From abf21ea1a73b4c8275bd0fe8469bda35508c31aa Mon Sep 17 00:00:00 2001 From: Mathias Bynens Date: Fri, 28 Nov 2014 10:50:12 +0100 Subject: [PATCH] punycode: update to v1.3.2 Changes since v1.2.3: * Email address support in `toASCII` and `toUnicode` * `punycode.ucs2.encode` now no longer mutates the `codePoints` argument * Ensure trailing `.` in domain names are preserved * Some minor code cleanup + bug fixes --- lib/punycode.js | 91 +++++++++++++++++++++++++++++++------------------ 1 file changed, 57 insertions(+), 34 deletions(-) diff --git a/lib/punycode.js b/lib/punycode.js index 8a959552d87cb5..82cc20769cd088 100644 --- a/lib/punycode.js +++ b/lib/punycode.js @@ -1,12 +1,17 @@ -/*! http://mths.be/punycode v1.2.3 by @mathias */ +/*! https://mths.be/punycode v1.3.2 by @mathias */ ;(function(root) { /** Detect free variables */ - var freeExports = typeof exports == 'object' && exports; + var freeExports = typeof exports == 'object' && exports && + !exports.nodeType && exports; var freeModule = typeof module == 'object' && module && - module.exports == freeExports && module; + !module.nodeType && module; var freeGlobal = typeof global == 'object' && global; - if (freeGlobal.global === freeGlobal || freeGlobal.window === freeGlobal) { + if ( + freeGlobal.global === freeGlobal || + freeGlobal.window === freeGlobal || + freeGlobal.self === freeGlobal + ) { root = freeGlobal; } @@ -32,8 +37,8 @@ /** Regular expressions */ regexPunycode = /^xn--/, - regexNonASCII = /[^ -~]/, // unprintable ASCII chars + non-ASCII chars - regexSeparators = /\x2E|\u3002|\uFF0E|\uFF61/g, // RFC 3490 separators + regexNonASCII = /[^\x20-\x7E]/, // unprintable ASCII chars + non-ASCII chars + regexSeparators = /[\x2E\u3002\uFF0E\uFF61]/g, // RFC 3490 separators /** Error messages */ errors = { @@ -72,23 +77,37 @@ */ function map(array, fn) { var length = array.length; + var result = []; while (length--) { - array[length] = fn(array[length]); + result[length] = fn(array[length]); } - return array; + return result; } /** - * A simple `Array#map`-like wrapper to work with domain name strings. + * A simple `Array#map`-like wrapper to work with domain name strings or email + * addresses. * @private - * @param {String} domain The domain name. + * @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) { - return map(string.split(regexSeparators), fn).join('.'); + var parts = string.split('@'); + var 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'); + var labels = string.split('.'); + var encoded = map(labels, fn).join('.'); + return result + encoded; } /** @@ -98,7 +117,7 @@ * UCS-2 exposes as separate characters) into a single code point, * matching UTF-16. * @see `punycode.ucs2.encode` - * @see + * @see * @memberOf punycode.ucs2 * @name decode * @param {String} string The Unicode input string (UCS-2). @@ -192,7 +211,7 @@ /** * Bias adaptation function as per section 3.4 of RFC 3492. - * http://tools.ietf.org/html/rfc3492#section-3.4 + * https://tools.ietf.org/html/rfc3492#section-3.4 * @private */ function adapt(delta, numPoints, firstTime) { @@ -307,8 +326,8 @@ } /** - * Converts a string of Unicode symbols to a Punycode string of ASCII-only - * symbols. + * 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. @@ -421,17 +440,18 @@ } /** - * Converts a Punycode string representing a domain name to Unicode. Only the - * Punycoded parts of the domain name will be converted, i.e. it doesn't - * matter if you call it on a string that has already been converted to - * Unicode. + * 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} domain The Punycode domain name to convert to Unicode. + * @param {String} input The Punycoded domain name or email address to + * convert to Unicode. * @returns {String} The Unicode representation of the given Punycode * string. */ - function toUnicode(domain) { - return mapDomain(domain, function(string) { + function toUnicode(input) { + return mapDomain(input, function(string) { return regexPunycode.test(string) ? decode(string.slice(4).toLowerCase()) : string; @@ -439,15 +459,18 @@ } /** - * Converts a Unicode string representing a domain name 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. + * 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} domain The domain name to convert, as a Unicode string. - * @returns {String} The Punycode representation of the given domain name. + * @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. */ - function toASCII(domain) { - return mapDomain(domain, function(string) { + function toASCII(input) { + return mapDomain(input, function(string) { return regexNonASCII.test(string) ? 'xn--' + encode(string) : string; @@ -463,11 +486,11 @@ * @memberOf punycode * @type String */ - 'version': '1.2.3', + 'version': '1.3.2', /** * An object of methods to convert from JavaScript's internal character * representation (UCS-2) to Unicode code points, and back. - * @see + * @see * @memberOf punycode * @type Object */ @@ -489,11 +512,11 @@ typeof define.amd == 'object' && define.amd ) { - define(function() { + define('punycode', function() { return punycode; }); - } else if (freeExports && !freeExports.nodeType) { - if (freeModule) { // in Node.js or RingoJS v0.8.0+ + } else if (freeExports && freeModule) { + if (module.exports == freeExports) { // in Node.js or RingoJS v0.8.0+ freeModule.exports = punycode; } else { // in Narwhal or RingoJS v0.7.0- for (key in punycode) {