Dec 3, 2015 · Dec 2, 2015
diff --git a/html5lib/filters/optionaltags.py b/html5lib/filters/optionaltags.py
        elif tagname == 'colgroup':
            # A colgroup element's start tag may be omitted if the first thing
            # inside the colgroup element is a col element, and if the element
            # is not immediatelypreceeded by another colgroup element whose
            # is not immediatelypreceded by another colgroup element whose
            # end tag has been omitted.
            if type in ("StartTag", "EmptyTag"):
                # XXX: we do not look at the preceding event, so instead we never
        elif tagname == 'tbody':
            # A tbody element's start tag may be omitted if the first thing
            # inside the tbody element is a tr element, and if the element is
            # not immediatelypreceeded by a tbody, thead, or tfoot element
            # not immediatelypreceded by a tbody, thead, or tfoot element
            # whose end tag has been omitted.
            if type == "StartTag":
                # omit the thead and tfoot elements' end tag when they are
diff --git a/html5lib/html5parser.py b/html5lib/html5parser.py
                self.tree.openElements.pop()
            if (not self.parser.innerHTML and
                    self.tree.openElements[-1].name != "frameset"):
                # If we're not in innerHTML mode and thethecurrent node is not a
                # If we're not in innerHTML mode and the current node is not a
                # "frameset" element (anymore) then switch.
                self.parser.phase = self.parser.phases["afterFrameset"]

diff --git a/html5lib/inputstream.py b/html5lib/inputstream.py
        if encoding is None and parseMeta:
            encoding = self.detectEncodingMeta()
            confidence = "tentative"
        # Guess with chardet, ifavaliable
        # Guess with chardet, ifavailable
        if encoding is None and chardet:
            confidence = "tentative"
            try:
diff --git a/html5lib/tests/support.py b/html5lib/tests/support.py
 from html5lib import treebuilders
 del base_path

 # Build a dict ofavaliable trees
 # Build a dict ofavailable trees
 treeTypes = {"DOM": treebuilders.getTreeBuilder("dom")}

 # Try whatever etree implementations areavaliable from a list that are
 # Try whatever etree implementations areavailable from a list that are
 #"supposed" to work
 try:
    import xml.etree.ElementTree as ElementTree
diff --git a/html5lib/treebuilders/etree_lxml.py b/html5lib/treebuilders/etree_lxml.py
        """Create the document root"""
        # Because of the way libxml2 works, it doesn't seem to be possible to
        # alter information like the doctype after the tree has been parsed.
        # Therefore we need to use the built-in parser to create ouriniial
        # Therefore we need to use the built-in parser to create ourinitial
        # tree, after which we can add elements like normal
        docStr = ""
        if self.doctype:
diff --git a/html5lib/utils.py b/html5lib/utils.py
        return dict.get(self, key, self.default)


 # Some utility functions todal with weirdness around UCS2 vs UCS4
 # Some utility functions todeal with weirdness around UCS2 vs UCS4
 # python builds

 def isSurrogatePair(data):
diff --git a/utils/spider.py b/utils/spider.py
                except KeyError:
                    pass

        #Remove all non-http URLs anda dd a sutiable base URL where that is
        #Remove all non-http URLs andadd a suitable base URL where that is
        #missing
        newUrls = set()
        for url in urls:
Original file line number	Diff line number	Diff line change
Expand Up		@@ -58,7 +58,7 @@ def is_optional_start(self, tagname, previous, next):
		elif tagname == 'colgroup':
		# A colgroup element's start tag may be omitted if the first thing
		# inside the colgroup element is a col element, and if the element
		# is not immediatelypreceeded by another colgroup element whose
		# is not immediatelypreceded by another colgroup element whose
		# end tag has been omitted.
		if type in ("StartTag", "EmptyTag"):
		# XXX: we do not look at the preceding event, so instead we never
Expand All		@@ -70,7 +70,7 @@ def is_optional_start(self, tagname, previous, next):
		elif tagname == 'tbody':
		# A tbody element's start tag may be omitted if the first thing
		# inside the tbody element is a tr element, and if the element is
		# not immediatelypreceeded by a tbody, thead, or tfoot element
		# not immediatelypreceded by a tbody, thead, or tfoot element
		# whose end tag has been omitted.
		if type == "StartTag":
		# omit the thead and tfoot elements' end tag when they are
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -2564,7 +2564,7 @@ def endTagFrameset(self, token):
		self.tree.openElements.pop()
		if (not self.parser.innerHTML and
		self.tree.openElements[-1].name != "frameset"):
		# If we're not in innerHTML mode and thethecurrent node is not a
		# If we're not in innerHTML mode and the current node is not a
		# "frameset" element (anymore) then switch.
		self.parser.phase = self.parser.phases["afterFrameset"]

Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -469,7 +469,7 @@ def detectEncoding(self, parseMeta=True, chardet=True):
		if encoding is None and parseMeta:
		encoding = self.detectEncodingMeta()
		confidence = "tentative"
		# Guess with chardet, ifavaliable
		# Guess with chardet, ifavailable
		if encoding is None and chardet:
		confidence = "tentative"
		try:
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -16,10 +16,10 @@
		from html5lib import treebuilders
		del base_path

		# Build a dict ofavaliable trees
		# Build a dict ofavailable trees
		treeTypes = {"DOM": treebuilders.getTreeBuilder("dom")}

		# Try whatever etree implementations areavaliable from a list that are
		# Try whatever etree implementations areavailable from a list that are
		#"supposed" to work
		try:
		import xml.etree.ElementTree as ElementTree
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -315,7 +315,7 @@ def insertRoot(self, token):
		"""Create the document root"""
		# Because of the way libxml2 works, it doesn't seem to be possible to
		# alter information like the doctype after the tree has been parsed.
		# Therefore we need to use the built-in parser to create ouriniial
		# Therefore we need to use the built-in parser to create ourinitial
		# tree, after which we can add elements like normal
		docStr = ""
		if self.doctype:
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -64,7 +64,7 @@ def __getitem__(self, key):
		return dict.get(self, key, self.default)


		# Some utility functions todal with weirdness around UCS2 vs UCS4
		# Some utility functions todeal with weirdness around UCS2 vs UCS4
		# python builds

		def isSurrogatePair(data):
Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -80,7 +80,7 @@ def updateURLs(self, tree):
		except KeyError:
		pass

		#Remove all non-http URLs anda dd a sutiable base URL where that is
		#Remove all non-http URLs andadd a suitable base URL where that is
		#missing
		newUrls = set()
		for url in urls:
Expand Down