(function(f){if(typeof exports==="object"&&typeof module!=="undefined"){module.exports=f()}else if(typeof define==="function"&&define.amd){define([],f)}else{var g;if(typeof window!=="undefined"){g=window}else if(typeof global!=="undefined"){g=global}else if(typeof self!=="undefined"){g=self}else{g=this}g.psl = f()}})(function(){var define,module,exports;return (function(){function r(e,n,t){function o(i,f){if(!n[i]){if(!e[i]){var c="function"==typeof require&&require;if(!f&&c)return c(i,!0);if(u)return u(i,!0);var a=new Error("Cannot find module '"+i+"'");throw a.code="MODULE_NOT_FOUND",a}var p=n[i]={exports:{}};e[i][0].call(p.exports,function(r){var n=e[i][1][r];return o(n||r)},p,p.exports,r,e,n,t)}return n[i].exports}for(var u="function"==typeof require&&require,i=0;i= punySuffix.length) { // return memo; // } //} return rule; }, null); }; // // Error codes and messages. // exports.errorCodes = { DOMAIN_TOO_SHORT: 'Domain name too short.', DOMAIN_TOO_LONG: 'Domain name too long. It should be no more than 255 chars.', LABEL_STARTS_WITH_DASH: 'Domain name label can not start with a dash.', LABEL_ENDS_WITH_DASH: 'Domain name label can not end with a dash.', LABEL_TOO_LONG: 'Domain name label should be at most 63 chars long.', LABEL_TOO_SHORT: 'Domain name label should be at least 1 character long.', LABEL_INVALID_CHARS: 'Domain name label can only contain alphanumeric characters or dashes.' }; // // Validate domain name and throw if not valid. // // From wikipedia: // // Hostnames are composed of series of labels concatenated with dots, as are all // domain names. Each label must be between 1 and 63 characters long, and the // entire hostname (including the delimiting dots) has a maximum of 255 chars. // // Allowed chars: // // * `a-z` // * `0-9` // * `-` but not as a starting or ending character // * `.` as a separator for the textual portions of a domain name // // * http://en.wikipedia.org/wiki/Domain_name // * http://en.wikipedia.org/wiki/Hostname // internals.validate = function (input) { // Before we can validate we need to take care of IDNs with unicode chars. var ascii = Punycode.toASCII(input); if (ascii.length < 1) { return 'DOMAIN_TOO_SHORT'; } if (ascii.length > 255) { return 'DOMAIN_TOO_LONG'; } // Check each part's length and allowed chars. var labels = ascii.split('.'); var label; for (var i = 0; i < labels.length; ++i) { label = labels[i]; if (!label.length) { return 'LABEL_TOO_SHORT'; } if (label.length > 63) { return 'LABEL_TOO_LONG'; } if (label.charAt(0) === '-') { return 'LABEL_STARTS_WITH_DASH'; } if (label.charAt(label.length - 1) === '-') { return 'LABEL_ENDS_WITH_DASH'; } if (!/^[a-z0-9\-]+$/.test(label)) { return 'LABEL_INVALID_CHARS'; } } }; // // Public API // // // Parse domain. // exports.parse = function (input) { if (typeof input !== 'string') { throw new TypeError('Domain name must be a string.'); } // Force domain to lowercase. var domain = input.slice(0).toLowerCase(); // Handle FQDN. // TODO: Simply remove trailing dot? if (domain.charAt(domain.length - 1) === '.') { domain = domain.slice(0, domain.length - 1); } // Validate and sanitise input. var error = internals.validate(domain); if (error) { return { input: input, error: { message: exports.errorCodes[error], code: error } }; } var parsed = { input: input, tld: null, sld: null, domain: null, subdomain: null, listed: false }; var domainParts = domain.split('.'); // Non-Internet TLD if (domainParts[domainParts.length - 1] === 'local') { return parsed; } var handlePunycode = function () { if (!/xn--/.test(domain)) { return parsed; } if (parsed.domain) { parsed.domain = Punycode.toASCII(parsed.domain); } if (parsed.subdomain) { parsed.subdomain = Punycode.toASCII(parsed.subdomain); } return parsed; }; var rule = internals.findRule(domain); // Unlisted tld. if (!rule) { if (domainParts.length < 2) { return parsed; } parsed.tld = domainParts.pop(); parsed.sld = domainParts.pop(); parsed.domain = [parsed.sld, parsed.tld].join('.'); if (domainParts.length) { parsed.subdomain = domainParts.pop(); } return handlePunycode(); } // At this point we know the public suffix is listed. parsed.listed = true; var tldParts = rule.suffix.split('.'); var privateParts = domainParts.slice(0, domainParts.length - tldParts.length); if (rule.exception) { privateParts.push(tldParts.shift()); } parsed.tld = tldParts.join('.'); if (!privateParts.length) { return handlePunycode(); } if (rule.wildcard) { tldParts.unshift(privateParts.pop()); parsed.tld = tldParts.join('.'); } if (!privateParts.length) { return handlePunycode(); } parsed.sld = privateParts.pop(); parsed.domain = [parsed.sld, parsed.tld].join('.'); if (privateParts.length) { parsed.subdomain = privateParts.join('.'); } return handlePunycode(); }; // // Get domain. // exports.get = function (domain) { if (!domain) { return null; } return exports.parse(domain).domain || null; }; // // Check whether domain belongs to a known public suffix. // exports.isValid = function (domain) { var parsed = exports.parse(domain); return Boolean(parsed.domain && parsed.listed); }; },{"./data/rules.json":1,"punycode/":3}],3:[function(require,module,exports){ '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; },{}]},{},[2])(2) });