')
-
-
- """
- tb = treebuilders.getTreeBuilder(treebuilder)
- p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
- return p.parse(doc, **kwargs)
-
-
-def parseFragment(doc, container="div", treebuilder="etree", namespaceHTMLElements=True, **kwargs):
- """Parse an HTML fragment as a string or file-like object into a tree
-
- :arg doc: the fragment to parse as a string or file-like object
-
- :arg container: the container context to parse the fragment in
-
- :arg treebuilder: the treebuilder to use when parsing
-
- :arg namespaceHTMLElements: whether or not to namespace HTML elements
-
- :returns: parsed tree
-
- Example:
-
- >>> from html5lib.html5libparser import parseFragment
- >>> parseFragment('this is a fragment')
-
-
- """
- tb = treebuilders.getTreeBuilder(treebuilder)
- p = HTMLParser(tb, namespaceHTMLElements=namespaceHTMLElements)
- return p.parseFragment(doc, container=container, **kwargs)
-
-
-def method_decorator_metaclass(function):
- class Decorated(type):
- def __new__(meta, classname, bases, classDict):
- 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 Decorated
-
-
-class HTMLParser(object):
- """HTML parser
-
- Generates a tree structure from a stream of (possibly malformed) HTML.
-
- """
-
- def __init__(self, tree=None, strict=False, namespaceHTMLElements=True, debug=False):
- """
- :arg tree: a treebuilder class controlling the type of tree that will be
- returned. Built in treebuilders can be accessed through
- html5lib.treebuilders.getTreeBuilder(treeType)
-
- :arg strict: raise an exception when a parse error is encountered
-
- :arg namespaceHTMLElements: whether or not to namespace HTML elements
-
- :arg debug: whether or not to enable debug mode which logs things
-
- Example:
-
- >>> from html5lib.html5parser import HTMLParser
- >>> parser = HTMLParser() # generates parser with etree builder
- >>> parser = HTMLParser('lxml', strict=True) # generates parser with lxml builder which is strict
-
- """
-
- # Raise an exception on the first error encountered
- self.strict = strict
-
- if tree is None:
- tree = treebuilders.getTreeBuilder("etree")
- self.tree = tree(namespaceHTMLElements)
- self.errors = []
-
- self.phases = {name: cls(self, self.tree) for name, cls in
- getPhases(debug).items()}
-
- def _parse(self, stream, innerHTML=False, container="div", scripting=False, **kwargs):
-
- self.innerHTMLMode = innerHTML
- self.container = container
- self.scripting = scripting
- self.tokenizer = _tokenizer.HTMLTokenizer(stream, parser=self, **kwargs)
- self.reset()
-
- try:
- self.mainLoop()
- except _ReparseException:
- self.reset()
- self.mainLoop()
-
- def reset(self):
- self.tree.reset()
- self.firstStartTag = False
- self.errors = []
- self.log = [] # only used with debug mode
- # "quirks" / "limited quirks" / "no quirks"
- self.compatMode = "no quirks"
-
- if self.innerHTMLMode:
- self.innerHTML = self.container.lower()
-
- if self.innerHTML in cdataElements:
- self.tokenizer.state = self.tokenizer.rcdataState
- elif self.innerHTML in rcdataElements:
- self.tokenizer.state = self.tokenizer.rawtextState
- elif self.innerHTML == 'plaintext':
- self.tokenizer.state = self.tokenizer.plaintextState
- else:
- # state already is data state
- # self.tokenizer.state = self.tokenizer.dataState
- pass
- self.phase = self.phases["beforeHtml"]
- self.phase.insertHtmlElement()
- self.resetInsertionMode()
- else:
- self.innerHTML = False # pylint:disable=redefined-variable-type
- self.phase = self.phases["initial"]
-
- self.lastPhase = None
-
- self.beforeRCDataPhase = None
-
- self.framesetOK = True
-
- @property
- def documentEncoding(self):
- """Name of the character encoding that was used to decode the input stream, or
- :obj:`None` if that is not determined yet
-
- """
- if not hasattr(self, 'tokenizer'):
- return None
- return self.tokenizer.stream.charEncoding[0].name
-
- def isHTMLIntegrationPoint(self, element):
- if (element.name == "annotation-xml" and
- element.namespace == namespaces["mathml"]):
- return ("encoding" in element.attributes and
- element.attributes["encoding"].translate(
- 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"]
- StartTagToken = tokenTypes["StartTag"]
- EndTagToken = tokenTypes["EndTag"]
- CommentToken = tokenTypes["Comment"]
- DoctypeToken = tokenTypes["Doctype"]
- ParseErrorToken = tokenTypes["ParseError"]
-
- for token in self.tokenizer:
- prev_token = None
- new_token = token
- while new_token is not None:
- prev_token = new_token
- currentNode = self.tree.openElements[-1] if self.tree.openElements else None
- currentNodeNamespace = currentNode.namespace if currentNode else None
- 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
- else:
- if (len(self.tree.openElements) == 0 or
- currentNodeNamespace == self.tree.defaultNamespace or
- (self.isMathMLTextIntegrationPoint(currentNode) and
- ((type == StartTagToken and
- token["name"] not in frozenset(["mglyph", "malignmark"])) or
- type in (CharactersToken, SpaceCharactersToken))) or
- (currentNodeNamespace == namespaces["mathml"] and
- currentNodeName == "annotation-xml" and
- type == StartTagToken and
- token["name"] == "svg") or
- (self.isHTMLIntegrationPoint(currentNode) and
- type in (StartTagToken, CharactersToken, SpaceCharactersToken))):
- phase = self.phase
- else:
- phase = self.phases["inForeignContent"]
-
- if type == CharactersToken:
- new_token = phase.processCharacters(new_token)
- elif type == SpaceCharactersToken:
- new_token = phase.processSpaceCharacters(new_token)
