+30
-6
lines changedFilter options
+30
-6
lines changed Original file line number Diff line number Diff line change
@@ -59,6 +59,10 @@ const decodingMap = {
59 59
const encodedAttr = /&(?:lt|gt|quot|amp);/g
60 60
const encodedAttrWithNewLines = /&(?:lt|gt|quot|amp|#10);/g
61 61 62 +
// #5992
63 +
const isIgnoreNewlineTag = makeMap('pre,textarea', true)
64 +
const shouldIgnoreFirstNewline = (tag, html) => tag && isIgnoreNewlineTag(tag) && html[0] === '\n'
65 + 62 66
function decodeAttr (value, shouldDecodeNewlines) {
63 67
const re = shouldDecodeNewlines ? encodedAttrWithNewLines : encodedAttr
64 68
return value.replace(re, match => decodingMap[match])
@@ -75,6 +79,9 @@ export function parseHTML (html, options) {
75 79
last = html
76 80
// Make sure we're not in a plaintext content element like script/style
77 81
if (!lastTag || !isPlainTextElement(lastTag)) {
82 +
if (shouldIgnoreFirstNewline(lastTag, html)) {
83 +
advance(1)
84 +
}
78 85
let textEnd = html.indexOf('<')
79 86
if (textEnd === 0) {
80 87
// Comment:
@@ -152,16 +159,19 @@ export function parseHTML (html, options) {
152 159
options.chars(text)
153 160
}
154 161
} else {
155 -
var stackedTag = lastTag.toLowerCase()
156 -
var reStackedTag = reCache[stackedTag] || (reCache[stackedTag] = new RegExp('([\\s\\S]*?)(</' + stackedTag + '[^>]*>)', 'i'))
157 -
var endTagLength = 0
158 -
var rest = html.replace(reStackedTag, function (all, text, endTag) {
162 +
let endTagLength = 0
163 +
const stackedTag = lastTag.toLowerCase()
164 +
const reStackedTag = reCache[stackedTag] || (reCache[stackedTag] = new RegExp('([\\s\\S]*?)(</' + stackedTag + '[^>]*>)', 'i'))
165 +
const rest = html.replace(reStackedTag, function (all, text, endTag) {
159 166
endTagLength = endTag.length
160 167
if (!isPlainTextElement(stackedTag) && stackedTag !== 'noscript') {
161 168
text = text
162 169
.replace(/<!--([\s\S]*?)-->/g, '$1')
163 170
.replace(/<!\[CDATA\[([\s\S]*?)]]>/g, '$1')
164 171
}
172 +
if (shouldIgnoreFirstNewline(stackedTag, text)) {
173 +
text = text.slice(1)
174 +
}
165 175
if (options.chars) {
166 176
options.chars(text)
167 177
}
@@ -495,6 +495,21 @@ describe('parser', () => {
495 495
expect(span.children[0].text).toBe(' ')
496 496
})
497 497 498 +
// #5992
499 +
it('ignore the first newline in <pre> tag', function () {
500 +
const options = extend({}, baseOptions)
501 +
const ast = parse('<div><pre>\nabc</pre>\ndef<pre>\n\nabc</pre></div>', options)
502 +
const pre = ast.children[0]
503 +
expect(pre.children[0].type).toBe(3)
504 +
expect(pre.children[0].text).toBe('abc')
505 +
const text = ast.children[1]
506 +
expect(text.type).toBe(3)
507 +
expect(text.text).toBe('\ndef')
508 +
const pre2 = ast.children[2]
509 +
expect(pre2.children[0].type).toBe(3)
510 +
expect(pre2.children[0].text).toBe('\nabc')
511 +
})
512 + 498 513
it('forgivingly handle < in plain text', () => {
499 514
const options = extend({}, baseOptions)
500 515
const ast = parse('<p>1 < 2 < 3</p>', options)
@@ -530,8 +545,7 @@ describe('parser', () => {
530 545
expect(whitespace.children.length).toBe(1)
531 546
expect(whitespace.children[0].type).toBe(3)
532 547
// textarea is whitespace sensitive
533 -
expect(whitespace.children[0].text).toBe(`
534 -
<p>Test 1</p>
548 +
expect(whitespace.children[0].text).toBe(` <p>Test 1</p>
535 549
test2
536 550
`)
537 551 You can’t perform that action at this time.
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4