Give the Formatter class more control over formatting decisions.

1 files changed, 12 insertions, 6 deletions

diff --git a/bs4/builder/__init__.py b/bs4/builder/__init__.py
index c5e6e84..e087f07 100644
--- a/bs4/builder/__init__.py
+++ b/bs4/builder/__init__.py
@@ -7,7 +7,6 @@ import sys
 from bs4.element import (
     CharsetMetaAttributeValue,
     ContentMetaAttributeValue,
-    HTMLAwareEntitySubstitution,
     nonwhitespace_re
     )
 
@@ -90,7 +89,6 @@ class TreeBuilder(object):
 
     is_xml = False
     picklable = False
-    preserve_whitespace_tags = set()
     empty_element_tags = None # A tag will be considered an empty-element
                               # tag when and only when it has no contents.
     
@@ -98,9 +96,11 @@ class TreeBuilder(object):
     # comma-separated list of CDATA, rather than a single CDATA.
     DEFAULT_CDATA_LIST_ATTRIBUTES = {}
 
+    DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
+    
     USE_DEFAULT = object()
     
-    def __init__(self, multi_valued_attributes=USE_DEFAULT):
+    def __init__(self, multi_valued_attributes=USE_DEFAULT, preserve_whitespace_tags=USE_DEFAULT):
         """Constructor.
 
         :param multi_valued_attributes: If this is set to None, the
@@ -110,14 +110,19 @@ class TreeBuilder(object):
         for an example.
 
         Internally, these are called "CDATA list attributes", but that
-        probably doesn't make sense to an end-use, so the argument ame
+        probably doesn't make sense to an end-user, so the argument name
         is `multi_valued_attributes`.
+
+        :param preserve_whitespace_tags:
         """
         self.soup = None
         if multi_valued_attributes is self.USE_DEFAULT:
             multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES
         self.cdata_list_attributes = multi_valued_attributes
-
+        if preserve_whitespace_tags is self.USE_DEFAULT:
+            preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS
+        self.preserve_whitespace_tags = preserve_whitespace_tags
+            
     def initialize_soup(self, soup):
         """The BeautifulSoup object has been initialized and is now
         being associated with the TreeBuilder.
@@ -253,7 +258,6 @@ class HTMLTreeBuilder(TreeBuilder):
     Such as which tags are empty-element tags.
     """
 
-    preserve_whitespace_tags = HTMLAwareEntitySubstitution.preserve_whitespace_tags
     empty_element_tags = set([
         # These are from HTML5.
         'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
@@ -292,6 +296,8 @@ class HTMLTreeBuilder(TreeBuilder):
         "output" : ["for"],
         }
 
+    DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
+    
     def set_up_substitutions(self, tag):
         # We are only interested in <meta> tags
         if tag.name != 'meta':