1 | /*! https://mths.be/punycode v1.3.2 by @mathias */
|
2 | ;(function(root) {
|
3 |
|
4 | /** Detect free variables */
|
5 | var freeExports = typeof exports == 'object' && exports &&
|
6 | !exports.nodeType && exports;
|
7 | var freeModule = typeof module == 'object' && module &&
|
8 | !module.nodeType && module;
|
9 | var freeGlobal = typeof global == 'object' && global;
|
10 | if (
|
11 | freeGlobal.global === freeGlobal ||
|
12 | freeGlobal.window === freeGlobal ||
|
13 | freeGlobal.self === freeGlobal
|
14 | ) {
|
15 | root = freeGlobal;
|
16 | }
|
17 |
|
18 | /**
|
19 | * The `punycode` object.
|
20 | * @name punycode
|
21 | * @type Object
|
22 | */
|
23 | var punycode,
|
24 |
|
25 | /** Highest positive signed 32-bit float value */
|
26 | maxInt = 2147483647, // aka. 0x7FFFFFFF or 2^31-1
|
27 |
|
28 | /** Bootstring parameters */
|
29 | base = 36,
|
30 | tMin = 1,
|
31 | tMax = 26,
|
32 | skew = 38,
|
33 | damp = 700,
|
34 | initialBias = 72,
|
35 | initialN = 128, // 0x80
|
36 | delimiter = '-', // '\x2D'
|
37 |
|
38 | /** Regular expressions */
|
39 | regexPunycode = /^xn--/,
|
40 | regexNonASCII = /[^\x20-\x7E]/, // unprintable ASCII chars + non-ASCII chars
|
41 | regexSeparators = /[\x2E\u3002\uFF0E\uFF61]/g, // RFC 3490 separators
|
42 |
|
43 | /** Error messages */
|
44 | errors = {
|
45 | 'overflow': 'Overflow: input needs wider integers to process',
|
46 | 'not-basic': 'Illegal input >= 0x80 (not a basic code point)',
|
47 | 'invalid-input': 'Invalid input'
|
48 | },
|
49 |
|
50 | /** Convenience shortcuts */
|
51 | baseMinusTMin = base - tMin,
|
52 | floor = Math.floor,
|
53 | stringFromCharCode = String.fromCharCode,
|
54 |
|
55 | /** Temporary variable */
|
56 | key;
|
57 |
|
58 | /*--------------------------------------------------------------------------*/
|
59 |
|
60 | /**
|
61 | * A generic error utility function.
|
62 | * @private
|
63 | * @param {String} type The error type.
|
64 | * @returns {Error} Throws a `RangeError` with the applicable error message.
|
65 | */
|
66 | function error(type) {
|
67 | throw RangeError(errors[type]);
|
68 | }
|
69 |
|
70 | /**
|
71 | * A generic `Array#map` utility function.
|
72 | * @private
|
73 | * @param {Array} array The array to iterate over.
|
74 | * @param {Function} callback The function that gets called for every array
|
75 | * item.
|
76 | * @returns {Array} A new array of values returned by the callback function.
|
77 | */
|
78 | function map(array, fn) {
|
79 | var length = array.length;
|
80 | var result = [];
|
81 | while (length--) {
|
82 | result[length] = fn(array[length]);
|
83 | }
|
84 | return result;
|
85 | }
|
86 |
|
87 | /**
|
88 | * A simple `Array#map`-like wrapper to work with domain name strings or email
|
89 | * addresses.
|
90 | * @private
|
91 | * @param {String} domain The domain name or email address.
|
92 | * @param {Function} callback The function that gets called for every
|
93 | * character.
|
94 | * @returns {Array} A new string of characters returned by the callback
|
95 | * function.
|
96 | */
|
97 | function mapDomain(string, fn) {
|
98 | var parts = string.split('@');
|
99 | var result = '';
|
100 | if (parts.length > 1) {
|
101 | // In email addresses, only the domain name should be punycoded. Leave
|
102 | // the local part (i.e. everything up to `@`) intact.
|
103 | result = parts[0] + '@';
|
104 | string = parts[1];
|
105 | }
|
106 | // Avoid `split(regex)` for IE8 compatibility. See #17.
