aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/node_modules/undici/lib/fetch/dataURL.js
blob: 7b6a606106dd69561d196c3064ed0382e662217f (plain) (blame)
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
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
const assert = require('assert')
const { atob } = require('buffer')
const { isomorphicDecode } = require('./util')

const encoder = new TextEncoder()

/**
 * @see https://mimesniff.spec.whatwg.org/#http-token-code-point
 */
const HTTP_TOKEN_CODEPOINTS = /^[!#$%&'*+-.^_|~A-Za-z0-9]+$/
const HTTP_WHITESPACE_REGEX = /(\u000A|\u000D|\u0009|\u0020)/ // eslint-disable-line
/**
 * @see https://mimesniff.spec.whatwg.org/#http-quoted-string-token-code-point
 */
const HTTP_QUOTED_STRING_TOKENS = /[\u0009|\u0020-\u007E|\u0080-\u00FF]/ // eslint-disable-line

// https://fetch.spec.whatwg.org/#data-url-processor
/** @param {URL} dataURL */
function dataURLProcessor (dataURL) {
  // 1. Assert: dataURL’s scheme is "data".
  assert(dataURL.protocol === 'data:')

  // 2. Let input be the result of running the URL
  // serializer on dataURL with exclude fragment
  // set to true.
  let input = URLSerializer(dataURL, true)

  // 3. Remove the leading "data:" string from input.
  input = input.slice(5)

  // 4. Let position point at the start of input.
  const position = { position: 0 }

  // 5. Let mimeType be the result of collecting a
  // sequence of code points that are not equal
  // to U+002C (,), given position.
  let mimeType = collectASequenceOfCodePointsFast(
    ',',
    input,
    position
  )

  // 6. Strip leading and trailing ASCII whitespace
  // from mimeType.
  // Undici implementation note: we need to store the
  // length because if the mimetype has spaces removed,
  // the wrong amount will be sliced from the input in
  // step #9
  const mimeTypeLength = mimeType.length
  mimeType = removeASCIIWhitespace(mimeType, true, true)

  // 7. If position is past the end of input, then
  // return failure
  if (position.position >= input.length) {
    return 'failure'
  }

  // 8. Advance position by 1.
  position.position++

  // 9. Let encodedBody be the remainder of input.
  const encodedBody = input.slice(mimeTypeLength + 1)

  // 10. Let body be the percent-decoding of encodedBody.
  let body = stringPercentDecode(encodedBody)

  // 11. If mimeType ends with U+003B (;), followed by
  // zero or more U+0020 SPACE, followed by an ASCII
  // case-insensitive match for "base64", then:
  if (/;(\u0020){0,}base64$/i.test(mimeType)) {
    // 1. Let stringBody be the isomorphic decode of body.
    const stringBody = isomorphicDecode(body)

    // 2. Set body to the forgiving-base64 decode of
    // stringBody.
    body = forgivingBase64(stringBody)

    // 3. If body is failure, then return failure.
    if (body === 'failure') {
      return 'failure'
    }

    // 4. Remove the last 6 code points from mimeType.
    mimeType = mimeType.slice(0, -6)

    // 5. Remove trailing U+0020 SPACE code points from mimeType,
    // if any.
    mimeType = mimeType.replace(/(\u0020)+$/, '')

    // 6. Remove the last U+003B (;) code point from mimeType.
    mimeType = mimeType.slice(0, -1)
  }

  // 12. If mimeType starts with U+003B (;), then prepend
  // "text/plain" to mimeType.
  if (mimeType.startsWith(';')) {
    mimeType = 'text/plain' + mimeType
  }

  // 13. Let mimeTypeRecord be the result of parsing
  // mimeType.
  let mimeTypeRecord = parseMIMEType(mimeType)

  // 14. If mimeTypeRecord is failure, then set
  // mimeTypeRecord to text/plain;charset=US-ASCII.
  if (mimeTypeRecord === 'failure') {
    mimeTypeRecord = parseMIMEType('text/plain;charset=US-ASCII')
  }

  // 15. Return a new data: URL struct whose MIME
  // type is mimeTypeRecord and body is body.
  // https://fetch.spec.whatwg.org/#data-url-struct
  return { mimeType: mimeTypeRecord, body }
}

// https://url.spec.whatwg.org/#concept-url-serializer
/**
 * @param {URL} url
 * @param {boolean} excludeFragment
 */
function URLSerializer (url, excludeFragment = false) {
  if (!excludeFragment) {
    return url.href
  }

  const href = url.href
  const hashLength = url.hash.length

  return hashLength === 0 ? href : href.substring(0, href.length - hashLength)
}

// https://infra.spec.whatwg.org/#collect-a-sequence-of-code-points
/**
 * @param {(char: string) => boolean} condition
 * @param {string} input
 * @param {{ position: number }} position
 */
function collectASequenceOfCodePoints (condition, input, position) {
  // 1. Let result be the empty string.
  let result = ''

