s without a value= attribute")
- else:
- value_list = self.fieldStorage.getlist(field_name)
- if value_list:
- field_index = field_indices.setdefault(field_name, 0)
- if field_index < len(value_list):
- value = value_list[field_index]
- else:
- value = ""
- if (is_select_multiple or not is_selected_option_found) and option_value == value:
- if option_selected_index < 0:
- token["data"].append((u"selected", u""))
- field_indices[field_name] = field_index + 1
- is_selected_option_found = True
- elif option_selected_index >= 0:
- del token["data"][option_selected_index]
-
- elif field_type is not None and field_name and type == "EndTag":
- name = token["name"].lower()
- if name == field_type:
- if name == "textarea":
- value_list = self.fieldStorage.getlist(field_name)
- if value_list:
- field_index = field_indices.setdefault(field_name, 0)
- if field_index < len(value_list):
- value = value_list[field_index]
- else:
- value = ""
- yield {"type": "Characters", "data": value}
- field_indices[field_name] = field_index + 1
-
- field_name = None
-
- elif name == "option" and field_type == "select":
- pass # TODO: part of "option without value= attribute" processing
-
- elif field_type == "textarea":
- continue # ignore token
-
- yield token
diff --git a/lib/html5lib/filters/inject_meta_charset.py b/lib/html5lib/filters/inject_meta_charset.py
index 8e04d8ac..ca33b70b 100644
--- a/lib/html5lib/filters/inject_meta_charset.py
+++ b/lib/html5lib/filters/inject_meta_charset.py
@@ -1,4 +1,7 @@
-import _base
+from __future__ import absolute_import, division, unicode_literals
+
+from . import _base
+
class Filter(_base.Filter):
def __init__(self, source, encoding):
@@ -13,44 +16,44 @@ class Filter(_base.Filter):
for token in _base.Filter.__iter__(self):
type = token["type"]
if type == "StartTag":
- if token["name"].lower() == u"head":
+ if token["name"].lower() == "head":
state = "in_head"
elif type == "EmptyTag":
- if token["name"].lower() == u"meta":
- # replace charset with actual encoding
- has_http_equiv_content_type = False
- for (namespace,name),value in token["data"].iteritems():
- if namespace != None:
- continue
- elif name.lower() == u'charset':
- token["data"][(namespace,name)] = self.encoding
- meta_found = True
- break
- elif name == u'http-equiv' and value.lower() == u'content-type':
- has_http_equiv_content_type = True
- else:
- if has_http_equiv_content_type and (None, u"content") in token["data"]:
- token["data"][(None, u"content")] = u'text/html; charset=%s' % self.encoding
- meta_found = True
+ if token["name"].lower() == "meta":
+ # replace charset with actual encoding
+ has_http_equiv_content_type = False
+ for (namespace, name), value in token["data"].items():
+ if namespace is not None:
+ continue
+ elif name.lower() == 'charset':
+ token["data"][(namespace, name)] = self.encoding
+ meta_found = True
+ break
+ elif name == 'http-equiv' and value.lower() == 'content-type':
+ has_http_equiv_content_type = True
+ else:
+ if has_http_equiv_content_type and (None, "content") in token["data"]:
+ token["data"][(None, "content")] = 'text/html; charset=%s' % self.encoding
+ meta_found = True
- elif token["name"].lower() == u"head" and not meta_found:
+ elif token["name"].lower() == "head" and not meta_found:
# insert meta into empty head
- yield {"type": "StartTag", "name": u"head",
+ yield {"type": "StartTag", "name": "head",
"data": token["data"]}
- yield {"type": "EmptyTag", "name": u"meta",
- "data": {(None, u"charset"): self.encoding}}
- yield {"type": "EndTag", "name": u"head"}
+ yield {"type": "EmptyTag", "name": "meta",
+ "data": {(None, "charset"): self.encoding}}
+ yield {"type": "EndTag", "name": "head"}
meta_found = True
continue
elif type == "EndTag":
- if token["name"].lower() == u"head" and pending:
+ if token["name"].lower() == "head" and pending:
# insert meta into head (if necessary) and flush pending queue
yield pending.pop(0)
if not meta_found:
- yield {"type": "EmptyTag", "name": u"meta",
- "data": {(None, u"charset"): self.encoding}}
+ yield {"type": "EmptyTag", "name": "meta",
+ "data": {(None, "charset"): self.encoding}}
while pending:
yield pending.pop(0)
meta_found = True
diff --git a/lib/html5lib/filters/lint.py b/lib/html5lib/filters/lint.py
index ea5c619f..7cc99a4b 100644
--- a/lib/html5lib/filters/lint.py
+++ b/lib/html5lib/filters/lint.py
@@ -1,13 +1,18 @@
+from __future__ import absolute_import, division, unicode_literals
+
from gettext import gettext
_ = gettext
-import _base
-from html5lib.constants import cdataElements, rcdataElements, voidElements
+from . import _base
+from ..constants import cdataElements, rcdataElements, voidElements
-from html5lib.constants import spaceCharacters
-spaceCharacters = u"".join(spaceCharacters)
+from ..constants import spaceCharacters
+spaceCharacters = "".join(spaceCharacters)
+
+
+class LintError(Exception):
+ pass
-class LintError(Exception): pass
class Filter(_base.Filter):
def __iter__(self):
@@ -18,24 +23,24 @@ class Filter(_base.Filter):
if type in ("StartTag", "EmptyTag"):
name = token["name"]
if contentModelFlag != "PCDATA":
- raise LintError(_("StartTag not in PCDATA content model flag: %s") % name)
- if not isinstance(name, unicode):
- raise LintError(_(u"Tag name is not a string: %r") % name)
+ raise LintError(_("StartTag not in PCDATA content model flag: %(tag)s") % {"tag": name})
+ if not isinstance(name, str):
+ raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
if not name:
- raise LintError(_(u"Empty tag name"))
+ raise LintError(_("Empty tag name"))
if type == "StartTag" and name in voidElements:
- raise LintError(_(u"Void element reported as StartTag token: %s") % name)
+ raise LintError(_("Void element reported as StartTag token: %(tag)s") % {"tag": name})
elif type == "EmptyTag" and name not in voidElements:
- raise LintError(_(u"Non-void element reported as EmptyTag token: %s") % token["name"])
+ 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, unicode):
- raise LintError(_("Attribute name is not a string: %r") % name)
+ if not isinstance(name, str):
+ raise LintError(_("Attribute name is not a string: %(name)r") % {"name": name})
if not name:
- raise LintError(_(u"Empty attribute name"))
- if not isinstance(value, unicode):
- raise LintError(_("Attribute value is not a string: %r") % value)
+ raise LintError(_("Empty attribute name"))
+ if not isinstance(value, str):
+ raise LintError(_("Attribute value is not a string: %(value)r") % {"value": value})
if name in cdataElements:
contentModelFlag = "CDATA"
elif name in rcdataElements:
@@ -45,15 +50,15 @@ class Filter(_base.Filter):
elif type == "EndTag":
name = token["name"]
- if not isinstance(name, unicode):
- raise LintError(_(u"Tag name is not a string: %r") % name)
+ if not isinstance(name, str):
+ raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
if not name:
- raise LintError(_(u"Empty tag name"))
+ raise LintError(_("Empty tag name"))
if name in voidElements:
- raise LintError(_(u"Void element reported as EndTag token: %s") % name)
+ raise LintError(_("Void element reported as EndTag token: %(tag)s") % {"tag": name})
start_name = open_elements.pop()
if start_name != name:
- raise LintError(_(u"EndTag (%s) does not match StartTag (%s)") % (name, start_name))
+ raise LintError(_("EndTag (%(end)s) does not match StartTag (%(start)s)") % {"end": name, "start": start_name})
contentModelFlag = "PCDATA"
elif type == "Comment":
@@ -62,27 +67,27 @@ class Filter(_base.Filter):
elif type in ("Characters", "SpaceCharacters"):
data = token["data"]
- if not isinstance(data, unicode):
- raise LintError(_("Attribute name is not a string: %r") % data)
+ if not isinstance(data, str):
+ raise LintError(_("Attribute name is not a string: %(name)r") % {"name": data})
if not data:
- raise LintError(_(u"%s token with empty data") % type)
+ raise LintError(_("%(type)s token with empty data") % {"type": type})
if type == "SpaceCharacters":
data = data.strip(spaceCharacters)
if data:
- raise LintError(_(u"Non-space character(s) found in SpaceCharacters token: ") % data)
+ raise LintError(_("Non-space character(s) found in SpaceCharacters token: %(token)r") % {"token": data})
elif type == "Doctype":
name = token["name"]
if contentModelFlag != "PCDATA":
- raise LintError(_("Doctype not in PCDATA content model flag: %s") % name)
- if not isinstance(name, unicode):
- raise LintError(_(u"Tag name is not a string: %r") % name)
+ raise LintError(_("Doctype not in PCDATA content model flag: %(name)s") % {"name": name})
+ if not isinstance(name, str):
+ raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
# XXX: what to do with token["data"] ?
elif type in ("ParseError", "SerializeError"):
pass
else:
- raise LintError(_(u"Unknown token type: %s") % type)
+ raise LintError(_("Unknown token type: %(type)s") % {"type": type})
yield token
diff --git a/lib/html5lib/filters/optionaltags.py b/lib/html5lib/filters/optionaltags.py
index a77aa72c..fefe0b30 100644
--- a/lib/html5lib/filters/optionaltags.py
+++ b/lib/html5lib/filters/optionaltags.py
@@ -1,4 +1,7 @@
-import _base
+from __future__ import absolute_import, division, unicode_literals
+
+from . import _base
+
class Filter(_base.Filter):
def slider(self):
@@ -14,8 +17,8 @@ class Filter(_base.Filter):
for previous, token, next in self.slider():
type = token["type"]
if type == "StartTag":
- if (token["data"] or
- not self.is_optional_start(token["name"], previous, next)):
+ if (token["data"] or
+ not self.is_optional_start(token["name"], previous, next)):
yield token
elif type == "EndTag":
if not self.is_optional_end(token["name"], next):
@@ -73,7 +76,7 @@ class Filter(_base.Filter):
# omit the thead and tfoot elements' end tag when they are
# immediately followed by a tbody element. See is_optional_end.
if previous and previous['type'] == 'EndTag' and \
- previous['name'] in ('tbody','thead','tfoot'):
+ previous['name'] in ('tbody', 'thead', 'tfoot'):
return False
return next["name"] == 'tr'
else:
@@ -121,10 +124,10 @@ class Filter(_base.Filter):
# 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
diff --git a/lib/html5lib/filters/sanitizer.py b/lib/html5lib/filters/sanitizer.py
index 00235278..b206b54e 100644
--- a/lib/html5lib/filters/sanitizer.py
+++ b/lib/html5lib/filters/sanitizer.py
@@ -1,8 +1,12 @@
-import _base
-from html5lib.sanitizer import HTMLSanitizerMixin
+from __future__ import absolute_import, division, unicode_literals
+
+from . import _base
+from ..sanitizer import HTMLSanitizerMixin
+
class Filter(_base.Filter, HTMLSanitizerMixin):
def __iter__(self):
for token in _base.Filter.__iter__(self):
token = self.sanitize_token(token)
- if token: yield token
+ if token:
+ yield token
diff --git a/lib/html5lib/filters/whitespace.py b/lib/html5lib/filters/whitespace.py
index 74d6f4d8..dfc60eeb 100644
--- a/lib/html5lib/filters/whitespace.py
+++ b/lib/html5lib/filters/whitespace.py
@@ -1,16 +1,13 @@
-try:
- frozenset
-except NameError:
- # Import from the sets module for python 2.3
- from sets import ImmutableSet as frozenset
+from __future__ import absolute_import, division, unicode_literals
import re
-import _base
-from html5lib.constants import rcdataElements, spaceCharacters
-spaceCharacters = u"".join(spaceCharacters)
+from . import _base
+from ..constants import rcdataElements, spaceCharacters
+spaceCharacters = "".join(spaceCharacters)
+
+SPACES_REGEX = re.compile("[%s]+" % spaceCharacters)
-SPACES_REGEX = re.compile(u"[%s]+" % spaceCharacters)
class Filter(_base.Filter):
@@ -21,7 +18,7 @@ class Filter(_base.Filter):
for token in _base.Filter.__iter__(self):
type = token["type"]
if type == "StartTag" \
- and (preserve or token["name"] in self.spacePreserveElements):
+ and (preserve or token["name"] in self.spacePreserveElements):
preserve += 1
elif type == "EndTag" and preserve:
@@ -29,13 +26,13 @@ class Filter(_base.Filter):
elif not preserve and type == "SpaceCharacters" and token["data"]:
# Test on token["data"] above to not introduce spaces where there were not
- token["data"] = u" "
+ token["data"] = " "
elif not preserve and type == "Characters":
token["data"] = collapse_spaces(token["data"])
yield token
+
def collapse_spaces(text):
return SPACES_REGEX.sub(' ', text)
-
diff --git a/lib/html5lib/html5parser.py b/lib/html5lib/html5parser.py
index 08a8f8ad..b0f14f39 100644
--- a/lib/html5lib/html5parser.py
+++ b/lib/html5lib/html5parser.py
@@ -1,89 +1,65 @@
-try:
- frozenset
-except NameError:
- # Import from the sets module for python 2.3
- from sets import Set as set
- from sets import ImmutableSet as frozenset
+from __future__ import absolute_import, division, unicode_literals
+from six import with_metaclass
-try:
- any
-except:
- # Implement 'any' for python 2.4 and previous
- def any(iterable):
- for element in iterable:
- if element:
- return True
- return False
-
-try:
- "abc".startswith(("a", "b"))
- def startswithany(str, prefixes):
- return str.startswith(prefixes)
-except:
- # Python 2.4 doesn't accept a tuple as argument to string startswith
- def startswithany(str, prefixes):
- for prefix in prefixes:
- if str.startswith(prefix):
- return True
- return False
-
-import sys
import types
-import inputstream
-import tokenizer
+from . import inputstream
+from . import tokenizer
-import treebuilders
-from treebuilders._base import Marker
-from treebuilders import simpletree
+from . import treebuilders
+from .treebuilders._base import Marker
-import utils
-import constants
-from constants import spaceCharacters, asciiUpper2Lower
-from constants import formattingElements, specialElements
-from constants import headingElements, tableInsertModeElements
-from constants import cdataElements, rcdataElements, voidElements
-from constants import tokenTypes, ReparseException, namespaces, spaceCharacters
-from constants import htmlIntegrationPointElements, mathmlTextIntegrationPointElements
+from . import utils
+from . import constants
+from .constants import spaceCharacters, asciiUpper2Lower
+from .constants import specialElements
+from .constants import headingElements
+from .constants import cdataElements, rcdataElements
+from .constants import tokenTypes, ReparseException, namespaces
+from .constants import htmlIntegrationPointElements, mathmlTextIntegrationPointElements
+from .constants import adjustForeignAttributes as adjustForeignAttributesMap
-def parse(doc, treebuilder="simpletree", encoding=None,
+
+def parse(doc, treebuilder="etree", encoding=None,
namespaceHTMLElements=True):
"""Parse a string or file-like object into a tree"""
