-
Notifications
You must be signed in to change notification settings - Fork 137
/
ExpensiMark.js
688 lines (626 loc) · 28.3 KB
/
ExpensiMark.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
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
import _ from 'underscore';
import Str from './str';
import {URL_REGEX} from './Url';
import {CONST} from './CONST';
const SLACK_SPAN_NEW_LINE_TAG = '<span class="c-mrkdwn__br" data-stringify-type="paragraph-break" style="box-sizing: inherit; display: block; height: unset;"></span>';
export default class ExpensiMark {
constructor() {
/**
* The list of regex replacements to do on a comment. Check the link regex is first so links are processed
* before other delimiters
*
* @type {Object[]}
*/
this.rules = [
/**
* Apply the code-fence first so that we avoid replacing anything inside of it that we're not supposed to
* (aka any rule with the '(?![^<]*<\/pre>)' avoidance in it
*/
{
name: 'codeFence',
// < is a backtick symbol we are matching on three of them before then after a new line character
regex: /(```[\n]?)((?:\s*?(?![\n]?```(?!`))[\S])+\s*?)((?=\n?)```)/g,
// We're using a function here to perform an additional replace on the content
// inside the backticks because Android is not able to use <pre> tags and does
// not respect whitespace characters at all like HTML does. We do not want to mess
// with the new lines here since they need to be converted into <br>. And we don't
// want to do this anywhere else since that would break HTML.
// will create styling issues so use  
replacement: (match, __, textWithinFences) => {
const group = textWithinFences.replace(/(?:(?![\n\r])\s)/g, ' ');
return `<pre>${group}</pre>`;
},
},
/**
* Apply inline code-block to avoid applying any other formatting rules inside of it,
* like we do for the multi-line code-blocks
*/
{
name: 'inlineCodeBlock',
// Use the url escaped version of a backtick (`) symbol. Mobile platforms do not support lookbehinds,
// so capture the first and third group and place them in the replacement.
regex: /(\B|_|)`(.*?\S.*?)`(\B|_|)(?![^<]*<\/pre>)/g,
replacement: '$1<code>$2</code>$3',
},
/**
* Apply the hereMention first because the string @here is still a valid mention for the userMention regex.
* This ensures that the hereMention is always considered first, even if it is followed by a valid userMention.
*/
{
name: 'hereMentions',
regex: /((`|<code>|<pre>)\s*?)?[`.a-zA-Z]?@here\b/gm,
replacement: (match) => {
if (!Str.isValidMention(match)) {
return match;
}
return `<mention-here>${match}</mention-here>`;
},
},
/**
* This regex matches a valid user mention in a string.
* A user mention is a string that starts with the '@' symbol and is followed by a valid user's primary login
*
* Note: currently we are only allowing mentions in a format of @+19728974297@expensify.sms and @username@example.com
* The username can contain any combination of alphanumeric letters, numbers, and underscores
*/
{
name: 'userMentions',
regex: new RegExp(`((`|<code>|<pre>)\\s*?)?[\`.a-zA-Z]?@+${CONST.REG_EXP.EMAIL_PART}`, 'gm'),
replacement: (match) => {
if (!Str.isValidMention(match)) {
return match;
}
return `<mention-user>${match}</mention-user>`;
},
},
/**
* Converts markdown style links to anchor tags e.g. [Expensify](concierge@expensify.com)
* We need to convert before the auto email link rule and the manual link rule since it will not try to create a link
* from an existing anchor tag.
*/
{
name: 'email',
process: (textToProcess, replacement) => {
const regex = new RegExp(
`\\[([^[\\]]*)]\\(${CONST.REG_EXP.MARKDOWN_EMAIL}\\)`, 'gim'
);
return this.modifyTextForEmailLinks(regex, textToProcess, replacement);
},
replacement: (match, g1, g2) => `<a href="mailto:${g2}">${g1.trim()}</a>`,
},
/**
* Converts markdown style links to anchor tags e.g. [Expensify](https://www.expensify.com)
* We need to convert before the autolink rule since it will not try to create a link
* from an existing anchor tag.
