Improved performance of _replace_cdata_list_attribute_values, and greatly reduced the number of times it is called.

3 files changed, 12 insertions, 10 deletions

diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py
index e59dae2..740f5f2 100644
--- a/bs4/builder/__init__.py
+++ b/bs4/builder/__init__.py
@@ -147,16 +147,18 @@ class TreeBuilder(object):
 
         Modifies its input in place.
         """
+        if not attrs:
+            return attrs
         if self.cdata_list_attributes:
             universal = self.cdata_list_attributes.get('*', [])
             tag_specific = self.cdata_list_attributes.get(
-                tag_name.lower(), [])
-            for cdata_list_attr in itertools.chain(universal, tag_specific):
-                if cdata_list_attr in attrs:
-                    # Basically, we have a "class" attribute whose
-                    # value is a whitespace-separated list of CSS
-                    # classes. Split it into a list.
-                    value = attrs[cdata_list_attr]
+                tag_name.lower(), None)
+            for attr in attrs.keys():
+                if attr in universal or (tag_specific and attr in tag_specific):
+                    # We have a "class"-type attribute whose string
+                    # value is a whitespace-separated list of
+                    # values. Split it into a list.
+                    value = attrs[attr]
                     if isinstance(value, basestring):
                         values = whitespace_re.split(value)
                     else:
@@ -167,7 +169,7 @@ class TreeBuilder(object):
                         # leave the value alone rather than trying to
                         # split it again.
                         values = value
-                    attrs[cdata_list_attr] = values
+                    attrs[attr] = values
         return attrs
 
 class SAXTreeBuilder(TreeBuilder):
diff --git a/bs4/diagnose.py b/bs4/diagnose.py
index b6eaa8d..c5a0c06 100644
--- a/bs4/diagnose.py
+++ b/bs4/diagnose.py
@@ -192,7 +192,7 @@ def profile(num_elements=100000, parser="lxml"):
     stats.strip_dirs()
     cumulative = stats.sort_stats("cumulative")
     total = stats.sort_stats("time")
-    import pdb; pdb.set_trace()
+    cumulative.print_stats(50)
 
 if __name__ == '__main__':
     #diagnose(sys.stdin.read())
diff --git a/bs4/element.py b/bs4/element.py
index f6864f2..7b63b30 100644
--- a/bs4/element.py
+++ b/bs4/element.py
@@ -746,7 +746,7 @@ class Tag(PageElement):
         self.prefix = prefix
         if attrs is None:
             attrs = {}
-        elif builder.cdata_list_attributes:
+        elif attrs and builder.cdata_list_attributes:
             attrs = builder._replace_cdata_list_attribute_values(
                 self.name, attrs)
         else: