punycode: update to v2.0.0

Punycode v2.0.0 drops support for old and non-Node environments.

PR-URL: https://github.com/nodejs/node/pull/7267
Fixes: https://github.com/nodejs/node/issues/7224
Reviewed-By: Ben Noordhuis <info@bnoordhuis.nl>
Reviewed-By: Roman Reiss <me@silverwind.io>

lib/punycode.js

@@ -1,73 +1,48 @@
-/*! https://mths.be/punycode v1.3.2 by @mathias */
+'use strict';
-;(function(root) {
+
-
+/** Highest positive signed 32-bit float value */
-	/** Detect free variables */
+const maxInt = 2147483647; // aka. 0x7FFFFFFF or 2^31-1
-	var freeExports = typeof exports == 'object' && exports &&
+
-		!exports.nodeType && exports;
+/** Bootstring parameters */
-	var freeModule = typeof module == 'object' && module &&
+const base = 36;
-		!module.nodeType && module;
+const tMin = 1;
-	var freeGlobal = typeof global == 'object' && global;
+const tMax = 26;
-	if (
+const skew = 38;
-		freeGlobal.global === freeGlobal ||
+const damp = 700;
-		freeGlobal.window === freeGlobal ||
+const initialBias = 72;
-		freeGlobal.self === freeGlobal
+const initialN = 128; // 0x80
-	) {
+const delimiter = '-'; // '\x2D'
-		root = freeGlobal;
+
-	}
+/** Regular expressions */
-
+const regexPunycode = /^xn--/;
-	/**
+const regexNonASCII = /[^\x20-\x7E]/; // unprintable ASCII chars + non-ASCII chars
-	 * The `punycode` object.
+const regexSeparators = /[\x2E\u3002\uFF0E\uFF61]/g; // RFC 3490 separators
-	 * @name punycode
+
-	 * @type Object
+/** Error messages */
-	 */
+const errors = {
-	var punycode,
-
-	/** Highest positive signed 32-bit float value */
-	maxInt = 2147483647, // aka. 0x7FFFFFFF or 2^31-1
-
-	/** Bootstring parameters */
-	base = 36,
-	tMin = 1,
-	tMax = 26,
-	skew = 38,
-	damp = 700,
-	initialBias = 72,
-	initialN = 128, // 0x80
-	delimiter = '-', // '\x2D'
-
-	/** Regular expressions */
-	regexPunycode = /^xn--/,
-	regexNonASCII = /[^\x20-\x7E]/, // unprintable ASCII chars + non-ASCII chars
-	regexSeparators = /[\x2E\u3002\uFF0E\uFF61]/g, // RFC 3490 separators
-
-	/** Error messages */
-	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 */
+/** Convenience shortcuts */
-	baseMinusTMin = base - tMin,
+const baseMinusTMin = base - tMin;
-	floor = Math.floor,
+const floor = Math.floor;
-	stringFromCharCode = String.fromCharCode,
+const stringFromCharCode = String.fromCharCode;
 
-	/** Temporary variable */
+/*--------------------------------------------------------------------------*/
-	key;
 
-	/*--------------------------------------------------------------------------*/
+/**
-
-	/**
  * 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) {
+function error(type) {
 	throw new RangeError(errors[type]);
-	}
+}
 
