": { "type": "git", "url": "https://github.com/mathiasbynens/punycode.js.git" }, "bugs": "https://github.com/mathiasbynens/punycode.js/issues", "files": [ "LICENSE-MIT.txt", "punycode.js", "punycode.es6.js" ], "scripts": { "test": "mocha tests", "build": "node scripts/prepublish.js" }, "devDependencies": { "codecov": "^3.8.3", "nyc": "^15.1.0", "mocha": "^10.2.0" }, "jspm": { "map": { "./punycode.js": { "node": "@node/punycode" } } } } punycode.js-2.3.1/punycode.js000066400000000000000000000306471451777266100161740ustar00rootroot00000000000000'use strict'; /** Highest positive signed 32-bit float value */ const maxInt = 2147483647; // aka. 0x7FFFFFFF or 2^31-1 /** Bootstring parameters */ const base = 36; const tMin = 1; const tMax = 26; const skew = 38; const damp = 700; const initialBias = 72; const initialN = 128; // 0x80 const delimiter = '-'; // '\x2D' /** Regular expressions */ const regexPunycode = /^xn--/; const regexNonASCII = /[^\0-\x7F]/; // Note: U+007F DEL is excluded too. const regexSeparators = /[\x2E\u3002\uFF0E\uFF61]/g; // RFC 3490 separators /** Error messages */ const errors = { 'overflow': 'Overflow: input needs wider integers to process', 'not-basic': 'Illegal input >= 0x80 (not a basic code point)', 'invalid-input': 'Invalid input' }; /** Convenience shortcuts */ const baseMinusTMin = base - tMin; const floor = Math.floor; const stringFromCharCode = String.fromCharCode; /*--------------------------------------------------------------------------*/ /** * A generic error utility function. * @private * @param {String} type The error type. * @returns {Error} Throws a `RangeError` with the applicable error message. */ function error(type) { throw new RangeError(errors[type]); } /** * A generic `Array#map` utility function. * @private * @param {Array} array The array to iterate over. * @param {Function} callback The function that gets called for every array * item. * @returns {Array} A new array of values returned by the callback function. */ function map(array, callback) { const result = []; let length = array.length; while (length--) { result[length] = callback(array[length]); } return result; } /** * A simple `Array#map`-like wrapper to work with domain name strings or email * addresses. * @private * @param {String} domain The domain name or email address. * @param {Function} callback The function that gets called for every * character. * @returns {String} A new string of characters returned by the callback * function. */ function mapDomain(domain, callback) { const parts = domain.split('@'); let result = ''; if (parts.length > 1) { // In email addresses, only the domain name should be punycoded. Leave // the local part (i.e. everything up to `@`) intact. result = parts[0] + '@'; domain = parts[1]; } // Avoid `split(regex)` for IE8 compatibility. See #17. domain = domain.replace(regexSeparators, '\x2E'); const labels = domain.split('.'); const encoded = map(labels, callback).join('.'); return result + encoded; } /** * Creates an array containing the numeric code points of each Unicode * character in the string. While JavaScript uses UCS-2 internally, * this function will convert a pair of surrogate halves (each of which * UCS-2 exposes as separate characters) into a single code point, * matching UTF-16. * @see `punycode.ucs2.encode` * @see * @memberOf punycode.ucs2 * @name decode * @param {String} string The Unicode input string (UCS-2). * @returns {Array} The new array of code points. */ function ucs2decode(string) { const output = []; let counter = 0; const length = string.length; while (counter < length) { const value = string.charCodeAt(counter++); if (value >= 0xD800 && value <= 0xDBFF && counter < length) { // It's a high surrogate, and there is a next character. const extra = string.charCodeAt(counter++); if ((extra & 0xFC00) == 0xDC00) { // Low surrogate. output.push(((value & 0x3FF) << 10) + (extra & 0x3FF) + 