/
utils.js
661 lines (567 loc) · 17.7 KB
/
utils.js
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
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
import { stringifyRequest, urlToRequest } from 'loader-utils';
function isASCIIWhitespace(character) {
return (
// Horizontal tab
character === '\u0009' ||
// New line
character === '\u000A' ||
// Form feed
character === '\u000C' ||
// Carriage return
character === '\u000D' ||
// Space
character === '\u0020'
);
}
// (Don't use \s, to avoid matching non-breaking space)
// eslint-disable-next-line no-control-regex
const regexLeadingSpaces = /^[ \t\n\r\u000c]+/;
// eslint-disable-next-line no-control-regex
const regexLeadingCommasOrSpaces = /^[, \t\n\r\u000c]+/;
// eslint-disable-next-line no-control-regex
const regexLeadingNotSpaces = /^[^ \t\n\r\u000c]+/;
const regexTrailingCommas = /[,]+$/;
const regexNonNegativeInteger = /^\d+$/;
// ( Positive or negative or unsigned integers or decimals, without or without exponents.
// Must include at least one digit.
// According to spec tests any decimal point must be followed by a digit.
// No leading plus sign is allowed.)
// https://html.spec.whatwg.org/multipage/infrastructure.html#valid-floating-point-number
const regexFloatingPoint = /^-?(?:[0-9]+|[0-9]*\.[0-9]+)(?:[eE][+-]?[0-9]+)?$/;
export function parseSrcset(input) {
// 1. Let input be the value passed to this algorithm.
const inputLength = input.length;
let url;
let descriptors;
let currentDescriptor;
let state;
let c;
// 2. Let position be a pointer into input, initially pointing at the start
// of the string.
let position = 0;
let startUrlPosition;
// eslint-disable-next-line consistent-return
function collectCharacters(regEx) {
let chars;
const match = regEx.exec(input.substring(position));
if (match) {
[chars] = match;
position += chars.length;
return chars;
}
}
// 3. Let candidates be an initially empty source set.
const candidates = [];
// 4. Splitting loop: Collect a sequence of characters that are space
// characters or U+002C COMMA characters. If any U+002C COMMA characters
// were collected, that is a parse error.
// eslint-disable-next-line no-constant-condition
while (true) {
collectCharacters(regexLeadingCommasOrSpaces);
// 5. If position is past the end of input, return candidates and abort these steps.
if (position >= inputLength) {
if (candidates.length === 0) {
throw new Error('Must contain one or more image candidate strings');
}
// (we're done, this is the sole return path)
return candidates;
}
// 6. Collect a sequence of characters that are not space characters,
// and let that be url.
startUrlPosition = position;
url = collectCharacters(regexLeadingNotSpaces);
// 7. Let descriptors be a new empty list.
descriptors = [];
// 8. If url ends with a U+002C COMMA character (,), follow these substeps:
// (1). Remove all trailing U+002C COMMA characters from url. If this removed
// more than one character, that is a parse error.
if (url.slice(-1) === ',') {
url = url.replace(regexTrailingCommas, '');
// (Jump ahead to step 9 to skip tokenization and just push the candidate).
parseDescriptors();
}
// Otherwise, follow these substeps:
else {
tokenize();
}
// 16. Return to the step labeled splitting loop.
}
/**
* Tokenizes descriptor properties prior to parsing
* Returns undefined.
*/
function tokenize() {
// 8.1. Descriptor tokenizer: Skip whitespace
collectCharacters(regexLeadingSpaces);
// 8.2. Let current descriptor be the empty string.
currentDescriptor = '';
// 8.3. Let state be in descriptor.
state = 'in descriptor';
// eslint-disable-next-line no-constant-condition
while (true) {
// 8.4. Let c be the character at position.
c = input.charAt(position);
// Do the following depending on the value of state.
// For the purpose of this step, "EOF" is a special character representing
// that position is past the end of input.
// In descriptor
if (state === 'in descriptor') {
// Do the following, depending on the value of c:
// Space character
// If current descriptor is not empty, append current descriptor to
// descriptors and let current descriptor be the empty string.
