HtmlToText no longer makes the array unique

michaeltelford · Oct 17, 2024 · 803fb91 · 803fb91
1 parent d3e5cc7
commit 803fb91
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 1 deletion.
diff --git a/lib/wgit/html_to_text.rb b/lib/wgit/html_to_text.rb
@@ -118,7 +118,6 @@ def extract_arr
         .split("\n")
         .map(&:strip)
         .reject(&:empty?)
-        .uniq
     end
 
     # Extracts and returns a text string from the @parser HTML.

diff --git a/test/test_html_to_text.rb b/test/test_html_to_text.rb
@@ -225,6 +225,19 @@ def test_extract__getting_started_wiki
     ], doc.text
   end
 
+  def test_extract__dups_are_not_removed
+    doc = Wgit::Document.new "http://www.mytestsite.com/home", <<~HTML
+      <p>Note: The text search index lists all document fields.</p>
+      <hr>
+      <p>Note: The text search index lists all document fields.</p>
+    HTML
+
+    assert_equal [
+      "Note: The text search index lists all document fields.",
+      "Note: The text search index lists all document fields."
+    ], doc.text
+  end
+
   private
 
   def gsub_use_case_content(use_case, content)