tb = treebuilders.getTreeBuilder(treebuilder)
p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
return p.parse(doc, encoding=encoding)
-def parseFragment(doc, container="div", treebuilder="simpletree", encoding=None,
+
+def parseFragment(doc, container="div", treebuilder="etree", encoding=None,
namespaceHTMLElements=True):
tb = treebuilders.getTreeBuilder(treebuilder)
p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
return p.parseFragment(doc, container=container, encoding=encoding)
+
def method_decorator_metaclass(function):
class Decorated(type):
def __new__(meta, classname, bases, classDict):
- for attributeName, attribute in classDict.iteritems():
- if type(attribute) == types.FunctionType:
+ for attributeName, attribute in classDict.items():
+ if isinstance(attribute, types.FunctionType):
attribute = function(attribute)
classDict[attributeName] = attribute
- return type.__new__(meta, classname, bases, classDict)
+ return type.__new__(meta, classname, bases, classDict)
return Decorated
+
class HTMLParser(object):
"""HTML parser. Generates a tree structure from a stream of (possibly
malformed) HTML"""
- def __init__(self, tree = simpletree.TreeBuilder,
- tokenizer = tokenizer.HTMLTokenizer, strict = False,
- namespaceHTMLElements = True, debug=False):
+ def __init__(self, tree=None, tokenizer=tokenizer.HTMLTokenizer,
+ strict=False, namespaceHTMLElements=True, debug=False):
"""
strict - raise an exception when a parse error is encountered
tree - a treebuilder class controlling the type of tree that will be
returned. Built in treebuilders can be accessed through
html5lib.treebuilders.getTreeBuilder(treeType)
-
+
tokenizer - a class that provides a stream of tokens to the treebuilder.
This may be replaced for e.g. a sanitizer which converts some tags to
text
@@ -92,12 +68,14 @@ class HTMLParser(object):
# Raise an exception on the first error encountered
self.strict = strict
+ if tree is None:
+ tree = treebuilders.getTreeBuilder("etree")
self.tree = tree(namespaceHTMLElements)
self.tokenizer_class = tokenizer
self.errors = []
self.phases = dict([(name, cls(self, self.tree)) for name, cls in
- getPhases(debug).iteritems()])
+ getPhases(debug).items()])
def _parse(self, stream, innerHTML=False, container="div",
encoding=None, parseMeta=True, useChardet=True, **kwargs):
@@ -106,7 +84,7 @@ class HTMLParser(object):
self.container = container
self.tokenizer = self.tokenizer_class(stream, encoding=encoding,
parseMeta=parseMeta,
- useChardet=useChardet,
+ useChardet=useChardet,
parser=self, **kwargs)
self.reset()
@@ -114,14 +92,14 @@ class HTMLParser(object):
try:
self.mainLoop()
break
- except ReparseException, e:
+ except ReparseException:
self.reset()
def reset(self):
self.tree.reset()
self.firstStartTag = False
self.errors = []
- self.log = [] #only used with debug mode
+ self.log = [] # only used with debug mode
# "quirks" / "limited quirks" / "no quirks"
self.compatMode = "no quirks"
@@ -152,18 +130,18 @@ class HTMLParser(object):
self.framesetOK = True
def isHTMLIntegrationPoint(self, element):
- if (element.name == "annotation-xml" and
- element.namespace == namespaces["mathml"]):
+ if (element.name == "annotation-xml" and
+ element.namespace == namespaces["mathml"]):
return ("encoding" in element.attributes and
element.attributes["encoding"].translate(
- asciiUpper2Lower) in
+ asciiUpper2Lower) in
("text/html", "application/xhtml+xml"))
else:
return (element.namespace, element.name) in htmlIntegrationPointElements
def isMathMLTextIntegrationPoint(self, element):
return (element.namespace, element.name) in mathmlTextIntegrationPointElements
-
+
def mainLoop(self):
CharactersToken = tokenTypes["Characters"]
SpaceCharactersToken = tokenTypes["SpaceCharacters"]
@@ -172,7 +150,7 @@ class HTMLParser(object):
CommentToken = tokenTypes["Comment"]
DoctypeToken = tokenTypes["Doctype"]
ParseErrorToken = tokenTypes["ParseError"]
-
+
for token in self.normalizedTokens():
new_token = token
while new_token is not None:
@@ -181,7 +159,7 @@ class HTMLParser(object):
currentNodeName = currentNode.name if currentNode else None
type = new_token["type"]
-
+
if type == ParseErrorToken:
self.parseError(new_token["data"], new_token.get("datavars", {}))
new_token = None
@@ -191,7 +169,7 @@ class HTMLParser(object):
(self.isMathMLTextIntegrationPoint(currentNode) and
((type == StartTagToken and
token["name"] not in frozenset(["mglyph", "malignmark"])) or
- type in (CharactersToken, SpaceCharactersToken))) or
+ type in (CharactersToken, SpaceCharactersToken))) or
(currentNodeNamespace == namespaces["mathml"] and
currentNodeName == "annotation-xml" and
token["name"] == "svg") or
@@ -204,7 +182,7 @@ class HTMLParser(object):
if type == CharactersToken:
new_token = phase.processCharacters(new_token)
elif type == SpaceCharactersToken:
- new_token= phase.processSpaceCharacters(new_token)
+ new_token = phase.processSpaceCharacters(new_token)
elif type == StartTagToken:
new_token = phase.processStartTag(new_token)
elif type == EndTagToken:
@@ -215,10 +193,9 @@ class HTMLParser(object):
new_token = phase.processDoctype(new_token)
if (type == StartTagToken and token["selfClosing"]
- and not token["selfClosingAcknowledged"]):
+ and not token["selfClosingAcknowledged"]):
self.parseError("non-void-element-with-trailing-solidus",
- {"name":token["name"]})
-
+ {"name": token["name"]})
# When the loop finishes it's EOF
reprocess = True
@@ -243,14 +220,14 @@ class HTMLParser(object):
regardless of any BOM or later declaration (such as in a meta
element)
"""
- self._parse(stream, innerHTML=False, encoding=encoding,
+ self._parse(stream, innerHTML=False, encoding=encoding,
parseMeta=parseMeta, useChardet=useChardet)
return self.tree.getDocument()
-
+
def parseFragment(self, stream, container="div", encoding=None,
parseMeta=False, useChardet=True):
"""Parse a HTML fragment into a well-formed tree fragment
-
+
container - name of the element we're setting the innerHTML property