- elif type == StartTagToken:
- new_token = phase.processStartTag(new_token)
- elif type == EndTagToken:
- new_token = phase.processEndTag(new_token)
- elif type == CommentToken:
- new_token = phase.processComment(new_token)
- elif type == DoctypeToken:
- new_token = phase.processDoctype(new_token)
-
- if (type == StartTagToken and prev_token["selfClosing"] and
- not prev_token["selfClosingAcknowledged"]):
- self.parseError("non-void-element-with-trailing-solidus",
- {"name": prev_token["name"]})
-
- # When the loop finishes it's EOF
- reprocess = True
- phases = []
- while reprocess:
- phases.append(self.phase)
- reprocess = self.phase.processEOF()
- if reprocess:
- assert self.phase not in phases
-
- def parse(self, stream, *args, **kwargs):
- """Parse a HTML document into a well-formed tree
-
- :arg stream: a file-like object or string containing the HTML to be parsed
-
- The optional encoding parameter must be a string that indicates
- the encoding. If specified, that encoding will be used,
- regardless of any BOM or later declaration (such as in a meta
- element).
-
- :arg scripting: treat noscript elements as if JavaScript was turned on
-
- :returns: parsed tree
-
- Example:
-
- >>> from html5lib.html5parser import HTMLParser
- >>> parser = HTMLParser()
- >>> parser.parse('
This is a doc
')
-
-
- """
- self._parse(stream, False, None, *args, **kwargs)
- return self.tree.getDocument()
-
- def parseFragment(self, stream, *args, **kwargs):
- """Parse a HTML fragment into a well-formed tree fragment
-
- :arg container: name of the element we're setting the innerHTML
- property if set to None, default to 'div'
-
- :arg stream: a file-like object or string containing the HTML to be parsed
-
- The optional encoding parameter must be a string that indicates
- the encoding. If specified, that encoding will be used,
- regardless of any BOM or later declaration (such as in a meta
- element)
-
- :arg scripting: treat noscript elements as if JavaScript was turned on
-
- :returns: parsed tree
-
- Example:
-
- >>> from html5lib.html5libparser import HTMLParser
- >>> parser = HTMLParser()
- >>> parser.parseFragment('this is a fragment')
-
-
- """
- self._parse(stream, True, *args, **kwargs)
- return self.tree.getFragment()
-
- def parseError(self, errorcode="XXX-undefined-error", datavars=None):
- # XXX The idea is to make errorcode mandatory.
- if datavars is None:
- datavars = {}
- self.errors.append((self.tokenizer.stream.position(), errorcode, datavars))
- if self.strict:
- raise ParseError(E[errorcode] % datavars)
-
- def adjustMathMLAttributes(self, token):
- adjust_attributes(token, adjustMathMLAttributes)
-
- def adjustSVGAttributes(self, token):
- adjust_attributes(token, adjustSVGAttributes)
-
- def adjustForeignAttributes(self, token):
- adjust_attributes(token, adjustForeignAttributesMap)
-
- def reparseTokenNormal(self, token):
- # pylint:disable=unused-argument
- self.parser.phase()
-
- def resetInsertionMode(self):
- # The name of this method is mostly historical. (It's also used in the
- # 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"
- }
- for node in self.tree.openElements[::-1]:
- nodeName = node.name
- new_phase = None
- if node == self.tree.openElements[0]:
- assert self.innerHTML
- last = True
- nodeName = self.innerHTML
- # Check for conditions that should only happen in the innerHTML
- # case
- if nodeName in ("select", "colgroup", "head", "html"):
- assert self.innerHTML
-
- if not last and node.namespace != self.tree.defaultNamespace:
- continue
-
- if nodeName in newModes:
- new_phase = self.phases[newModes[nodeName]]
- break
- elif last:
- new_phase = self.phases["inBody"]
- break
-
- self.phase = new_phase
-
- def parseRCDataRawtext(self, token, contentType):
- # Generic RCDATA/RAWTEXT Parsing algorithm
- assert contentType in ("RAWTEXT", "RCDATA")
-
- self.tree.insertElement(token)
-
- if contentType == "RAWTEXT":
- self.tokenizer.state = self.tokenizer.rawtextState
- else:
- self.tokenizer.state = self.tokenizer.rcdataState
-
- self.originalPhase = self.phase
-
- self.phase = self.phases["text"]
-
-
-@_utils.memoize
-def getPhases(debug):
- def log(function):
- """Logger that records which phase processes each token"""
- type_names = {value: key for key, value in tokenTypes.items()}
-
- def wrapped(self, *args, **kwargs):
- if function.__name__.startswith("process") and len(args) > 0:
- token = args[0]
- info = {"type": type_names[token['type']]}
- if token['type'] in tagTokenTypes:
- info["name"] = token['name']
-
- self.parser.log.append((self.parser.tokenizer.state.__name__,
- self.parser.phase.__class__.__name__,
- self.__class__.__name__,
- function.__name__,
- info))
- return function(self, *args, **kwargs)
- else:
- return function(self, *args, **kwargs)
- return wrapped
-
- def getMetaclass(use_metaclass, metaclass_func):
- if use_metaclass:
- return method_decorator_metaclass(metaclass_func)
- else:
- return type
-
- # pylint:disable=unused-argument
- class Phase(with_metaclass(getMetaclass(debug, log))):
- """Base class for helper object that implements each phase of processing
- """
- __slots__ = ("parser", "tree", "__startTagCache", "__endTagCache")
-
- def __init__(self, parser, tree):
- self.parser = parser
- self.tree = tree
- self.__startTagCache = {}
- self.__endTagCache = {}
-
- def processEOF(self):
- raise NotImplementedError
-
- def processComment(self, token):
- # For most phases the following is correct. Where it's not it will be
- # overridden.
