Add a converter that finds gist URLs and converts these to gist short…

…codes for Hugo

---

For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/ashishb/wp2hugo?shareId=XXXX-XXXX-XXXX-XXXX).

src/wp2hugo/internal/hugogenerator/hugo_generator_test.go

@@ -31,3 +31,16 @@ func TestFootnote(t *testing.T) {
 	const expectedMarkdown = "Some text[^1] with a footnote\n\n[^1]: Here we are: the footnote."
 	assert.True(t, strings.Contains(hugoPage.Markdown(), expectedMarkdown))
 }
+
+func TestMarkdownExtractorWithLink1(t *testing.T) {
+	const sampleHTMLInput = `<p><a href="https://gist.github.com/lawrencegripper/8e701b0d201e65af0f8bc9b8b0b14207">Gist Link</a></p>`
+	const expectedMarkdownOutput = `{{< gist lawrencegripper 8e701b0d201e65af0f8bc9b8b0b14207 >}}`
+
+	url1, err := url.Parse("https://example.com")
+	assert.Nil(t, err)
+	page, err := NewPage(nil, *url1, "author", "Title", nil, false, nil, nil, nil, sampleHTMLInput, nil, nil)
+	assert.Nil(t, err)
+	md, err := page.getMarkdown(nil, sampleHTMLInput, nil)
+	assert.Nil(t, err)
+	assert.Equal(t, expectedMarkdownOutput, *md)
+}

src/wp2hugo/internal/hugogenerator/hugopage/html_to_markdown_converter.go

@@ -11,13 +11,15 @@ import (
 
 var youtubeID = regexp.MustCompile(`youtube\.com/embed/([^\&\?\/]+)`)
 var googleMapsID = regexp.MustCompile(`google\.com/maps/d/.*embed\?mid=([0-9A-Za-z-_]+)`)
+var gistID = regexp.MustCompile(`gist\.github\.com/([^/]+)/([0-9a-f]+)`)
 
 func getMarkdownConverter() *md.Converter {
 	converter := md.NewConverter("", true, nil)
 	converter.Use(getYouTubeForHugoConverter())
 	converter.Use(getGoogleMapsEmbedForHugoConverter())
 	converter.Use(convertCustomBRToNewline())
 	converter.Use(convertBrToNewline())
+	converter.Use(convertGistURLsToShortcodes())
 	return converter
 }
 
@@ -75,3 +77,28 @@ func getGoogleMapsEmbedForHugoConverter() md.Plugin {
 		}
 	}
 }
+
+func convertGistURLsToShortcodes() md.Plugin {
+	return func(c *md.Converter) []md.Rule {
+		return []md.Rule{
+			{
+				Filter: []string{"a"},
+				Replacement: func(content string, selec *goquery.Selection, opt *md.Options) *string {
+					href := selec.AttrOr("href", "")
+					parts := gistID.FindStringSubmatch(href)
+					if len(parts) != 3 {
+						return nil
+					}
+					user := parts[1]
+					id := parts[2]
+					text := fmt.Sprintf("{{< gist %s %s >}}", user, id)
+					log.Debug().
+						Str("user", user).
+						Str("id", id).
+						Msg("Gist URL found")
+					return &text
+				},
+			},
+		}
+	}
+}

src/wp2hugo/internal/hugogenerator/hugopage/html_to_markdown_converter_test.go

@@ -9,9 +9,20 @@ const _textWithIframe = `
 <p><iframe src="https://www.google.com/maps/d/u/0/embed?mid=1lcjyzfxxXcdDP3XkrikfqIJryfFi4ZA&amp;ehbc=2E312F" width="640" height="480"></iframe></p>
 `
 
+const _textWithGist = `
+<p><a href="https://gist.github.com/lawrencegripper/8e701b0d201e65af0f8bc9b8b0b14207">Gist Link</a></p>
+`
+
 func TestIframe(t *testing.T) {
 	converter := getMarkdownConverter()
 	result, err := converter.ConvertString(_textWithIframe)
 	assert.NoError(t, err)
 	assert.Contains(t, result, `{{< googlemaps src="1lcjyzfxxXcdDP3XkrikfqIJryfFi4ZA" width=640 height=480 >}}`)
 }
+
+func TestGist(t *testing.T) {
+	converter := getMarkdownConverter()
+	result, err := converter.ConvertString(_textWithGist)
+	assert.NoError(t, err)
+	assert.Contains(t, result, `{{< gist lawrencegripper 8e701b0d201e65af0f8bc9b8b0b14207 >}}`)
+}