-	/**
+/**
  * A generic `Array#map` utility function.
  * @private
  * @param {Array} array The array to iterate over.
@@ -75,16 +50,16 @@
  * item.
  * @returns {Array} A new array of values returned by the callback function.
  */
-	function map(array, fn) {
+function map(array, fn) {
-		var length = array.length;
+	const result = [];
-		var 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
@@ -94,9 +69,9 @@
  * @returns {Array} A new string of characters returned by the callback
  * function.
  */
-	function mapDomain(string, fn) {
+function mapDomain(string, fn) {
-		var parts = string.split('@');
+	const parts = string.split('@');
-		var result = '';
+	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.
@@ -105,12 +80,12 @@
 	}
 	// Avoid `split(regex)` for IE8 compatibility. See #17.
 	string = string.replace(regexSeparators, '\x2E');
-		var labels = string.split('.');
+	const labels = string.split('.');
-		var encoded = map(labels, fn).join('.');
+	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
@@ -123,22 +98,20 @@
  * @param {String} string The Unicode input string (UCS-2).
  * @returns {Array} The new array of code points.
  */
-	function ucs2decode(string) {
+function ucs2decode(string) {
-		var output = [],
+	const output = [];
-		    counter = 0,
+	let counter = 0;
-		    length = string.length,
+	const length = string.length;
-		    value,
-		    extra;
 	while (counter < length) {
-			value = string.charCodeAt(counter++);
+		const value = string.charCodeAt(counter++);
 		if (value >= 0xD800 && value <= 0xDBFF && counter < length) {
-				// high surrogate, and there is a next character
+			// It's a high surrogate, and there is a next character.
-				extra = string.charCodeAt(counter++);
+			const extra = string.charCodeAt(counter++);
-				if ((extra & 0xFC00) == 0xDC00) { // low surrogate
+			if ((extra & 0xFC00) == 0xDC00) { // Low surrogate.
 				output.push(((value & 0x3FF) << 10) + (extra & 0x3FF) + 0x10000);
 			} else {
-					// unmatched surrogate; only append this code unit, in case the next
+				// It's an unmatched surrogate; only append this code unit, in case the
-					// code unit is the high surrogate of a surrogate pair
+				// next code unit is the high surrogate of a surrogate pair.
 				output.push(value);
 				counter--;
 			}
@@ -147,9 +120,9 @@
 		}
 	}
 	return output;
-	}
+}
 
-	/**
+/**
  * Creates a string based on an array of numeric code points.
  * @see `punycode.ucs2.decode`
  * @memberOf punycode.ucs2
@@ -157,20 +130,9 @@
  * @param {Array} codePoints The array of numeric code points.
  * @returns {String} The new Unicode string (UCS-2).
  */
-	function ucs2encode(array) {
+const ucs2encode = array => String.fromCodePoint(...array);
-		return map(array, function(value) {
-			var output = '';
-			if (value > 0xFFFF) {
-				value -= 0x10000;
-				output += stringFromCharCode(value >>> 10 & 0x3FF | 0xD800);
-				value = 0xDC00 | value & 0x3FF;
-			}
-			output += stringFromCharCode(value);
-			return output;
-		}).join('');
-	}
 
-	/**
+/**
  * Converts a basic code point into a digit/integer.
  * @see `digitToBasic()`
  * @private
@@ -179,20 +141,20 @@
  * representing integers) in the range `0` to `base - 1`, or `base` if
  * the code point does not represent a value.
  */
-	function basicToDigit(codePoint) {
+const basicToDigit = function(codePoint) {
-		if (codePoint - 48 < 10) {
+	if (codePoint - 0x30 < 0x0A) {
-			return codePoint - 22;
+		return codePoint - 0x16;
 	}
-		if (codePoint - 65 < 26) {
+	if (codePoint - 0x41 < 0x1A) {
-			return codePoint - 65;
+		return codePoint - 0x41;
 	}
-		if (codePoint - 97 < 26) {
+	if (codePoint - 0x61 < 0x1A) {
-			return codePoint - 97;
+		return codePoint - 0x61;
 	}
 	return base;
-	}
+};
 
-	/**
+/**
  * Converts a digit/integer into a basic code point.
  * @see `basicToDigit()`
  * @private
@@ -203,63 +165,52 @@
  * used; else, the lowercase form is used. The behavior is undefined
  * if `flag` is non-zero and `digit` has no uppercase form.
  */
-	function digitToBasic(digit, flag) {
+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
  */
-	function adapt(delta, numPoints, firstTime) {
+const adapt = function(delta, numPoints, firstTime) {
-		var k = 0;
+	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.
  */
-	function decode(input) {
+const decode = function(input) {
-		// Don't use UCS-2
+	// Don't use UCS-2.
-		var output = [],
+	const output = [];
-		    inputLength = input.length,
+	const inputLength = input.length;
-		    out,
+	let i = 0;
-		    i = 0,
+	let n = initialN;
-		    n = initialN,
+	let bias = initialBias;
-		    bias = initialBias,
-		    basic,
-		    j,
-		    index,
-		    oldi,
-		    w,
-		    k,
-		    digit,
-		    t,
-		    /** Cached calculation results */
-		    baseMinusT;
 
 	// 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.
 