- self.tree.insertComment(token, self.tree.openElements[-1])
-
- def processDoctype(self, token):
- self.parser.parseError("unexpected-doctype")
-
- def processCharacters(self, token):
- self.tree.insertText(token["data"])
-
- def processSpaceCharacters(self, token):
- self.tree.insertText(token["data"])
-
- def processStartTag(self, token):
- # Note the caching is done here rather than BoundMethodDispatcher as doing it there
- # requires a circular reference to the Phase, and this ends up with a significant
- # (CPython 2.7, 3.8) GC cost when parsing many short inputs
- name = token["name"]
- # In Py2, using `in` is quicker in general than try/except KeyError
- # In Py3, `in` is quicker when there are few cache hits (typically short inputs)
- if name in self.__startTagCache:
- func = self.__startTagCache[name]
- else:
- func = self.__startTagCache[name] = self.startTagHandler[name]
- # bound the cache size in case we get loads of unknown tags
- while len(self.__startTagCache) > len(self.startTagHandler) * 1.1:
- # this makes the eviction policy random on Py < 3.7 and FIFO >= 3.7
- self.__startTagCache.pop(next(iter(self.__startTagCache)))
- return func(token)
-
- def startTagHtml(self, token):
- 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"].items():
- if attr not in self.tree.openElements[0].attributes:
- self.tree.openElements[0].attributes[attr] = value
- self.parser.firstStartTag = False
-
- def processEndTag(self, token):
- # Note the caching is done here rather than BoundMethodDispatcher as doing it there
- # requires a circular reference to the Phase, and this ends up with a significant
- # (CPython 2.7, 3.8) GC cost when parsing many short inputs
- name = token["name"]
- # In Py2, using `in` is quicker in general than try/except KeyError
- # In Py3, `in` is quicker when there are few cache hits (typically short inputs)
- if name in self.__endTagCache:
- func = self.__endTagCache[name]
- else:
- func = self.__endTagCache[name] = self.endTagHandler[name]
- # bound the cache size in case we get loads of unknown tags
- while len(self.__endTagCache) > len(self.endTagHandler) * 1.1:
- # this makes the eviction policy random on Py < 3.7 and FIFO >= 3.7
- self.__endTagCache.pop(next(iter(self.__endTagCache)))
- return func(token)
-
- class InitialPhase(Phase):
- __slots__ = tuple()
-
- def processSpaceCharacters(self, token):
- pass
-
- def processComment(self, token):
- self.tree.insertComment(token, self.tree.document)
-
- def processDoctype(self, token):
- name = token["name"]
- publicId = token["publicId"]
- systemId = token["systemId"]
- correct = token["correct"]
-
- 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:
- publicId = ""
-
- self.tree.insertDoctype(token)
-
- if publicId != "":
- publicId = publicId.translate(asciiUpper2Lower)
-
- if (not correct or token["name"] != "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
- publicId.startswith(
- ("-//w3c//dtd html 4.01 frameset//",
- "-//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 (publicId.startswith(
- ("-//w3c//dtd xhtml 1.0 frameset//",
- "-//w3c//dtd xhtml 1.0 transitional//")) or
- publicId.startswith(
- ("-//w3c//dtd html 4.01 frameset//",
- "-//w3c//dtd html 4.01 transitional//")) and
- systemId is not None):
- self.parser.compatMode = "limited quirks"
-
- self.parser.phase = self.parser.phases["beforeHtml"]
-
- def anythingElse(self):
- self.parser.compatMode = "quirks"
- self.parser.phase = self.parser.phases["beforeHtml"]
-
- def processCharacters(self, token):
- self.parser.parseError("expected-doctype-but-got-chars")
- self.anythingElse()
- return token
-
- def processStartTag(self, token):
- self.parser.parseError("expected-doctype-but-got-start-tag",
- {"name": token["name"]})
- self.anythingElse()
- return token
-
- def processEndTag(self, token):
- self.parser.parseError("expected-doctype-but-got-end-tag",
- {"name": token["name"]})
- self.anythingElse()
- return token
-
- def processEOF(self):
- self.parser.parseError("expected-doctype-but-got-eof")
- self.anythingElse()
- return True
-
- class BeforeHtmlPhase(Phase):
- __slots__ = tuple()
-
- # helper methods
- def insertHtmlElement(self):
- self.tree.insertRoot(impliedTagToken("html", "StartTag"))
- self.parser.phase = self.parser.phases["beforeHead"]
-
- # other
- def processEOF(self):
- self.insertHtmlElement()
- return True
-
- def processComment(self, token):
- self.tree.insertComment(token, self.tree.document)
-
- def processSpaceCharacters(self, token):
- pass
-
- def processCharacters(self, token):
- self.insertHtmlElement()
- return token
-
- def processStartTag(self, token):
- if token["name"] == "html":
- self.parser.firstStartTag = True
- self.insertHtmlElement()
- return token
-
- def processEndTag(self, token):
