from __future__ import absolute_import, division, unicode_literals from pip._vendor.six import with_metaclass import types from . import inputstream from . import tokenizer from . import treebuilders from .treebuilders._base import Marker 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 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="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.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, 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 """ # 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).items()]) def _parse(self, stream, innerHTML=False, container="div", encoding=None, parseMeta=True, useChardet=True, **kwargs): self.innerHTMLMode = innerHTML self.container = container self.tokenizer = self.tokenizer_class(stream, encoding=encoding, parseMeta=parseMeta, useChardet=useChardet, parser=self, **kwargs) self.reset() while True: try: self.mainLoop() break except ReparseException: self.reset() 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 self.phase = self.phases["initial"] self.lastPhase = None self.beforeRCDataPhase = None self.framesetOK = True 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.normalizedTokens(): new_token = token while new_token is not None: 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 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 token["selfClosing"] and not token["selfClosingAcknowledged"]): self.parseError("non-void-element-with-trailing-solidus", {"name": 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 normalizedTokens(self): for token in self.tokenizer: yield self.normalizeToken(token) def parse(self, stream, encoding=None, parseMeta=True, useChardet=True): """Parse a HTML document into a well-formed tree stream - a filelike 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) """ 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' stream - a filelike 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) """ self._parse(stream, True, container=container, encoding=encoding) return self.tree.getFragment() def parseError(self, errorcode="XXX-undefined-error", datavars={}): # XXX The idea is to make errorcode mandatory. self.errors.append((self.tokenizer.stream.position(), errorcode, datavars)) if self.strict: raise ParseError def normalizeToken(self, token): """ HTML5 specific normalizations to the token stream """ if token["type"] == tokenTypes["StartTag"]: token["data"] = dict(token["data"][::-1]) return token def adjustMathMLAttributes(self, token): 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": "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"]) } for originalName in token["data"].keys(): if originalName in replacements: foreignName = replacements[originalName] token["data"][foreignName] = token["data"][originalName] del token["data"][originalName] def reparseTokenNormal(self, token): 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 contentType - RCDATA or RAWTEXT """ 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"] 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.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']]} 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__, 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 class Phase(with_metaclass(getMetaclass(debug, log))): """Base class for helper object that implements each phase of processing """ def __init__(self, parser, tree): self.parser = parser self.tree = tree 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): return self.startTagHandler[token["name"]](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): return self.endTagHandler[token["name"]](token) class InitialPhase(Phase): 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): # 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): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) self.startTagHandler = utils.MethodDispatcher([ ("html", self.startTagHtml), ("head", self.startTagHead) ]) self.startTagHandler.default = self.startTagOther self.endTagHandler = utils.MethodDispatcher([ (("head", "body", "html", "br"), self.endTagImplyHead) ]) self.endTagHandler.default = self.endTagOther 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"]}) class InHeadPhase(Phase): def __init__(self, parser, tree): Phase.__init__(self, parser, tree) self.startTagHandler = utils.MethodDispatcher([ ("html", self.startTagHtml), ("title", self.startTagTitle), (("noscript", "noframes", "style"), self.startTagNoScriptNoFramesStyle), ("script", self.startTagScript), (("base", "basefont", "bgsound", "command", "link"), self.startTagBaseLinkCommand), ("meta", self.startTagMeta), ("head", self.startTagHead) ]) self.startTagHandler.default = self.startTagOther self. endTagHandler = utils.MethodDispatcher([ ("head", self.endTagHead), (("br", "html", "body"), self.endTagHtmlBodyBr) ]) self.endTagHandler.default = self.endTagOther # 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 startTagNoScriptNoFramesStyle(self, token): # Need to decide whether to implement the scripting-disabled case self.parser.parseRCDataRawtext(token, "RAWTEXT") 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")) # 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) self.startTagHandler = utils.MethodDispatcher([ ("html", self.startTagHtml), ("body", self.startTagBody), ("frameset", self.startTagFrameset), (("base", "basefont", "bgsound", "link", "meta", "noframes", "script", "style", "title"), self.startTagFromHead), ("head", self.startTagHead) ]) self.startTagHandler.default = self.startTagOther self.endTagHandler = utils.MethodDispatcher([(("body", "html", "br"), self.endTagHtmlBodyBr)]) self.endTagHandler.default = self.endTagOther 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 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 
            self.processSpaceCharactersNonPre = self.processSpaceCharacters

            self.startTagHandler = utils.MethodDispatcher([
                ("html", self.startTagHtml),
                (("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", "main", "menu", "nav", "ol", "p",
                  "section", "summary", "ul"),
                 self.startTagCloseP),
                (headingElements, self.startTagHeading),
                (("pre", "listing"), self.startTagPreListing),
                ("form", self.startTagForm),
                (("li", "dd", "dt"), self.startTagListItem),
                ("plaintext", self.startTagPlaintext),
                ("a", self.startTagA),
                (("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),
                ("xmp", self.startTagXmp),
                ("table", self.startTagTable),
                (("area", "br", "embed", "img", "keygen", "wbr"),
                 self.startTagVoidFormatting),
                (("param", "source", "track"), self.startTagParamSource),
                ("input", self.startTagInput),
                ("hr", self.startTagHr),
                ("image", self.startTagImage),
                ("isindex", self.startTagIsIndex),
                ("textarea", self.startTagTextarea),
                ("iframe", self.startTagIFrame),
                (("noembed", "noframes", "noscript"), self.startTagRawtext),
                ("select", self.startTagSelect),
                (("rp", "rt"), self.startTagRpRt),
                (("option", "optgroup"), self.startTagOpt),
                (("math"), self.startTagMath),
                (("svg"), self.startTagSvg),
                (("caption", "col", "colgroup", "frame", "head",
                  "tbody", "td", "tfoot", "th", "thead",
                  "tr"), self.startTagMisplaced)
            ])
            self.startTagHandler.default = self.startTagOther

            self.endTagHandler = utils.MethodDispatcher([
                ("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),
                (("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),
                ("br", self.endTagBr),
            ])
            self.endTagHandler.default = self.endTagOther

        def isMatchingFormattingElement(self, node1, node2):
            if node1.name != node2.name or node1.namespace != node2.namespace:
                return False
            elif len(node1.attributes) != len(node2.attributes):
                return False
            else:
                attributes1 = sorted(node1.attributes.items())
                attributes2 = sorted(node2.attributes.items())
                for attr1, attr2 in zip(attributes1, attributes2):
                    if attr1 != attr2:
                        return False
            return True

        # 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