-		basic = input.lastIndexOf(delimiter);
+	let basic = input.lastIndexOf(delimiter);
 	if (basic < 0) {
 		basic = 0;
 	}
 
-		for (j = 0; j < basic; ++j) {
+	for (let j = 0; j < basic; ++j) {
 		// if it's not a basic code point
 		if (input.charCodeAt(j) >= 0x80) {
 			error('not-basic');
@@ -270,33 +221,34 @@
 	// Main decoding loop: start just after the last delimiter if any basic code
 	// points were copied; start at the beginning otherwise.
 
-		for (index = basic > 0 ? basic + 1 : 0; index < inputLength; /* no final expression */) {
+	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`.
-			for (oldi = i, w = 1, k = base; /* no condition */; k += base) {
+		let oldi = i;
+		for (let w = 1, k = base; /* no condition */; k += base) {
 
 			if (index >= inputLength) {
 				error('invalid-input');
 			}
 
-				digit = basicToDigit(input.charCodeAt(index++));
+			const digit = basicToDigit(input.charCodeAt(index++));
 
 			if (digit >= base || digit > floor((maxInt - i) / w)) {
 				error('overflow');
 			}
 
 			i += digit * w;
-				t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias);
+			const t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias);
 
 			if (digit < t) {
 				break;
 			}
 
-				baseMinusT = base - t;
+			const baseMinusT = base - t;
 			if (w > floor(maxInt / baseMinusT)) {
 				error('overflow');
 			}
@@ -305,7 +257,7 @@
 
 		}
 
-			out = output.length + 1;
+		const out = output.length + 1;
 		bias = adapt(i - oldi, out, oldi == 0);
 
 		// `i` was supposed to wrap around from `out` to `0`,
@@ -317,66 +269,49 @@
 		n += floor(i / out);
 		i %= out;
 
-			// Insert `n` at position `i` of the output
+		// Insert `n` at position `i` of the output.
 		output.splice(i++, 0, n);
 
 	}
 
-		return ucs2encode(output);
+	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.
  */
-	function encode(input) {
+const encode = function(input) {
-		var n,
+	const output = [];
-		    delta,
+
-		    handledCPCount,
+	// Convert the input in UCS-2 to an array of Unicode code points.
-		    basicLength,
-		    bias,
-		    j,
-		    m,
-		    q,
-		    k,
-		    t,
-		    currentValue,
-		    output = [],
-		    /** `inputLength` will hold the number of code points in `input`. */
-		    inputLength,
-		    /** Cached calculation results */
-		    handledCPCountPlusOne,
-		    baseMinusT,
-		    qMinusT;
-
-		// Convert the input in UCS-2 to Unicode
 	input = ucs2decode(input);
 
-		// Cache the length
+	// Cache the length.
-		inputLength = input.length;
+	let inputLength = input.length;
 
-		// Initialize the state
+	// Initialize the state.
-		n = initialN;
+	let n = initialN;
-		delta = 0;
+	let delta = 0;
-		bias = initialBias;
+	let bias = initialBias;
 
-		// Handle the basic code points
+	// Handle the basic code points.
-		for (j = 0; j < inputLength; ++j) {
+	for (const currentValue of input) {
-			currentValue = input[j];
 		if (currentValue < 0x80) {
 			output.push(stringFromCharCode(currentValue));
 		}
 	}
 
-		handledCPCount = basicLength = output.length;
+	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 - if it is not empty - with a delimiter
+	// Finish the basic string with a delimiter unless it's empty.
 	if (basicLength) {
 		output.push(delimiter);
 	}
@@ -386,16 +321,16 @@
 