// Set state to after descriptor.
if (isASCIIWhitespace(c)) {
if (currentDescriptor) {
descriptors.push(currentDescriptor);
currentDescriptor = '';
state = 'after descriptor';
}
}
// U+002C COMMA (,)
// Advance position to the next character in input. If current descriptor
// is not empty, append current descriptor to descriptors. Jump to the step
// labeled descriptor parser.
else if (c === ',') {
position += 1;
if (currentDescriptor) {
descriptors.push(currentDescriptor);
}
parseDescriptors();
return;
}
// U+0028 LEFT PARENTHESIS (()
// Append c to current descriptor. Set state to in parens.
else if (c === '\u0028') {
currentDescriptor += c;
state = 'in parens';
}
// EOF
// If current descriptor is not empty, append current descriptor to
// descriptors. Jump to the step labeled descriptor parser.
else if (c === '') {
if (currentDescriptor) {
descriptors.push(currentDescriptor);
}
parseDescriptors();
return;
// Anything else
// Append c to current descriptor.
} else {
currentDescriptor += c;
}
}
// In parens
else if (state === 'in parens') {
// U+0029 RIGHT PARENTHESIS ())
// Append c to current descriptor. Set state to in descriptor.
if (c === ')') {
currentDescriptor += c;
state = 'in descriptor';
}
// EOF
// Append current descriptor to descriptors. Jump to the step labeled
// descriptor parser.
else if (c === '') {
descriptors.push(currentDescriptor);
parseDescriptors();
return;
}
// Anything else
// Append c to current descriptor.
else {
currentDescriptor += c;
}
}
// After descriptor
else if (state === 'after descriptor') {
// Do the following, depending on the value of c:
if (isASCIIWhitespace(c)) {
// Space character: Stay in this state.
}
// EOF: Jump to the step labeled descriptor parser.
else if (c === '') {
parseDescriptors();
return;
}
// Anything else
// Set state to in descriptor. Set position to the previous character in input.
else {
state = 'in descriptor';
position -= 1;
}
}
// Advance position to the next character in input.
position += 1;
}
}
/**
* Adds descriptor properties to a candidate, pushes to the candidates array
* @return undefined
*/
// Declared outside of the while loop so that it's only created once.
function parseDescriptors() {
// 9. Descriptor parser: Let error be no.
let pError = false;
// 10. Let width be absent.
// 11. Let density be absent.
// 12. Let future-compat-h be absent. (We're implementing it now as h)
let w;
let d;
let h;
let i;
const candidate = {};
let desc;
let lastChar;
let value;
let intVal;
let floatVal;
// 13. For each descriptor in descriptors, run the appropriate set of steps
// from the following list:
for (i = 0; i < descriptors.length; i++) {
desc = descriptors[i];
lastChar = desc[desc.length - 1];
value = desc.substring(0, desc.length - 1);
intVal = parseInt(value, 10);
floatVal = parseFloat(value);
// If the descriptor consists of a valid non-negative integer followed by
// a U+0077 LATIN SMALL LETTER W character
if (regexNonNegativeInteger.test(value) && lastChar === 'w') {
// If width and density are not both absent, then let error be yes.
if (w || d) {
pError = true;
}
// Apply the rules for parsing non-negative integers to the descriptor.
// If the result is zero, let error be yes.
// Otherwise, let width be the result.
if (intVal === 0) {
pError = true;
} else {
w = intVal;
}
}
// If the descriptor consists of a valid floating-point number followed by
// a U+0078 LATIN SMALL LETTER X character
else if (regexFloatingPoint.test(value) && lastChar === 'x') {
// If width, density and future-compat-h are not all absent, then let error
// be yes.
if (w || d || h) {
pError = true;
}
// Apply the rules for parsing floating-point number values to the descriptor.
// If the result is less than zero, let error be yes. Otherwise, let density
// be the result.
if (floatVal < 0) {
pError = true;
} else {
d = floatVal;
}
}
// If the descriptor consists of a valid non-negative integer followed by
// a U+0068 LATIN SMALL LETTER H character
else if (regexNonNegativeInteger.test(value) && lastChar === 'h') {
// If height and density are not both absent, then let error be yes.
if (h || d) {
pError = true;
}
// Apply the rules for parsing non-negative integers to the descriptor.
