@kamilkisiela/fast-url-parser
Version:
Extremely fast implementation of node core url library
270 lines (241 loc) • 8.36 kB
JavaScript
// 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
};