combine selectors

Author: nattsw

lib/translation/post_detection_text.rb

@@ -3,6 +3,16 @@
 module DiscourseAi
   module Translation
     class PostDetectionText
+      SELECTORS = [
+        "a.hashtag-cooked", # categories or tags are usually in site's language
+        "a.mention", # mentions are based on the mentioned's user's name
+        "aside.onebox", # onebox external content
+        ".lightbox-wrapper", # image captions
+        "blockquote, aside.quote",
+        "img.emoji",
+        "code, pre",
+      ]
+
       def self.get_text(post)
         return if post.blank?
         cooked = post.cooked
@@ -11,29 +21,12 @@ def self.get_text(post)
         doc = Nokogiri::HTML5.fragment(cooked)
         original = doc.text.strip
 
-        # quotes and blockquotes
-        doc.css("blockquote, aside.quote").remove
-        # image captions
-        doc.css(".lightbox-wrapper").remove
-
+        # these selectors are preferred to be removed,
+        # as they may not be in the user's language
+        doc.css(*SELECTORS).remove
         necessary = doc.text.strip
 
-        # oneboxes (external content)
-        doc.css("aside.onebox").remove
-        # code blocks
-        doc.css("code, pre").remove
-        # hashtags
-        doc.css("a.hashtag-cooked").remove
-        # emoji
-        doc.css("img.emoji").remove
-        # mentions
-        doc.css("a.mention").remove
-
-        preferred = doc.text.strip
-
-        return preferred if preferred.present?
-        return necessary if necessary.present?
-        original
+        necessary.present? ? necessary : original
       end
     end
   end

spec/lib/translation/post_detection_text_spec.rb

@@ -58,11 +58,6 @@
       expect(described_class.get_text(post)).to eq("Hello World")
     end
 
-    it "falls back to necessary text when preferred is empty" do
-      post.cooked = '<aside class="quote">Quote</aside><a class="mention">@user</a>'
-      expect(described_class.get_text(post)).to eq("@user")
-    end
-
     it "falls back to cooked when all filtering removes all content" do
       post.cooked = "<blockquote>Quote</blockquote>"
       expect(described_class.get_text(post)).to eq("Quote")