- if token["name"] not in ("head", "body", "html", "br"):
- self.parser.parseError("unexpected-end-tag-before-html",
- {"name": token["name"]})
- else:
- self.insertHtmlElement()
- return token
-
- class BeforeHeadPhase(Phase):
- __slots__ = tuple()
-
- def processEOF(self):
- self.startTagHead(impliedTagToken("head", "StartTag"))
- return True
-
- def processSpaceCharacters(self, token):
- pass
-
- def processCharacters(self, token):
- self.startTagHead(impliedTagToken("head", "StartTag"))
- return token
-
- def startTagHtml(self, token):
- return self.parser.phases["inBody"].processStartTag(token)
-
- def startTagHead(self, token):
- self.tree.insertElement(token)
- self.tree.headPointer = self.tree.openElements[-1]
- self.parser.phase = self.parser.phases["inHead"]
-
- def startTagOther(self, token):
- self.startTagHead(impliedTagToken("head", "StartTag"))
- return token
-
- def endTagImplyHead(self, token):
- self.startTagHead(impliedTagToken("head", "StartTag"))
- return token
-
- def endTagOther(self, token):
- self.parser.parseError("end-tag-after-implied-root",
- {"name": token["name"]})
-
- startTagHandler = _utils.MethodDispatcher([
- ("html", startTagHtml),
- ("head", startTagHead)
- ])
- startTagHandler.default = startTagOther
-
- endTagHandler = _utils.MethodDispatcher([
- (("head", "body", "html", "br"), endTagImplyHead)
- ])
- endTagHandler.default = endTagOther
-
- class InHeadPhase(Phase):
- __slots__ = tuple()
-
- # the real thing
- def processEOF(self):
- self.anythingElse()
- return True
-
- def processCharacters(self, token):
- self.anythingElse()
- return token
-
- def startTagHtml(self, token):
- return self.parser.phases["inBody"].processStartTag(token)
-
- def startTagHead(self, token):
- self.parser.parseError("two-heads-are-not-better-than-one")
-
- def startTagBaseLinkCommand(self, token):
- self.tree.insertElement(token)
- self.tree.openElements.pop()
- token["selfClosingAcknowledged"] = True
-
- def startTagMeta(self, token):
- self.tree.insertElement(token)
- self.tree.openElements.pop()
- token["selfClosingAcknowledged"] = True
-
- attributes = token["data"]
- if self.parser.tokenizer.stream.charEncoding[1] == "tentative":
- if "charset" in attributes:
- self.parser.tokenizer.stream.changeEncoding(attributes["charset"])
- 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
- # to be encoded and as a ASCII-superset works.
- data = _inputstream.EncodingBytes(attributes["content"].encode("utf-8"))
- parser = _inputstream.ContentAttrParser(data)
- codec = parser.parse()
- self.parser.tokenizer.stream.changeEncoding(codec)
-
- def startTagTitle(self, token):
- self.parser.parseRCDataRawtext(token, "RCDATA")
-
- def startTagNoFramesStyle(self, token):
- # Need to decide whether to implement the scripting-disabled case
- self.parser.parseRCDataRawtext(token, "RAWTEXT")
-
- def startTagNoscript(self, token):
- if self.parser.scripting:
- self.parser.parseRCDataRawtext(token, "RAWTEXT")
- else:
- self.tree.insertElement(token)
- self.parser.phase = self.parser.phases["inHeadNoscript"]
-
- def startTagScript(self, token):
- self.tree.insertElement(token)
- self.parser.tokenizer.state = self.parser.tokenizer.scriptDataState
- self.parser.originalPhase = self.parser.phase
- self.parser.phase = self.parser.phases["text"]
-
- def startTagOther(self, token):
- self.anythingElse()
- return token
-
- def endTagHead(self, token):
- node = self.parser.tree.openElements.pop()
- assert node.name == "head", "Expected head got %s" % node.name
- self.parser.phase = self.parser.phases["afterHead"]
-
- def endTagHtmlBodyBr(self, token):
- self.anythingElse()
- return token
-
- def endTagOther(self, token):
- self.parser.parseError("unexpected-end-tag", {"name": token["name"]})
-
- def anythingElse(self):
- self.endTagHead(impliedTagToken("head"))
-
- startTagHandler = _utils.MethodDispatcher([
- ("html", startTagHtml),
- ("title", startTagTitle),
- (("noframes", "style"), startTagNoFramesStyle),
- ("noscript", startTagNoscript),
- ("script", startTagScript),
- (("base", "basefont", "bgsound", "command", "link"),
- startTagBaseLinkCommand),
- ("meta", startTagMeta),
- ("head", startTagHead)
- ])
- startTagHandler.default = startTagOther
-
- endTagHandler = _utils.MethodDispatcher([
- ("head", endTagHead),
- (("br", "html", "body"), endTagHtmlBodyBr)
- ])
- endTagHandler.default = endTagOther
-
- class InHeadNoscriptPhase(Phase):
- __slots__ = tuple()
-
- def processEOF(self):
- self.parser.parseError("eof-in-head-noscript")
- self.anythingElse()
- return True
-
- def processComment(self, token):
- return self.parser.phases["inHead"].processComment(token)
-
- def processCharacters(self, token):
- self.parser.parseError("char-in-head-noscript")
- self.anythingElse()
- return token
-
- def processSpaceCharacters(self, token):