if set to None, default to 'div'
@@ -279,100 +256,87 @@ class HTMLParser(object):
return token
def adjustMathMLAttributes(self, token):
- replacements = {"definitionurl":u"definitionURL"}
- for k,v in replacements.iteritems():
+ replacements = {"definitionurl": "definitionURL"}
+ for k, v in replacements.items():
if k in token["data"]:
token["data"][v] = token["data"][k]
del token["data"][k]
def adjustSVGAttributes(self, token):
replacements = {
- "attributename":u"attributeName",
- "attributetype":u"attributeType",
- "basefrequency":u"baseFrequency",
- "baseprofile":u"baseProfile",
- "calcmode":u"calcMode",
- "clippathunits":u"clipPathUnits",
- "contentscripttype":u"contentScriptType",
- "contentstyletype":u"contentStyleType",
- "diffuseconstant":u"diffuseConstant",
- "edgemode":u"edgeMode",
- "externalresourcesrequired":u"externalResourcesRequired",
- "filterres":u"filterRes",
- "filterunits":u"filterUnits",
- "glyphref":u"glyphRef",
- "gradienttransform":u"gradientTransform",
- "gradientunits":u"gradientUnits",
- "kernelmatrix":u"kernelMatrix",
- "kernelunitlength":u"kernelUnitLength",
- "keypoints":u"keyPoints",
- "keysplines":u"keySplines",
- "keytimes":u"keyTimes",
- "lengthadjust":u"lengthAdjust",
- "limitingconeangle":u"limitingConeAngle",
- "markerheight":u"markerHeight",
- "markerunits":u"markerUnits",
- "markerwidth":u"markerWidth",
- "maskcontentunits":u"maskContentUnits",
- "maskunits":u"maskUnits",
- "numoctaves":u"numOctaves",
- "pathlength":u"pathLength",
- "patterncontentunits":u"patternContentUnits",
- "patterntransform":u"patternTransform",
- "patternunits":u"patternUnits",
- "pointsatx":u"pointsAtX",
- "pointsaty":u"pointsAtY",
- "pointsatz":u"pointsAtZ",
- "preservealpha":u"preserveAlpha",
- "preserveaspectratio":u"preserveAspectRatio",
- "primitiveunits":u"primitiveUnits",
- "refx":u"refX",
- "refy":u"refY",
- "repeatcount":u"repeatCount",
- "repeatdur":u"repeatDur",
- "requiredextensions":u"requiredExtensions",
- "requiredfeatures":u"requiredFeatures",
- "specularconstant":u"specularConstant",
- "specularexponent":u"specularExponent",
- "spreadmethod":u"spreadMethod",
- "startoffset":u"startOffset",
- "stddeviation":u"stdDeviation",
- "stitchtiles":u"stitchTiles",
- "surfacescale":u"surfaceScale",
- "systemlanguage":u"systemLanguage",
- "tablevalues":u"tableValues",
- "targetx":u"targetX",
- "targety":u"targetY",
- "textlength":u"textLength",
- "viewbox":u"viewBox",
- "viewtarget":u"viewTarget",
- "xchannelselector":u"xChannelSelector",
- "ychannelselector":u"yChannelSelector",
- "zoomandpan":u"zoomAndPan"
- }
- for originalName in token["data"].keys():
+ "attributename": "attributeName",
+ "attributetype": "attributeType",
+ "basefrequency": "baseFrequency",
+ "baseprofile": "baseProfile",
+ "calcmode": "calcMode",
+ "clippathunits": "clipPathUnits",
+ "contentscripttype": "contentScriptType",
+ "contentstyletype": "contentStyleType",
+ "diffuseconstant": "diffuseConstant",
+ "edgemode": "edgeMode",
+ "externalresourcesrequired": "externalResourcesRequired",
+ "filterres": "filterRes",
+ "filterunits": "filterUnits",
+ "glyphref": "glyphRef",
+ "gradienttransform": "gradientTransform",
+ "gradientunits": "gradientUnits",
+ "kernelmatrix": "kernelMatrix",
+ "kernelunitlength": "kernelUnitLength",
+ "keypoints": "keyPoints",
+ "keysplines": "keySplines",
+ "keytimes": "keyTimes",
+ "lengthadjust": "lengthAdjust",
+ "limitingconeangle": "limitingConeAngle",
+ "markerheight": "markerHeight",
+ "markerunits": "markerUnits",
+ "markerwidth": "markerWidth",
+ "maskcontentunits": "maskContentUnits",
+ "maskunits": "maskUnits",
+ "numoctaves": "numOctaves",
+ "pathlength": "pathLength",
+ "patterncontentunits": "patternContentUnits",
+ "patterntransform": "patternTransform",
+ "patternunits": "patternUnits",
+ "pointsatx": "pointsAtX",
+ "pointsaty": "pointsAtY",
+ "pointsatz": "pointsAtZ",
+ "preservealpha": "preserveAlpha",
+ "preserveaspectratio": "preserveAspectRatio",
+ "primitiveunits": "primitiveUnits",
+ "refx": "refX",
+ "refy": "refY",
+ "repeatcount": "repeatCount",
+ "repeatdur": "repeatDur",
+ "requiredextensions": "requiredExtensions",
+ "requiredfeatures": "requiredFeatures",
+ "specularconstant": "specularConstant",
+ "specularexponent": "specularExponent",
+ "spreadmethod": "spreadMethod",
+ "startoffset": "startOffset",
+ "stddeviation": "stdDeviation",
+ "stitchtiles": "stitchTiles",
+ "surfacescale": "surfaceScale",
+ "systemlanguage": "systemLanguage",
+ "tablevalues": "tableValues",
+ "targetx": "targetX",
+ "targety": "targetY",
+ "textlength": "textLength",
+ "viewbox": "viewBox",
+ "viewtarget": "viewTarget",
+ "xchannelselector": "xChannelSelector",
+ "ychannelselector": "yChannelSelector",
+ "zoomandpan": "zoomAndPan"
+ }
+ for originalName in list(token["data"].keys()):
if originalName in replacements:
svgName = replacements[originalName]
token["data"][svgName] = token["data"][originalName]
del token["data"][originalName]
def adjustForeignAttributes(self, token):
- replacements = {
- "xlink:actuate":("xlink", "actuate", namespaces["xlink"]),
- "xlink:arcrole":("xlink", "arcrole", namespaces["xlink"]),
- "xlink:href":("xlink", "href", namespaces["xlink"]),
- "xlink:role":("xlink", "role", namespaces["xlink"]),
- "xlink:show":("xlink", "show", namespaces["xlink"]),
- "xlink:title":("xlink", "title", namespaces["xlink"]),
- "xlink:type":("xlink", "type", namespaces["xlink"]),
- "xml:base":("xml", "base", namespaces["xml"]),
- "xml:lang":("xml", "lang", namespaces["xml"]),
- "xml:space":("xml", "space", namespaces["xml"]),
- "xmlns":(None, "xmlns", namespaces["xmlns"]),
- "xmlns:xlink":("xmlns", "xlink", namespaces["xmlns"])
- }
+ replacements = adjustForeignAttributesMap
- for originalName in token["data"].iterkeys():
+ for originalName in token["data"].keys():
if originalName in replacements:
foreignName = replacements[originalName]
token["data"][foreignName] = token["data"][originalName]
@@ -386,20 +350,20 @@ class HTMLParser(object):
