pip._vendor.html5lib.inputstream Namespace Reference

Classes
class	BufferedIOBase
class	BufferedStream
class	HTMLUnicodeInputStream
class	HTMLBinaryInputStream
class	EncodingBytes
class	EncodingParser
class	ContentAttrParser

Functions
def	HTMLInputStream
def	codecName

Variables
	BytesIO = StringIO
tuple	spaceCharactersBytes = frozenset([item.encode("ascii") for item in spaceCharacters])
tuple	asciiLettersBytes = frozenset([item.encode("ascii") for item in asciiLetters])
tuple	asciiUppercaseBytes = frozenset([item.encode("ascii") for item in asciiUppercase])
tuple	spacesAngleBrackets = spaceCharactersBytes|frozenset([b">", b"<"])
tuple	invalid_unicode_re = re.compile("[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uD800-\uDFFF\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]")
tuple	non_bmp_invalid_codepoints
tuple	ascii_punctuation_re = re.compile("[\u0009-\u000D\u0020-\u002F\u003A-\u0040\u005B-\u0060\u007B-\u007E]")
dictionary	charsUntilRegEx = {}

Function Documentation

def pip._vendor.html5lib.inputstream.codecName

(

encoding

)

Return the python codec name corresponding to an encoding or None if the
string doesn't correspond to a valid encoding.

def pip._vendor.html5lib.inputstream.HTMLInputStream	(		source,
			encoding = None,
			parseMeta = True,
			chardet = True
	)

Variable Documentation

tuple pip._vendor.html5lib.inputstream.ascii_punctuation_re = re.compile("[\u0009-\u000D\u0020-\u002F\u003A-\u0040\u005B-\u0060\u007B-\u007E]")

tuple pip._vendor.html5lib.inputstream.asciiLettersBytes = frozenset([item.encode("ascii") for item in asciiLetters])

tuple pip._vendor.html5lib.inputstream.asciiUppercaseBytes = frozenset([item.encode("ascii") for item in asciiUppercase])

pip._vendor.html5lib.inputstream.BytesIO = StringIO

dictionary pip._vendor.html5lib.inputstream.charsUntilRegEx = {}

tuple pip._vendor.html5lib.inputstream.invalid_unicode_re = re.compile("[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uD800-\uDFFF\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]")

tuple pip._vendor.html5lib.inputstream.non_bmp_invalid_codepoints

Initial value:

= set([0x1FFFE, 0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE,
                                  0x3FFFF, 0x4FFFE, 0x4FFFF, 0x5FFFE, 0x5FFFF,
                                  0x6FFFE, 0x6FFFF, 0x7FFFE, 0x7FFFF, 0x8FFFE,
                                  0x8FFFF, 0x9FFFE, 0x9FFFF, 0xAFFFE, 0xAFFFF,
                                  0xBFFFE, 0xBFFFF, 0xCFFFE, 0xCFFFF, 0xDFFFE,
                                  0xDFFFF, 0xEFFFE, 0xEFFFF, 0xFFFFE, 0xFFFFF,
                                  0x10FFFE, 0x10FFFF])

tuple pip._vendor.html5lib.inputstream.spaceCharactersBytes = frozenset([item.encode("ascii") for item in spaceCharacters])

tuple pip._vendor.html5lib.inputstream.spacesAngleBrackets = spaceCharactersBytes|frozenset([b">", b"<"])