// If the result is zero, let error be yes. Otherwise, let future-compat-h
// be the result.
if (intVal === 0) {
pError = true;
} else {
h = intVal;
}
// Anything else, Let error be yes.
} else {
pError = true;
}
}
// 15. If error is still no, then append a new image source to candidates whose
// URL is url, associated with a width width if not absent and a pixel
// density density if not absent. Otherwise, there is a parse error.
if (!pError) {
candidate.source = { value: url, startIndex: startUrlPosition };
if (w) {
candidate.width = { value: w };
}
if (d) {
candidate.density = { value: d };
}
if (h) {
candidate.height = { value: h };
}
candidates.push(candidate);
} else {
throw new Error(
`Invalid srcset descriptor found in '${input}' at '${desc}'`
);
}
}
}
export function parseSrc(input) {
if (!input) {
throw new Error('Must be non-empty');
}
let startIndex = 0;
let value = input;
while (isASCIIWhitespace(value.substring(0, 1))) {
startIndex += 1;
value = value.substring(1, value.length);
}
while (isASCIIWhitespace(value.substring(value.length - 1, value.length))) {
value = value.substring(0, value.length - 1);
}
if (!value) {
throw new Error('Must be non-empty');
}
return { value, startIndex };
}
export function normalizeUrl(url) {
return decodeURIComponent(url).replace(/[\t\n\r]/g, '');
}
export function requestify(url, root) {
return urlToRequest(url, root);
}
function isProductionMode(loaderContext) {
return loaderContext.mode === 'production' || !loaderContext.mode;
}
const defaultMinimizerOptions = {
caseSensitive: true,
// `collapseBooleanAttributes` is not always safe, since this can break CSS attribute selectors and not safe for XHTML
collapseWhitespace: true,
conservativeCollapse: true,
keepClosingSlash: true,
// We need ability to use cssnano, or setup own function without extra dependencies
minifyCSS: true,
minifyJS: true,
// `minifyURLs` is unsafe, because we can't guarantee what the base URL is
// `removeAttributeQuotes` is not safe in some rare cases, also HTML spec recommends against doing this
removeComments: true,
// `removeEmptyAttributes` is not safe, can affect certain style or script behavior
removeRedundantAttributes: true,
removeScriptTypeAttributes: true,
removeStyleLinkTypeAttributes: true,
// `useShortDoctype` is not safe for XHTML
};
function getMinimizeOption(rawOptions, loaderContext) {
if (typeof rawOptions.minimize === 'undefined') {
return isProductionMode(loaderContext) ? defaultMinimizerOptions : false;
}
if (typeof rawOptions.minimize === 'boolean') {
return rawOptions.minimize === true ? defaultMinimizerOptions : false;
}
return rawOptions.minimize;
}
function getAttributeValue(attributes, name) {
const lowercasedAttributes = Object.keys(attributes).reduce((keys, k) => {
// eslint-disable-next-line no-param-reassign
keys[k.toLowerCase()] = k;
return keys;
}, {});
return attributes[lowercasedAttributes[name.toLowerCase()]];
}
const defaultAttributes = [
{
tag: 'audio',
attribute: 'src',
type: 'src',
},
{
tag: 'embed',
attribute: 'src',
type: 'src',
},
{
tag: 'img',
attribute: 'src',
type: 'src',
},
{
tag: 'img',
attribute: 'srcset',
type: 'srcset',
},
{
tag: 'input',
attribute: 'src',
type: 'src',
},
{
tag: 'link',
attribute: 'href',
type: 'src',
filter: (tag, attribute, attributes) => {
if (!/stylesheet/i.test(getAttributeValue(attributes, 'rel'))) {
return false;
}
if (
attributes.type &&
getAttributeValue(attributes, 'type').trim().toLowerCase() !==
'text/css'
) {
return false;
}
return true;
},
},
{
tag: 'object',
attribute: 'data',
type: 'src',
},
{
tag: 'script',
attribute: 'src',