- return self.parser.phases["inHead"].processSpaceCharacters(token)
-
- def startTagHtml(self, token):
- return self.parser.phases["inBody"].processStartTag(token)
-
- def startTagBaseLinkCommand(self, token):
- return self.parser.phases["inHead"].processStartTag(token)
-
- def startTagHeadNoscript(self, token):
- self.parser.parseError("unexpected-start-tag", {"name": token["name"]})
-
- def startTagOther(self, token):
- self.parser.parseError("unexpected-inhead-noscript-tag", {"name": token["name"]})
- self.anythingElse()
- return token
-
- def endTagNoscript(self, token):
- node = self.parser.tree.openElements.pop()
- assert node.name == "noscript", "Expected noscript got %s" % node.name
- self.parser.phase = self.parser.phases["inHead"]
-
- def endTagBr(self, token):
- self.parser.parseError("unexpected-inhead-noscript-tag", {"name": token["name"]})
- self.anythingElse()
- return token
-
- def endTagOther(self, token):
- self.parser.parseError("unexpected-end-tag", {"name": token["name"]})
-
- def anythingElse(self):
- # Caller must raise parse error first!
- self.endTagNoscript(impliedTagToken("noscript"))
-
- startTagHandler = _utils.MethodDispatcher([
- ("html", startTagHtml),
- (("basefont", "bgsound", "link", "meta", "noframes", "style"), startTagBaseLinkCommand),
- (("head", "noscript"), startTagHeadNoscript),
- ])
- startTagHandler.default = startTagOther
-
- endTagHandler = _utils.MethodDispatcher([
- ("noscript", endTagNoscript),
- ("br", endTagBr),
- ])
- endTagHandler.default = endTagOther
-
- class AfterHeadPhase(Phase):
- __slots__ = tuple()
-
- def processEOF(self):
- self.anythingElse()
- return True
-
- def processCharacters(self, token):
- self.anythingElse()
- return token
-
- def startTagHtml(self, token):
- return self.parser.phases["inBody"].processStartTag(token)
-
- def startTagBody(self, token):
- self.parser.framesetOK = False
- self.tree.insertElement(token)
- self.parser.phase = self.parser.phases["inBody"]
-
- def startTagFrameset(self, token):
- self.tree.insertElement(token)
- self.parser.phase = self.parser.phases["inFrameset"]
-
- def startTagFromHead(self, token):
- self.parser.parseError("unexpected-start-tag-out-of-my-head",
- {"name": token["name"]})
- self.tree.openElements.append(self.tree.headPointer)
- self.parser.phases["inHead"].processStartTag(token)
- for node in self.tree.openElements[::-1]:
- if node.name == "head":
- self.tree.openElements.remove(node)
- break
-
- def startTagHead(self, token):
- self.parser.parseError("unexpected-start-tag", {"name": token["name"]})
-
- def startTagOther(self, token):
- self.anythingElse()
- return token
-
- def endTagHtmlBodyBr(self, token):
- self.anythingElse()
- return token
-
- def endTagOther(self, token):
- 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
-
- startTagHandler = _utils.MethodDispatcher([
- ("html", startTagHtml),
- ("body", startTagBody),
- ("frameset", startTagFrameset),
- (("base", "basefont", "bgsound", "link", "meta", "noframes", "script",
- "style", "title"),
- startTagFromHead),
- ("head", startTagHead)
- ])
- startTagHandler.default = startTagOther
- endTagHandler = _utils.MethodDispatcher([(("body", "html", "br"),
- endTagHtmlBodyBr)])
- endTagHandler.default = endTagOther
-
- class InBodyPhase(Phase):
- # http://www.whatwg.org/specs/web-apps/current-work/#parsing-main-inbody
- # the really-really-really-very crazy mode
- __slots__ = ("processSpaceCharacters",)
-
- def __init__(self, *args, **kwargs):
- super(InBodyPhase, self).__init__(*args, **kwargs)
- # Set this to the default handler
- self.processSpaceCharacters = self.processSpaceCharactersNonPre
-
- def isMatchingFormattingElement(self, node1, node2):
- return (node1.name == node2.name and
- node1.namespace == node2.namespace and
- node1.attributes == node2.attributes)
-
- # helper
- 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])
- self.tree.activeFormattingElements.append(element)
-
- # the real deal
- def processEOF(self):
- allowed_elements = frozenset(("dd", "dt", "li", "p", "tbody", "td",
- "tfoot", "th", "thead", "tr", "body",
- "html"))
- for node in self.tree.openElements[::-1]:
- if node.name not in allowed_elements:
- self.parser.parseError("expected-closing-tag-but-got-eof")
- break
- # Stop parsing
-
- def processSpaceCharactersDropNewline(self, token):
- # Sometimes (start of
, , and ";
- support.noCloneChecked = !!div.cloneNode( true ).lastChild.defaultValue;
-
- // Support: IE <=9 only
- // IE <=9 replaces ";
- support.option = !!div.lastChild;
-} )();
-
-
-// We have to close these tags to support XHTML (#13200)
-var wrapMap = {
-
- // XHTML parsers do not magically insert elements in the
- // same way that tag soup parsers do. So we cannot shorten
- // this by omitting or other required elements.