  // 2. While position doesn’t point past the end of input and the
  // code point at position within input meets the condition condition:
  while (position.position < input.length && condition(input[position.position])) {
    // 1. Append that code point to the end of result.
    result += input[position.position]

    // 2. Advance position by 1.
    position.position++
  }

  // 3. Return result.
  return result
}

/**
 * A faster collectASequenceOfCodePoints that only works when comparing a single character.
 * @param {string} char
 * @param {string} input
 * @param {{ position: number }} position
 */
function collectASequenceOfCodePointsFast (char, input, position) {
  const idx = input.indexOf(char, position.position)
  const start = position.position

  if (idx === -1) {
    position.position = input.length
    return input.slice(start)
  }

  position.position = idx
  return input.slice(start, position.position)
}

// https://url.spec.whatwg.org/#string-percent-decode
/** @param {string} input */
function stringPercentDecode (input) {
  // 1. Let bytes be the UTF-8 encoding of input.
  const bytes = encoder.encode(input)

  // 2. Return the percent-decoding of bytes.
  return percentDecode(bytes)
}

// https://url.spec.whatwg.org/#percent-decode
/** @param {Uint8Array} input */
function percentDecode (input) {
  // 1. Let output be an empty byte sequence.
  /** @type {number[]} */
  const output = []

  // 2. For each byte byte in input:
  for (let i = 0; i < input.length; i++) {
    const byte = input[i]

    // 1. If byte is not 0x25 (%), then append byte to output.
    if (byte !== 0x25) {
      output.push(byte)

    // 2. Otherwise, if byte is 0x25 (%) and the next two bytes
    // after byte in input are not in the ranges
    // 0x30 (0) to 0x39 (9), 0x41 (A) to 0x46 (F),
    // and 0x61 (a) to 0x66 (f), all inclusive, append byte
    // to output.
    } else if (
      byte === 0x25 &&
      !/^[0-9A-Fa-f]{2}$/i.test(String.fromCharCode(input[i + 1], input[i + 2]))
    ) {
      output.push(0x25)

    // 3. Otherwise:
    } else {
      // 1. Let bytePoint be the two bytes after byte in input,
      // decoded, and then interpreted as hexadecimal number.
      const nextTwoBytes = String.fromCharCode(input[i + 1], input[i + 2])
      const bytePoint = Number.parseInt(nextTwoBytes, 16)

      // 2. Append a byte whose value is bytePoint to output.
      output.push(bytePoint)

      // 3. Skip the next two bytes in input.
      i += 2
    }
  }

  // 3. Return output.
  return Uint8Array.from(output)
}

// https://mimesniff.spec.whatwg.org/#parse-a-mime-type
/** @param {string} input */
function parseMIMEType (input) {
  // 1. Remove any leading and trailing HTTP whitespace
  // from input.
  input = removeHTTPWhitespace(input, true, true)

  // 2. Let position be a position variable for input,
  // initially pointing at the start of input.
  const position = { position: 0 }

  // 3. Let type be the result of collecting a sequence
  // of code points that are not U+002F (/) from
  // input, given position.
  const type = collectASequenceOfCodePointsFast(
    '/',
    input,
    position
  )

  // 4. If type is the empty string or does not solely
  // contain HTTP token code points, then return failure.
  // https://mimesniff.spec.whatwg.org/#http-token-code-point
  if (type.length === 0 || !HTTP_TOKEN_CODEPOINTS.test(type)) {
    return 'failure'
  }

  // 5. If position is past the end of input, then return
  // failure
  if (position.position > input.length) {
    return 'failure'
  }

  // 6. Advance position by 1. (This skips past U+002F (/).)
  position.position++

  // 7. Let subtype be the result of collecting a sequence of
  // code points that are not U+003B (;) from input, given
  // position.
  let subtype = collectASequenceOfCodePointsFast(
    ';',
    input,
    position
  )

  // 8. Remove any trailing HTTP whitespace from subtype.
  subtype = removeHTTPWhitespace(subtype, false, true)

  // 9. If subtype is the empty string or does not solely
  // contain HTTP token code points, then return failure.
  if (subtype.length === 0 || !HTTP_TOKEN_CODEPOINTS.test(subtype)) {
    return 'failure'
  }

  const typeLowercase = type.toLowerCase()
  const subtypeLowercase = subtype.toLowerCase()

