diff options
Diffstat (limited to 'node_modules/punycode')
| -rw-r--r-- | node_modules/punycode/LICENSE-MIT.txt | 20 | ||||
| -rw-r--r-- | node_modules/punycode/README.md | 122 | ||||
| -rw-r--r-- | node_modules/punycode/package.json | 58 | ||||
| -rw-r--r-- | node_modules/punycode/punycode.es6.js | 441 | ||||
| -rw-r--r-- | node_modules/punycode/punycode.js | 440 |
5 files changed, 1081 insertions, 0 deletions
diff --git a/node_modules/punycode/LICENSE-MIT.txt b/node_modules/punycode/LICENSE-MIT.txt new file mode 100644 index 0000000..a41e0a7 --- /dev/null +++ b/node_modules/punycode/LICENSE-MIT.txt @@ -0,0 +1,20 @@ +Copyright Mathias Bynens <https://mathiasbynens.be/> + +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. diff --git a/node_modules/punycode/README.md b/node_modules/punycode/README.md new file mode 100644 index 0000000..ee2f9d6 --- /dev/null +++ b/node_modules/punycode/README.md @@ -0,0 +1,122 @@ +# Punycode.js [](https://travis-ci.org/bestiejs/punycode.js) [](https://codecov.io/gh/bestiejs/punycode.js) [](https://gemnasium.com/bestiejs/punycode.js) + +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). + +The current version supports recent versions of Node.js only. It provides a CommonJS module and an ES6 module. For the old version that offers the same functionality with broader support, including Rhino, Ringo, Narwhal, and web browsers, see [v1.4.1](https://github.com/bestiejs/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/): + +```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. + +## Author + +| [](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. diff --git a/node_modules/punycode/package.json b/node_modules/punycode/package.json new file mode 100644 index 0000000..9202ccf --- /dev/null +++ b/node_modules/punycode/package.json @@ -0,0 +1,58 @@ +{ + "name": "punycode", + "version": "2.1.1", + "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/bestiejs/punycode.js.git" + }, + "bugs": "https://github.com/bestiejs/punycode.js/issues", + "files": [ + "LICENSE-MIT.txt", + "punycode.js", + "punycode.es6.js" + ], + "scripts": { + "test": "mocha tests", + "prepublish": "node scripts/prepublish.js" + }, + "devDependencies": { + "codecov": "^1.0.1", + "istanbul": "^0.4.1", + "mocha": "^2.5.3" + }, + "jspm": { + "map": { + "./punycode.js": { + "node": "@node/punycode" + } + } + } +} diff --git a/node_modules/punycode/punycode.es6.js b/node_modules/punycode/punycode.es6.js new file mode 100644 index 0000000..4610bc9 --- /dev/null +++ b/node_modules/punycode/punycode.es6.js @@ -0,0 +1,441 @@ +'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-\x7E]/; // non-ASCII chars +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, fn) { + const result = []; + let length = array.length; + while (length--) { + result[length] = fn(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 {Array} A new string of characters returned by the callback + * function. + */ +function mapDomain(string, fn) { + const parts = string.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] + '@'; + string = parts[1]; + } + // Avoid `split(regex)` for IE8 compatibility. See #17. + string = string.replace(regexSeparators, '\x2E'); + const labels = string.split('.'); + const encoded = map(labels, fn).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 <https://mathiasbynens.be/notes/javascript-encoding> + * @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 = array => String.fromCodePoint(...array); + +/** + * 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 < 0x0A) { + return codePoint - 0x16; + } + if (codePoint - 0x41 < 0x1A) { + return codePoint - 0x41; + } + if (codePoint - 0x61 < 0x1A) { + 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`. + let 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 || 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. + let 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)); + } + } + + let 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 <n,i> state to <m,0>, + // 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': '2.1.0', + /** + * An object of methods to convert from JavaScript's internal character + * representation (UCS-2) to Unicode code points, and back. + * @see <https://mathiasbynens.be/notes/javascript-encoding> + * @memberOf punycode + * @type Object + */ + 'ucs2': { + 'decode': ucs2decode, + 'encode': ucs2encode + }, + 'decode': decode, + 'encode': encode, + 'toASCII': toASCII, + 'toUnicode': toUnicode +}; + +export { ucs2decode, ucs2encode, decode, encode, toASCII, toUnicode }; +export default punycode; diff --git a/node_modules/punycode/punycode.js b/node_modules/punycode/punycode.js new file mode 100644 index 0000000..ea61fd0 --- /dev/null +++ b/node_modules/punycode/punycode.js @@ -0,0 +1,440 @@ +'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-\x7E]/; // non-ASCII chars +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, fn) { + const result = []; + let length = array.length; + while (length--) { + result[length] = fn(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 {Array} A new string of characters returned by the callback + * function. + */ +function mapDomain(string, fn) { + const parts = string.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] + '@'; + string = parts[1]; + } + // Avoid `split(regex)` for IE8 compatibility. See #17. + string = string.replace(regexSeparators, '\x2E'); + const labels = string.split('.'); + const encoded = map(labels, fn).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 <https://mathiasbynens.be/notes/javascript-encoding> + * @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 = array => String.fromCodePoint(...array); + +/** + * 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 < 0x0A) { + return codePoint - 0x16; + } + if (codePoint - 0x41 < 0x1A) { + return codePoint - 0x41; + } + if (codePoint - 0x61 < 0x1A) { + 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`. + let 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 || 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. + let 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)); + } + } + + let 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 <n,i> state to <m,0>, + // 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': '2.1.0', + /** + * An object of methods to convert from JavaScript's internal character + * representation (UCS-2) to Unicode code points, and back. + * @see <https://mathiasbynens.be/notes/javascript-encoding> + * @memberOf punycode + * @type Object + */ + 'ucs2': { + 'decode': ucs2decode, + 'encode': ucs2encode + }, + 'decode': decode, + 'encode': encode, + 'toASCII': toASCII, + 'toUnicode': toUnicode +}; + +module.exports = punycode; |