|
107 | string = string.replace(regexSeparators, '\x2E');
|
108 | var labels = string.split('.');
|
109 | var encoded = map(labels, fn).join('.');
|
110 | return result + encoded;
|
111 | }
|
112 |
|
113 | /**
|
114 | * Creates an array containing the numeric code points of each Unicode
|
115 | * character in the string. While JavaScript uses UCS-2 internally,
|
116 | * this function will convert a pair of surrogate halves (each of which
|
117 | * UCS-2 exposes as separate characters) into a single code point,
|
118 | * matching UTF-16.
|
119 | * @see `punycode.ucs2.encode`
|
120 | * @see <https://mathiasbynens.be/notes/javascript-encoding>
|
121 | * @memberOf punycode.ucs2
|
122 | * @name decode
|
123 | * @param {String} string The Unicode input string (UCS-2).
|
124 | * @returns {Array} The new array of code points.
|
125 | */
|
126 | function ucs2decode(string) {
|
127 | var output = [],
|
128 | counter = 0,
|
129 | length = string.length,
|
130 | value,
|
131 | extra;
|
132 | while (counter < length) {
|
133 | value = string.charCodeAt(counter++);
|
134 | if (value >= 0xD800 && value <= 0xDBFF && counter < length) {
|
135 | // high surrogate, and there is a next character
|
136 | extra = string.charCodeAt(counter++);
|
137 | if ((extra & 0xFC00) == 0xDC00) { // low surrogate
|
138 | output.push(((value & 0x3FF) << 10) + (extra & 0x3FF) + 0x10000);
|
139 | } else {
|
140 | // unmatched surrogate; only append this code unit, in case the next
|
141 | // code unit is the high surrogate of a surrogate pair
|
142 | output.push(value);
|
143 | counter--;
|
144 | }
|
145 | } else {
|
146 | output.push(value);
|
147 | }
|
148 | }
|
149 | return output;
|
150 | }
|
151 |
|
152 | /**
|
153 | * Creates a string based on an array of numeric code points.
|
154 | * @see `punycode.ucs2.decode`
|
155 | * @memberOf punycode.ucs2
|
156 | * @name encode
|
157 | * @param {Array} codePoints The array of numeric code points.
|
158 | * @returns {String} The new Unicode string (UCS-2).
|
159 | */
|
160 | function ucs2encode(array) {
|
161 | return map(array, function(value) {
|
162 | var output = '';
|
163 | if (value > 0xFFFF) {
|
164 | value -= 0x10000;
|
165 | output += stringFromCharCode(value >>> 10 & 0x3FF | 0xD800);
|
166 | value = 0xDC00 | value & 0x3FF;
|
167 | }
|
168 | output += stringFromCharCode(value);
|
169 | return output;
|
170 | }).join('');
|
171 | }
|
172 |
|
173 | /**
|
174 | * Converts a basic code point into a digit/integer.
|
175 | * @see `digitToBasic()`
|
176 | * @private
|
177 | * @param {Number} codePoint The basic numeric code point value.
|
178 | * @returns {Number} The numeric value of a basic code point (for use in
|
179 | * representing integers) in the range `0` to `base - 1`, or `base` if
|
180 | * the code point does not represent a value.
|
181 | */
|
182 | function basicToDigit(codePoint) {
|
183 | if (codePoint - 48 < 10) {
|
184 | return codePoint - 22;
|
185 | }
|
186 | if (codePoint - 65 < 26) {
|
187 | return codePoint - 65;
|
188 | }
|
189 | if (codePoint - 97 < 26) {
|
190 | return codePoint - 97;
|
191 | }
|
192 | return base;
|
193 | }
|
194 |
|
195 | /**
|
196 | * Converts a digit/integer into a basic code point.
|
197 | * @see `basicToDigit()`
|
198 | * @private
|
199 | * @param {Number} digit The numeric value of a basic code point.
|
200 | * @returns {Number} The basic code point whose value (when used for
|
201 | * representing integers) is `digit`, which needs to be in the range
|
202 | * `0` to `base - 1`. If `flag` is non-zero, the uppercase form is
|
203 | * used; else, the lowercase form is used. The behavior is undefined
|
204 | * if `flag` is non-zero and `digit` has no uppercase form.
