Punycode Es6
Punycode Es6
/*--------------------------------------------------------------------------*/
/**
* 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 <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 = 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.
// 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 */) {
i += digit * w;
const t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k -
bias);
if (digit < t) {
break;
}
w *= baseMinusT;
n += floor(i / out);
i %= out;
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 = [];
// 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;
}
}
delta += (m - n) * handledCPCountPlusOne;
n = m;
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;
});
};
/*--------------------------------------------------------------------------*/