- thead: [ 1, "
", "
" ],
- col: [ 2, "
", "
" ],
- tr: [ 2, "
", "
" ],
- td: [ 3, "
", "
" ],
-
- _default: [ 0, "", "" ]
-};
-
-wrapMap.tbody = wrapMap.tfoot = wrapMap.colgroup = wrapMap.caption = wrapMap.thead;
-wrapMap.th = wrapMap.td;
-
-// Support: IE <=9 only
-if ( !support.option ) {
- wrapMap.optgroup = wrapMap.option = [ 1, "" ];
-}
-
-
-function getAll( context, tag ) {
-
- // Support: IE <=9 - 11 only
- // Use typeof to avoid zero-argument method invocation on host objects (#15151)
- var ret;
-
- if ( typeof context.getElementsByTagName !== "undefined" ) {
- ret = context.getElementsByTagName( tag || "*" );
-
- } else if ( typeof context.querySelectorAll !== "undefined" ) {
- ret = context.querySelectorAll( tag || "*" );
-
- } else {
- ret = [];
- }
-
- if ( tag === undefined || tag && nodeName( context, tag ) ) {
- return jQuery.merge( [ context ], ret );
- }
-
- return ret;
-}
-
-
-// Mark scripts as having already been evaluated
-function setGlobalEval( elems, refElements ) {
- var i = 0,
- l = elems.length;
-
- for ( ; i < l; i++ ) {
- dataPriv.set(
- elems[ i ],
- "globalEval",
- !refElements || dataPriv.get( refElements[ i ], "globalEval" )
- );
- }
-}
-
-
-var rhtml = /<|&#?\w+;/;
-
-function buildFragment( elems, context, scripts, selection, ignored ) {
- var elem, tmp, tag, wrap, attached, j,
- fragment = context.createDocumentFragment(),
- nodes = [],
- i = 0,
- l = elems.length;
-
- for ( ; i < l; i++ ) {
- elem = elems[ i ];
-
- if ( elem || elem === 0 ) {
-
- // Add nodes directly
- if ( toType( elem ) === "object" ) {
-
- // Support: Android <=4.0 only, PhantomJS 1 only
- // push.apply(_, arraylike) throws on ancient WebKit
- jQuery.merge( nodes, elem.nodeType ? [ elem ] : elem );
-
- // Convert non-html into a text node
- } else if ( !rhtml.test( elem ) ) {
- nodes.push( context.createTextNode( elem ) );
-
- // Convert html into DOM nodes
- } else {
- tmp = tmp || fragment.appendChild( context.createElement( "div" ) );
-
- // Deserialize a standard representation
- tag = ( rtagName.exec( elem ) || [ "", "" ] )[ 1 ].toLowerCase();
- wrap = wrapMap[ tag ] || wrapMap._default;
- tmp.innerHTML = wrap[ 1 ] + jQuery.htmlPrefilter( elem ) + wrap[ 2 ];
-
- // Descend through wrappers to the right content
- j = wrap[ 0 ];
- while ( j-- ) {
- tmp = tmp.lastChild;
- }
-
- // Support: Android <=4.0 only, PhantomJS 1 only
- // push.apply(_, arraylike) throws on ancient WebKit
- jQuery.merge( nodes, tmp.childNodes );
-
- // Remember the top-level container
- tmp = fragment.firstChild;
-
- // Ensure the created nodes are orphaned (#12392)
- tmp.textContent = "";
- }
- }
- }
-
- // Remove wrapper from fragment
- fragment.textContent = "";
-
- i = 0;
- while ( ( elem = nodes[ i++ ] ) ) {
-
- // Skip elements already in the context collection (trac-4087)
- if ( selection && jQuery.inArray( elem, selection ) > -1 ) {
- if ( ignored ) {
- ignored.push( elem );
- }
- continue;
- }
-
- attached = isAttached( elem );
-
- // Append to fragment
- tmp = getAll( fragment.appendChild( elem ), "script" );
-
- // Preserve script evaluation history
- if ( attached ) {
- setGlobalEval( tmp );
- }
-
- // Capture executables
- if ( scripts ) {
- j = 0;
- while ( ( elem = tmp[ j++ ] ) ) {
- if ( rscriptType.test( elem.type || "" ) ) {
- scripts.push( elem );
- }
- }
- }
- }
-
- return fragment;
-}
-
-
-var
- rkeyEvent = /^key/,
- rmouseEvent = /^(?:mouse|pointer|contextmenu|drag|drop)|click/,
- rtypenamespace = /^([^.]*)(?:\.(.+)|)/;
-
-function returnTrue() {
- return true;
-}
-
-function returnFalse() {
- return false;
-}
-
-// Support: IE <=9 - 11+
-// focus() and blur() are asynchronous, except when they are no-op.
-// So expect focus to be synchronous when the element is already active,
-// and blur to be synchronous when the element is not already active.
-// (focus and blur are always synchronous in other supported browsers,
-// this just defines when we can count on it).
