Edit File: charset.pyc
� ��7ec @ s� d d d d g Z d d l Z d d l Z d d l Z d d l m Z d d l m Z d Z d Z d Z d Z d Z i e e d f d 6e e d f d 6e e d f d 6e e d f d 6e e d f d 6e e d f d 6e e d f d 6e e d f d 6e e d f d 6e e d f d 6e e d f d 6e e d f d 6dA d 6e e d f d 6e e d f d 6e d d f d 6e d d f d 6e d d f d 6e e d f d 6e e d f d 6d e d f d 6Z i d d! 6d d" 6d d# 6d d$ 6d d% 6d d& 6d d' 6d d( 6d d) 6d d* 6d d+ 6d d, 6d d- 6d d. 6d d/ 6d d0 6d d1 6d d2 6d d3 6d d4 6d5 d6 6d d7 6d8 d9 6d d: 6Z i d; d 6d< d 6d d 6Z d d d d= � Z d> � Z d? � Z d dB d@ � � YZ d S(C t Charsett add_aliast add_charsett add_codeci����N( t errors( t encode_7or8biti i i i s us-asciis iso-8859-1s iso-8859-2s iso-8859-3s iso-8859-4s iso-8859-9s iso-8859-10s iso-8859-13s iso-8859-14s iso-8859-15s iso-8859-16s windows-1252t visciit big5t gb2312s iso-2022-jps euc-jpt shift_jiss koi8-rs utf-8t 8bitt latin_1s latin-1t latin_2s latin-2t latin_3s latin-3t latin_4s latin-4t latin_5s latin-5t latin_6s latin-6t latin_7s latin-7t latin_8s latin-8t latin_9s latin-9t latin_10s latin-10s ks_c_5601-1987t cp949t euc_jps euc-krt euc_krt asciit eucgb2312_cnt big5_twc C s2 | t k r t d � � n | | | f t | <d S( s> 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. Optional output_charset is the character set that the output should be in. Conversions will proceed from input charset, to Unicode, to the output charset when the method Charset.convert() is called. The default is to output in the same character set as the input. Both input_charset and output_charset must have Unicode codec entries in the module's charset-to-codec mapping; use add_codec(charset, codecname) to add codecs the module does not know about. See the codecs module's documentation for more information. s! SHORTEST not allowed for body_encN( t SHORTESTt ValueErrort CHARSETS( t charsett header_enct body_enct output_charset( ( s% /usr/lib64/python2.7/email/charset.pyR l s c C s | t | <d S( s� Add a character set alias. alias is the alias name, e.g. latin-1 canonical is the character set's canonical name, e.g. iso-8859-1 N( t ALIASES( t aliast canonical( ( s% /usr/lib64/python2.7/email/charset.pyR � s c C s | t | <d S( s$ Add a codec that map characters in the given charset to/from Unicode. charset is the canonical name of a character set. codecname is the name of a Python codec, as appropriate for the second argument to the unicode() built-in, or to the encode() method of a Unicode string. N( t CODEC_MAP( R t codecname( ( s% /usr/lib64/python2.7/email/charset.pyR � s c B s� e Z d Z e d � Z d � Z e Z d � Z d � Z d � Z d � Z d � Z e d � Z d � Z d � Z e d � Z e d � Z RS( s@ Map character sets to their email properties. This class provides information about the requirements imposed on email for a specific character set. It also provides convenience routines for converting between character sets, given the availability of the applicable codecs. Given a character set, it will do its best to provide information on how to use that character set in an email in an RFC-compliant way. Certain character sets must be encoded with quoted-printable or base64 when used in email headers or bodies. Certain character sets must be converted outright, and are not allowed in email. Instances of this module expose the following information about a character set: input_charset: The initial character set specified. Common aliases are converted to their `official' email names (e.g. latin_1 is converted to iso-8859-1). Defaults to 7-bit us-ascii. header_encoding: If the character set must be encoded before it can be used in an email header, this attribute will be set to Charset.QP (for quoted-printable), Charset.BASE64 (for base64 encoding), or Charset.SHORTEST for the shortest of QP or BASE64 encoding. Otherwise, it will be None. body_encoding: Same as header_encoding, but describes the encoding for the mail message's body, which indeed may be different than the header encoding. Charset.SHORTEST is not allowed for body_encoding. output_charset: Some character sets must be converted before they can be used in email headers or bodies. If the input_charset is one of them, this attribute will contain the name of the charset output will be converted to. Otherwise, it will be None. input_codec: The name of the Python codec used to convert the input_charset to Unicode. If no conversion codec is necessary, this attribute will be None. output_codec: The name of the Python codec used to convert Unicode to the output_charset. If no conversion codec is necessary, this attribute will have the same value as the input_codec. c C s^ y2 t | t � r" | j d � n t | d � } Wn t k rT t j | � � n X| j � j d � } | t k p | t k s� y t j | � j } Wq� t k r� q� Xn t j | | � | _ t j | j t t d f � \ } } } | s� | j } n | | _ | | _ t j | | � | _ t j | j | j � | _ t j | j | j � | _ d S( NR ( t isinstancet unicodet encodet UnicodeErrorR t CharsetErrort lowerR" R t codecst lookupt namet LookupErrort gett