type: 'src',
filter: (tag, attribute, attributes) => {
if (attributes.type) {
const type = getAttributeValue(attributes, 'type').trim().toLowerCase();
if (
type !== 'module' &&
type !== 'text/javascript' &&
type !== 'application/javascript'
) {
return false;
}
}
return true;
},
},
{
tag: 'source',
attribute: 'src',
type: 'src',
},
{
tag: 'source',
attribute: 'srcset',
type: 'srcset',
},
{
tag: 'track',
attribute: 'src',
type: 'src',
},
{
tag: 'video',
attribute: 'poster',
type: 'src',
},
{
tag: 'video',
attribute: 'src',
type: 'src',
},
// SVG
{
tag: 'image',
attribute: 'xlink:href',
type: 'src',
},
{
tag: 'image',
attribute: 'href',
type: 'src',
},
{
tag: 'use',
attribute: 'xlink:href',
type: 'src',
},
{
tag: 'use',
attribute: 'href',
type: 'src',
},
];
function getAttributesOption(rawOptions) {
if (typeof rawOptions.attributes === 'undefined') {
return { list: defaultAttributes };
}
if (typeof rawOptions.attributes === 'boolean') {
return rawOptions.attributes === true ? { list: defaultAttributes } : false;
}
return { ...{ list: defaultAttributes }, ...rawOptions.attributes };
}
export function normalizeOptions(rawOptions, loaderContext) {
return {
preprocessor: rawOptions.preprocessor,
attributes: getAttributesOption(rawOptions),
minimize: getMinimizeOption(rawOptions, loaderContext),
esModule:
typeof rawOptions.esModule === 'undefined' ? false : rawOptions.esModule,
};
}
export function pluginRunner(plugins) {
return {
process: (content) => {
const result = {};
for (const plugin of plugins) {
// eslint-disable-next-line no-param-reassign
content = plugin(content, result);
}
result.html = content;
return result;
},
};
}
export function getFilter(filter, defaultFilter = null) {
return (attribute, value, resourcePath) => {
if (defaultFilter && !defaultFilter(value)) {
return false;
}
if (typeof filter === 'function') {
return filter(attribute, value, resourcePath);
}
return true;
};
}
const GET_SOURCE_FROM_IMPORT_NAME = '___HTML_LOADER_GET_SOURCE_FROM_IMPORT___';
export function getImportCode(html, loaderContext, imports, options) {
if (imports.length === 0) {
return '';
}
const stringifiedHelperRequest = stringifyRequest(
loaderContext,
require.resolve('./runtime/getUrl.js')
);
let code = options.esModule
? `import ${GET_SOURCE_FROM_IMPORT_NAME} from ${stringifiedHelperRequest};\n`
: `var ${GET_SOURCE_FROM_IMPORT_NAME} = require(${stringifiedHelperRequest});\n`;
for (const item of imports) {
const { importName, source } = item;
code += options.esModule
? `import ${importName} from ${source};\n`
: `var ${importName} = require(${source});\n`;
}
return `// Imports\n${code}`;
}
export function getModuleCode(html, replacements) {
let code = JSON.stringify(html)
// Invalid in JavaScript but valid HTML
.replace(/[\u2028\u2029]/g, (str) =>
str === '\u2029' ? '\\u2029' : '\\u2028'
);
let replacersCode = '';
for (const item of replacements) {
const { importName, replacementName, unquoted, hash } = item;
const getUrlOptions = []
.concat(hash ? [`hash: ${JSON.stringify(hash)}`] : [])
.concat(unquoted ? 'maybeNeedQuotes: true' : []);
const preparedOptions =
getUrlOptions.length > 0 ? `, { ${getUrlOptions.join(', ')} }` : '';
replacersCode += `var ${replacementName} = ${GET_SOURCE_FROM_IMPORT_NAME}(${importName}${preparedOptions});\n`;
code = code.replace(
new RegExp(replacementName, 'g'),
() => `" + ${replacementName} + "`
);
}
return `// Module\n${replacersCode}var code = ${code};\n`;
}
export function getExportCode(html, options) {
if (options.esModule) {
return `// Exports\nexport default code;`;
}
return `// Exports\nmodule.exports = code;`;
}