UNPKG

@kamilkisiela/fast-url-parser

Version:

Extremely fast implementation of node core url library

270 lines (241 loc) 8.36 kB
// taken directly from https://www.npmjs.com/package/punycode "use strict"; /** Highest positive signed 32-bit float value */ var maxInt = 2147483647; // aka. 0x7FFFFFFF or 2^31-1 /** Bootstring parameters */ var base = 36; var tMin = 1; var tMax = 26; var skew = 38; var damp = 700; var initialBias = 72; var initialN = 128; // 0x80 var delimiter = "-"; // '\x2D' /** Regular expressions */ var regexNonASCII = /[^\0-\x7F]/; // Note: U+007F DEL is excluded too. var regexSeparators = /[\x2E\u3002\uFF0E\uFF61]/g; // RFC 3490 separators /** Error messages */ var 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 */ var baseMinusTMin = base - tMin; var floor = Math.floor; var 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) { var result = []; var 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) { var parts = domain.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] + "@"; domain = parts[1]; } // Avoid `split(regex)` for IE8 compatibility. See #17. domain = domain.replace(regexSeparators, "\x2E"); var labels = domain.split("."); var 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 <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) { var output = []; var counter = 0; var length = string.length; while (counter < length) { var value = string.charCodeAt(counter++); if (value >= 0xd800 && value <= 0xdbff && counter < length) { // It's a high surrogate, and there is a next character. var 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; } /** * 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. */ var 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 */ var adapt = function (delta, numPoints, firstTime) { var 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 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. */ var encode = function (input) { var output = []; // Convert the input in UCS-2 to an array of Unicode code points. input = ucs2decode(input); // Cache the length. var inputLength = input.length; // Initialize the state. var n = initialN; var delta = 0; var bias = initialBias; // Handle the basic code points. for (var currentValue of input) { if (currentValue < 0x80) { output.push(stringFromCharCode(currentValue)); } } var basicLength = output.length; var 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: var m = maxInt; for (var 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. var handledCPCountPlusOne = handledCPCount + 1; if (m - n > floor((maxInt - delta) / handledCPCountPlusOne)) { error("overflow"); } delta += (m - n) * handledCPCountPlusOne; n = m; for (var currentValue of input) { if (currentValue < n && ++delta > maxInt) { error("overflow"); } if (currentValue === n) { // Represent delta as a generalized variable-length integer. var q = delta; for (var k = base /* no condition */; ; k += base) { var t = k <= bias ? tMin : k >= bias + tMax ? tMax : k - bias; if (q < t) { break; } var qMinusT = q - t; var 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 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. */ var toASCII = function (input) { return mapDomain(input, function (string) { return regexNonASCII.test(string) ? "xn--" + encode(string) : string; }); }; /*--------------------------------------------------------------------------*/ module.exports = { toASCII: toASCII };