0x10000); } else { // It's an unmatched surrogate; only append this code unit, in case the // next code unit is the high surrogate of a surrogate pair. output.push(value); counter--; } } else { output.push(value); } } return output; } /** * Creates a string based on an array of numeric code points. * @see `punycode.ucs2.decode` * @memberOf punycode.ucs2 * @name encode * @param {Array} codePoints The array of numeric code points. * @returns {String} The new Unicode string (UCS-2). */ const ucs2encode = codePoints => String.fromCodePoint(...codePoints); /** * Converts a basic code point into a digit/integer. * @see `digitToBasic()` * @private * @param {Number} codePoint The basic numeric code point value. * @returns {Number} The numeric value of a basic code point (for use in * representing integers) in the range `0` to `base - 1`, or `base` if * the code point does not represent a value. */ const basicToDigit = function(codePoint) { if (codePoint >= 0x30 && codePoint < 0x3A) { return 26 + (codePoint - 0x30); } if (codePoint >= 0x41 && codePoint < 0x5B) { return codePoint - 0x41; } if (codePoint >= 0x61 && codePoint < 0x7B) { return codePoint - 0x61; } return base; }; /** * Converts a digit/integer into a basic code point. * @see `basicToDigit()` * @private * @param {Number} digit The numeric value of a basic code point. * @returns {Number} The basic code point whose value (when used for * representing integers) is `digit`, which needs to be in the range * `0` to `base - 1`. If `flag` is non-zero, the uppercase form is * used; else, the lowercase form is used. The behavior is undefined * if `flag` is non-zero and `digit` has no uppercase form. */ const digitToBasic = function(digit, flag) { // 0..25 map to ASCII a..z or A..Z // 26..35 map to ASCII 0..9 return digit + 22 + 75 * (digit < 26) - ((flag != 0) << 5); }; /** * Bias adaptation function as per section 3.4 of RFC 3492. * https://tools.ietf.org/html/rfc3492#section-3.4 * @private */ const adapt = function(delta, numPoints, firstTime) { let k = 0; delta = firstTime ? floor(delta / damp) : delta >> 1; delta += floor(delta / numPoints); for (/* no initialization */; delta > baseMinusTMin * tMax >> 1; k += base) { delta = floor(delta / baseMinusTMin); } return floor(k + (baseMinusTMin + 1) * delta / (delta + skew)); }; /** * Converts a Punycode string of ASCII-only symbols to a string of Unicode * symbols. * @memberOf punycode * @param {String} input The Punycode string of ASCII-only symbols. * @returns {String} The resulting string of Unicode symbols. */ const decode = function(input) { // Don't use UCS-2. const output = []; const inputLength = input.length; let i = 0; let n = initialN; let bias = initialBias; // Handle the basic code points: let `basic` be the number of input code // points before the last delimiter, or `0` if there is none, then copy // the first basic code points to the output. let basic = input.lastIndexOf(delimiter); if (basic < 0) { basic = 0; } for (let j = 0; j < basic; ++j) { // if it's not a basic code point if (input.charCodeAt(j) >= 0x80) { error('not-basic'); } output.push(input.charCodeAt(j)); } // Main decoding loop: start just after the last delimiter if any basic code // points were copied; start at the beginning otherwise. for (let index = basic > 0 ? basic + 1 : 0; index < inputLength; /* no final expression */) { // `index` is the index of the next character to be consumed. // Decode a generalized variable-length integer into `delta`, // which gets added to `i`. The overflow checking is easier // if we increase `i` as we go, then subtract off its starting // value at the end to obtain `delta`. const oldi = i; for (let w = 1, k = base; /* no condition */; k += base) { if (index >= inputLength) { error('invalid-input'); } const digit = basicToDigit(input.charCodeAt(index++)); if (digit >= base) { error('invalid-input'); } if (digit > floor((maxInt - i) / w)) { error('overflow'); } i += digit * w; const t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias); if (digit < t) { break; } const baseMinusT = base - t; if (w > floor(maxInt / baseMinusT)) { error('overflow'); } w *= baseMinusT; } const out = output.length + 1; bias = adapt(i - oldi, out, oldi == 0); // `i` was supposed to wrap around from `out` to `0`, // incrementing `n` each time, so we'll fix that now: if (floor(i / out) > maxInt - n) { error('overflow'); } n += floor(i / out); i %= out; // Insert `n` at position `i` of the output. output.splice(i++, 0, n); } return String.fromCodePoint(...output); }; /** * Converts a string of Unicode symbols (e.g. a domain name label) to a * Punycode string of ASCII-only symbols. * @memberOf punycode * @param {String} input The string of Unicode symbols. * @returns {String} The resulting Punycode string of ASCII-only symbols. */ const encode = function(input) { const output = []; // Convert the input in UCS-2 to an array of Unicode code points. input = ucs2decode(input); // Cache the length. const inputLength = input.length; // Initialize the state. let n = initialN; let delta = 0; let bias = initialBias; // Handle the basic code points. for (const currentValue of input) { if (currentValue < 0x80) { output.push(stringFromCharCode(currentValue)); } } const basicLength = output.length; let handledCPCount = basicLength; // `handledCPCount` is the number of code points that have been handled; // `basicLength` is the number of basic code points. // Finish the basic string with a delimiter unless it's empty. if (basicLength) { output.push(delimiter); } // Main encoding loop: while (handledCPCount < inputLength) { // All non-basic code points < n have been handled already. Find the next // larger one: let m = maxInt; for (const currentValue of input) { if (currentValue >= n && currentValue < m) { m = currentValue; } } // Increase `delta` enough to advance the decoder's state to , // but guard against overflow. const handledCPCountPlusOne = handledCPCount + 1; if (m - n > floor((maxInt - delta) / handledCPCountPlusOne)) { error('overflow'); } delta += (m - n) * handledCPCountPlusOne; n = m; for (const currentValue of input) { if (currentValue < n && ++delta > maxInt) { error('overflow'); } if (currentValue === n) { // Represent delta as a generalized variable-length integer. let q = delta; for (let k = base; /* no condition */; k += base) { const t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias); if (q < t) { break; } const qMinusT = q - t; const baseMinusT = base - t; output.push( stringFromCharCode(digitToBasic(t + qMinusT % baseMinusT, 0)) ); q = floor(qMinusT / baseMinusT); } output.push(stringFromCharCode(digitToBasic(q, 0))); bias = adapt(delta, handledCPCountPlusOne, handledCPCount === basicLength); delta = 0; ++handledCPCount; } } ++delta; ++n; } return output.join(''); }; /** * Converts a Punycode string representing a domain name or an email address * to Unicode. Only the Punycoded parts of the input will be converted, i.e. * it doesn't matter if you call it on a string that has already been * converted to Unicode. * @memberOf punycode * @param {String} input The Punycoded domain name or email address to * convert to Unicode. * @returns {String} The Unicode representation of the given Punycode * string. */ const toUnicode = function(input) { return mapDomain(input, function(string) { return regexPunycode.test(string) ? decode(string.slice(4).toLowerCase()) : string; }); }; /** * Converts a Unicode string representing a domain name or an email address to * Punycode. Only the non-ASCII parts of the domain name will be converted, * i.e. it doesn't matter if you call it with a domain that's already in * ASCII. * @memberOf punycode * @param {String} input The domain name or email address to convert, as a * Unicode string. * @returns {String} The Punycode representation of the given domain name or * email address. */ const toASCII = function(input) { return mapDomain(input, function(string) { return regexNonASCII.test(string) ? 