# specification.)
last = False
newModes = {
- "select":"inSelect",
- "td":"inCell",
- "th":"inCell",
- "tr":"inRow",
- "tbody":"inTableBody",
- "thead":"inTableBody",
- "tfoot":"inTableBody",
- "caption":"inCaption",
- "colgroup":"inColumnGroup",
- "table":"inTable",
- "head":"inBody",
- "body":"inBody",
- "frameset":"inFrameset",
- "html":"beforeHead"
+ "select": "inSelect",
+ "td": "inCell",
+ "th": "inCell",
+ "tr": "inRow",
+ "tbody": "inTableBody",
+ "thead": "inTableBody",
+ "tfoot": "inTableBody",
+ "caption": "inCaption",
+ "colgroup": "inColumnGroup",
+ "table": "inTable",
+ "head": "inBody",
+ "body": "inBody",
+ "frameset": "inFrameset",
+ "html": "beforeHead"
}
for node in self.tree.openElements[::-1]:
nodeName = node.name
@@ -430,9 +394,9 @@ class HTMLParser(object):
contentType - RCDATA or RAWTEXT
"""
assert contentType in ("RAWTEXT", "RCDATA")
-
- element = self.tree.insertElement(token)
-
+
+ self.tree.insertElement(token)
+
if contentType == "RAWTEXT":
self.tokenizer.state = self.tokenizer.rawtextState
else:
@@ -442,25 +406,27 @@ class HTMLParser(object):
self.phase = self.phases["text"]
+
def getPhases(debug):
def log(function):
"""Logger that records which phase processes each token"""
- type_names = dict((value, key) for key, value in
- constants.tokenTypes.iteritems())
+ type_names = dict((value, key) for key, value in
+ constants.tokenTypes.items())
+
def wrapped(self, *args, **kwargs):
if function.__name__.startswith("process") and len(args) > 0:
token = args[0]
try:
- info = {"type":type_names[token['type']]}
+ info = {"type": type_names[token['type']]}
except:
raise
if token['type'] in constants.tagTokenTypes:
info["name"] = token['name']
self.parser.log.append((self.parser.tokenizer.state.__name__,
- self.parser.phase.__class__.__name__,
- self.__class__.__name__,
- function.__name__,
+ self.parser.phase.__class__.__name__,
+ self.__class__.__name__,
+ function.__name__,
info))
return function(self, *args, **kwargs)
else:
@@ -473,21 +439,9 @@ def getPhases(debug):
else:
return type
- class Phase(object):
+ class Phase(with_metaclass(getMetaclass(debug, log))):
"""Base class for helper object that implements each phase of processing
"""
- # Order should be (they can be omitted):
- # * EOF
- # * Comment
- # * Doctype
- # * SpaceCharacters
- # * Characters
- # * StartTag
- # - startTag* methods
- # * EndTag
- # - endTag* methods
-
- __metaclass__ = getMetaclass(debug, log)
def __init__(self, parser, tree):
self.parser = parser
@@ -514,11 +468,11 @@ def getPhases(debug):
return self.startTagHandler[token["name"]](token)
def startTagHtml(self, token):
- if self.parser.firstStartTag == False and token["name"] == "html":
- self.parser.parseError("non-html-root")
+ if not self.parser.firstStartTag and token["name"] == "html":
+ self.parser.parseError("non-html-root")
# XXX Need a check here to see if the first start tag token emitted is
# this token... If it's not, invoke self.parser.parseError().
- for attr, value in token["data"].iteritems():
+ for attr, value in token["data"].items():
if attr not in self.tree.openElements[0].attributes:
self.tree.openElements[0].attributes[attr] = value
self.parser.firstStartTag = False
@@ -539,8 +493,8 @@ def getPhases(debug):
systemId = token["systemId"]
correct = token["correct"]
- if (name != "html" or publicId != None or
- systemId != None and systemId != "about:legacy-compat"):
+ if (name != "html" or publicId is not None or
+ systemId is not None and systemId != "about:legacy-compat"):
self.parser.parseError("unknown-doctype")
if publicId is None:
@@ -552,79 +506,79 @@ def getPhases(debug):
publicId = publicId.translate(asciiUpper2Lower)
if (not correct or token["name"] != "html"
- or startswithany(publicId,
- ("+//silmaril//dtd html pro v0r11 19970101//",
- "-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
- "-//as//dtd html 3.0 aswedit + extensions//",
- "-//ietf//dtd html 2.0 level 1//",
- "-//ietf//dtd html 2.0 level 2//",
- "-//ietf//dtd html 2.0 strict level 1//",
- "-//ietf//dtd html 2.0 strict level 2//",
- "-//ietf//dtd html 2.0 strict//",
- "-//ietf//dtd html 2.0//",
- "-//ietf//dtd html 2.1e//",
- "-//ietf//dtd html 3.0//",
- "-//ietf//dtd html 3.2 final//",
- "-//ietf//dtd html 3.2//",
- "-//ietf//dtd html 3//",
- "-//ietf//dtd html level 0//",
- "-//ietf//dtd html level 1//",
- "-//ietf//dtd html level 2//",
- "-//ietf//dtd html level 3//",
- "-//ietf//dtd html strict level 0//",
- "-//ietf//dtd html strict level 1//",
- "-//ietf//dtd html strict level 2//",
- "-//ietf//dtd html strict level 3//",
- "-//ietf//dtd html strict//",
- "-//ietf//dtd html//",
- "-//metrius//dtd metrius presentational//",
- "-//microsoft//dtd internet explorer 2.0 html strict//",
- "-//microsoft//dtd internet explorer 2.0 html//",
- "-//microsoft//dtd internet explorer 2.0 tables//",
- "-//microsoft//dtd internet explorer 3.0 html strict//",
- "-//microsoft//dtd internet explorer 3.0 html//",
- "-//microsoft//dtd internet explorer 3.0 tables//",
- "-//netscape comm. corp.//dtd html//",
- "-//netscape comm. corp.//dtd strict html//",
- "-//o'reilly and associates//dtd html 2.0//",
- "-//o'reilly and associates//dtd html extended 1.0//",
- "-//o'reilly and associates//dtd html extended relaxed 1.0//",
- "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
- "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
- "-//spyglass//dtd html 2.0 extended//",
- "-//sq//dtd html 2.0 hotmetal + extensions//",
- "-//sun microsystems corp.//dtd hotjava html//",
- "-//sun microsystems corp.//dtd hotjava strict html//",
- "-//w3c//dtd html 3 1995-03-24//",
- "-//w3c//dtd html 3.2 draft//",
- "-//w3c//dtd html 3.2 final//",
- "-//w3c//dtd html 3.2//",
- "-//w3c//dtd html 3.2s draft//",
- "-//w3c//dtd html 4.0 frameset//",
- "-//w3c//dtd html 4.0 transitional//",
- "-//w3c//dtd html experimental 19960712//",
- "-//w3c//dtd html experimental 970421//",
- "-//w3c//dtd w3 html//",
- "-//w3o//dtd w3 html 3.0//",
- "-//webtechs//dtd mozilla html 2.0//",
- "-//webtechs//dtd mozilla html//"))
+ or publicId.startswith(
+ ("+//silmaril//dtd html pro v0r11 19970101//",
+ "-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
+ "-//as//dtd html 3.0 aswedit + extensions//",
+ "-//ietf//dtd html 2.0 level 1//",
