Apr 9, 2014 · Apr 7, 2014
diff --git a/html5lib/html5parser.py b/html5lib/html5parser.py
            attributes["name"] = "isindex"
            self.processStartTag(impliedTagToken("input", "StartTag",
                                                 attributes=attributes,
                                                 selfClosing=
                                                 token["selfClosing"]))
                                                 selfClosing=token["selfClosing"]))
            self.processEndTag(impliedTagToken("label"))
            self.processStartTag(impliedTagToken("hr", "StartTag"))
            self.processEndTag(impliedTagToken("form"))
diff --git a/html5lib/sanitizer.py b/html5lib/sanitizer.py
            elif prop.split('-')[0].lower() in ['background', 'border', 'margin',
                                                'padding']:
                for keyword in value.split():
                    ifnotkeyword in self.acceptable_css_keywords and \
                    if keyword not in self.acceptable_css_keywords and \
                            not re.match("^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword):
                        break
                else:
diff --git a/html5lib/serializer/htmlserializer.py b/html5lib/serializer/htmlserializer.py
                v = utils.surrogatePairToCodepoint(v)
            else:
                v = ord(v)
            ifnot v in encode_entity_map or k.islower():
            ifv not in encode_entity_map or k.islower():
                # prefer &lt; over &LT; and similarly for &amp;, &gt;, etc.
                encode_entity_map[v] = k

            elif type == "Entity":
                name = token["name"]
                key = name + ";"
                ifnotkey in entities:
                if key not in entities:
                    self.serializeError(_("Entity %s not recognized" % name))
                if self.resolve_entities and key not in xmlEntities:
                    data = entities[key]
diff --git a/html5lib/tests/test_tokenizer.py b/html5lib/tests/test_tokenizer.py
 def concatenateCharacterTokens(tokens):
    outputTokens = []
    for token in tokens:
        ifnot"ParseError" in token and token[0] == "Character":
            if (outputTokens andnot"ParseError" in outputTokens[-1] and
        if "ParseError" not in token and token[0] == "Character":
            if (outputTokens and "ParseError" not in outputTokens[-1] and
                    outputTokens[-1][0] == "Character"):
                outputTokens[-1][1] += token[1]
            else:
        # Sort the tokens into two groups; non-parse errors and parse errors
        tokens = {"expected": [[], []], "received": [[], []]}
        for tokenType, tokenList in zip(list(tokens.keys()),
                                       (expectedTokens, receivedTokens)):
 (expectedTokens, receivedTokens)):
            for token in tokenList:
                if token != "ParseError":
                    tokens[tokenType][0].append(token)
diff --git a/html5lib/treebuilders/dom.py b/html5lib/treebuilders/dom.py
            else:
                # HACK: allow text nodes as children of the document node
                if hasattr(self.dom, '_child_node_types'):
                    ifnotNode.TEXT_NODE in self.dom._child_node_types:
                    if Node.TEXT_NODE not in self.dom._child_node_types:
                        self.dom._child_node_types = list(self.dom._child_node_types)
                        self.dom._child_node_types.append(Node.TEXT_NODE)
                self.dom.appendChild(self.dom.createTextNode(data))
Original file line number	Diff line number	Diff line change
Expand Up		@@ -1216,8 +1216,7 @@ def startTagIsIndex(self, token):
		attributes["name"] = "isindex"
		self.processStartTag(impliedTagToken("input", "StartTag",
		attributes=attributes,
		selfClosing=
		token["selfClosing"]))
		selfClosing=token["selfClosing"]))
		self.processEndTag(impliedTagToken("label"))
		self.processStartTag(impliedTagToken("hr", "StartTag"))
		self.processEndTag(impliedTagToken("form"))
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -245,7 +245,7 @@ def sanitize_css(self, style):
		elif prop.split('-')[0].lower() in ['background', 'border', 'margin',
		'padding']:
		for keyword in value.split():
		ifnotkeyword in self.acceptable_css_keywords and \
		if keyword not in self.acceptable_css_keywords and \
		not re.match("^(#[0-9a-f]+\|rgb\(\d+%?,\d%?,?\d%?\)?\|\d{0,2}\.?\d{0,2}(cm\|em\|ex\|in\|mm\|pc\|pt\|px\|%\|,\|\))?)$", keyword):
		break
		else:
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -35,7 +35,7 @@
		v = utils.surrogatePairToCodepoint(v)
		else:
		v = ord(v)
		ifnot v in encode_entity_map or k.islower():
		ifv not in encode_entity_map or k.islower():
		# prefer < over &LT; and similarly for &, >, etc.
		encode_entity_map[v] = k

Expand DownExpand Up		@@ -291,7 +291,7 @@ def serialize(self, treewalker, encoding=None):
		elif type == "Entity":
		name = token["name"]
		key = name + ";"
		ifnotkey in entities:
		if key not in entities:
		self.serializeError(_("Entity %s not recognized" % name))
		if self.resolve_entities and key not in xmlEntities:
		data = entities[key]
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -68,8 +68,8 @@ def processParseError(self, token):
		def concatenateCharacterTokens(tokens):
		outputTokens = []
		for token in tokens:
		ifnot"ParseError" in token and token[0] == "Character":
		if (outputTokens andnot"ParseError" in outputTokens[-1] and
		if "ParseError" not in token and token[0] == "Character":
		if (outputTokens and "ParseError" not in outputTokens[-1] and
		outputTokens[-1][0] == "Character"):
		outputTokens[-1][1] += token[1]
		else:
Expand DownExpand Up		@@ -112,7 +112,7 @@ def tokensMatch(expectedTokens, receivedTokens, ignoreErrorOrder,
		# Sort the tokens into two groups; non-parse errors and parse errors
		tokens = {"expected": [[], []], "received": [[], []]}
		for tokenType, tokenList in zip(list(tokens.keys()),
		(expectedTokens, receivedTokens)):
		(expectedTokens, receivedTokens)):
		for token in tokenList:
		if token != "ParseError":
		tokens[tokenType][0].append(token)
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -158,7 +158,7 @@ def insertText(self, data, parent=None):
		else:
		# HACK: allow text nodes as children of the document node
		if hasattr(self.dom, '_child_node_types'):
		ifnotNode.TEXT_NODE in self.dom._child_node_types:
		if Node.TEXT_NODE not in self.dom._child_node_types:
		self.dom._child_node_types = list(self.dom._child_node_types)
		self.dom._child_node_types.append(Node.TEXT_NODE)
		self.dom.appendChild(self.dom.createTextNode(data))
Expand Down