Skip to content

Improve parsing of HTML anchor content #54

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
manuelpuyol merged 2 commits into from
May 16, 2022
Merged

Improve parsing of HTML anchor content #54

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
983a716
fix: skip child nodes of links
sorcio May 6, 2022
fd12c0f
fix: normalize whitespace in link labels
sorcio May 6, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 8 additions & 5 deletions src/paste-markdown-html.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,9 @@ function onPaste(event: ClipboardEvent) {
// Generate DOM tree from HTML string
const parser = new DOMParser()
const doc = parser.parseFromString(textHTMLClean, 'text/html')
const walker = doc.createTreeWalker(doc.body, NodeFilter.SHOW_ELEMENT)
const walker = doc.createTreeWalker(doc.body, NodeFilter.SHOW_ELEMENT, node =>
node.parentNode && isLink(node.parentNode) ? NodeFilter.FILTER_REJECT : NodeFilter.FILTER_ACCEPT
)

const markdown = convertToMarkdown(plaintext, walker)

Expand All @@ -53,7 +55,9 @@ function convertToMarkdown(plaintext: string, walker: TreeWalker): string {
// Walk through the DOM tree
while (currentNode && index < NODE_LIMIT) {
index++
const text = isLink(currentNode) ? currentNode.textContent || '' : (currentNode.firstChild as Text)?.wholeText || ''
const text = isLink(currentNode)
? (currentNode.textContent || '').replace(/[\t\n\r ]+/g, ' ')
: (currentNode.firstChild as Text)?.wholeText || ''

// No need to transform whitespace
if (isEmptyString(text)) {
Expand All @@ -66,7 +70,7 @@ function convertToMarkdown(plaintext: string, walker: TreeWalker): string {

if (markdownFoundIndex >= 0) {
if (isLink(currentNode)) {
const markdownLink = linkify(currentNode)
const markdownLink = linkify(currentNode, text)
// Transform 'example link plus more text' into 'example [link](example link) plus more text'
// Method: 'example [link](example link) plus more text' = 'example ' + '[link](example link)' + ' plus more text'
markdown =
Expand Down Expand Up @@ -97,8 +101,7 @@ function hasHTML(transfer: DataTransfer): boolean {
}

// Makes markdown link from a link element, avoiding special GitHub links
function linkify(element: HTMLAnchorElement): string {
const label = element.textContent || ''
function linkify(element: HTMLAnchorElement, label: string): string {
const url = element.href || ''
let markdown = ''

Expand Down
22 changes: 22 additions & 0 deletions test/test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,6 +148,28 @@ describe('paste-markdown', function () {
assert.equal(textarea.value, markdownSentence)
})

it('deals with links with nested html', function () {
// eslint-disable-next-line github/unescaped-html-literal
const sentence = `<a href="https://example.com/"><span>foo</span></a>
<a href="https://example.com/">bar</a>
foo bar`
const plaintextSentence = 'foo bar foo bar'
const markdownSentence = '[foo](https://example.com/) [bar](https://example.com/) foo bar'

paste(textarea, {'text/html': sentence, 'text/plain': plaintextSentence})
assert.equal(textarea.value, markdownSentence)
})

it('deals with link labels that contains line breaks in html', function () {
// eslint-disable-next-line github/unescaped-html-literal
const sentence = '<a href="https://example.com/">foo\nbar</a>'
const plaintextSentence = 'foo bar'
const markdownSentence = '[foo bar](https://example.com/)'

paste(textarea, {'text/html': sentence, 'text/plain': plaintextSentence})
assert.equal(textarea.value, markdownSentence)
})

it("doesn't render any markdown for html link without corresponding plaintext", function () {
// eslint-disable-next-line github/unescaped-html-literal
const link = `<meta charset='utf-8'><a href="https://github.com/monalisa/playground/issues/1">
Expand Down