'xn--' + encode(string) : string; }); }; /*--------------------------------------------------------------------------*/ /** Define the public API */ const punycode = { /** * A string representing the current Punycode.js version number. * @memberOf punycode * @type String */ 'version': '2.3.1', /** * An object of methods to convert from JavaScript's internal character * representation (UCS-2) to Unicode code points, and back. * @see * @memberOf punycode * @type Object */ 'ucs2': { 'decode': ucs2decode, 'encode': ucs2encode }, 'decode': decode, 'encode': encode, 'toASCII': toASCII, 'toUnicode': toUnicode }; module.exports = punycode; punycode.js-2.3.1/scripts/000077500000000000000000000000001451777266100154655ustar00rootroot00000000000000punycode.js-2.3.1/scripts/prepublish.js000066400000000000000000000011321451777266100201750ustar00rootroot00000000000000'use strict'; const fs = require('fs'); const path = require('path'); const regex = /module\.exports = punycode;/; const output = 'export { ucs2decode, ucs2encode, decode, encode, toASCII, toUnicode };\nexport default punycode;'; const sourceContents = fs.readFileSync(path.resolve(__dirname, '../punycode.js'), 'utf-8'); if (!regex.test(sourceContents)) { throw new Error('The underlying library has changed. Please update the prepublish script.'); } const outputContents = sourceContents.replace(regex, output); fs.writeFileSync(path.resolve(__dirname, '../punycode.es6.js'), outputContents); punycode.js-2.3.1/tests/000077500000000000000000000000001451777266100151405ustar00rootroot00000000000000punycode.js-2.3.1/tests/tests.js000066400000000000000000000250561451777266100166500ustar00rootroot00000000000000'use strict'; const assert = require('assert'); const punycode = require('../punycode.js'); const testData = { 'strings': [ { 'description': 'a single basic code point', 'decoded': 'Bach', 'encoded': 'Bach-' }, { 'description': 'a single non-ASCII character', 'decoded': '\xFC', 'encoded': 'tda' }, { 'description': 'multiple non-ASCII characters', 'decoded': '\xFC\xEB\xE4\xF6\u2665', 'encoded': '4can8av2009b' }, { 'description': 'mix of ASCII and non-ASCII characters', 'decoded': 'b\xFCcher', 'encoded': 'bcher-kva' }, { 'description': 'long string with both ASCII and non-ASCII characters', 'decoded': 'Willst du die Bl\xFCthe des fr\xFChen, die Fr\xFCchte des sp\xE4teren Jahres', 'encoded': 'Willst du die Blthe des frhen, die Frchte des spteren Jahres-x9e96lkal' }, // https://tools.ietf.org/html/rfc3492#section-7.1 { 'description': 'Arabic (Egyptian)', 'decoded': '\u0644\u064A\u0647\u0645\u0627\u0628\u062A\u0643\u0644\u0645\u0648\u0634\u0639\u0631\u0628\u064A\u061F', 'encoded': 'egbpdaj6bu4bxfgehfvwxn' }, { 'description': 'Chinese (simplified)', 'decoded': '\u4ED6\u4EEC\u4E3A\u4EC0\u4E48\u4E0D\u8BF4\u4E2d\u6587', 'encoded': 'ihqwcrb4cv8a8dqg056pqjye' }, { 'description': 'Chinese (traditional)', 'decoded': '\u4ED6\u5011\u7232\u4EC0\u9EBD\u4E0D\u8AAA\u4E2D\u6587', 'encoded': 'ihqwctvzc91f659drss3x8bo0yb' }, { 'description': 'Czech', 'decoded': 'Pro\u010Dprost\u011Bnemluv\xED\u010Desky', 'encoded': 'Proprostnemluvesky-uyb24dma41a' }, { 'description': 'Hebrew', 'decoded': '\u05DC\u05DE\u05D4\u05D4\u05DD\u05E4\u05E9\u05D5\u05D8\u05DC\u05D0\u05DE\u05D3\u05D1\u05E8\u05D9\u05DD\u05E2\u05D1\u05E8\u05D9\u05EA', 'encoded': '4dbcagdahymbxekheh6e0a7fei0b' }, { 'description': 'Hindi (Devanagari)', 'decoded': '\u092F\u0939\u0932\u094B\u0917\u0939\u093F\u0928\u094D\u0926\u0940\u0915\u094D\u092F\u094B\u0902\u0928\u0939\u0940\u0902\u092C\u094B\u0932\u0938\u0915\u0924\u0947\u0939\u0948\u0902', 'encoded': 'i1baa7eci9glrd9b2ae1bj0hfcgg6iyaf8o0a1dig0cd' }, { 'description': 'Japanese (kanji and hiragana)', 'decoded': '\u306A\u305C\u307F\u3093\u306A\u65E5\u672C\u8A9E\u3092\u8A71\u3057\u3066\u304F\u308C\u306A\u3044\u306E\u304B', 