8000 A few more cases where str data is being initalized rather than unicode) · html5lib/html5lib-python@eaea9f3 · GitHub
[go: up one dir, main page]
Skip to content

Commit eaea9f3

Browse files
jgrahamjgraham
committed
A few more cases where str data is being initalized rather than unicode)
--HG-- extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%40869
1 parent fc63d15 commit eaea9f3

File tree

1 file changed

+8
-8
lines changed

1 file changed

+8
-8
lines changed

‎src/html5lib/tokenizer.py

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -627,15 +627,15 @@ def bogusCommentState(self):
627627
def markupDeclarationOpenState(self):
628628
charStack = [self.stream.char(), self.stream.char()]
629629
if charStack == [u"-", u"-"]:
630-
self.currentToken = {"type": "Comment", "data": ""}
630+
self.currentToken = {"type": "Comment", "data": u""}
631631
self.state = self.states["commentStart"]
632632
else:
633633
for x in xrange(5):
634634
charStack.append(self.stream.char())
635635
# Put in explicit EOF check
636636
if (not EOF in charStack and
637637
"".join(charStack).upper() == u"DOCTYPE"):
638-
self.currentToken = {"type":"Doctype", "name":"",
638+
self.currentToken = {"type":"Doctype", "name":u"",
639639
"publicId":None, "systemId":None, "correct":True}
640640
self.state = self.states["doctype"]
641641
else:
@@ -822,10 +822,10 @@ def beforeDoctypePublicIdentifierState(self):
822822
if data in spaceCharacters:
823823
pass
824824
elif data == "\"":
825-
self.currentToken["publicId"] = ""
825+
self.currentToken["publicId"] = u""
826826
self.state = self.states["doctypePublicIdentifierDoubleQuoted"]
827827
elif data == "'":
828-
self.currentToken["publicId"] = ""
828+
self.currentToken["publicId"] = u""
829829
self.state = self.states["doctypePublicIdentifierSingleQuoted"]
830830
elif data == ">":
831831
self.tokenQueue.append({"type": "ParseError", "data":
@@ -878,10 +878,10 @@ def afterDoctypePublicIdentifierState(self):
878878
if data in spaceCharacters:
879879
pass
880880
elif data == "\"":
881-
self.currentToken["systemId"] = ""
881+
self.currentToken["systemId"] = u""
882882
self.state = self.states["doctypeSystemIdentifierDoubleQuoted"]
883883
elif data == "'":
884-
self.currentToken["systemId"] = ""
884+
self.currentToken["systemId"] = u""
885885
self.state = self.states["doctypeSystemIdentifierSingleQuoted"]
886886
elif data == ">":
887887
self.tokenQueue.append(self.currentToken)
@@ -903,10 +903,10 @@ def beforeDoctypeSystemIdentifierState(self):
903903
if data in spaceCharacters:
904904
pass
905905
elif data == "\"":
906-
self.currentToken["systemId"] = ""
906+
self.currentToken["systemId"] = u""
907907
self.state = self.states["doctypeSystemIdentifierDoubleQuoted"]
908908
elif data == "'":
909-
self.currentToken["systemId"] = ""
909+
self.currentToken["systemId"] = u""
910910
self.state = self.states["doctypeSystemIdentifierSingleQuoted"]
911911
elif data == ">":
912912
self.tokenQueue.append({"type": "ParseError", "data":

0 commit comments

Comments
 (0)
0