|
205 | */
|
206 | function digitToBasic(digit, flag) {
|
207 | // 0..25 map to ASCII a..z or A..Z
|
208 | // 26..35 map to ASCII 0..9
|
209 | return digit + 22 + 75 * (digit < 26) - ((flag != 0) << 5);
|
210 | }
|
211 |
|
212 | /**
|
213 | * Bias adaptation function as per section 3.4 of RFC 3492.
|
214 | * http://tools.ietf.org/html/rfc3492#section-3.4
|
215 | * @private
|
216 | */
|
217 | function adapt(delta, numPoints, firstTime) {
|
218 | var k = 0;
|
219 | delta = firstTime ? floor(delta / damp) : delta >> 1;
|
220 | delta += floor(delta / numPoints);
|
221 | for (/* no initialization */; delta > baseMinusTMin * tMax >> 1; k += base) {
|
222 | delta = floor(delta / baseMinusTMin);
|
223 | }
|
224 | return floor(k + (baseMinusTMin + 1) * delta / (delta + skew));
|
225 | }
|
226 |
|
227 | /**
|
228 | * Converts a Punycode string of ASCII-only symbols to a string of Unicode
|
229 | * symbols.
|
230 | * @memberOf punycode
|
231 | * @param {String} input The Punycode string of ASCII-only symbols.
|
232 | * @returns {String} The resulting string of Unicode symbols.
|
233 | */
|
234 | function decode(input) {
|
235 | // Don't use UCS-2
|
236 | var output = [],
|
237 | inputLength = input.length,
|
238 | out,
|
239 | i = 0,
|
240 | n = initialN,
|
241 | bias = initialBias,
|
242 | basic,
|
243 | j,
|
244 | index,
|
245 | oldi,
|
246 | w,
|
247 | k,
|
248 | digit,
|
249 | t,
|
250 | /** Cached calculation results */
|
251 | baseMinusT;
|
252 |
|
253 | // Handle the basic code points: let `basic` be the number of input code
|
254 | // points before the last delimiter, or `0` if there is none, then copy
|
255 | // the first basic code points to the output.
|
256 |
|
257 | basic = input.lastIndexOf(delimiter);
|
258 | if (basic < 0) {
|
259 | basic = 0;
|
260 | }
|
261 |
|
262 | for (j = 0; j < basic; ++j) {
|
263 | // if it's not a basic code point
|
264 | if (input.charCodeAt(j) >= 0x80) {
|
265 | error('not-basic');
|
266 | }
|
267 | output.push(input.charCodeAt(j));
|
268 | }
|
269 |
|
270 | // Main decoding loop: start just after the last delimiter if any basic code
|
271 | // points were copied; start at the beginning otherwise.
|
272 |
|
273 | for (index = basic > 0 ? basic + 1 : 0; index < inputLength; /* no final expression */) {
|
274 |
|
275 | // `index` is the index of the next character to be consumed.
|
276 | // Decode a generalized variable-length integer into `delta`,
|
277 | // which gets added to `i`. The overflow checking is easier
|
278 | // if we increase `i` as we go, then subtract off its starting
|
279 | // value at the end to obtain `delta`.
|
280 | for (oldi = i, w = 1, k = base; /* no condition */; k += base) {
|
281 |
|
282 | if (index >= inputLength) {
|
283 | error('invalid-input');
|
284 | }
|
285 |
|
286 | digit = basicToDigit(input.charCodeAt(index++));
|
287 |
|
288 | if (digit >= base || digit > floor((maxInt - i) / w)) {
|
289 | error('overflow');
|
290 | }
|
291 |
|
292 | i += digit * w;
|
293 | t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias);
|
294 |
|
295 | if (digit < t) {
|
296 | break;
|
297 | }
|
298 |
|
299 | baseMinusT = base - t;
|
300 | if (w > floor(maxInt / baseMinusT)) {
|
301 | error('overflow');
|
302 | }
|
303 |
|
304 | w *= baseMinusT;
|
305 |
|
306 | }
|
307 |
|
308 | out = output.length + 1;
|
309 | bias = adapt(i - oldi, out, oldi == 0);
|
310 |
|
311 | // `i` was supposed to wrap around from `out` to `0`,
|
312 | // incrementing `n` each time, so we'll fix that now:
|
313 | if (floor(i / out) > maxInt - n) {
|
314 | error('overflow');
|
315 | }
|
316 |
|
317 | n += floor(i / out);
|
318 | i %= out;
|
319 |
|
320 | // Insert `n` at position `i` of the output
|
321 | output.splice(i++, 0, n);
|
322 |
|
323 | }
|
324 |
|
325 | return ucs2encode(output);
|
326 | }
|
327 |
|
328 | /**
|
329 | * Converts a string of Unicode symbols (e.g. a domain name label) to a
|
330 | * Punycode string of ASCII-only symbols.