+ "-//ietf//dtd html 2.0 level 2//",
+ "-//ietf//dtd html 2.0 strict level 1//",
+ "-//ietf//dtd html 2.0 strict level 2//",
+ "-//ietf//dtd html 2.0 strict//",
+ "-//ietf//dtd html 2.0//",
+ "-//ietf//dtd html 2.1e//",
+ "-//ietf//dtd html 3.0//",
+ "-//ietf//dtd html 3.2 final//",
+ "-//ietf//dtd html 3.2//",
+ "-//ietf//dtd html 3//",
+ "-//ietf//dtd html level 0//",
+ "-//ietf//dtd html level 1//",
+ "-//ietf//dtd html level 2//",
+ "-//ietf//dtd html level 3//",
+ "-//ietf//dtd html strict level 0//",
+ "-//ietf//dtd html strict level 1//",
+ "-//ietf//dtd html strict level 2//",
+ "-//ietf//dtd html strict level 3//",
+ "-//ietf//dtd html strict//",
+ "-//ietf//dtd html//",
+ "-//metrius//dtd metrius presentational//",
+ "-//microsoft//dtd internet explorer 2.0 html strict//",
+ "-//microsoft//dtd internet explorer 2.0 html//",
+ "-//microsoft//dtd internet explorer 2.0 tables//",
+ "-//microsoft//dtd internet explorer 3.0 html strict//",
+ "-//microsoft//dtd internet explorer 3.0 html//",
+ "-//microsoft//dtd internet explorer 3.0 tables//",
+ "-//netscape comm. corp.//dtd html//",
+ "-//netscape comm. corp.//dtd strict html//",
+ "-//o'reilly and associates//dtd html 2.0//",
+ "-//o'reilly and associates//dtd html extended 1.0//",
+ "-//o'reilly and associates//dtd html extended relaxed 1.0//",
+ "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
+ "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
+ "-//spyglass//dtd html 2.0 extended//",
+ "-//sq//dtd html 2.0 hotmetal + extensions//",
+ "-//sun microsystems corp.//dtd hotjava html//",
+ "-//sun microsystems corp.//dtd hotjava strict html//",
+ "-//w3c//dtd html 3 1995-03-24//",
+ "-//w3c//dtd html 3.2 draft//",
+ "-//w3c//dtd html 3.2 final//",
+ "-//w3c//dtd html 3.2//",
+ "-//w3c//dtd html 3.2s draft//",
+ "-//w3c//dtd html 4.0 frameset//",
+ "-//w3c//dtd html 4.0 transitional//",
+ "-//w3c//dtd html experimental 19960712//",
+ "-//w3c//dtd html experimental 970421//",
+ "-//w3c//dtd w3 html//",
+ "-//w3o//dtd w3 html 3.0//",
+ "-//webtechs//dtd mozilla html 2.0//",
+ "-//webtechs//dtd mozilla html//"))
or publicId in
("-//w3o//dtd w3 html strict 3.0//en//",
"-/w3c/dtd html 4.0 transitional/en",
"html")
- or startswithany(publicId,
+ or publicId.startswith(
("-//w3c//dtd html 4.01 frameset//",
- "-//w3c//dtd html 4.01 transitional//")) and
- systemId == None
- or systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"):
+ "-//w3c//dtd html 4.01 transitional//")) and
+ systemId is None
+ or systemId and systemId.lower() == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"):
self.parser.compatMode = "quirks"
- elif (startswithany(publicId,
+ elif (publicId.startswith(
("-//w3c//dtd xhtml 1.0 frameset//",
"-//w3c//dtd xhtml 1.0 transitional//"))
- or startswithany(publicId,
+ or publicId.startswith(
("-//w3c//dtd html 4.01 frameset//",
- "-//w3c//dtd html 4.01 transitional//")) and
- systemId != None):
+ "-//w3c//dtd html 4.01 transitional//")) and
+ systemId is not None):
self.parser.compatMode = "limited quirks"
self.parser.phase = self.parser.phases["beforeHtml"]
@@ -640,13 +594,13 @@ def getPhases(debug):
def processStartTag(self, token):
self.parser.parseError("expected-doctype-but-got-start-tag",
- {"name": token["name"]})
+ {"name": token["name"]})
self.anythingElse()
return token
def processEndTag(self, token):
self.parser.parseError("expected-doctype-but-got-end-tag",
- {"name": token["name"]})
+ {"name": token["name"]})
self.anythingElse()
return token
@@ -655,7 +609,6 @@ def getPhases(debug):
self.anythingElse()
return True
-
class BeforeHtmlPhase(Phase):
# helper methods
def insertHtmlElement(self):
@@ -686,12 +639,11 @@ def getPhases(debug):
def processEndTag(self, token):
if token["name"] not in ("head", "body", "html", "br"):
self.parser.parseError("unexpected-end-tag-before-html",
- {"name": token["name"]})
+ {"name": token["name"]})
else:
self.insertHtmlElement()
return token
-
class BeforeHeadPhase(Phase):
def __init__(self, parser, tree):
Phase.__init__(self, parser, tree)
@@ -736,18 +688,18 @@ def getPhases(debug):
def endTagOther(self, token):
self.parser.parseError("end-tag-after-implied-root",
- {"name": token["name"]})
+ {"name": token["name"]})
class InHeadPhase(Phase):
def __init__(self, parser, tree):
Phase.__init__(self, parser, tree)
- self.startTagHandler = utils.MethodDispatcher([
+ self.startTagHandler = utils.MethodDispatcher([
("html", self.startTagHtml),
("title", self.startTagTitle),
(("noscript", "noframes", "style"), self.startTagNoScriptNoFramesStyle),
("script", self.startTagScript),
- (("base", "basefont", "bgsound", "command", "link"),
+ (("base", "basefont", "bgsound", "command", "link"),
self.startTagBaseLinkCommand),
("meta", self.startTagMeta),
("head", self.startTagHead)
@@ -761,7 +713,7 @@ def getPhases(debug):
self.endTagHandler.default = self.endTagOther
# the real thing
- def processEOF (self):
+ def processEOF(self):
self.anythingElse()
return True
@@ -789,7 +741,9 @@ def getPhases(debug):
if self.parser.tokenizer.stream.charEncoding[1] == "tentative":
if "charset" in attributes:
self.parser.tokenizer.stream.changeEncoding(attributes["charset"])
- elif "content" in attributes:
+ elif ("content" in attributes and
+ "http-equiv" in attributes and
+ attributes["http-equiv"].lower() == "content-type"):
# Encoding it as UTF-8 here is a hack, as really we should pass
# the abstract Unicode string, and just use the
# ContentAttrParser on that, but using UTF-8 allows all chars
@@ -803,7 +757,7 @@ def getPhases(debug):
self.parser.parseRCDataRawtext(token, "RCDATA")
def startTagNoScriptNoFramesStyle(self, token):
- #Need to decide whether to implement the scripting-disabled case
+ # Need to decide whether to implement the scripting-disabled case
self.parser.parseRCDataRawtext(token, "RAWTEXT")
def startTagScript(self, token):
@@ -818,7 +772,7 @@ def getPhases(debug):
def endTagHead(self, token):
node = self.parser.tree.openElements.pop()
- assert node.name == "head", "Expected head got %s"%node.name
+ assert node.name == "head", "Expected head got %s" % node.name
self.parser.phase = self.parser.phases["afterHead"]
def endTagHtmlBodyBr(self, token):
@@ -831,12 +785,10 @@ def getPhases(debug):
def anythingElse(self):
self.endTagHead(impliedTagToken("head"))