*/
{
name: 'link',
process: (textToProcess, replacement) => {
const regex = new RegExp(
`\\[([^\\][]*(?:\\[[^\\][]*][^\\][]*)*)]\\(${URL_REGEX}\\)(?![^<]*(<\\/pre>|<\\/code>))`,
'gi',
);
return this.modifyTextForUrlLinks(regex, textToProcess, replacement);
},
// We use a function here to check if there is already a https:// on the link.
// If there is not, we force the link to be absolute by prepending '//' to the target.
replacement: (match, g1, g2, g3) => {
if (!g1.trim()) {
return match;
}
const href = g3 ? g2.replace(g3, g3.toLowerCase()) : `https://${g2}`;
return `<a href="${href}" target="_blank" rel="noreferrer noopener">${g1.trim()}</a>`;
},
},
/**
* Automatically links emails that are not in a link. Runs before the autolinker as it will not link an
* email that is in a link
* Prevent emails from starting with [~_*]. Such emails should not be supported.
*/
{
name: 'autoEmail',
regex: new RegExp(
`(?![^<]*>|[^<>]*<\\/)${CONST.REG_EXP.MARKDOWN_EMAIL}(?![^<]*(<\\/pre>|<\\/code>|<\\/a>))`,
'gim',
),
replacement: '<a href="mailto:$1">$1</a>',
},
/**
* Automatically link urls. Runs last of our linkers since we want anything manual to link before this,
* and we do not want to break emails.
*/
{
name: 'autolink',
process: (textToProcess, replacement) => {
const regex = new RegExp(
`(?![^<]*>|[^<>]*<\\/)([_*~]*?)${URL_REGEX}\\1(?!((?:(?!<a).)+)?<\\/a>|[^<]*(<\\/pre>|<\\/code>))`,
'gi',
);
return this.modifyTextForUrlLinks(regex, textToProcess, replacement);
},
// We use a function here to check if there is already a https:// on the link.
// If there is not, we force the link to be absolute by prepending '//' to the target.
replacement: (match, g1, g2, g3) => {
const href = g3 ? g2.replace(g3, g3.toLowerCase()) : `https://${g2}`;
return `${g1}<a href="${href}" target="_blank" rel="noreferrer noopener">${g2}</a>${g1}`;
},
},
{
/**
* Use \b in this case because it will match on words, letters,
* and _: https://www.rexegg.com/regex-boundaries.html#wordboundary
* The !_blank is to prevent the `target="_blank">` section of the
* link replacement from being captured Additionally, something like
* `\b\_([^<>]*?)\_\b` doesn't work because it won't replace
* `_https://www.test.com_`
* Use [\s\S]* instead of .* to match newline
*/
name: 'italic',
regex: /(?!_blank")[^\W_]?_((?![\s_])[\s\S]*?[^\s_])_(?![^\W_])(?![^<]*(<\/pre>|<\/code>|<\/a>|_blank))/g,
replacement: (match, g1) => (g1.includes('<pre>') ? match : `<em>${g1}</em>`),
},
{
// Use \B in this case because \b doesn't match * or ~.
// \B will match everything that \b doesn't, so it works
// for * and ~: https://www.rexegg.com/regex-boundaries.html#notb
name: 'bold',
regex: /\B\*((?=\S)(([^\s*]|\s(?!\*))+?))\*\B(?![^<]*(<\/pre>|<\/code>|<\/a>))/g,
replacement: (match, g1) => (g1.includes('<pre>') ? match : `<strong>${g1}</strong>`),
},
{
name: 'strikethrough',
regex: /\B~((?=\S)((~~(?!~)|[^\s~]|\s(?!~))+?))~\B(?![^<]*(<\/pre>|<\/code>|<\/a>))/g,
replacement: '<del>$1</del>',
},
{
name: 'quote',
// We also want to capture a blank line before or after the quote so that we do not add extra spaces.
