pip._vendor.html5lib.html5parser.HTMLParser Class Reference

Inheritance diagram for pip._vendor.html5lib.html5parser.HTMLParser:

Public Member Functions
def	__init__
def	reset
def	isHTMLIntegrationPoint
def	isMathMLTextIntegrationPoint
def	mainLoop
def	normalizedTokens
def	parse
def	parseFragment
def	parseError
def	normalizeToken
def	adjustMathMLAttributes
def	adjustSVGAttributes
def	adjustForeignAttributes
def	reparseTokenNormal
def	resetInsertionMode
def	parseRCDataRawtext

Public Attributes
	strict
	tree
	tokenizer_class
	errors
	phases
	innerHTMLMode
	container
	tokenizer
	firstStartTag
	log
	compatMode
	innerHTML
	phase
	lastPhase
	beforeRCDataPhase
	framesetOK
	originalPhase

Private Member Functions
def	_parse

Detailed Description

HTML parser. Generates a tree structure from a stream of (possibly
    malformed) HTML

Constructor & Destructor Documentation

def pip._vendor.html5lib.html5parser.HTMLParser.__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

Member Function Documentation

def pip._vendor.html5lib.html5parser.HTMLParser._parse (   self,   stream,   innerHTML = False,   container = "div",   encoding = None,   parseMeta = True,   useChardet = True,   kwargs  )

private

def pip._vendor.html5lib.html5parser.HTMLParser.adjustForeignAttributes	(		self,
			token
	)

def pip._vendor.html5lib.html5parser.HTMLParser.adjustMathMLAttributes	(		self,
			token
	)

def pip._vendor.html5lib.html5parser.HTMLParser.adjustSVGAttributes	(		self,
			token
	)

def pip._vendor.html5lib.html5parser.HTMLParser.isHTMLIntegrationPoint	(		self,
			element
	)

def pip._vendor.html5lib.html5parser.HTMLParser.isMathMLTextIntegrationPoint	(		self,
			element
	)

def pip._vendor.html5lib.html5parser.HTMLParser.mainLoop

(

self

)

def pip._vendor.html5lib.html5parser.HTMLParser.normalizedTokens

(

self

)

def pip._vendor.html5lib.html5parser.HTMLParser.normalizeToken	(		self,
			token
	)

HTML5 specific normalizations to the token stream 

def pip._vendor.html5lib.html5parser.HTMLParser.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)

def pip._vendor.html5lib.html5parser.HTMLParser.parseError	(		self,
			errorcode = "XXX-undefined-error",
			datavars = {}
	)

def pip._vendor.html5lib.html5parser.HTMLParser.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)

def pip._vendor.html5lib.html5parser.HTMLParser.parseRCDataRawtext	(		self,
			token,
			contentType
	)

Generic RCDATA/RAWTEXT Parsing algorithm
contentType - RCDATA or RAWTEXT

def pip._vendor.html5lib.html5parser.HTMLParser.reparseTokenNormal	(		self,
			token
	)

def pip._vendor.html5lib.html5parser.HTMLParser.reset

(

self

)

def pip._vendor.html5lib.html5parser.HTMLParser.resetInsertionMode

(

self

)

Member Data Documentation

pip._vendor.html5lib.html5parser.HTMLParser.beforeRCDataPhase

pip._vendor.html5lib.html5parser.HTMLParser.compatMode

pip._vendor.html5lib.html5parser.HTMLParser.container

pip._vendor.html5lib.html5parser.HTMLParser.errors

pip._vendor.html5lib.html5parser.HTMLParser.firstStartTag

pip._vendor.html5lib.html5parser.HTMLParser.framesetOK

pip._vendor.html5lib.html5parser.HTMLParser.innerHTML

pip._vendor.html5lib.html5parser.HTMLParser.innerHTMLMode

pip._vendor.html5lib.html5parser.HTMLParser.lastPhase

pip._vendor.html5lib.html5parser.HTMLParser.log

pip._vendor.html5lib.html5parser.HTMLParser.originalPhase

pip._vendor.html5lib.html5parser.HTMLParser.phase

pip._vendor.html5lib.html5parser.HTMLParser.phases

pip._vendor.html5lib.html5parser.HTMLParser.strict

pip._vendor.html5lib.html5parser.HTMLParser.tokenizer

pip._vendor.html5lib.html5parser.HTMLParser.tokenizer_class

pip._vendor.html5lib.html5parser.HTMLParser.tree

---

The documentation for this class was generated from the following file:

• orbits/lib/python2.7/site-packages/pip/_vendor/html5lib/html5parser.py