'encoded': 'n8jok5ay5dzabd5bym9f0cm5685rrjetr6pdxa' }, { 'description': 'Korean (Hangul syllables)', 'decoded': '\uC138\uACC4\uC758\uBAA8\uB4E0\uC0AC\uB78C\uB4E4\uC774\uD55C\uAD6D\uC5B4\uB97C\uC774\uD574\uD55C\uB2E4\uBA74\uC5BC\uB9C8\uB098\uC88B\uC744\uAE4C', 'encoded': '989aomsvi5e83db1d2a355cv1e0vak1dwrv93d5xbh15a0dt30a5jpsd879ccm6fea98c' }, /** * As there's no way to do it in JavaScript, Punycode.js doesn't support * mixed-case annotation (which is entirely optional as per the RFC). * So, while the RFC sample string encodes to: * `b1abfaaepdrnnbgefbaDotcwatmq2g4l` * Without mixed-case annotation it has to encode to: * `b1abfaaepdrnnbgefbadotcwatmq2g4l` * https://github.com/mathiasbynens/punycode.js/issues/3 */ { 'description': 'Russian (Cyrillic)', 'decoded': '\u043F\u043E\u0447\u0435\u043C\u0443\u0436\u0435\u043E\u043D\u0438\u043D\u0435\u0433\u043E\u0432\u043E\u0440\u044F\u0442\u043F\u043E\u0440\u0443\u0441\u0441\u043A\u0438', 'encoded': 'b1abfaaepdrnnbgefbadotcwatmq2g4l' }, { 'description': 'Spanish', 'decoded': 'Porqu\xE9nopuedensimplementehablarenEspa\xF1ol', 'encoded': 'PorqunopuedensimplementehablarenEspaol-fmd56a' }, { 'description': 'Vietnamese', 'decoded': 'T\u1EA1isaoh\u1ECDkh\xF4ngth\u1EC3ch\u1EC9n\xF3iti\u1EBFngVi\u1EC7t', 'encoded': 'TisaohkhngthchnitingVit-kjcr8268qyxafd2f1b9g' }, { 'decoded': '3\u5E74B\u7D44\u91D1\u516B\u5148\u751F', 'encoded': '3B-ww4c5e180e575a65lsy2b' }, { 'decoded': '\u5B89\u5BA4\u5948\u7F8E\u6075-with-SUPER-MONKEYS', 'encoded': '-with-SUPER-MONKEYS-pc58ag80a8qai00g7n9n' }, { 'decoded': 'Hello-Another-Way-\u305D\u308C\u305E\u308C\u306E\u5834\u6240', 'encoded': 'Hello-Another-Way--fc4qua05auwb3674vfr0b' }, { 'decoded': '\u3072\u3068\u3064\u5C4B\u6839\u306E\u4E0B2', 'encoded': '2-u9tlzr9756bt3uc0v' }, { 'decoded': 'Maji\u3067Koi\u3059\u308B5\u79D2\u524D', 'encoded': 'MajiKoi5-783gue6qz075azm5e' }, { 'decoded': '\u30D1\u30D5\u30A3\u30FCde\u30EB\u30F3\u30D0', 'encoded': 'de-jg4avhby1noc0d' }, { 'decoded': '\u305D\u306E\u30B9\u30D4\u30FC\u30C9\u3067', 'encoded': 'd9juau41awczczp' }, /** * This example is an ASCII string that breaks the existing rules for host * name labels. (It's not a realistic example for IDNA, because IDNA never * encodes pure ASCII labels.) */ { 'description': 'ASCII string that breaks the existing rules for host-name labels', 'decoded': '-> $1.00 <-', 'encoded': '-> $1.00 <--' } ], 'ucs2': [ // Every Unicode symbol is tested separately. These are just the extra // tests for symbol combinations: { 'description': 'Consecutive astral symbols', 'decoded': [127829, 119808, 119558, 119638], 'encoded': '\uD83C\uDF55\uD835\uDC00\uD834\uDF06\uD834\uDF56' }, { 'description': 'U+D800 (high surrogate) followed by non-surrogates', 'decoded': [55296, 97, 98], 'encoded': '\uD800ab' }, { 'description': 'U+DC00 (low surrogate) followed by non-surrogates', 'decoded': [56320, 97, 98], 'encoded': '\uDC00ab' }, { 'description': 'High surrogate followed by another high surrogate', 'decoded': [0xD800, 0xD800], 'encoded': '\uD800\uD800' }, { 'description': 'Unmatched high surrogate, followed by a surrogate pair, followed by an unmatched high surrogate', 'decoded': [0xD800, 0x1D306, 0xD800], 'encoded': '\uD800\uD834\uDF06\uD800' }, { 'description': 'Low surrogate followed by another low surrogate', 'decoded': [0xDC00, 0xDC00], 'encoded': '\uDC00\uDC00' }, { 'description': 'Unmatched low surrogate, followed by a surrogate pair, followed by an unmatched low surrogate', 'decoded': [0xDC00, 0x1D306, 0xDC00], 'encoded': '\uDC00\uD834\uDF06\uDC00' } ], 'domains': [ { 'decoded': 'ma\xF1ana.com', 'encoded': 'xn--maana-pta.com' }, { // https://github.com/mathiasbynens/punycode.js/issues/17 'decoded': 'example.com.', 'encoded': 'example.com.' }, { 'decoded': 'b\xFCcher.com', 'encoded': 'xn--bcher-kva.com' }, { 'decoded': 'caf\xE9.com', 'encoded': 'xn--caf-dma.com' }, { 