0 )Z٫{-i[D# Copyright (C) 2001-2006 Python Software Foundation # Author: Ben Gertzfield, Barry Warsaw # Contact: email-sig@python.org __all__ = [ 'Charset', 'add_alias', 'add_charset', 'add_codec', ] import codecs import email.base64mime import email.quoprimime from email import errors from email.encoders import encode_7or8bit # Flags for types of header encodings QP = 1 # Quoted-Printable BASE64 = 2 # Base64 SHORTEST = 3 # the shorter of QP and base64, but only for headers # In "=?charset?q?hello_world?=", the =?, ?q?, and ?= add up to 7 MISC_LEN = 7 DEFAULT_CHARSET = 'us-ascii' # Defaults CHARSETS = { # input header enc body enc output conv 'iso-8859-1': (QP, QP, None), 'iso-8859-2': (QP, QP, None), 'iso-8859-3': (QP, QP, None), 'iso-8859-4': (QP, QP, None), # iso-8859-5 is Cyrillic, and not especially used # iso-8859-6 is Arabic, also not particularly used # iso-8859-7 is Greek, QP will not make it readable # iso-8859-8 is Hebrew, QP will not make it readable 'iso-8859-9': (QP, QP, None), 'iso-8859-10': (QP, QP, None), # iso-8859-11 is Thai, QP will not make it readable 'iso-8859-13': (QP, QP, None), 'iso-8859-14': (QP, QP, None), 'iso-8859-15': (QP, QP, None), 'iso-8859-16': (QP, QP, None), 'windows-1252':(QP, QP, None), 'viscii': (QP, QP, None), 'us-ascii': (None, None, None), 'big5': (BASE64, BASE64, None), 'gb2312': (BASE64, BASE64, None), 'euc-jp': (BASE64, None, 'iso-2022-jp'), 'shift_jis': (BASE64, None, 'iso-2022-jp'), 'iso-2022-jp': (BASE64, None, None), 'koi8-r': (BASE64, BASE64, None), 'utf-8': (SHORTEST, BASE64, 'utf-8'), # We're making this one up to represent raw unencoded 8-bit '8bit': (None, BASE64, 'utf-8'), } # Aliases for other commonly-used names for character sets. Map # them to the real ones used in email. ALIASES = { 'latin_1': 'iso-8859-1', 'latin-1': 'iso-8859-1', 'latin_2': 'iso-8859-2', 'latin-2': 'iso-8859-2', 'latin_3': 'iso-8859-3', 'latin-3': 'iso-8859-3', 'latin_4': 'iso-8859-4', 'latin-4': 'iso-8859-4', 'latin_5': 'iso-8859-9', 'latin-5': 'iso-8859-9', 'latin_6': 'iso-8859-10', 'latin-6': 'iso-8859-10', 'latin_7': 'iso-8859-13', 'latin-7': 'iso-8859-13', 'latin_8': 'iso-8859-14', 'latin-8': 'iso-8859-14', 'latin_9': 'iso-8859-15', 'latin-9': 'iso-8859-15', 'latin_10':'iso-8859-16', 'latin-10':'iso-8859-16', 'cp949': 'ks_c_5601-1987', 'euc_jp': 'euc-jp', 'euc_kr': 'euc-kr', 'ascii': 'us-ascii', } # Map charsets to their Unicode codec strings. CODEC_MAP = { 'gb2312': 'eucgb2312_cn', 'big5': 'big5_tw', # Hack: We don't want *any* conversion for stuff marked us-ascii, as all # sorts of garbage might be sent to us in the guise of 7-bit us-ascii. # Let that stuff pass through without conversion to/from Unicode. 'us-ascii': None, } # Convenience functions for extending the above mappings def add_charset(charset, header_enc=None, body_enc=None, output_charset=None): """Add character set properties to the global registry. charset is the input character set, and must be the canonical name of a character set. Optional header_enc and body_enc is either Charset.QP for quoted-printable, Charset.BASE64 for base64 encoding, Charset.SHORTEST for the shortest of qp or base64 encoding, or None for no encoding. SHORTEST is only valid for header_enc. It describes how message headers and message bodies in the input charset are to be encoded. Default is no encoding. O