// block quotes naturally appear on their own line. Blockquotes should not appear in code fences or
// inline code blocks. A single prepending space should be stripped if it exists
process: (textToProcess, replacement) => {
const regex = new RegExp(
/\n?^> *(?! )(?![^<]*(?:<\/pre>|<\/code>))([^\v\n\r]+)\n?/gm,
);
return this.modifyTextForQuote(regex, textToProcess, replacement);
},
replacement: (g1) => {
const replacedText = this.replace(g1, {filterRules: ['heading1'], shouldEscapeText: false});
return `<blockquote>${replacedText}</blockquote>`;
},
},
{
name: 'heading1',
regex: /^# +(?! )((?:(?!<pre>|\n|\r\n).)+)\n?/gm,
replacement: '<h1>$1</h1>',
},
{
name: 'newline',
regex: /\n/g,
replacement: '<br />',
},
{
// We're removing <br /> because when </pre> and <br /> occur together, an extra line is added.
name: 'replacepre',
regex: /<\/pre>\s*<br\s*[/]?>/gi,
replacement: '</pre>',
},
{
// We're removing <br /> because when <br /> and <pre> occur together, an extra line is added.
name: 'replacebr',
regex: /<br\s*[/]?><pre>\s*/gi,
replacement: ' <pre>',
},
];
/**
* The list of regex replacements to do on a HTML comment for converting it to markdown.
* Order of rules is important
* @type {Object[]}
*/
this.htmlToMarkdownRules = [
// Used to Exclude tags
{
name: 'replacepre',
regex: /<\/pre>(.)/gi,
replacement: '</pre><br />$1',
},
{
name: 'exclude',
regex: new RegExp(
[
'<(script|style)(?:"[^"]*"|\'[^\']*\'|[^\'">])*>([\\s\\S]*?)<\\/\\1>',
'(?![^<]*(<\\/pre>|<\\/code>))(\n|\r\n)?',
].join(''),
'gim',
),
replacement: '',
},
{
name: 'newline',
// Replaces open and closing <br><br/> tags with a single <br/>
// Slack uses special <span> tag for empty lines instead of <br> tag
pre: inputString => inputString.replace('<br></br>', '<br/>').replace('<br><br/>', '<br/>')
.replace(/(<tr.*?<\/tr>)/g, '$1<br/>').replace('<br/></tbody>', '')
.replace(SLACK_SPAN_NEW_LINE_TAG + SLACK_SPAN_NEW_LINE_TAG, '<br/><br/><br/>')
.replace(SLACK_SPAN_NEW_LINE_TAG, '<br/><br/>'),
// Include the immediately followed newline as `<br>\n` should be equal to one \n.
regex: /<br(?:"[^"]*"|'[^']*'|[^'"><])*>\n?/gi,
replacement: '\n',
},
{
name: 'heading1',
regex: /[^\S\r\n]*<(h1)(?:"[^"]*"|'[^']*'|[^'">])*>(.*?)<\/\1>(?![^<]*(<\/pre>|<\/code>))[^\S\r\n]*/gi,
replacement: '[block]# $2[block]',
},
{
name: 'listItem',
regex: /\s*<(li)(?:"[^"]*"|'[^']*'|[^'">])*>(.*?)<\/\1>(?![^<]*(<\/pre>|<\/code>))\s*/gi,
replacement: '<li> $2</li>',
},
// Use [\s\S]* instead of .* to match newline
{
name: 'italic',
regex: /<(em|i)(?:"[^"]*"|'[^']*'|[^'">])*>([\s\S]*?)<\/\1>(?![^<]*(<\/pre>|<\/code>))/gi,
replacement: '_$2_',
},
{
name: 'bold',
regex: /<(b|strong)(?:"[^"]*"|'[^']*'|[^'">])*>([\s\S]*?)<\/\1>(?![^<]*(<\/pre>|<\/code>))/gi,
replacement: '*$2*',
},
{
name: 'strikethrough',
regex: /<(del)(?:"[^"]*"|'[^']*'|[^'">])*>([\s\S]*?)<\/\1>(?![^<]*(<\/pre>|<\/code>))/gi,
replacement: '~$2~',
},
{
name: 'quote',
regex: /\n?<(blockquote|q)(?:"[^"]*"|'[^']*'|[^'">])*>([\s\S]*?)<\/\1>(?![^<]*(<\/pre>|<\/code>))/gi,
replacement: (match, g1, g2) => {
// We remove the line break before heading inside quote to avoid adding extra line
const resultString = g2.replace(/\n?(\[block\]# )/g, '$1')
.replace(/(\[block\])+/g, '\n')
.trim()
.split('\n')
.map(m => `> ${m}`)
.join('\n');
return `\n${resultString}\n`;
},
},
{
name: 'inlineCodeBlock',
regex: /<(code)(?:"[^"]*"|'[^']*'|[^'">])*>(.*?)<\/\1>(?![^<]*(<\/pre>|<\/code>))/gi,
replacement: '`$2`',
},
{
name: 'codeFence',
regex: /<(pre)(?:"[^"]*"|'[^']*'|[^'">])*>([\s\S]*?)(\n?)<\/\1>(?![^<]*(<\/pre>|<\/code>))/gi,
replacement: (match, g1, g2) => `\`\`\`\n${g2}\n\`\`\``,
},
{
name: 'anchor',
regex: /<(a)[^><]*href\s*=\s*(['"])(.*?)\2(?:".*?"|'.*?'|[^'"><])*>([\s\S]*?)<\/\1>(?![^<]*(<\/pre>|<\/code>))/gi,
