summaryrefslogtreecommitdiff
path: root/node_modules/mdurl/build/index.cjs.js
blob: bfa6f01456ade6e37e51d9fd4ef49ca2b18e80bb (plain)
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
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
'use strict';

/* eslint-disable no-bitwise */

const decodeCache = {};

function getDecodeCache (exclude) {
  let cache = decodeCache[exclude];
  if (cache) { return cache }

  cache = decodeCache[exclude] = [];

  for (let i = 0; i < 128; i++) {
    const ch = String.fromCharCode(i);
    cache.push(ch);
  }

  for (let i = 0; i < exclude.length; i++) {
    const ch = exclude.charCodeAt(i);
    cache[ch] = '%' + ('0' + ch.toString(16).toUpperCase()).slice(-2);
  }

  return cache
}

// Decode percent-encoded string.
//
function decode (string, exclude) {
  if (typeof exclude !== 'string') {
    exclude = decode.defaultChars;
  }

  const cache = getDecodeCache(exclude);

  return string.replace(/(%[a-f0-9]{2})+/gi, function (seq) {
    let result = '';

    for (let i = 0, l = seq.length; i < l; i += 3) {
      const b1 = parseInt(seq.slice(i + 1, i + 3), 16);

      if (b1 < 0x80) {
        result += cache[b1];
        continue
      }

      if ((b1 & 0xE0) === 0xC0 && (i + 3 < l)) {
        // 110xxxxx 10xxxxxx
        const b2 = parseInt(seq.slice(i + 4, i + 6), 16);

        if ((b2 & 0xC0) === 0x80) {
          const chr = ((b1 << 6) & 0x7C0) | (b2 & 0x3F);

          if (chr < 0x80) {
            result += '\ufffd\ufffd';
          } else {
            result += String.fromCharCode(chr);
          }

          i += 3;
          continue
        }
      }

      if ((b1 & 0xF0) === 0xE0 && (i + 6 < l)) {
        // 1110xxxx 10xxxxxx 10xxxxxx
        const b2 = parseInt(seq.slice(i + 4, i + 6), 16);
        const b3 = parseInt(seq.slice(i + 7, i + 9), 16);

        if ((b2 & 0xC0) === 0x80 && (b3 & 0xC0) === 0x80) {
          const chr = ((b1 << 12) & 0xF000) | ((b2 << 6) & 0xFC0) | (b3 & 0x3F);

          if (chr < 0x800 || (chr >= 0xD800 && chr <= 0xDFFF)) {
            result += '\ufffd\ufffd\ufffd';
          } else {
            result += String.fromCharCode(chr);
          }

          i += 6;
          continue
        }
      }

      if ((b1 & 0xF8) === 0xF0 && (i + 9 < l)) {
        // 111110xx 10xxxxxx 10xxxxxx 10xxxxxx
        const b2 = parseInt(seq.slice(i + 4, i + 6), 16);
        const b3 = parseInt(seq.slice(i + 7, i + 9), 16);
        const b4 = parseInt(seq.slice(i + 10, i + 12), 16);

        if ((b2 & 0xC0) === 0x80 && (b3 & 0xC0) === 0x80 && (b4 & 0xC0) === 0x80) {
          let chr = ((b1 << 18) & 0x1C0000) | ((b2 << 12) & 0x3F000) | ((b3 << 6) & 0xFC0) | (b4 & 0x3F);

          if (chr < 0x10000 || chr > 0x10FFFF) {
            result += '\ufffd\ufffd\ufffd\ufffd';
          } else {
            chr -= 0x10000;
            result += String.fromCharCode(0xD800 + (chr >> 10), 0xDC00 + (chr & 0x3FF));
          }

          i += 9;
          continue
        }
      }

      result += '\ufffd';
    }

    return result
  })
}

decode.defaultChars = ';/?:@&=+$,#';
decode.componentChars = '';

const encodeCache = {};