|
331 | * @memberOf punycode
|
332 | * @param {String} input The string of Unicode symbols.
|
333 | * @returns {String} The resulting Punycode string of ASCII-only symbols.
|
334 | */
|
335 | function encode(input) {
|
336 | var n,
|
337 | delta,
|
338 | handledCPCount,
|
339 | basicLength,
|
340 | bias,
|
341 | j,
|
342 | m,
|
343 | q,
|
344 | k,
|
345 | t,
|
346 | currentValue,
|
347 | output = [],
|
348 | /** `inputLength` will hold the number of code points in `input`. */
|
349 | inputLength,
|
350 | /** Cached calculation results */
|
351 | handledCPCountPlusOne,
|
352 | baseMinusT,
|
353 | qMinusT;
|
354 |
|
355 | // Convert the input in UCS-2 to Unicode
|
356 | input = ucs2decode(input);
|
357 |
|
358 | // Cache the length
|
359 | inputLength = input.length;
|
360 |
|
361 | // Initialize the state
|
362 | n = initialN;
|
363 | delta = 0;
|
364 | bias = initialBias;
|
365 |
|
366 | // Handle the basic code points
|
367 | for (j = 0; j < inputLength; ++j) {
|
368 | currentValue = input[j];
|
369 | if (currentValue < 0x80) {
|
370 | output.push(stringFromCharCode(currentValue));
|
371 | }
|
372 | }
|
373 |
|
374 | handledCPCount = basicLength = output.length;
|
375 |
|
376 | // `handledCPCount` is the number of code points that have been handled;
|
377 | // `basicLength` is the number of basic code points.
|
378 |
|
379 | // Finish the basic string - if it is not empty - with a delimiter
|
380 | if (basicLength) {
|
381 | output.push(delimiter);
|
382 | }
|
383 |
|
384 | // Main encoding loop:
|
385 | while (handledCPCount < inputLength) {
|
386 |
|
387 | // All non-basic code points < n have been handled already. Find the next
|
388 | // larger one:
|
389 | for (m = maxInt, j = 0; j < inputLength; ++j) {
|
390 | currentValue = input[j];
|
391 | if (currentValue >= n && currentValue < m) {
|
392 | m = currentValue;
|
393 | }
|
394 | }
|
395 |
|
396 | // Increase `delta` enough to advance the decoder's <n,i> state to <m,0>,
|
397 | // but guard against overflow
|
398 | handledCPCountPlusOne = handledCPCount + 1;
|
399 | if (m - n > floor((maxInt - delta) / handledCPCountPlusOne)) {
|
400 | error('overflow');
|
401 | }
|
402 |
|
403 | delta += (m - n) * handledCPCountPlusOne;
|
404 | n = m;
|
405 |
|
406 | for (j = 0; j < inputLength; ++j) {
|
407 | currentValue = input[j];
|
408 |
|
409 | if (currentValue < n && ++delta > maxInt) {
|
410 | error('overflow');
|
411 | }
|
412 |
|
413 | if (currentValue == n) {
|
414 | // Represent delta as a generalized variable-length integer
|
415 | for (q = delta, k = base; /* no condition */; k += base) {
|
416 | t = k <= bias ? tMin : (k >= bias + tMax ? tMax : k - bias);
|
417 | if (q < t) {
|
418 | break;
|
419 | }
|
420 | qMinusT = q - t;
|
421 | baseMinusT = base - t;
|
422 | output.push(
|
423 | stringFromCharCode(digitToBasic(t + qMinusT % baseMinusT, 0))
|
424 | );
|
425 | q = floor(qMinusT / baseMinusT);
|
426 | }
|
427 |
|
428 | output.push(stringFromCharCode(digitToBasic(q, 0)));
|
429 | bias = adapt(delta, handledCPCountPlusOne, handledCPCount == basicLength);
|
430 | delta = 0;
|
431 | ++handledCPCount;
|
432 | }
|
433 | }
|
434 |
|
435 | ++delta;
|
436 | ++n;
|
437 |
|
438 | }
|
439 | return output.join('');
|
440 | }
|
441 |
|
442 | /**
|
443 | * Converts a Punycode string representing a domain name or an email address
|
444 | * to Unicode. Only the Punycoded parts of the input will be converted, i.e.