-function expectSync( elem, type ) {
- return ( elem === safeActiveElement() ) === ( type === "focus" );
-}
-
-// Support: IE <=9 only
-// Accessing document.activeElement can throw unexpectedly
-// https://bugs.jquery.com/ticket/13393
-function safeActiveElement() {
- try {
- return document.activeElement;
- } catch ( err ) { }
-}
-
-function on( elem, types, selector, data, fn, one ) {
- var origFn, type;
-
- // Types can be a map of types/handlers
- if ( typeof types === "object" ) {
-
- // ( types-Object, selector, data )
- if ( typeof selector !== "string" ) {
-
- // ( types-Object, data )
- data = data || selector;
- selector = undefined;
- }
- for ( type in types ) {
- on( elem, type, selector, data, types[ type ], one );
- }
- return elem;
- }
-
- if ( data == null && fn == null ) {
-
- // ( types, fn )
- fn = selector;
- data = selector = undefined;
- } else if ( fn == null ) {
- if ( typeof selector === "string" ) {
-
- // ( types, selector, fn )
- fn = data;
- data = undefined;
- } else {
-
- // ( types, data, fn )
- fn = data;
- data = selector;
- selector = undefined;
- }
- }
- if ( fn === false ) {
- fn = returnFalse;
- } else if ( !fn ) {
- return elem;
- }
-
- if ( one === 1 ) {
- origFn = fn;
- fn = function( event ) {
-
- // Can use an empty set, since event contains the info
- jQuery().off( event );
- return origFn.apply( this, arguments );
- };
-
- // Use same guid so caller can remove using origFn
- fn.guid = origFn.guid || ( origFn.guid = jQuery.guid++ );
- }
- return elem.each( function() {
- jQuery.event.add( this, types, fn, data, selector );
- } );
-}
-
-/*
- * Helper functions for managing events -- not part of the public interface.
- * Props to Dean Edwards' addEvent library for many of the ideas.
- */
-jQuery.event = {
-
- global: {},
-
- add: function( elem, types, handler, data, selector ) {
-
- var handleObjIn, eventHandle, tmp,
- events, t, handleObj,
- special, handlers, type, namespaces, origType,
- elemData = dataPriv.get( elem );
-
- // Only attach events to objects that accept data
- if ( !acceptData( elem ) ) {
- return;
- }
-
- // Caller can pass in an object of custom data in lieu of the handler
- if ( handler.handler ) {
- handleObjIn = handler;
- handler = handleObjIn.handler;
- selector = handleObjIn.selector;
- }
-
- // Ensure that invalid selectors throw exceptions at attach time
- // Evaluate against documentElement in case elem is a non-element node (e.g., document)
- if ( selector ) {
- jQuery.find.matchesSelector( documentElement, selector );
- }
-
- // Make sure that the handler has a unique ID, used to find/remove it later
- if ( !handler.guid ) {
- handler.guid = jQuery.guid++;
- }
-
- // Init the element's event structure and main handler, if this is the first
- if ( !( events = elemData.events ) ) {
- events = elemData.events = Object.create( null );
- }
- if ( !( eventHandle = elemData.handle ) ) {
- eventHandle = elemData.handle = function( e ) {
-
- // Discard the second event of a jQuery.event.trigger() and
- // when an event is called after a page has unloaded
- return typeof jQuery !== "undefined" && jQuery.event.triggered !== e.type ?
- jQuery.event.dispatch.apply( elem, arguments ) : undefined;
- };
- }
-
- // Handle multiple events separated by a space
- types = ( types || "" ).match( rnothtmlwhite ) || [ "" ];
- t = types.length;
- while ( t-- ) {
- tmp = rtypenamespace.exec( types[ t ] ) || [];
- type = origType = tmp[ 1 ];
- namespaces = ( tmp[ 2 ] || "" ).split( "." ).sort();
-
- // There *must* be a type, no attaching namespace-only handlers
- if ( !type ) {
- continue;
- }
-
- // If event changes its type, use the special event handlers for the changed type
- special = jQuery.event.special[ type ] || {};
-
- // If selector defined, determine special event api type, otherwise given type
- type = ( selector ? special.delegateType : special.bindType ) || type;
-
- // Update special based on newly reset type
- special = jQuery.event.special[ type ] || {};
-
- // handleObj is passed to all event handlers
- handleObj = jQuery.extend( {
- type: type,
- origType: origType,
- data: data,
- handler: handler,
- guid: handler.guid,
- selector: selector,
- needsContext: selector && jQuery.expr.match.needsContext.test( selector ),
- namespace: namespaces.join( "." )
- }, handleObjIn );
-
- // Init the event handler queue if we're the first
- if ( !( handlers = events[ type ] ) ) {
- handlers = events[ type ] = [];
- handlers.delegateCount = 0;
-
- // Only use addEventListener if the special events handler returns false
- if ( !special.setup ||
- special.setup.call( elem, data, namespaces, eventHandle ) === false ) {
-
- if ( elem.addEventListener ) {
- elem.addEventListener( type, eventHandle );
- }
- }
- }
-
- if ( special.add ) {
- special.add.call( elem, handleObj );
-
- if ( !handleObj.handler.guid ) {