-
# XXX If we implement a parser for which scripting is disabled we need to
# implement this phase.
#
# class InHeadNoScriptPhase(Phase):
-
class AfterHeadPhase(Phase):
def __init__(self, parser, tree):
Phase.__init__(self, parser, tree)
@@ -845,13 +797,13 @@ def getPhases(debug):
("html", self.startTagHtml),
("body", self.startTagBody),
("frameset", self.startTagFrameset),
- (("base", "basefont", "bgsound", "link", "meta", "noframes", "script",
+ (("base", "basefont", "bgsound", "link", "meta", "noframes", "script",
"style", "title"),
- self.startTagFromHead),
+ self.startTagFromHead),
("head", self.startTagHead)
])
self.startTagHandler.default = self.startTagOther
- self.endTagHandler = utils.MethodDispatcher([(("body", "html", "br"),
+ self.endTagHandler = utils.MethodDispatcher([(("body", "html", "br"),
self.endTagHtmlBodyBr)])
self.endTagHandler.default = self.endTagOther
@@ -877,7 +829,7 @@ def getPhases(debug):
def startTagFromHead(self, token):
self.parser.parseError("unexpected-start-tag-out-of-my-head",
- {"name": token["name"]})
+ {"name": token["name"]})
self.tree.openElements.append(self.tree.headPointer)
self.parser.phases["inHead"].processStartTag(token)
for node in self.tree.openElements[::-1]:
@@ -886,7 +838,7 @@ def getPhases(debug):
break
def startTagHead(self, token):
- self.parser.parseError("unexpected-start-tag", {"name":token["name"]})
+ self.parser.parseError("unexpected-start-tag", {"name": token["name"]})
def startTagOther(self, token):
self.anythingElse()
@@ -897,43 +849,42 @@ def getPhases(debug):
return token
def endTagOther(self, token):
- self.parser.parseError("unexpected-end-tag", {"name":token["name"]})
+ self.parser.parseError("unexpected-end-tag", {"name": token["name"]})
def anythingElse(self):
self.tree.insertElement(impliedTagToken("body", "StartTag"))
self.parser.phase = self.parser.phases["inBody"]
self.parser.framesetOK = True
-
class InBodyPhase(Phase):
# http://www.whatwg.org/specs/web-apps/current-work/#parsing-main-inbody
# the really-really-really-very crazy mode
def __init__(self, parser, tree):
Phase.__init__(self, parser, tree)
- #Keep a ref to this for special handling of whitespace in
+ # Keep a ref to this for special handling of whitespace in
self.processSpaceCharactersNonPre = self.processSpaceCharacters
self.startTagHandler = utils.MethodDispatcher([
("html", self.startTagHtml),
- (("base", "basefont", "bgsound", "command", "link", "meta",
- "noframes", "script", "style", "title"),
+ (("base", "basefont", "bgsound", "command", "link", "meta",
+ "noframes", "script", "style", "title"),
self.startTagProcessInHead),
("body", self.startTagBody),
("frameset", self.startTagFrameset),
(("address", "article", "aside", "blockquote", "center", "details",
"details", "dir", "div", "dl", "fieldset", "figcaption", "figure",
- "footer", "header", "hgroup", "menu", "nav", "ol", "p",
+ "footer", "header", "hgroup", "main", "menu", "nav", "ol", "p",
"section", "summary", "ul"),
- self.startTagCloseP),
+ self.startTagCloseP),
(headingElements, self.startTagHeading),
(("pre", "listing"), self.startTagPreListing),
("form", self.startTagForm),
(("li", "dd", "dt"), self.startTagListItem),
- ("plaintext",self.startTagPlaintext),
+ ("plaintext", self.startTagPlaintext),
("a", self.startTagA),
- (("b", "big", "code", "em", "font", "i", "s", "small", "strike",
- "strong", "tt", "u"),self.startTagFormatting),
+ (("b", "big", "code", "em", "font", "i", "s", "small", "strike",
+ "strong", "tt", "u"), self.startTagFormatting),
("nobr", self.startTagNobr),
("button", self.startTagButton),
(("applet", "marquee", "object"), self.startTagAppletMarqueeObject),
@@ -961,21 +912,21 @@ def getPhases(debug):
self.startTagHandler.default = self.startTagOther
self.endTagHandler = utils.MethodDispatcher([
- ("body",self.endTagBody),
- ("html",self.endTagHtml),
- (("address", "article", "aside", "blockquote", "center",
- "details", "dir", "div", "dl", "fieldset", "figcaption", "figure",
- "footer", "header", "hgroup", "listing", "menu", "nav", "ol", "pre",
+ ("body", self.endTagBody),
+ ("html", self.endTagHtml),
+ (("address", "article", "aside", "blockquote", "button", "center",
+ "details", "dialog", "dir", "div", "dl", "fieldset", "figcaption", "figure",
+ "footer", "header", "hgroup", "listing", "main", "menu", "nav", "ol", "pre",
"section", "summary", "ul"), self.endTagBlock),
("form", self.endTagForm),
- ("p",self.endTagP),
+ ("p", self.endTagP),
(("dd", "dt", "li"), self.endTagListItem),
(headingElements, self.endTagHeading),
(("a", "b", "big", "code", "em", "font", "i", "nobr", "s", "small",
"strike", "strong", "tt", "u"), self.endTagFormatting),
- (("applet", "marquee", "object"), self.endTagAppletMarqueeObject),
+ (("applet", "marquee", "object"), self.endTagAppletMarqueeObject),
("br", self.endTagBr),
- ])
+ ])
self.endTagHandler.default = self.endTagOther
def isMatchingFormattingElement(self, node1, node2):
@@ -995,14 +946,14 @@ def getPhases(debug):
def addFormattingElement(self, token):
self.tree.insertElement(token)
element = self.tree.openElements[-1]
-
+
matchingElements = []
for node in self.tree.activeFormattingElements[::-1]:
if node is Marker:
break
elif self.isMatchingFormattingElement(node, element):
matchingElements.append(node)
-
+
assert len(matchingElements) <= 3
if len(matchingElements) == 3:
self.tree.activeFormattingElements.remove(matchingElements[-1])
@@ -1017,7 +968,7 @@ def getPhases(debug):
if node.name not in allowed_elements:
self.parser.parseError("expected-closing-tag-but-got-eof")
break
- #Stop parsing
+ # Stop parsing
def processSpaceCharactersDropNewline(self, token):
# Sometimes (start of , , and "]
-},
-
-{"description": "text within "]
-},
-
-{"description": "text within "]
-}
-
-]}
\ No newline at end of file
diff --git a/lib/html5lib/tests/testdata/sniffer/htmlOrFeed.json b/lib/html5lib/tests/testdata/sniffer/htmlOrFeed.json
deleted file mode 100644
index c1506dbc..00000000
--- a/lib/html5lib/tests/testdata/sniffer/htmlOrFeed.json
+++ /dev/null
@@ -1,43 +0,0 @@
-[
- {"type": "text/html", "input": ""},
- {"type": "text/html", "input": ""},
- {"type": "text/html", "input": ""},
- {"type": "text/html", "input": ""},
- {"type": "text/html", "input": ""},
- {"type": "application/rss+xml", "input": "\n\n302 Found \n\nFound \nThe document has moved here .