input_charsetR t BASE64t Nonet header_encodingt body_encodingR! R% t input_codect output_codec( t selfR2 t henct benct conv( ( s% /usr/lib64/python2.7/email/charset.pyt __init__� s0 c C s | j j � S( N( R2 R, ( R9 ( ( s% /usr/lib64/python2.7/email/charset.pyt __str__� s c C s t | � t | � j � k S( N( t strR, ( R9 t other( ( s% /usr/lib64/python2.7/email/charset.pyt __eq__� s c C s | j | � S( N( RA ( R9 R@ ( ( s% /usr/lib64/python2.7/email/charset.pyt __ne__� s c C sC | j t k s t � | j t k r( d S| j t k r; d St Sd S( sC Return the content-transfer-encoding used for body encoding. This is either the string `quoted-printable' or `base64' depending on the encoding used, or it is a function in which case you should call the function with a single argument, the Message object being encoded. The function should then set the Content-Transfer-Encoding header itself to whatever is appropriate. Returns "quoted-printable" if self.body_encoding is QP. Returns "base64" if self.body_encoding is BASE64. Returns "7bit" otherwise. s quoted-printablet base64N( R6 R t AssertionErrort QPR3 R ( R9 ( ( s% /usr/lib64/python2.7/email/charset.pyt get_body_encoding� s c C s6 | j | j k r. t | | j � j | j � S| Sd S( s: Convert a string from the input_codec to the output_codec.N( R7 R8 R( R) ( R9 t s( ( s% /usr/lib64/python2.7/email/charset.pyt convert s c C sR t | t � s | j d k r" | Sy t | | j d � SWn t k rM | SXd S( s� Convert a possibly multibyte string to a safely splittable format. Uses the input_codec to try and convert the string to Unicode, so it can be safely split on character boundaries (even for multibyte characters). Returns the string as-is if it isn't known how to convert it to Unicode with the input_charset. Characters that could not be converted to Unicode will be replaced with the Unicode replacement character U+FFFD. t replaceN( R' R( R7 R4 R0 ( R9 RG ( ( s% /usr/lib64/python2.7/email/charset.pyt to_splittable s c C sh | r | j } n | j } t | t � s7 | d k r; | Sy | j | d � SWn t k rc | SXd S( s* Convert a splittable string back into an encoded string. Uses the proper codec to try and convert the string from Unicode back into an encoded format. Return the string as-is if it is not Unicode, or if it could not be converted from Unicode. Characters that could not be converted from Unicode will be replaced with an appropriate character (usually '?'). If to_output is True (the default), uses output_codec to convert to an encoded format. If to_output is False, uses input_codec. RI N( R8 R7 R' R( R4 R) R0 ( R9 t ustrt to_outputt codec( ( s% /usr/lib64/python2.7/email/charset.pyt from_splittable+ s c C s | j p | j S( s� Return the output character set. This is self.output_charset if that is not None, otherwise it is self.input_charset. ( R! R2 ( R9 ( ( s% /usr/lib64/python2.7/email/charset.pyt get_output_charsetD s c C s� | j � } | j t k r9 t j j | � t | � t S| j t k rf t j j | � t | � t S| j t k r� t j j | � } t j j | � } t | | � t | � t St | � Sd S( s/ Return the length of the encoded header string.N( RO R5 R3 t emailt base64mimet base64_lent lent MISC_LENRE t quoprimimet header_quopri_lenR t min( R9 RG t csett lenb64t lenqp( ( s% /usr/lib64/python2.7/email/charset.pyt encoded_header_lenL s c C s� | j � } | r$ | j | � } n | j t k rF t j j | | � S| j t k rn t j j | | d d �S| j t k r� t j j | � } t j j | � } | | k r� t j j | | � St j j | | d d �Sn | Sd S( sE Header-encode a string, optionally converting it to output_charset. If convert is True, the string will be converted from the input charset to the output charset automatically. This is not useful for multibyte character sets, which have line length issues (multibyte characters must be split on a character, not a byte boundary); use the high-level Header class to deal with these issues. convert defaults to False. The type of encoding (base64 or quoted-printable) will be based on self.header_encoding. t maxlinelenN( RO RH R5 R3 RP RQ t header_encodeRE RU R4 R RR RV ( R9 RG RH RX RY RZ ( ( s% /usr/lib64/python2.7/email/charset.pyR] [ s c C s^ | r | j | � } n | j t k r7 t j j | � S| j t k rV t j j | � S| Sd S( s� Body-encode a string and convert it to output_charset. If convert is True (the default), the string will be converted from the input charset to output charset automatically. Unlike header_encode(), there are no issues with byte boundaries and multibyte charsets in email bodies, so this is usually pretty safe. The type of encoding (base64 or quoted-printable) will be based on self.body_encoding. N( RH R6 R3 RP RQ t body_encodeRE RU ( R9 RG RH ( ( s% /usr/lib64/python2.7/email/charset.pyR^ z s ( t __name__t __module__t __doc__t DEFAULT_CHARSETR= R> t __repr__RA RB RF RH RJ t TrueRN RO R[ t FalseR] R^ ( ( ( s% /usr/lib64/python2.7/email/charset.pyR � s + & ( NNN( ( t __all__R- t email.base64mimeRP t email.quoprimimeR t email.encodersR RE R3 R RT Rb R4 R R" R% R R R R ( ( ( s% /usr/lib64/python2.7/email/charset.pyt <module> s