- handleObj.handler.guid = handler.guid;
- }
- }
-
- // Add to the element's handler list, delegates in front
- if ( selector ) {
- handlers.splice( handlers.delegateCount++, 0, handleObj );
- } else {
- handlers.push( handleObj );
- }
-
- // Keep track of which events have ever been used, for event optimization
- jQuery.event.global[ type ] = true;
- }
-
- },
-
- // Detach an event or set of events from an element
- remove: function( elem, types, handler, selector, mappedTypes ) {
-
- var j, origCount, tmp,
- events, t, handleObj,
- special, handlers, type, namespaces, origType,
- elemData = dataPriv.hasData( elem ) && dataPriv.get( elem );
-
- if ( !elemData || !( events = elemData.events ) ) {
- return;
- }
-
- // Once for each type.namespace in types; type may be omitted
- types = ( types || "" ).match( rnothtmlwhite ) || [ "" ];
- t = types.length;
- while ( t-- ) {
- tmp = rtypenamespace.exec( types[ t ] ) || [];
- type = origType = tmp[ 1 ];
- namespaces = ( tmp[ 2 ] || "" ).split( "." ).sort();
-
- // Unbind all events (on this namespace, if provided) for the element
- if ( !type ) {
- for ( type in events ) {
- jQuery.event.remove( elem, type + types[ t ], handler, selector, true );
- }
- continue;
- }
-
- special = jQuery.event.special[ type ] || {};
- type = ( selector ? special.delegateType : special.bindType ) || type;
- handlers = events[ type ] || [];
- tmp = tmp[ 2 ] &&
- new RegExp( "(^|\\.)" + namespaces.join( "\\.(?:.*\\.|)" ) + "(\\.|$)" );
-
- // Remove matching events
- origCount = j = handlers.length;
- while ( j-- ) {
- handleObj = handlers[ j ];
-
- if ( ( mappedTypes || origType === handleObj.origType ) &&
- ( !handler || handler.guid === handleObj.guid ) &&
- ( !tmp || tmp.test( handleObj.namespace ) ) &&
- ( !selector || selector === handleObj.selector ||
- selector === "**" && handleObj.selector ) ) {
- handlers.splice( j, 1 );
-
- if ( handleObj.selector ) {
- handlers.delegateCount--;
- }
- if ( special.remove ) {
- special.remove.call( elem, handleObj );
- }
- }
- }
-
- // Remove generic event handler if we removed something and no more handlers exist
- // (avoids potential for endless recursion during removal of special event handlers)
- if ( origCount && !handlers.length ) {
- if ( !special.teardown ||
- special.teardown.call( elem, namespaces, elemData.handle ) === false ) {
-
- jQuery.removeEvent( elem, type, elemData.handle );
- }
-
- delete events[ type ];
- }
- }
-
- // Remove data and the expando if it's no longer used
- if ( jQuery.isEmptyObject( events ) ) {
- dataPriv.remove( elem, "handle events" );
- }
- },
-
- dispatch: function( nativeEvent ) {
-
- var i, j, ret, matched, handleObj, handlerQueue,
- args = new Array( arguments.length ),
-
- // Make a writable jQuery.Event from the native event object
- event = jQuery.event.fix( nativeEvent ),
-
- handlers = (
- dataPriv.get( this, "events" ) || Object.create( null )
- )[ event.type ] || [],
- special = jQuery.event.special[ event.type ] || {};
-
- // Use the fix-ed jQuery.Event rather than the (read-only) native event
- args[ 0 ] = event;
-
- for ( i = 1; i < arguments.length; i++ ) {
- args[ i ] = arguments[ i ];
- }
-
- event.delegateTarget = this;
-
- // Call the preDispatch hook for the mapped type, and let it bail if desired
- if ( special.preDispatch && special.preDispatch.call( this, event ) === false ) {
- return;
- }
-
- // Determine handlers
- handlerQueue = jQuery.event.handlers.call( this, event, handlers );
-
- // Run delegates first; they may want to stop propagation beneath us
- i = 0;
- while ( ( matched = handlerQueue[ i++ ] ) && !event.isPropagationStopped() ) {
- event.currentTarget = matched.elem;
-
- j = 0;
- while ( ( handleObj = matched.handlers[ j++ ] ) &&
- !event.isImmediatePropagationStopped() ) {
-
- // If the event is namespaced, then each handler is only invoked if it is
- // specially universal or its namespaces are a superset of the event's.
- if ( !event.rnamespace || handleObj.namespace === false ||
- event.rnamespace.test( handleObj.namespace ) ) {
-
- event.handleObj = handleObj;
- event.data = handleObj.data;
-
- ret = ( ( jQuery.event.special[ handleObj.origType ] || {} ).handle ||
- handleObj.handler ).apply( matched.elem, args );
-
- if ( ret !== undefined ) {
- if ( ( event.result = ret ) === false ) {
- event.preventDefault();
- event.stopPropagation();
- }
- }
- }
- }
- }
-
- // Call the postDispatch hook for the mapped type
- if ( special.postDispatch ) {
- special.postDispatch.call( this, event );
- }
-
- return event.result;
- },
-
- handlers: function( event, handlers ) {
- var i, handleObj, sel, matchedHandlers, matchedSelectors,
- handlerQueue = [],
- delegateCount = handlers.delegateCount,
- cur = event.target;
-
- // Find delegate handlers
- if ( delegateCount &&
-
- // Support: IE <=9
- // Black-hole SVG