fix: normalize whitespace in link labels

Author: sorcio

src/paste-markdown-html.ts

@@ -55,7 +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)) {
@@ -68,7 +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 =
@@ -99,8 +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 = ''
 

test/test.js

@@ -160,6 +160,16 @@ describe('paste-markdown', function () {
       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">