replacement: (match, g1, g2, g3, g4) => {
const email = g3.startsWith('mailto:') ? g3.slice(7) : '';
if (email === g4) {
return email;
}
return `[${g4}](${email || g3})`;
},
},
];
/**
* The list of rules to covert the HTML to text.
* Order of rules is important
* @type {Object[]}
*/
this.htmlToTextRules = [
{
name: 'breakline',
regex: /<br[^>]*>/gi,
replacement: '\n',
},
{
name: 'blockquoteWrapHeadingOpen',
regex: /<blockquote><h1>/gi,
replacement: '<blockquote>',
},
{
name: 'blockquoteWrapHeadingClose',
regex: /<\/h1><\/blockquote>/gi,
replacement: '</blockquote>',
},
{
name: 'blockElementOpen',
regex: /(.|\s)<(blockquote|h1|pre)>/gi,
replacement: '$1\n',
},
{
name: 'blockElementClose',
regex: /<\/(blockquote|h1|pre)>(.|\s)/gm,
replacement: '\n$2',
},
{
name: 'stripTag',
regex: /(<([^>]+)>)/gi,
replacement: '',
},
];
}
/**
* Replaces markdown with html elements
*
* @param {String} text - Text to parse as markdown
* @param {Object} [options] - Options to customize the markdown parser
* @param {String[]} [options.filterRules=[]] - An array of name of rules as defined in this class.
* If not provided, all available rules will be applied.
* @param {Boolean} [options.shouldEscapeText=true] - Whether or not the text should be escaped
*
* @returns {String}
*/
replace(text, {filterRules = [], shouldEscapeText = true} = {}) {
// This ensures that any html the user puts into the comment field shows as raw html
let replacedText = shouldEscapeText ? _.escape(text) : text;
const rules = _.isEmpty(filterRules) ? this.rules : _.filter(this.rules, rule => _.contains(filterRules, rule.name));
rules.forEach((rule) => {
// Pre-process text before applying regex
if (rule.pre) {
replacedText = rule.pre(replacedText);
}
if (rule.process) {
replacedText = rule.process(replacedText, rule.replacement);
} else {
replacedText = replacedText.replace(rule.regex, rule.replacement);
}
// Post-process text after applying regex
if (rule.post) {
replacedText = rule.post(replacedText);
}
});
return replacedText;
}
/**
* Checks matched URLs for validity and replace valid links with html elements
*
* @param {RegExp} regex
* @param {String} textToCheck
* @param {Function} replacement
*
* @returns {String}
*/
modifyTextForUrlLinks(regex, textToCheck, replacement) {
let match = regex.exec(textToCheck);
let replacedText = '';
let startIndex = 0;
while (match !== null) {
// we want to avoid matching email address domains
let abort = false;
if ((match.index !== 0) && (textToCheck[match.index - 1] === '@')) {
abort = true;
}
// we want to avoid matching ending ) unless it is a closing parenthesis for the URL
if (textToCheck[(match.index + match[2].length) - 1] === ')' && !match[2].includes('(')) {
match[0] = match[0].substr(0, match[0].length - 1);
match[2] = match[2].substr(0, match[2].length - 1);
}
// remove extra ) parentheses
let brace = 0;
if (match[2][match[2].length - 1] === ')') {
for (let i = 0; i < match[2].length; i++) {
if (match[2][i] === '(') {
brace++;
}
if (match[2][i] === ')') {
brace--;
}
}
if (brace) {
match[0] = match[0].substr(0, match[0].length + brace);
match[2] = match[2].substr(0, match[2].length + brace);
}
}
replacedText = replacedText.concat(textToCheck.substr(startIndex, (match.index - startIndex)));
if (abort) {
replacedText = replacedText.concat(textToCheck.substr(match.index, (match[0].length)));
} else {
const urlRegex = new RegExp(`^${URL_REGEX}$`, 'i');
// `match[1]` contains the text inside the [] of the markdown e.g. [example](https://example.com)
// At the entry of function this.replace, text is already escaped due to the rules that precede the link
// rule (eg, codeFence, inlineCodeBlock, email), so we don't need to escape the text again here.