\n\n"},
- {"type": "text/html", "input": "\r\n\r\n Xiaxue - Chicken pie blogger.
-#errors
-#document
-|
-|
-|
-|
-|
-#errors
-Line: 1 Col: 9 Unexpected end tag (strong). Expected DOCTYPE.
-Line: 1 Col: 9 Unexpected end tag (strong) after the (implied) root element.
-Line: 1 Col: 13 Unexpected end tag (b) after the (implied) root element.
-Line: 1 Col: 18 Unexpected end tag (em) after the (implied) root element.
-Line: 1 Col: 22 Unexpected end tag (i) after the (implied) root element.
-Line: 1 Col: 26 Unexpected end tag (u) after the (implied) root element.
-Line: 1 Col: 35 Unexpected end tag (strike) after the (implied) root element.
-Line: 1 Col: 39 Unexpected end tag (s) after the (implied) root element.
-Line: 1 Col: 47 Unexpected end tag (blink) after the (implied) root element.
-Line: 1 Col: 52 Unexpected end tag (tt) after the (implied) root element.
-Line: 1 Col: 58 Unexpected end tag (pre) after the (implied) root element.
-Line: 1 Col: 64 Unexpected end tag (big) after the (implied) root element.
-Line: 1 Col: 72 Unexpected end tag (small) after the (implied) root element.
-Line: 1 Col: 79 Unexpected end tag (font) after the (implied) root element.
-Line: 1 Col: 88 Unexpected end tag (select) after the (implied) root element.
-Line: 1 Col: 93 Unexpected end tag (h1) after the (implied) root element.
-Line: 1 Col: 98 Unexpected end tag (h2) after the (implied) root element.
-Line: 1 Col: 103 Unexpected end tag (h3) after the (implied) root element.
-Line: 1 Col: 108 Unexpected end tag (h4) after the (implied) root element.
-Line: 1 Col: 113 Unexpected end tag (h5) after the (implied) root element.
-Line: 1 Col: 118 Unexpected end tag (h6) after the (implied) root element.
-Line: 1 Col: 125 Unexpected end tag (body) after the (implied) root element.
-Line: 1 Col: 130 Unexpected end tag (br). Treated as br element.
-Line: 1 Col: 134 End tag (a) violates step 1, paragraph 1 of the adoption agency algorithm.
-Line: 1 Col: 140 This element (img) has no end tag.
-Line: 1 Col: 148 Unexpected end tag (title). Ignored.
-Line: 1 Col: 155 Unexpected end tag (span). Ignored.
-Line: 1 Col: 163 Unexpected end tag (style). Ignored.
-Line: 1 Col: 172 Unexpected end tag (script). Ignored.
-Line: 1 Col: 180 Unexpected end tag (table). Ignored.
-Line: 1 Col: 185 Unexpected end tag (th). Ignored.
-Line: 1 Col: 190 Unexpected end tag (td). Ignored.
-Line: 1 Col: 195 Unexpected end tag (tr). Ignored.
-Line: 1 Col: 203 This element (frame) has no end tag.
-Line: 1 Col: 210 This element (area) has no end tag.
-Line: 1 Col: 217 Unexpected end tag (link). Ignored.
-Line: 1 Col: 225 This element (param) has no end tag.
-Line: 1 Col: 230 This element (hr) has no end tag.
-Line: 1 Col: 238 This element (input) has no end tag.
-Line: 1 Col: 244 Unexpected end tag (col). Ignored.
-Line: 1 Col: 251 Unexpected end tag (base). Ignored.
-Line: 1 Col: 258 Unexpected end tag (meta). Ignored.
-Line: 1 Col: 269 This element (basefont) has no end tag.
-Line: 1 Col: 279 This element (bgsound) has no end tag.
-Line: 1 Col: 287 This element (embed) has no end tag.
-Line: 1 Col: 296 This element (spacer) has no end tag.
-Line: 1 Col: 300 Unexpected end tag (p). Ignored.
-Line: 1 Col: 305 End tag (dd) seen too early. Expected other end tag.
-Line: 1 Col: 310 End tag (dt) seen too early. Expected other end tag.
-Line: 1 Col: 320 Unexpected end tag (caption). Ignored.
-Line: 1 Col: 331 Unexpected end tag (colgroup). Ignored.
-Line: 1 Col: 339 Unexpected end tag (tbody). Ignored.
-Line: 1 Col: 347 Unexpected end tag (tfoot). Ignored.
-Line: 1 Col: 355 Unexpected end tag (thead). Ignored.
-Line: 1 Col: 365 End tag (address) seen too early. Expected other end tag.
-Line: 1 Col: 378 End tag (blockquote) seen too early. Expected other end tag.
-Line: 1 Col: 387 End tag (center) seen too early. Expected other end tag.
-Line: 1 Col: 393 Unexpected end tag (dir). Ignored.
-Line: 1 Col: 399 End tag (div) seen too early. Expected other end tag.
-Line: 1 Col: 404 End tag (dl) seen too early. Expected other end tag.
-Line: 1 Col: 415 End tag (fieldset) seen too early. Expected other end tag.
-Line: 1 Col: 425 End tag (listing) seen too early. Expected other end tag.
-Line: 1 Col: 432 End tag (menu) seen too early. Expected other end tag.
-Line: 1 Col: 437 End tag (ol) seen too early. Expected other end tag.
-Line: 1 Col: 442 End tag (ul) seen too early. Expected other end tag.
-Line: 1 Col: 447 End tag (li) seen too early. Expected other end tag.
-Line: 1 Col: 454 End tag (nobr) violates step 1, paragraph 1 of the adoption agency algorithm.
-Line: 1 Col: 460 This element (wbr) has no end tag.
-Line: 1 Col: 476 End tag (button) seen too early. Expected other end tag.
-Line: 1 Col: 486 End tag (marquee) seen too early. Expected other end tag.
-Line: 1 Col: 495 End tag (object) seen too early. Expected other end tag.
-Line: 1 Col: 513 Unexpected end tag (html). Ignored.
-Line: 1 Col: 513 Unexpected end tag (frameset). Ignored.
-Line: 1 Col: 520 Unexpected end tag (head). Ignored.
-Line: 1 Col: 529 Unexpected end tag (iframe). Ignored.
-Line: 1 Col: 537 This element (image) has no end tag.
-Line: 1 Col: 547 This element (isindex) has no end tag.
-Line: 1 Col: 557 Unexpected end tag (noembed). Ignored.
-Line: 1 Col: 568 Unexpected end tag (noframes). Ignored.
-Line: 1 Col: 579 Unexpected end tag (noscript). Ignored.
-Line: 1 Col: 590 Unexpected end tag (optgroup). Ignored.
-Line: 1 Col: 599 Unexpected end tag (option). Ignored.
-Line: 1 Col: 611 Unexpected end tag (plaintext). Ignored.
-Line: 1 Col: 622 Unexpected end tag (textarea). Ignored.
-#document
-|
-|
-|
-|