lukechilds
/
node
mirror of https://github.com/lukechilds/node.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

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>
v6.x
Mathias Bynens 9 years ago
committed by Jeremiah Senkpiel
parent
e1d6bd9e30
commit
fb39025e31
2 changed files with 389 additions and 479 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 290
      lib/punycode.js
  2. 4
      test/message/core_line_numbers.out

290
lib/punycode.js
View File

@ -1,59 +1,34 @@
/*! https://mths.be/punycode v1.3.2 by @mathias */
;(function(root) {
/** Detect free variables */
var freeExports = typeof exports == 'object' && exports &&
!exports.nodeType && exports;
var freeModule = typeof module == 'object' && module &&
!module.nodeType && module;
var freeGlobal = typeof global == 'object' && global;
if (
freeGlobal.global === freeGlobal ||
freeGlobal.window === freeGlobal ||
freeGlobal.self === freeGlobal
) {
root = freeGlobal;
}
/**
* The `punycode` object.
* @name punycode
* @type Object
*/
var punycode,
'use strict';
/** Highest positive signed 32-bit float value */
maxInt = 2147483647, // aka. 0x7FFFFFFF or 2^31-1
const 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'
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 */
regexPunycode = /^xn--/,
regexNonASCII = /[^\x20-\x7E]/, // unprintable ASCII chars + non-ASCII chars
regexSeparators = /[\x2E\u3002\uFF0E\uFF61]/g, // RFC 3490 separators
const regexPunycode = /^xn--/;
const regexNonASCII = /[^\x20-\x7E]/; // unprintable ASCII chars + non-ASCII chars
const regexSeparators = /[\x2E\u3002\uFF0E\uFF61]/g; // RFC 3490 separators
/** Error messages */
errors = {
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 */
baseMinusTMin = base - tMin,
floor = Math.floor,
stringFromCharCode = String.fromCharCode,
/** Temporary variable */
key;
const baseMinusTMin = base - tMin;
const floor = Math.floor;
const stringFromCharCode = String.fromCharCode;
/*--------------------------------------------------------------------------*/
@ -76,8 +51,8 @@
* @returns {Array} A new array of values returned by the callback function.
*/
function map(array, fn) {
var length = array.length;
var result = [];
const result = [];
let length = array.length;
while (length--) {
result[length] = fn(array[length]);
}
@ -95,8 +70,8 @@
* function.
*/
function mapDomain(string, fn) {
var parts = string.split('@');
var result = '';
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.
@ -105,8 +80,8 @@
}
// Avoid `split(regex)` for IE8 compatibility. See #17.
string = string.replace(regexSeparators, '\x2E');
var labels = string.split('.');
var encoded = map(labels, fn).join('.');
const labels = string.split('.');
const encoded = map(labels, fn).join('.');
return result + encoded;
}
@ -124,21 +99,19 @@
* @returns {Array} The new array of code points.
*/
function ucs2decode(string) {
var output = [],
counter = 0,
length = string.length,
value,
extra;
const output = [];
let counter = 0;
const length = string.length;
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
extra = string.charCodeAt(counter++);
if ((extra & 0xFC00) == 0xDC00) { // low surrogate
// 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 {
// unmatched surrogate; only append this code unit, in case the next
// code unit is the high surrogate of a surrogate pair
// 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--;
}
@ -157,18 +130,7 @@
* @param {Array} codePoints The array of numeric code points.
* @returns {String} The new Unicode string (UCS-2).
*/
function ucs2encode(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('');
}
const ucs2encode = array => String.fromCodePoint(...array);
/**
* Converts a basic code point into a digit/integer.
@ -179,18 +141,18 @@
* representing integers) in the range `0` to `base - 1`, or `base` if
* the code point does not represent a value.
*/
function basicToDigit(codePoint) {
if (codePoint - 48 < 10) {
return codePoint - 22;
const basicToDigit = function(codePoint) {
if (codePoint - 0x30 < 0x0A) {
return codePoint - 0x16;
}
if (codePoint - 65 < 26) {
return codePoint - 65;
if (codePoint - 0x41 < 0x1A) {
return codePoint - 0x41;
}
if (codePoint - 97 < 26) {
return codePoint - 97;
if (codePoint - 0x61 < 0x1A) {
return codePoint - 0x61;
}
return base;
}
};
/**
* Converts a digit/integer into a basic code point.
@ -203,26 +165,26 @@
* 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) {
var k = 0;
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
@ -231,35 +193,24 @@
* @param {String} input The Punycode string of ASCII-only symbols.
* @returns {String} The resulting string of Unicode symbols.
*/
function decode(input) {
// Don't use UCS-2
var output = [],
inputLength = input.length,
out,
i = 0,
n = initialN,
bias = initialBias,
basic,
j,
index,
oldi,
w,
k,
digit,
t,
/** Cached calculation results */
baseMinusT;
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.
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`,
@ -317,13 +269,13 @@
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
@ -332,51 +284,34 @@
* @param {String} input The string of Unicode symbols.
* @returns {String} The resulting Punycode string of ASCII-only symbols.
*/
function encode(input) {
var n,
delta,
handledCPCount,
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
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
inputLength = input.length;
// Cache the length.
let inputLength = input.length;
// Initialize the state
n = initialN;
delta = 0;
bias = initialBias;
// Initialize the state.
let n = initialN;
let delta = 0;
let bias = initialBias;
// Handle the basic code points
for (j = 0; j < inputLength; ++j) {
currentValue = input[j];
// Handle the basic code points.
for (const currentValue of input) {
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) {
currentValue = input[j];
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
handledCPCountPlusOne = handledCPCount + 1;
// but guard against overflow.
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) {
currentValue = input[j];
for (const currentValue of input) {
if (currentValue < n && ++delta > maxInt) {
error('overflow');
}
if (currentValue == n) {
// Represent delta as a generalized variable-length integer
for (q = delta, k = base; /* no condition */; k += base) {
t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias);
// 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;
}
qMinusT = q - t;
baseMinusT = base - t;
const qMinusT = q - t;
const baseMinusT = base - t;
output.push(
stringFromCharCode(digitToBasic(t + qMinusT % baseMinusT, 0))
);
@ -437,7 +370,7 @@
}
return output.join('');
}
};
/**
* Converts a Punycode string representing a domain name or an email address
@ -450,13 +383,13 @@
* @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
@ -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 */
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.
@ -504,27 +437,4 @@
'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;

4
test/message/core_line_numbers.out
View File

@ -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:*:*)

Write Preview
Loading…
Cancel
Save