HTML parsers treat all HTML4 and HTML5 empty element tags (aka void element tags) correctly. [bug=1656909]

2 files changed, 19 insertions, 2 deletions

diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py
index 601979b..fdb3362 100644
--- a/bs4/builder/__init__.py
+++ b/bs4/builder/__init__.py
@@ -232,8 +232,13 @@ class HTMLTreeBuilder(TreeBuilder):
     """
 
     preserve_whitespace_tags = HTMLAwareEntitySubstitution.preserve_whitespace_tags
-    empty_element_tags = set(['br' , 'hr', 'input', 'img', 'meta',
-                              'spacer', 'link', 'frame', 'base'])
+    empty_element_tags = set([
+        # These are from HTML5.
+        'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
+
+        # These are from HTML4, removed in HTML5.
+        'spacer', 'frame'
+    ])
 
     # The HTML standard defines these attributes as containing a
     # space-separated list of values, not a single value. That is,
diff --git a/bs4/testing.py b/bs4/testing.py
index 733cc29..9d89de7 100644
--- a/bs4/testing.py
+++ b/bs4/testing.py
@@ -69,6 +69,18 @@ class HTMLTreeBuilderSmokeTest(object):
     markup in these tests, there's not much room for interpretation.
     """
 
+    def test_empty_element_tags(self):
+        """Verify that all HTML4 and HTML5 empty element (aka void element) tags
+        are handled correctly.
+        """
+        for name in [
+                'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
+                'spacer', 'frame'
+        ]:
+            soup = self.soup("")
+            new_tag = soup.new_tag(name)
+            self.assertEqual(True, new_tag.is_empty_element)
+    
     def test_pickle_and_unpickle_identity(self):
         # Pickling a tree, then unpickling it, yields a tree identical
         # to the original.