Add custom linkify regex to exclude parenthesis at the end of link (#42)

* add linkify custom regex to excluding parenthesis in the end of link

* Update src/parsing/parsing.go

Co-authored-by: Ben Visness <bvisness@users.noreply.github.com>

* Update src/parsing/parsing_test.go

Co-authored-by: Ben Visness <bvisness@users.noreply.github.com>

* Update src/parsing/parsing_test.go

Co-authored-by: Ben Visness <bvisness@users.noreply.github.com>

* remove unecesary test in the plaintext markdown test

* Remove the new unnecessary `NotContains` test

---------

Co-authored-by: Ben Visness <bvisness@users.noreply.github.com>

Author: makrusali

src/parsing/parsing.go

@@ -2,6 +2,7 @@ package parsing
 
 import (
 	"bytes"
+	"regexp"
 
 	"github.com/yuin/goldmark/parser"
 	"github.com/yuin/goldmark/renderer/html"
@@ -106,6 +107,9 @@ type MarkdownOptions struct {
 	Education bool
 }
 
+// modified from https://github.com/yuin/goldmark/blob/master/extension/linkify.go (urlRegexp)
+var customLinkifyURLRegex = regexp.MustCompile(`^(?:http|https|ftp)://[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-z]+(?::\d+)?(?:[/#?](?:[-a-zA-Z0-9@:%_+.~#$!?&/=;,'">\^{}\[\]` + "`" + `]|\([-a-zA-Z0-9@:%_+~#$!?&/=;'">\^{}\[\]` + "`" + `]|\)[-a-zA-Z0-9@:%_+~#$!?&/=;'">\^{}\[\]` + "`" + `])*)?`)
+
 func makeGoldmark(rawHTML bool, opts ...goldmark.Option) goldmark.Markdown {
 	// We need to re-create Goldmark's default parsers to disable HTML parsing.
 	// Or enable it again. yay
@@ -131,6 +135,9 @@ func makeGoldmark(rawHTML bool, opts ...goldmark.Option) goldmark.Markdown {
 		util.Prioritized(parser.NewAutoLinkParser(), 300),
 		// util.Prioritized(parser.NewRawHTMLParser(), 400),
 		util.Prioritized(parser.NewEmphasisParser(), 500),
+		util.Prioritized(extension.NewLinkifyParser(
+			extension.WithLinkifyURLRegexp(customLinkifyURLRegex),
+		), 600),
 	}
 
 	if rawHTML {

src/parsing/parsing_test.go

@@ -38,26 +38,31 @@ And here's my favorite YouTube video:
 https://youtu.be/dQw4w9WgXcQ
 
 I hope you like it as much as I do.
+
+If you paste a link in parentheses (like https://handmade.network/), the site should not pick up the closing parenthesis as part of the link.
 `
 	t.Run("Real post Markdown", func(t *testing.T) {
 		html := ParseMarkdown(md, PostMarkdown)
 		t.Log(html)
 		assert.Contains(t, html, `<img src="coolimage.png"`)
 		assert.Contains(t, html, "<iframe")
+		assert.Contains(t, html, `<a href="https://handmade.network/">https://handmade.network/</a>`)
 	})
 	t.Run("Post edit preview Markdown", func(t *testing.T) {
 		html := ParseMarkdown(md, PostEditPreviewMarkdown)
 		t.Log(html)
 		assert.Contains(t, html, `<img src="coolimage.png"`)
 		assert.Contains(t, html, `<img src="https://img.youtube.com/vi/dQw4w9WgXcQ/hqdefault.jpg"`)
 		assert.NotContains(t, html, "<iframe")
+		assert.Contains(t, html, `<a href="https://handmade.network/">https://handmade.network/</a>`)
 	})
 	t.Run("Post preview Markdown", func(t *testing.T) {
 		html := ParseMarkdown(md, PostPreviewMarkdown)
 		t.Log(html)
 		assert.Contains(t, html, `<img src="coolimage.png"`)
 		assert.Contains(t, html, `<a href="https://youtu.be/dQw4w9WgXcQ"`)
 		assert.NotContains(t, html, "<iframe")
+		assert.Contains(t, html, `<a href="https://handmade.network/">https://handmade.network/</a>`)
 	})
 	t.Run("Plaintext Markdown", func(t *testing.T) {
 		html := ParseMarkdown(md, PlaintextMarkdown)