Some more HTML to Markdown fixes (#5046)

* FIX: handle spaces better within emphasis tags in html_to_markdown

* FIX: handle line breaks at beginning of emphasis tags in html_to_markdown

lib/html_to_markdown.rb

@@ -178,6 +178,7 @@ class HtmlToMarkdown
   end
 
   def visit_br(node)
+    return if node.previous_sibling.nil? && EMPHASIS.include?(node.parent.name)
     @stack[-1].markdown << "\n"
   end
 
@@ -185,29 +186,30 @@ class HtmlToMarkdown
     @stack[-1].markdown << "\n\n---\n\n"
   end
 
-  def visit_strong(node)
+  EMPHASIS ||= %w{b strong i em}
-    return if node.text.blank?
+  EMPHASIS.each do |tag|
-    delimiter = node.text["*"] ? "__" : "**"
+    class_eval <<-RUBY
+      def visit_#{tag}(node)
+        return if node.text.empty?
+        return @stack[-1].markdown << " " if node.text.blank?
+        times = "#{tag}" == "i" || "#{tag}" == "em" ? 1 : 2
+        delimiter = (node.text["*"] ? "_" : "*") * times
+        @stack[-1].markdown << " " if node.text[0] == " "
         @stack[-1].markdown << delimiter
         traverse(node)
         @stack[-1].markdown.chomp!
-    @stack[-1].markdown << delimiter
+        if @stack[-1].markdown[-1] == " "
+          @stack[-1].markdown.chomp!(" ")
+          append_space = true
         end
-
-  alias :visit_b :visit_strong
-
-  def visit_em(node)
-    return if node.text.blank?
-    delimiter = node.text["*"] ? "_" : "*"
-    @stack[-1].markdown << delimiter
-    traverse(node)
-    @stack[-1].markdown.chomp!
         @stack[-1].markdown << delimiter
+        @stack[-1].markdown << " " if append_space
+      end
+    RUBY
   end
-
-  alias :visit_i :visit_em
 
   def visit_text(node)
+    node.content = node.content.gsub(/\A[[:space:]]+/, "") if node.previous_element.nil? && EMPHASIS.include?(node.parent.name)
     @stack[-1].markdown << node.text.gsub(/\s{2,}/, " ")
   end
 

spec/components/html_to_markdown_spec.rb

@@ -231,11 +231,13 @@ describe HtmlToMarkdown do
   context "with an oddly placed <br>" do
 
     it "handles <strong>" do
+      expect(html_to_markdown("<strong><br>Bold</strong>")).to eq("**Bold**")
       expect(html_to_markdown("<strong>Bold<br></strong>")).to eq("**Bold**")
       expect(html_to_markdown("<strong>Bold<br>text</strong>")).to eq("**Bold\ntext**")
     end
 
     it "handles <em>" do
+      expect(html_to_markdown("<em><br>Italic</em>")).to eq("*Italic*")
       expect(html_to_markdown("<em>Italic<br></em>")).to eq("*Italic*")
       expect(html_to_markdown("<em>Italic<br>text</em>")).to eq("*Italic\ntext*")
     end
@@ -247,11 +249,41 @@ describe HtmlToMarkdown do
     it "handles <strong>" do
       expect(html_to_markdown("<strong></strong>")).to eq("")
       expect(html_to_markdown("<strong>   </strong>")).to eq("")
+      expect(html_to_markdown("Some<strong> </strong>text")).to eq("Some text")
+      expect(html_to_markdown("Some<strong>    </strong>text")).to eq("Some text")
     end
 
     it "handles <em>" do
       expect(html_to_markdown("<em></em>")).to eq("")
       expect(html_to_markdown("<em>   </em>")).to eq("")
+      expect(html_to_markdown("Some<em> </em>text")).to eq("Some text")
+      expect(html_to_markdown("Some<em>    </em>text")).to eq("Some text")
+    end
+
+  end
+
+  context "with spaces around text" do
+
+    it "handles <strong>" do
+      expect(html_to_markdown("<strong> Bold</strong>")).to eq("**Bold**")
+      expect(html_to_markdown("<strong>     Bold</strong>")).to eq("**Bold**")
+      expect(html_to_markdown("<strong>Bold </strong>")).to eq("**Bold**")
+      expect(html_to_markdown("<strong>Bold     </strong>")).to eq("**Bold**")
+      expect(html_to_markdown("Some<strong> bold</strong> text")).to eq("Some **bold** text")
+      expect(html_to_markdown("Some<strong>     bold</strong> text")).to eq("Some **bold** text")
+      expect(html_to_markdown("Some <strong>bold </strong>text")).to eq("Some **bold** text")
+      expect(html_to_markdown("Some <strong>bold     </strong>text")).to eq("Some **bold** text")
+    end
+
+    it "handles <em>" do
+      expect(html_to_markdown("<em> Italic</em>")).to eq("*Italic*")
+      expect(html_to_markdown("<em>     Italic</em>")).to eq("*Italic*")
+      expect(html_to_markdown("<em>Italic </em>")).to eq("*Italic*")
+      expect(html_to_markdown("<em>Italic     </em>")).to eq("*Italic*")
+      expect(html_to_markdown("Some<em> italic</em> text")).to eq("Some *italic* text")
+      expect(html_to_markdown("Some<em>     italic</em> text")).to eq("Some *italic* text")
+      expect(html_to_markdown("Some <em>italic </em>text")).to eq("Some *italic* text")
+      expect(html_to_markdown("Some <em>italic     </em>text")).to eq("Some *italic* text")
     end
 
   end