  // 10. Let mimeType be a new MIME type record whose type
  // is type, in ASCII lowercase, and subtype is subtype,
  // in ASCII lowercase.
  // https://mimesniff.spec.whatwg.org/#mime-type
  const mimeType = {
    type: typeLowercase,
    subtype: subtypeLowercase,
    /** @type {Map<string, string>} */
    parameters: new Map(),
    // https://mimesniff.spec.whatwg.org/#mime-type-essence
    essence: `${typeLowercase}/${subtypeLowercase}`
  }

  // 11. While position is not past the end of input:
  while (position.position < input.length) {
    // 1. Advance position by 1. (This skips past U+003B (;).)
    position.position++

    // 2. Collect a sequence of code points that are HTTP
    // whitespace from input given position.
    collectASequenceOfCodePoints(
      // https://fetch.spec.whatwg.org/#http-whitespace
      char => HTTP_WHITESPACE_REGEX.test(char),
      input,
      position
    )

    // 3. Let parameterName be the result of collecting a
    // sequence of code points that are not U+003B (;)
    // or U+003D (=) from input, given position.
    let parameterName = collectASequenceOfCodePoints(
      (char) => char !== ';' && char !== '=',
      input,
      position
    )

    // 4. Set parameterName to parameterName, in ASCII
    // lowercase.
    parameterName = parameterName.toLowerCase()

    // 5. If position is not past the end of input, then:
    if (position.position < input.length) {
      // 1. If the code point at position within input is
      // U+003B (;), then continue.
      if (input[position.position] === ';') {
        continue
      }

      // 2. Advance position by 1. (This skips past U+003D (=).)
      position.position++
    }

    // 6. If position is past the end of input, then break.
    if (position.position > input.length) {
      break
    }

    // 7. Let parameterValue be null.
    let parameterValue = null

    // 8. If the code point at position within input is
    // U+0022 ("), then:
    if (input[position.position] === '"') {
      // 1. Set parameterValue to the result of collecting
      // an HTTP quoted string from input, given position
      // and the extract-value flag.
      parameterValue = collectAnHTTPQuotedString(input, position, true)

      // 2. Collect a sequence of code points that are not
      // U+003B (;) from input, given position.
      collectASequenceOfCodePointsFast(
        ';',
        input,
        position
      )

    // 9. Otherwise:
    } else {
      // 1. Set parameterValue to the result of collecting
      // a sequence of code points that are not U+003B (;)
      // from input, given position.
      parameterValue = collectASequenceOfCodePointsFast(
        ';',
        input,
        position
      )

      // 2. Remove any trailing HTTP whitespace from parameterValue.
      parameterValue = removeHTTPWhitespace(parameterValue, false, true)

      // 3. If parameterValue is the empty string, then continue.
      if (parameterValue.length === 0) {
        continue
      }
    }

    // 10. If all of the following are true
    // - parameterName is not the empty string
    // - parameterName solely contains HTTP token code points
    // - parameterValue solely contains HTTP quoted-string token code points
    // - mimeType’s parameters[parameterName] does not exist
    // then set mimeType’s parameters[parameterName] to parameterValue.
    if (
      parameterName.length !== 0 &&
      HTTP_TOKEN_CODEPOINTS.test(parameterName) &&
      (parameterValue.length === 0 || HTTP_QUOTED_STRING_TOKENS.test(parameterValue)) &&
      !mimeType.parameters.has(parameterName)
    ) {
      mimeType.parameters.set(parameterName, parameterValue)
    }
  }

  // 12. Return mimeType.
  return mimeType
}

// https://infra.spec.whatwg.org/#forgiving-base64-decode
/** @param {string} data */
function forgivingBase64 (data) {
  // 1. Remove all ASCII whitespace from data.
  data = data.replace(/[\u0009\u000A\u000C\u000D\u0020]/g, '')  // eslint-disable-line

  // 2. If data’s code point length divides by 4 leaving
  // no remainder, then:
  if (data.length % 4 === 0) {
    // 1. If data ends with one or two U+003D (=) code points,
    // then remove them from data.
    data = data.replace(/=?=$/, '')
  }

  // 3. If data’s code point length divides by 4 leaving
  // a remainder of 1, then return failure.
  if (data.length % 4 === 1) {
    return 'failure'
  }

  // 4. If data contains a code point that is not one of
  //  U+002B (+)
  //  U+002F (/)
  //  ASCII alphanumeric
  // then return failure.
  if (/[^+/0-9A-Za-z]/.test(data)) {
    return 'failure'
  }

  const binary = atob(data)
  const bytes = new Uint8Array(binary.length)

  for (let byte = 0; byte < binary.length; byte++) {
    bytes[byte] = binary.charCodeAt(byte)
  }

  return bytes
}

// https://fetch.spec.whatwg.org/#collect-an-http-quoted-string
// tests: https://fetch.spec.whatwg.org/#example-http-quoted-string
/**
 * @param {string} input
 * @param {{ position: number }} position
 * @param {boolean?} extractValue
 */
function collectAnHTTPQuotedString (input, position, extractValue) {
  // 1. Let positionStart be position.
  const positionStart = position.position

