Update script and example for unescaping HTML.

gkellogg · gkellogg · commit bdd89df62b01 · 2018-11-28T15:53:51.000-08:00
diff --git a/common/extract-examples.rb b/common/extract-examples.rb
@@ -336,8 +336,7 @@ def save_example(examples:, element:, title:, example_number:, error:, warn:)
         next
       end
     when 'table'
-      doc = Nokogiri::HTML.parse(content) {|c| c.strict}
-      content = CGI.unescapeHTML(doc.inner_html)
+      content = Nokogiri::HTML.parse(content)
     when 'ttl', 'trig'
       begin
         reader_errors = []
@@ -554,8 +553,7 @@ def save_example(examples:, element:, title:, example_number:, error:, warn:)
           $stderr.puts "expected:\n" + expected.to_trig if verbose
         when 'table'
           expected = begin
-            doc = Nokogiri::HTML.parse(content)
-            table_to_dataset(doc)
+            table_to_dataset(content.xpath('/html/body/table'))
           rescue
             errors << "Example #{ex[:number]} at line #{ex[:line]} raised error reading table: #{$!}"
             RDF::Dataset.new
diff --git a/index.html b/index.html
@@ -8609,15 +8609,13 @@ <h3>Graph Containers</h3>
         <head>
           <base href="http://dbpedia.org/resource/"/>****
           <script type="application/ld+json">
-          < ! - -
           {
             "@context": "https://json-ld.org/contexts/person.jsonld",
             "@id": ****"John_Lennon"****,
             "name": "John Lennon",
             "born": "1940-10-09",
             "spouse": ****"Cynthia_Lennon"****
           }
-          - - >
           </script>
         ****</head>
       </html>****
