Comprehension/fix plagiarism nil error (#7976)

* Refactor plagiarism highlighting to handle edge cases

Because of the way that we calculate plagiarism, the code that identifies the matched string for highlighting removes any cases of multiple spaces in a row.  We need to account for that edge case in case a student entry actually has multiple spaces.

* Add tests for Plagiarism edge case

services/QuillLMS/engines/comprehension/lib/comprehension/comprehension/plagiarism_check.rb

@@ -120,8 +120,17 @@ def passage_word_arrays
     end
 
     private def get_highlight(text, cleaned_text)
-      start_index = cleaned_text.index(matched_slice)
+      extra_space_indexes = []
+      cleaned_text.each_char.with_index { |c, i| extra_space_indexes.push(i) if c == ' ' && cleaned_text[i+1] == ' ' }
+
+      space_normalized_text = cleaned_text.split.join(' ')
+
+      start_index = space_normalized_text.index(matched_slice)
+      extra_space_indexes.each { |i| start_index += 1 if i <= start_index }
+
       end_index = start_index + matched_slice.size - 1
+      extra_space_indexes.each { |i| end_index += 1 if i > start_index && i <= end_index }
+
       char_positions = text.enum_for(:scan, /[A-Za-z0-9\s]/).map { |c| Regexp.last_match.begin(0) }
       text[char_positions[start_index]..char_positions[end_index]]
     end

services/QuillLMS/engines/comprehension/spec/lib/plagiarism_check_spec.rb

@@ -52,6 +52,54 @@ module Comprehension
         expect(feedback[:rule_uid]).to(be_truthy)
         expect(feedback[:concept_uid]).to(be_truthy)
       end
+
+      context 'space normalization handling' do
+        let(:feedback) { "this is some standard plagiarism feedback" }
+
+        it 'should successfully highlight even when the user entry has multiple consecutive spaces but the passage does not' do
+          entry = "This phrase plagiarises from  the    passage even     though it  has a ton of spaces in it."
+          passage = "From the passage even though it has a ton of spaces."
+
+          plagiarism_check = Comprehension::PlagiarismCheck.new(entry, passage, feedback, rule)
+          feedback = plagiarism_check.feedback_object
+
+          expect(feedback[:highlight][0][:text]).to eq("from  the    passage even     though it  has a ton of spaces")
+          expect(feedback[:highlight][1][:text]).to eq("From the passage even though it has a ton of spaces")
+        end
+
+        it 'should successfully highlight even when the passage has multiple consecutive spaces but the user entry does not' do
+          entry = "This phrase plagiarises from the passage even though it has a ton of spaces in it."
+          passage = "From the  passage even    though it has   a ton of spaces."
+
+          plagiarism_check = Comprehension::PlagiarismCheck.new(entry, passage, feedback, rule)
+          feedback = plagiarism_check.feedback_object
+
+          expect(feedback[:highlight][0][:text]).to eq("from the passage even though it has a ton of spaces")
+          expect(feedback[:highlight][1][:text]).to eq("From the  passage even    though it has   a ton of spaces")
+        end
+
+        it 'should successfully highlight even when the user entry has isolated punctuation but the passage does not' do
+          entry = "This phrase plagiarises from - the  --  passage even -  -  though it , has a ton of spaces in it."
+          passage = "From the passage even though it has a ton of spaces."
+
+          plagiarism_check = Comprehension::PlagiarismCheck.new(entry, passage, feedback, rule)
+          feedback = plagiarism_check.feedback_object
+
+          expect(feedback[:highlight][0][:text]).to eq("from - the  --  passage even -  -  though it , has a ton of spaces")
+          expect(feedback[:highlight][1][:text]).to eq("From the passage even though it has a ton of spaces")
+        end
+
+        it 'should successfully highlight even when the passage has isolated punctuation but the user entry does not' do
+          entry = "This phrase plagiarises from the passage even though it has a ton of spaces in it."
+          passage = "From the - passage even - - - though it has --  a ton of spaces."
+
+          plagiarism_check = Comprehension::PlagiarismCheck.new(entry, passage, feedback, rule)
+          feedback = plagiarism_check.feedback_object
+
+          expect(feedback[:highlight][0][:text]).to eq("from the passage even though it has a ton of spaces")
+          expect(feedback[:highlight][1][:text]).to eq("From the - passage even - - - though it has --  a ton of spaces")
+        end
+      end
     end
   end
 end