// Create a lookup array where anything but characters in `chars` string
// and alphanumeric chars is percent-encoded.
//
function getEncodeCache (exclude) {
  let cache = encodeCache[exclude];
  if (cache) { return cache }

  cache = encodeCache[exclude] = [];

  for (let i = 0; i < 128; i++) {
    const ch = String.fromCharCode(i);

    if (/^[0-9a-z]$/i.test(ch)) {
      // always allow unencoded alphanumeric characters
      cache.push(ch);
    } else {
      cache.push('%' + ('0' + i.toString(16).toUpperCase()).slice(-2));
    }
  }

  for (let i = 0; i < exclude.length; i++) {
    cache[exclude.charCodeAt(i)] = exclude[i];
  }

  return cache
}

// Encode unsafe characters with percent-encoding, skipping already
// encoded sequences.
//
//  - string       - string to encode
//  - exclude      - list of characters to ignore (in addition to a-zA-Z0-9)
//  - keepEscaped  - don't encode '%' in a correct escape sequence (default: true)
//
function encode (string, exclude, keepEscaped) {
  if (typeof exclude !== 'string') {
    // encode(string, keepEscaped)
    keepEscaped = exclude;
    exclude = encode.defaultChars;
  }

  if (typeof keepEscaped === 'undefined') {
    keepEscaped = true;
  }

  const cache = getEncodeCache(exclude);
  let result = '';

  for (let i = 0, l = string.length; i < l; i++) {
    const code = string.charCodeAt(i);

    if (keepEscaped && code === 0x25 /* % */ && i + 2 < l) {
      if (/^[0-9a-f]{2}$/i.test(string.slice(i + 1, i + 3))) {
        result += string.slice(i, i + 3);
        i += 2;
        continue
      }
    }

    if (code < 128) {
      result += cache[code];
      continue
    }

    if (code >= 0xD800 && code <= 0xDFFF) {
      if (code >= 0xD800 && code <= 0xDBFF && i + 1 < l) {
        const nextCode = string.charCodeAt(i + 1);
        if (nextCode >= 0xDC00 && nextCode <= 0xDFFF) {
          result += encodeURIComponent(string[i] + string[i + 1]);
          i++;
          continue
        }
      }
      result += '%EF%BF%BD';
      continue
    }

    result += encodeURIComponent(string[i]);
  }

  return result
}

encode.defaultChars = ";/?:@&=+$,-_.!~*'()#";
encode.componentChars = "-_.!~*'()";

function format (url) {
  let result = '';

  result += url.protocol || '';
  result += url.slashes ? '//' : '';
  result += url.auth ? url.auth + '@' : '';

  if (url.hostname && url.hostname.indexOf(':') !== -1) {
    // ipv6 address
    result += '[' + url.hostname + ']';
  } else {
    result += url.hostname || '';
  }

  result += url.port ? ':' + url.port : '';
  result += url.pathname || '';
  result += url.search || '';
  result += url.hash || '';

  return result
}

// Copyright Joyent, Inc. and other Node contributors.
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the
// "Software"), to deal in the Software without restriction, including
// without limitation the rights to use, copy, modify, merge, publish,
// distribute, sublicense, and/or sell copies of the Software, and to permit
// persons to whom the Software is furnished to do so, subject to the
// following conditions:
//
// The above copyright notice and this permission notice shall be included
// in all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
// OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
// MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
// NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
// DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
// OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
// USE OR OTHER DEALINGS IN THE SOFTWARE.

//
// Changes from joyent/node:
//
// 1. No leading slash in paths,
//    e.g. in `url.parse('http://foo?bar')` pathname is ``, not `/`
//
// 2. Backslashes are not replaced with slashes,
//    so `http:\\example.org\` is treated like a relative path
//
// 3. Trailing colon is treated like a part of the path,
//    i.e. in `http://example.org:foo` pathname is `:foo`
//
// 4. Nothing is URL-encoded in the resulting object,
//    (in joyent/node some chars in auth and paths are encoded)
//
// 5. `url.parse()` does not have `parseQueryString` argument
//
// 6. Removed extraneous result properties: `host`, `path`, `query`, etc.,
//    which can be constructed using other parts of the url.
//

function Url () {
  this.protocol = null;
  this.slashes = null;
  this.auth = null;
  this.port = null;
  this.hostname = null;
  this.hash = null;
  this.search = null;
  this.pathname = null;
}

