Remove trailing whitespace (fixes #18).

Author: gsnedders

html5lib/__init__.py

@@ -1,6 +1,6 @@
 from __future__ import absolute_import, division, unicode_literals
 
-""" 
+"""
 HTML parsing library based on the WHATWG "HTML5"
 specification. The parser is designed to be compatible with existing
 HTML found in the wild and implements well-defined error recovery that
@@ -10,7 +10,7 @@
 
 import html5lib
 f = open("my_document.html")
-tree = html5lib.parse(f) 
+tree = html5lib.parse(f)
 """
 __version__ = "0.95-dev"
 from .html5parser import HTMLParser, parse, parseFragment

html5lib/constants.py

@@ -6,9 +6,9 @@
 EOF = None
 
 E = {
-    "null-character": 
+    "null-character":
        _("Null character in input stream, replaced with U+FFFD."),
-    "invalid-codepoint": 
+    "invalid-codepoint":
        _("Invalid codepoint in stream."),
     "incorrectly-placed-solidus":
        _("Solidus (/) incorrectly placed in tag."),
@@ -378,7 +378,7 @@
     (namespaces["html"], "iframe"),
     # Note that image is commented out in the spec as "this isn't an
     # element that can end up on the stack, so it doesn't matter,"
-    (namespaces["html"], "image"), 
+    (namespaces["html"], "image"),
     (namespaces["html"], "img"),
     (namespaces["html"], "input"),
     (namespaces["html"], "isindex"),
@@ -3069,7 +3069,7 @@
     "ParseError":7
 }
 
-tagTokenTypes = frozenset((tokenTypes["StartTag"], tokenTypes["EndTag"], 
+tagTokenTypes = frozenset((tokenTypes["StartTag"], tokenTypes["EndTag"],
                            tokenTypes["EmptyTag"]))
 
 

html5lib/filters/optionaltags.py

@@ -16,7 +16,7 @@ def __iter__(self):
         for previous, token, next in self.slider():
             type = token["type"]
             if type == "StartTag":
-                if (token["data"] or 
+                if (token["data"] or
                     not self.is_optional_start(token["name"], previous, next)):
                     yield token
             elif type == "EndTag":
@@ -123,10 +123,10 @@ def is_optional_end(self, tagname, next):
             # there is no more content in the parent element.
             if type in ("StartTag", "EmptyTag"):
                 return next["name"] in ('address', 'article', 'aside',
-                                        'blockquote', 'datagrid', 'dialog', 
+                                        'blockquote', 'datagrid', 'dialog',
                                         'dir', 'div', 'dl', 'fieldset', 'footer',
                                         'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
-                                        'header', 'hr', 'menu', 'nav', 'ol', 
+                                        'header', 'hr', 'menu', 'nav', 'ol',
                                         'p', 'pre', 'section', 'table', 'ul')
             else:
                 return type == "EndTag" or type is None

html5lib/html5parser.py

@@ -17,8 +17,8 @@
 
 letter = " | ".join([baseChar, ideographic])
 
-#Without the 
-name = " | ".join([letter, digit, ".", "-", "_", combiningCharacter, 
+#Without the
+name = " | ".join([letter, digit, ".", "-", "_", combiningCharacter,
                        extender])
 nameFirst = " | ".join([letter, "_"])
 
@@ -40,7 +40,7 @@ def charStringToList(chars):
                 break
         if not foundMatch:
             assert len(item) == 1
-            
+
             rv.append([ord(item)] * 2)
     rv = normaliseCharList(rv)
     return rv
@@ -62,7 +62,7 @@ def normaliseCharList(charList):
 
 #We don't really support characters above the BMP :(
 max_unicode = int("FFFF", 16)
-    
+
 def missingRanges(charList):
     rv = []
     if charList[0] != 0:
@@ -103,8 +103,8 @@ def escapeRegexp(string):
 
 class InfosetFilter(object):
     replacementRegexp = re.compile(r"U[\dA-F]{5,5}")
-    def __init__(self, replaceChars = None,  
-                 dropXmlnsLocalName = False, 
+    def __init__(self, replaceChars = None,
+                 dropXmlnsLocalName = False,
                  dropXmlnsAttrNs = False,
                  preventDoubleDashComments = False,
                  preventDashAtCommentEnd = False,
@@ -124,7 +124,7 @@ def coerceAttribute(self, name, namespace=None):
         if self.dropXmlnsLocalName and name.startswith("xmlns:"):
             warnings.warn("Attributes cannot begin with xmlns", DataLossWarning)
             return None
-        elif (self.dropXmlnsAttrNs and 
+        elif (self.dropXmlnsAttrNs and
               namespace == "http://www.w3.org/2000/xmlns/"):
             warnings.warn("Attributes cannot be in the xml namespace", DataLossWarning)
             return None
@@ -140,7 +140,7 @@ def coerceComment(self, data):
                 warnings.warn("Comments cannot contain adjacent dashes", DataLossWarning)
                 data = data.replace("--", "- -")
         return data
-    
+
     def coerceCharacters(self, data):
         if self.replaceFormFeedCharacters:
             for i in range(data.count("\x0C")):
@@ -166,7 +166,7 @@ def toXmlName(self, name):
             replacement = self.getReplacementCharacter(char)
             nameRestOutput = nameRestOutput.replace(char, replacement)
         return nameFirstOutput + nameRestOutput
-    
+
     def getReplacementCharacter(self, char):
         if char in self.replaceCache:
             replacement = self.replaceCache[char]