@@ -5,14 +5,35 @@
 
 class Sanitizer
   def sanitize(html)
-    sanitized = sanitizer_implementation.fragment(html)
-    with_fixed_whitespace = sanitized.strip.gsub(/(?:&nbsp;| )+/, ' ')
-    CGI.unescapeHTML with_fixed_whitespace
+    remove_problematic_html(html)
+      .gsub('&nbsp;', ' ')
+      .squeeze(' ')
+      .strip
   end
 
   private
 
+  def remove_problematic_html(raw)
+    html = raw.to_s
+    if html.include? '<'
+      sanitizer_implementation.fragment(html)
+    else
+      # If there is not an angle bracket, no need to parse it as HTML
+      html
+    end
+  end
+
+  # :reek:FeatureEnvy
   def sanitizer_implementation
-    @sanitizer_implementation ||= Sanitize.new(elements: %w[b em i strong])
+    @sanitizer_implementation ||= begin
+      remove_entities = lambda do |env|
+        node = env[:node]
+        if node.is_a? Nokogiri::XML::Text
+          sanitized = Sanitize.fragment(CGI.unescapeHTML(node.content))
+          sanitized.tr("\u00A0", ' ')
+        end
+      end
+      Sanitize.new(elements: %w[b em i strong], transformers: remove_entities)
+    end
   end
 end
@@ -25,3 +25,20 @@
     library_staff_repo.delete
   end
 end
+
+Benchmark.ips do |b|
+  long_string = <<~END_LONG_STRING
+    •Bayesian networks (BNs) offer an alternative approach to risk estimation.•A BN of mercury risks to panthers replicated traditional probabilistic estimates.•BNs facilitate
+    quantification of uncertainty and causal inference.\nTraditionally hazard quotients (HQs) have been computed for ecological risk assessment, often without quantifying the
+    underlying uncertainties in the risk estimate. We demonstrate a Bayesian network approach to quantitatively assess uncertainties in HQs using a retrospective case study of
+    dietary mercury (Hg) risks to Florida panthers (Puma concolor coryi). The Bayesian network was parameterized, using exposure data from a previous Monte Carlo-based assessment
+    of Hg risks (Barron et al., 2004. ECOTOX 13=>223), as a representative example of the uncertainty and complexity in HQ calculations. Mercury HQs and risks to Florida panthers
+    determined from a Bayesian network analysis were nearly identical to those determined using the prior Monte Carlo probabilistic assessment and demonstrated the ability of the
+    Bayesian network to replicate conventional HQ-based approaches. Sensitivity analysis of the Bayesian network showed greatest influence on risk estimates from daily ingested
+    dose by panthers and mercury levels in prey, and less influence from toxicity reference values. Diagnostic inference was used in a high-risk scenario to demonstrate the
+    capabilities of Bayesian networks for examining probable causes for observed effects. Application of Bayesian networks in the computation of HQs provides a transparent and
+    quantitative analysis of uncertainty in risks."
+  END_LONG_STRING
+  sanitizer = Sanitizer.new
+  b.report('sanitizer') { sanitizer.sanitize long_string }
+end
@@ -20,6 +20,26 @@
       expect(sanitizer.sanitize(test_string)).to eq(expected)
     end
 
+    it 'does not convert html entities into malicious tags' do
+      test_string = '&lt;script src="example.com"&gt;&lt;/script&gt;<p>This is a test</p>'
+      expected = '&lt;script src="example.com"&gt;&lt;/script&gt; This is a test'
+
+      expect(sanitizer.sanitize(test_string)).to eq(expected)
+    end
+
+    it 'does not convert double html entities into malicious tags' do
+      test_string = '&amp;lt;script src="example.com"&amp;gt;&amp;lt;/script&amp;gt;<p>This is a test</p>'
+      expected = '&amp;lt;script src="example.com"&amp;gt;&amp;lt;/script&amp;gt; This is a test'
+
+      expect(sanitizer.sanitize(test_string)).to eq(expected)
+    end
+
+    it 'keeps meaningful &lt;' do
+      test_string = '5 &lt; 10'
+
+      expect(sanitizer.sanitize(test_string)).to eq(test_string)
+    end
+
     it 'removes link tags' do
       test_string = '<link rel="example.com">This is a test'
       expected = 'This is a test'