// If the text `match[1]` exactly matches a URL, we skip translating the filterRules
// So that special characters such as ['_', '*', '~'] are preserved in the text.
const linkText = urlRegex.test(match[1]) ? match[1] : this.replace(match[1], {
filterRules: ['bold', 'strikethrough', 'italic'],
shouldEscapeText: false,
});
replacedText = replacedText.concat(replacement(match[0], linkText, match[2], match[3]));
}
startIndex = match.index + (match[0].length);
// Now we move to the next match that the js regex found in the text
match = regex.exec(textToCheck);
}
if (startIndex < textToCheck.length) {
replacedText = replacedText.concat(textToCheck.substr(startIndex));
}
return replacedText;
}
/**
* Checks matched Emails for validity and replace valid links with html elements
*
* @param {RegExp} regex
* @param {String} textToCheck
* @param {Function} replacement
*
* @returns {String}
*/
modifyTextForEmailLinks(regex, textToCheck, replacement) {
let match = regex.exec(textToCheck);
let replacedText = '';
let startIndex = 0;
while (match !== null) {
replacedText = replacedText.concat(textToCheck.substr(startIndex, (match.index - startIndex)));
// `match[1]` contains the text inside []. Text is already escaped due to the rules
// that precede the link rule (eg, codeFence, inlineCodeBlock, email).
const linkText = this.replace(match[1], {
filterRules: ['bold', 'strikethrough', 'italic'],
shouldEscapeText: false,
});
replacedText = replacedText.concat(replacement(match[0], linkText, match[2]));
startIndex = match.index + (match[0].length);
// Now we move to the next match that the js regex found in the text
match = regex.exec(textToCheck);
}
if (startIndex < textToCheck.length) {
replacedText = replacedText.concat(textToCheck.substr(startIndex));
}
return replacedText;
}
/**
* replace [block] with '\n' if :
* 1. We have text before the [block].
* 2. The text does not end with a new line.
* 3. The text does not have quote mark '>' .
* 4. [block] not the last [block] in the string.
*
* @param {String} htmlString
* @returns {String}
*/
replaceBlockWithNewLine(htmlString) {
const splitText = htmlString.split('[block]');
let joinedText = '';
// Delete whitespace at the end
while (splitText.length) {
if (splitText[splitText.length - 1].trim().length > 0 || splitText[splitText.length - 1].match(/\n/)) {
break;
}
splitText.pop();
}
splitText.forEach((text, index) => {
if (text.trim().length === 0 && !text.match(/\n/)) {
return;
}
// Insert '\n' unless it ends with '\n' or '>' or it's the last [block].
