From b8f2cbf41c2007fcec4676e53e6a4e95590126f6 Mon Sep 17 00:00:00 2001
From: Gerhard Schlager <gerhard.schlager@discourse.org>
Date: Sun, 9 Jun 2024 12:51:23 +0200
Subject: [PATCH] DEV: Add `additional_allowed_tags` to `HtmlToMarkdown`

Import script often use subclasses of `HtmlToMarkdown` and might need to allow additional tags that can be used within the custom class.
---
 lib/html_to_markdown.rb           |  2 +-
 spec/lib/html_to_markdown_spec.rb | 37 +++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/lib/html_to_markdown.rb b/lib/html_to_markdown.rb
index d302f6f2380..3052cedd318 100644
--- a/lib/html_to_markdown.rb
+++ b/lib/html_to_markdown.rb
@@ -26,7 +26,7 @@ class HtmlToMarkdown
   end
 
   def remove_not_allowed!(doc)
-    allowed = Set.new
+    allowed = Set.new(@opts[:additional_allowed_tags] || [])
 
     HtmlToMarkdown.private_instance_methods.each do |m|
       if tag = m.to_s[/^visit_(.+)/, 1]
diff --git a/spec/lib/html_to_markdown_spec.rb b/spec/lib/html_to_markdown_spec.rb
index 34b2cd30869..821d2ad1f15 100644
--- a/spec/lib/html_to_markdown_spec.rb
+++ b/spec/lib/html_to_markdown_spec.rb
@@ -65,6 +65,43 @@ RSpec.describe HtmlToMarkdown do
     expect(html_to_markdown(html)).to eq(markdown.strip)
   end
 
+  it "removes tags that aren't allowed" do
+    html = <<~HTML
+      <custom>Text withing custom <span>tag</span></custom>
+      <div>Text within allowed tag</div>
+    HTML
+
+    expect(html_to_markdown(html)).to eq("Text within allowed tag")
+  end
+
+  it "allows additional tags that can be consumed by subclasses" do
+    class ExtendedHtmlToMarkdown < HtmlToMarkdown
+      def to_markdown
+        yield @doc
+        super
+      end
+    end
+
+    html = <<~HTML
+      <custom-image image-id="42">Image text</custom-image>
+      <div>Text within allowed tag</div>
+    HTML
+
+    md =
+      ExtendedHtmlToMarkdown
+        .new(html)
+        .to_markdown { |doc| expect(doc.css("custom-image")).to be_empty }
+    expect(md).to eq("Text within allowed tag")
+
+    md =
+      ExtendedHtmlToMarkdown
+        .new(html, { additional_allowed_tags: ["custom-image"] })
+        .to_markdown do |doc|
+          doc.css("custom-image").each { |img| img.replace("Image #{img["image-id"]}") }
+        end
+    expect(md).to eq("Image 42\nText within allowed tag")
+  end
+
   it "doesn't error on non-inline elements like (aside, section)" do
     html = <<~HTML
       <aside class="quote no-group">