  // 2. Let value be the empty string.
  let value = ''

  // 3. Assert: the code point at position within input
  // is U+0022 (").
  assert(input[position.position] === '"')

  // 4. Advance position by 1.
  position.position++

  // 5. While true:
  while (true) {
    // 1. Append the result of collecting a sequence of code points
    // that are not U+0022 (") or U+005C (\) from input, given
    // position, to value.
    value += collectASequenceOfCodePoints(
      (char) => char !== '"' && char !== '\\',
      input,
      position
    )

    // 2. If position is past the end of input, then break.
    if (position.position >= input.length) {
      break
    }

    // 3. Let quoteOrBackslash be the code point at position within
    // input.
    const quoteOrBackslash = input[position.position]

    // 4. Advance position by 1.
    position.position++

    // 5. If quoteOrBackslash is U+005C (\), then:
    if (quoteOrBackslash === '\\') {
      // 1. If position is past the end of input, then append
      // U+005C (\) to value and break.
      if (position.position >= input.length) {
        value += '\\'
        break
      }

      // 2. Append the code point at position within input to value.
      value += input[position.position]

      // 3. Advance position by 1.
      position.position++

    // 6. Otherwise:
    } else {
      // 1. Assert: quoteOrBackslash is U+0022 (").
      assert(quoteOrBackslash === '"')

      // 2. Break.
      break
    }
  }

  // 6. If the extract-value flag is set, then return value.
  if (extractValue) {
    return value
  }

  // 7. Return the code points from positionStart to position,
  // inclusive, within input.
  return input.slice(positionStart, position.position)
}

/**
 * @see https://mimesniff.spec.whatwg.org/#serialize-a-mime-type
 */
function serializeAMimeType (mimeType) {
  assert(mimeType !== 'failure')
  const { parameters, essence } = mimeType

  // 1. Let serialization be the concatenation of mimeType’s
  //    type, U+002F (/), and mimeType’s subtype.
  let serialization = essence

  // 2. For each name → value of mimeType’s parameters:
  for (let [name, value] of parameters.entries()) {
    // 1. Append U+003B (;) to serialization.
    serialization += ';'

    // 2. Append name to serialization.
    serialization += name

    // 3. Append U+003D (=) to serialization.
    serialization += '='

    // 4. If value does not solely contain HTTP token code
    //    points or value is the empty string, then:
    if (!HTTP_TOKEN_CODEPOINTS.test(value)) {
      // 1. Precede each occurence of U+0022 (") or
      //    U+005C (\) in value with U+005C (\).
      value = value.replace(/(\\|")/g, '\\$1')

      // 2. Prepend U+0022 (") to value.
      value = '"' + value

      // 3. Append U+0022 (") to value.
      value += '"'
    }

    // 5. Append value to serialization.
    serialization += value
  }

  // 3. Return serialization.
  return serialization
}

/**
 * @see https://fetch.spec.whatwg.org/#http-whitespace
 * @param {string} char
 */
function isHTTPWhiteSpace (char) {
  return char === '\r' || char === '\n' || char === '\t' || char === ' '
}

/**
 * @see https://fetch.spec.whatwg.org/#http-whitespace
 * @param {string} str
 */
function removeHTTPWhitespace (str, leading = true, trailing = true) {
  let lead = 0
  let trail = str.length - 1

  if (leading) {
    for (; lead < str.length && isHTTPWhiteSpace(str[lead]); lead++);
  }

  if (trailing) {
    for (; trail > 0 && isHTTPWhiteSpace(str[trail]); trail--);
  }

  return str.slice(lead, trail + 1)
}

/**
 * @see https://infra.spec.whatwg.org/#ascii-whitespace
 * @param {string} char
 */
function isASCIIWhitespace (char) {
  return char === '\r' || char === '\n' || char === '\t' || char === '\f' || char === ' '
}

/**
 * @see https://infra.spec.whatwg.org/#strip-leading-and-trailing-ascii-whitespace
 */
function removeASCIIWhitespace (str, leading = true, trailing = true) {
  let lead = 0
  let trail = str.length - 1

  if (leading) {
    for (; lead < str.length && isASCIIWhitespace(str[lead]); lead++);
  }

  if (trailing) {
    for (; trail > 0 && isASCIIWhitespace(str[trail]); trail--);
  }

  return str.slice(lead, trail + 1)
}

module.exports = {
  dataURLProcessor,
  URLSerializer,
  collectASequenceOfCodePoints,
  collectASequenceOfCodePointsFast,
  stringPercentDecode,
  parseMIMEType,
  collectAnHTTPQuotedString,
  serializeAMimeType
}