if (text.match(/[\n|>][>]?[\s]?$/) || index === splitText.length - 1) {
joinedText += text;
} else {
joinedText += `${text}\n`;
}
});
return joinedText;
}
/**
* Replaces HTML with markdown
*
* @param {String} htmlString
*
* @returns {String}
*/
htmlToMarkdown(htmlString) {
let generatedMarkdown = htmlString;
const body = /<(body)(?:"[^"]*"|'[^']*'|[^'"><])*>(?:\n|\r\n)?([\s\S]*?)(?:\n|\r\n)?<\/\1>(?![^<]*(<\/pre>|<\/code>))/im;
const parseBodyTag = generatedMarkdown.match(body);
// If body tag is found then use the content of body rather than the whole HTML
if (parseBodyTag) {
generatedMarkdown = parseBodyTag[2];
}
this.htmlToMarkdownRules.forEach((rule) => {
// Pre-processes input HTML before applying regex
if (rule.pre) {
generatedMarkdown = rule.pre(generatedMarkdown);
}
generatedMarkdown = generatedMarkdown.replace(rule.regex, rule.replacement);
});
generatedMarkdown = generatedMarkdown.replace(
/<div.*?>|<\/div>|<comment.*?>|\n<\/comment>|<\/comment>|<h2>|<\/h2>|<h3>|<\/h3>|<h4>|<\/h4>|<h5>|<\/h5>|<h6>|<\/h6>|<p>|<\/p>|<li>|<\/li>/gm,
'[block]',
);
return Str.htmlDecode(this.replaceBlockWithNewLine(Str.stripHTML(generatedMarkdown)));
}
/**
* Convert HTML to text
*
* @param {String} htmlString
* @returns {String}
*/
htmlToText(htmlString) {
let replacedText = htmlString;
this.htmlToTextRules.forEach((rule) => {
replacedText = replacedText.replace(rule.regex, rule.replacement);
});
return replacedText;
}
/**
* Modify text for Quotes replacing chevrons with html elements
*
* @param {RegExp} regex
* @param {String} textToCheck
* @param {Function} replacement
*
* @returns {String}
*/
modifyTextForQuote(regex, textToCheck, replacement) {
let replacedText = '';
let textToFormat = '';
const match = textToCheck.match(regex);
// If there's matches we need to modify the quotes
if (match !== null) {
let insideCodefence = false;
// Split the textToCheck in lines
const textSplitted = textToCheck.split('\n');
for (let i = 0; i < textSplitted.length; i++) {
if (!insideCodefence) {
// We need to know when there is a start of codefence so we dont quote
insideCodefence = Str.contains(textSplitted[i], '<pre>');
}
// We only want to modify lines starting with > that is not codefence
if (Str.startsWith(textSplitted[i], '>') && !insideCodefence) {
textToFormat += `${textSplitted[i]}\n`;
} else {
// Make sure we will only modify if we have Text needed to be formatted for quote
if (textToFormat !== '') {
replacedText += this.formatTextForQuote(regex, textToFormat, replacement);
textToFormat = '';
}
// We dont want a \n after the textSplitted if it is the last row
if (i === textSplitted.length - 1) {
replacedText += `${textSplitted[i]}`;
} else {
replacedText += `${textSplitted[i]}\n`;
}
// We need to know when we are not inside codefence anymore
if (insideCodefence) {
insideCodefence = !Str.contains(textSplitted[i], '</pre>');
}
}
}
// When loop ends we need the last quote to be formatted if we have quotes at last rows
if (textToFormat !== '') {
replacedText += this.formatTextForQuote(regex, textToFormat, replacement);
}
// Replace all the blank lines between quotes, if there are only blank lines between them
replacedText = replacedText.replace(/(<\/blockquote>((\s*)+)<blockquote>)/g, '</blockquote><blockquote>');
} else {
// If we doesn't have matches make sure the function will return the same textToCheck
replacedText = textToCheck;
}
return replacedText;
}
/**
* Format the content of blockquote if the text matches the regex or else just return the original text
*
* @param {RegExp} regex
* @param {String} textToCheck
* @param {Function} replacement
*
* @returns {String}
*/
formatTextForQuote(regex, textToCheck, replacement) {
if (textToCheck.match(regex)) {
// Remove '>' and trim each line of quote content
let textToFormat = textToCheck.split('\n').map(row => row.substr(4).trim()).join('\n');
// Remove leading and trailing line breaks
textToFormat = textToFormat.trim();
return replacement(textToFormat);
}
return textToCheck;
}
}