 		// All non-basic code points < n have been handled already. Find the next
 		// larger one:
-			for (m = maxInt, j = 0; j < inputLength; ++j) {
+		let m = maxInt;
-				currentValue = input[j];
+		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
+		// but guard against overflow.
-			handledCPCountPlusOne = handledCPCount + 1;
+		const handledCPCountPlusOne = handledCPCount + 1;
 		if (m - n > floor((maxInt - delta) / handledCPCountPlusOne)) {
 			error('overflow');
 		}
@@ -403,22 +338,20 @@
 		delta += (m - n) * handledCPCountPlusOne;
 		n = m;
 
-			for (j = 0; j < inputLength; ++j) {
+		for (const currentValue of input) {
-				currentValue = input[j];
-
 			if (currentValue < n && ++delta > maxInt) {
 				error('overflow');
 			}
-
 			if (currentValue == n) {
-					// Represent delta as a generalized variable-length integer
+				// Represent delta as a generalized variable-length integer.
-					for (q = delta, k = base; /* no condition */; k += base) {
+				let q = delta;
-						t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias);
+				for (let k = base; /* no condition */; k += base) {
+					const t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias);
 					if (q < t) {
 						break;
 					}
-						qMinusT = q - t;
+					const qMinusT = q - t;
-						baseMinusT = base - t;
+					const baseMinusT = base - t;
 					output.push(
 						stringFromCharCode(digitToBasic(t + qMinusT % baseMinusT, 0))
 					);
@@ -437,9 +370,9 @@
 
 	}
 	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
@@ -450,15 +383,15 @@
  * @returns {String} The Unicode representation of the given Punycode
  * string.
  */
-	function toUnicode(input) {
+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
@@ -469,24 +402,24 @@
  * @returns {String} The Punycode representation of the given domain name or
  * email address.
  */
-	function toASCII(input) {
+const toASCII = function(input) {
 	return mapDomain(input, function(string) {
 		return regexNonASCII.test(string)
 			? 'xn--' + encode(string)
 			: string;
 	});
-	}
+};
 
-	/*--------------------------------------------------------------------------*/
+/*--------------------------------------------------------------------------*/
 
-	/** Define the public API */
+/** Define the public API */
-	punycode = {
+const punycode = {
 	/**
 	 * A string representing the current Punycode.js version number.
 	 * @memberOf punycode
 	 * @type String
 	 */
-		'version': '1.3.2',
+	'version': '2.0.0',
 	/**
 	 * An object of methods to convert from JavaScript's internal character
 	 * representation (UCS-2) to Unicode code points, and back.
@@ -502,29 +435,6 @@
 	'encode': encode,
 	'toASCII': toASCII,
 	'toUnicode': toUnicode
-	};
+};
-
-	/** Expose `punycode` */
-	// Some AMD build optimizers, like r.js, check for specific condition patterns
-	// like the following:
-	if (
-		typeof define == 'function' &&
-		typeof define.amd == 'object' &&
-		define.amd
-	) {
-		define('punycode', function() {
-			return punycode;
-		});
-	} else if (freeExports && freeModule) {
-		if (module.exports == freeExports) { // in Node.js or RingoJS v0.8.0+
-			freeModule.exports = punycode;
-		} else { // in Narwhal or RingoJS v0.7.0-
-			for (key in punycode) {
-				punycode.hasOwnProperty(key) && (freeExports[key] = punycode[key]);
-			}
-		}
-	} else { // in Rhino or a web browser
-		root.punycode = punycode;
-	}
 
-}(this));
+module.exports = punycode;

test/message/core_line_numbers.out

@@ -1,9 +1,9 @@
-punycode.js:67
+punycode.js:42
 	throw new RangeError(errors[type]);
 	^
 
 RangeError: Invalid input
-    at error (punycode.js:67:*)
+    at error (punycode.js:42:*)
     at Object.decode (punycode.js:*:*)
     at Object.<anonymous> (*test*message*core_line_numbers.js:*:*)
     at Module._compile (module.js:*:*)