// Reference: RFC 3986, RFC 1808, RFC 2396

// define these here so at least they only have to be
// compiled once on the first module load.
const protocolPattern = /^([a-z0-9.+-]+:)/i;
const portPattern = /:[0-9]*$/;

// Special case for a simple path URL
/* eslint-disable-next-line no-useless-escape */
const simplePathPattern = /^(\/\/?(?!\/)[^\?\s]*)(\?[^\s]*)?$/;

// RFC 2396: characters reserved for delimiting URLs.
// We actually just auto-escape these.
const delims = ['<', '>', '"', '`', ' ', '\r', '\n', '\t'];

// RFC 2396: characters not allowed for various reasons.
const unwise = ['{', '}', '|', '\\', '^', '`'].concat(delims);

// Allowed by RFCs, but cause of XSS attacks.  Always escape these.
const autoEscape = ['\''].concat(unwise);
// Characters that are never ever allowed in a hostname.
// Note that any invalid chars are also handled, but these
// are the ones that are *expected* to be seen, so we fast-path
// them.
const nonHostChars = ['%', '/', '?', ';', '#'].concat(autoEscape);
const hostEndingChars = ['/', '?', '#'];
const hostnameMaxLen = 255;
const hostnamePartPattern = /^[+a-z0-9A-Z_-]{0,63}$/;
const hostnamePartStart = /^([+a-z0-9A-Z_-]{0,63})(.*)$/;
// protocols that can allow "unsafe" and "unwise" chars.
// protocols that never have a hostname.
const hostlessProtocol = {
  javascript: true,
  'javascript:': true
};
// protocols that always contain a // bit.
const slashedProtocol = {
  http: true,
  https: true,
  ftp: true,
  gopher: true,
  file: true,
  'http:': true,
  'https:': true,
  'ftp:': true,
  'gopher:': true,
  'file:': true
};

function urlParse (url, slashesDenoteHost) {
  if (url && url instanceof Url) return url

  const u = new Url();
  u.parse(url, slashesDenoteHost);
  return u
}

Url.prototype.parse = function (url, slashesDenoteHost) {
  let lowerProto, hec, slashes;
  let rest = url;

  // trim before proceeding.
  // This is to support parse stuff like "  http://foo.com  \n"
  rest = rest.trim();

  if (!slashesDenoteHost && url.split('#').length === 1) {
    // Try fast path regexp
    const simplePath = simplePathPattern.exec(rest);
    if (simplePath) {
      this.pathname = simplePath[1];
      if (simplePath[2]) {
        this.search = simplePath[2];
      }
      return this
    }
  }

  let proto = protocolPattern.exec(rest);
  if (proto) {
    proto = proto[0];
    lowerProto = proto.toLowerCase();
    this.protocol = proto;
    rest = rest.substr(proto.length);
  }

  // figure out if it's got a host
  // user@server is *always* interpreted as a hostname, and url
  // resolution will treat //foo/bar as host=foo,path=bar because that's
  // how the browser resolves relative URLs.
  /* eslint-disable-next-line no-useless-escape */
  if (slashesDenoteHost || proto || rest.match(/^\/\/[^@\/]+@[^@\/]+/)) {
    slashes = rest.substr(0, 2) === '//';
    if (slashes && !(proto && hostlessProtocol[proto])) {
      rest = rest.substr(2);
      this.slashes = true;
    }
  }

  if (!hostlessProtocol[proto] &&
      (slashes || (proto && !slashedProtocol[proto]))) {
    // there's a hostname.
    // the first instance of /, ?, ;, or # ends the host.
    //
    // If there is an @ in the hostname, then non-host chars *are* allowed
    // to the left of the last @ sign, unless some host-ending character
    // comes *before* the @-sign.
    // URLs are obnoxious.
    //
    // ex:
    // http://a@b@c/ => user:a@b host:c
    // http://a@b?@c => user:a host:c path:/?@c

    // v0.12 TODO(isaacs): This is not quite how Chrome does things.
    // Review our test case against browsers more comprehensively.