'decoded': '\u2603-\u2318.com', 'encoded': 'xn----dqo34k.com' }, { 'decoded': '\uD400\u2603-\u2318.com', 'encoded': 'xn----dqo34kn65z.com' }, { 'description': 'Emoji', 'decoded': '\uD83D\uDCA9.la', 'encoded': 'xn--ls8h.la' }, { 'description': 'Non-printable ASCII', 'decoded': '\0\x01\x02foo.bar', 'encoded': '\0\x01\x02foo.bar' }, { 'description': 'Email address', 'decoded': '\u0434\u0436\u0443\u043C\u043B\u0430@\u0434\u0436p\u0443\u043C\u043B\u0430\u0442\u0435\u0441\u0442.b\u0440\u0444a', 'encoded': '\u0434\u0436\u0443\u043C\u043B\u0430@xn--p-8sbkgc5ag7bhce.xn--ba-lmcq' }, { // https://github.com/mathiasbynens/punycode.js/pull/115 'decoded': 'foo\x7F.example', 'encoded': 'foo\x7F.example' } ], 'separators': [ { 'description': 'Using U+002E as separator', 'decoded': 'ma\xF1ana\x2Ecom', 'encoded': 'xn--maana-pta.com' }, { 'description': 'Using U+3002 as separator', 'decoded': 'ma\xF1ana\u3002com', 'encoded': 'xn--maana-pta.com' }, { 'description': 'Using U+FF0E as separator', 'decoded': 'ma\xF1ana\uFF0Ecom', 'encoded': 'xn--maana-pta.com' }, { 'description': 'Using U+FF61 as separator', 'decoded': 'ma\xF1ana\uFF61com', 'encoded': 'xn--maana-pta.com' } ] }; describe('punycode.ucs2.decode', function() { for (const object of testData.ucs2) { it(object.description, function() { assert.deepEqual( punycode.ucs2.decode(object.encoded), object.decoded, object.description ); }); } it('throws RangeError: Illegal input >= 0x80 (not a basic code point)', function() { assert.throws( function() { punycode.decode('\x81-'); }, RangeError ); }); it('throws RangeError: Overflow: input needs wider integers to process', function() { assert.throws( function() { punycode.decode('\x81'); }, RangeError ); }); }); describe('punycode.ucs2.encode', function() { for (const object of testData.ucs2) { it(object.description, function() { assert.deepEqual( punycode.ucs2.encode(object.decoded), object.encoded ); }); } const codePoints = [0x61, 0x62, 0x63]; const result = punycode.ucs2.encode(codePoints); it('does not mutate argument array', function() { assert.deepEqual(result, 'abc'); assert.deepEqual(codePoints, [0x61, 0x62, 0x63]); }); }); describe('punycode.decode', function() { for (const object of testData.strings) { it(object.description || object.encoded, function() { assert.deepEqual( punycode.decode(object.encoded), object.decoded ); }); } it('handles uppercase Z', function() { assert.deepEqual(punycode.decode('ZZZ'), '\u7BA5'); }); it('throws RangeError: Invalid input', function() { assert.throws( function() { punycode.decode('ls8h='); }, RangeError ); }); }); describe('punycode.encode', function() { for (const object of testData.strings) { it(object.description || object.decoded, function() { assert.deepEqual( punycode.encode(object.decoded), object.encoded ); }); } }); describe('punycode.toUnicode', function() { for (const object of testData.domains) { it(object.description || object.encoded, function() { assert.deepEqual( punycode.toUnicode(object.encoded), object.decoded ); }); } for (const object of testData.strings) { it('does not convert names (or other strings) that don\'t start with `xn--`', function() { assert.deepEqual( punycode.toUnicode(object.encoded), object.encoded ); assert.deepEqual( punycode.toUnicode(object.decoded), object.decoded ); }); } }); describe('punycode.toASCII', function() { for (const object of testData.domains) { it(object.description || object.decoded, function() { assert.deepEqual( punycode.toASCII(object.decoded), object.encoded ); }); } for (const object of testData.strings) { it('does not convert domain names (or other strings) that are already in ASCII', function() { assert.deepEqual( punycode.toASCII(object.encoded), object.encoded ); }); } for (const object of testData.separators) { it('supports IDNA2003 separators for backwards compatibility', function() { assert.deepEqual( punycode.toASCII(object.decoded), object.encoded ); }); } });