punycode.js 12.3 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440
'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-\x7E]/; // non-ASCII chars
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, fn) {
	const result = [];
	let length = array.length;
	while (length--) {
		result[length] = fn(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 {Array} A new string of characters returned by the callback
 * function.
 */
function mapDomain(string, fn) {
	const parts = string.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] + '@';
		string = parts[1];
	}
	// Avoid `split(regex)` for IE8 compatibility. See #17.
	string = string.replace(regexSeparators, '\x2E');
	const labels = string.split('.');
	const encoded = map(labels, fn).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 = array => String.fromCodePoint(...array);

/**
 * 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 < 0x0A) {
		return codePoint - 0x16;
	}
	if (codePoint - 0x41 < 0x1A) {
		return codePoint - 0x41;
	}
	if (codePoint - 0x61 < 0x1A) {
		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`.
		let 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 || 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.
	let 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));
		}
	}

	let 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 <n,i> state to <m,0>,
		// 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': '2.1.0',
	/**
	 * An object of methods to convert from JavaScript's internal character
	 * representation (UCS-2) to Unicode code points, and back.
	 * @see <https://mathiasbynens.be/notes/javascript-encoding>
	 * @memberOf punycode
	 * @type Object
	 */
	'ucs2': {
		'decode': ucs2decode,
		'encode': ucs2encode
	},
	'decode': decode,
	'encode': encode,
	'toASCII': toASCII,
	'toUnicode': toUnicode
};

module.exports = punycode;