    // find the first instance of any hostEndingChars
    let hostEnd = -1;
    for (let i = 0; i < hostEndingChars.length; i++) {
      hec = rest.indexOf(hostEndingChars[i]);
      if (hec !== -1 && (hostEnd === -1 || hec < hostEnd)) {
        hostEnd = hec;
      }
    }

    // at this point, either we have an explicit point where the
    // auth portion cannot go past, or the last @ char is the decider.
    let auth, atSign;
    if (hostEnd === -1) {
      // atSign can be anywhere.
      atSign = rest.lastIndexOf('@');
    } else {
      // atSign must be in auth portion.
      // http://a@b/c@d => host:b auth:a path:/c@d
      atSign = rest.lastIndexOf('@', hostEnd);
    }

    // Now we have a portion which is definitely the auth.
    // Pull that off.
    if (atSign !== -1) {
      auth = rest.slice(0, atSign);
      rest = rest.slice(atSign + 1);
      this.auth = auth;
    }

    // the host is the remaining to the left of the first non-host char
    hostEnd = -1;
    for (let i = 0; i < nonHostChars.length; i++) {
      hec = rest.indexOf(nonHostChars[i]);
      if (hec !== -1 && (hostEnd === -1 || hec < hostEnd)) {
        hostEnd = hec;
      }
    }
    // if we still have not hit it, then the entire thing is a host.
    if (hostEnd === -1) {
      hostEnd = rest.length;
    }

    if (rest[hostEnd - 1] === ':') { hostEnd--; }
    const host = rest.slice(0, hostEnd);
    rest = rest.slice(hostEnd);

    // pull out port.
    this.parseHost(host);

    // we've indicated that there is a hostname,
    // so even if it's empty, it has to be present.
    this.hostname = this.hostname || '';

    // if hostname begins with [ and ends with ]
    // assume that it's an IPv6 address.
    const ipv6Hostname = this.hostname[0] === '[' &&
        this.hostname[this.hostname.length - 1] === ']';

    // validate a little.
    if (!ipv6Hostname) {
      const hostparts = this.hostname.split(/\./);
      for (let i = 0, l = hostparts.length; i < l; i++) {
        const part = hostparts[i];
        if (!part) { continue }
        if (!part.match(hostnamePartPattern)) {
          let newpart = '';
          for (let j = 0, k = part.length; j < k; j++) {
            if (part.charCodeAt(j) > 127) {
              // we replace non-ASCII char with a temporary placeholder
              // we need this to make sure size of hostname is not
              // broken by replacing non-ASCII by nothing
              newpart += 'x';
            } else {
              newpart += part[j];
            }
          }
          // we test again with ASCII char only
          if (!newpart.match(hostnamePartPattern)) {
            const validParts = hostparts.slice(0, i);
            const notHost = hostparts.slice(i + 1);
            const bit = part.match(hostnamePartStart);
            if (bit) {
              validParts.push(bit[1]);
              notHost.unshift(bit[2]);
            }
            if (notHost.length) {
              rest = notHost.join('.') + rest;
            }
            this.hostname = validParts.join('.');
            break
          }
        }
      }
    }

    if (this.hostname.length > hostnameMaxLen) {
      this.hostname = '';
    }

    // strip [ and ] from the hostname
    // the host field still retains them, though
    if (ipv6Hostname) {
      this.hostname = this.hostname.substr(1, this.hostname.length - 2);
    }
  }

  // chop off from the tail first.
  const hash = rest.indexOf('#');
  if (hash !== -1) {
    // got a fragment string.
    this.hash = rest.substr(hash);
    rest = rest.slice(0, hash);
  }
  const qm = rest.indexOf('?');
  if (qm !== -1) {
    this.search = rest.substr(qm);
    rest = rest.slice(0, qm);
  }
  if (rest) { this.pathname = rest; }
  if (slashedProtocol[lowerProto] &&
      this.hostname && !this.pathname) {
    this.pathname = '';
  }

  return this
};

Url.prototype.parseHost = function (host) {
  let port = portPattern.exec(host);
  if (port) {
    port = port[0];
    if (port !== ':') {
      this.port = port.substr(1);
    }
    host = host.substr(0, host.length - port.length);
  }
  if (host) { this.hostname = host; }
};

exports.decode = decode;
exports.encode = encode;
exports.format = format;
exports.parse = urlParse;