Update lint filter for Py3 and namespaced attributes.

Author: gsnedders

html5lib/filters/lint.py

@@ -3,6 +3,8 @@
 from gettext import gettext
 _ = gettext
 
+from six import text_type
+
 from . import _base
 from ..constants import cdataElements, rcdataElements, voidElements
 
@@ -24,7 +26,7 @@ def __iter__(self):
                 name = token["name"]
                 if contentModelFlag != "PCDATA":
                     raise LintError(_("StartTag not in PCDATA content model flag: %(tag)s") % {"tag": name})
-                if not isinstance(name, str):
+                if not isinstance(name, text_type):
                     raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
                 if not name:
                     raise LintError(_("Empty tag name"))
@@ -34,12 +36,14 @@ def __iter__(self):
                     raise LintError(_("Non-void element reported as EmptyTag token: %(tag)s") % {"tag": token["name"]})
                 if type == "StartTag":
                     open_elements.append(name)
-                for name, value in token["data"]:
-                    if not isinstance(name, str):
+                for (ns, name), value in token["data"].items():
+                    if ns is not None and not isinstance(ns, text_type):
+                        raise LintError(_("Attribute namespace is not None or a string: %(name)r") % {"name": name})
+                    if not isinstance(name, text_type):
                         raise LintError(_("Attribute name is not a string: %(name)r") % {"name": name})
                     if not name:
                         raise LintError(_("Empty attribute name"))
-                    if not isinstance(value, str):
+                    if not isinstance(value, text_type):
                         raise LintError(_("Attribute value is not a string: %(value)r") % {"value": value})
                 if name in cdataElements:
                     contentModelFlag = "CDATA"
@@ -50,7 +54,7 @@ def __iter__(self):
 
             elif type == "EndTag":
                 name = token["name"]
-                if not isinstance(name, str):
+                if not isinstance(name, text_type):
                     raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
                 if not name:
                     raise LintError(_("Empty tag name"))
@@ -67,7 +71,7 @@ def __iter__(self):
 
             elif type in ("Characters", "SpaceCharacters"):
                 data = token["data"]
-                if not isinstance(data, str):
+                if not isinstance(data, text_type):
                     raise LintError(_("Attribute name is not a string: %(name)r") % {"name": data})
                 if not data:
                     raise LintError(_("%(type)s token with empty data") % {"type": type})
@@ -80,7 +84,7 @@ def __iter__(self):
                 name = token["name"]
                 if contentModelFlag != "PCDATA":
                     raise LintError(_("Doctype not in PCDATA content model flag: %(name)s") % {"name": name})
-                if not isinstance(name, str):
+                if not isinstance(name, text_type):
                     raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
                 # XXX: what to do with token["data"] ?