|
445 | * it doesn't matter if you call it on a string that has already been
|
446 | * converted to Unicode.
|
447 | * @memberOf punycode
|
448 | * @param {String} input The Punycoded domain name or email address to
|
449 | * convert to Unicode.
|
450 | * @returns {String} The Unicode representation of the given Punycode
|
451 | * string.
|
452 | */
|
453 | function toUnicode(input) {
|
454 | return mapDomain(input, function(string) {
|
455 | return regexPunycode.test(string)
|
456 | ? decode(string.slice(4).toLowerCase())
|
457 | : string;
|
458 | });
|
459 | }
|
460 |
|
461 | /**
|
462 | * Converts a Unicode string representing a domain name or an email address to
|
463 | * Punycode. Only the non-ASCII parts of the domain name will be converted,
|
464 | * i.e. it doesn't matter if you call it with a domain that's already in
|
465 | * ASCII.
|
466 | * @memberOf punycode
|
467 | * @param {String} input The domain name or email address to convert, as a
|
468 | * Unicode string.
|
469 | * @returns {String} The Punycode representation of the given domain name or
|
470 | * email address.
|
471 | */
|
472 | function toASCII(input) {
|
473 | return mapDomain(input, function(string) {
|
474 | return regexNonASCII.test(string)
|
475 | ? 'xn--' + encode(string)
|
476 | : string;
|
477 | });
|
478 | }
|
479 |
|
480 | /*--------------------------------------------------------------------------*/
|
481 |
|
482 | /** Define the public API */
|
483 | punycode = {
|
484 | /**
|
485 | * A string representing the current Punycode.js version number.
|
486 | * @memberOf punycode
|
487 | * @type String
|
488 | */
|
489 | 'version': '1.3.2',
|
490 | /**
|
491 | * An object of methods to convert from JavaScript's internal character
|
492 | * representation (UCS-2) to Unicode code points, and back.
|
493 | * @see <https://mathiasbynens.be/notes/javascript-encoding>
|
494 | * @memberOf punycode
|
495 | * @type Object
|
496 | */
|
497 | 'ucs2': {
|
498 | 'decode': ucs2decode,
|
499 | 'encode': ucs2encode
|
500 | },
|
501 | 'decode': decode,
|
502 | 'encode': encode,
|
503 | 'toASCII': toASCII,
|
504 | 'toUnicode': toUnicode
|
505 | };
|
506 |
|
507 | /** Expose `punycode` */
|
508 | // Some AMD build optimizers, like r.js, check for specific condition patterns
|
509 | // like the following:
|
510 | if (
|
511 | typeof define == 'function' &&
|
512 | typeof define.amd == 'object' &&
|
513 | define.amd
|
514 | ) {
|
515 | define('punycode', function() {
|
516 | return punycode;
|
517 | });
|
518 | } else if (freeExports && freeModule) {
|
519 | if (module.exports == freeExports) { // in Node.js or RingoJS v0.8.0+
|
520 | freeModule.exports = punycode;
|
521 | } else { // in Narwhal or RingoJS v0.7.0-
|
522 | for (key in punycode) {
|
523 | punycode.hasOwnProperty(key) && (freeExports[key] = punycode[key]);
|
524 | }
|
525 | }
|
526 | } else { // in Rhino or a web browser
|
527 | root.punycode = punycode;
|
528 | }
|
529 |
|
530 | }(this));
|