a
XC?hèB ã @ sn g d ¢Z ddlmZ ddlZddlZddlmZ ddlmZ dZ dZ
dZ d Z d
Z
d Zd Ze e dfe e dfe e dfe e dfe e dfe e dfe e dfe e dfe e dfe e dfe e dfe e dfd
e
e
dfe
e
dfe
ddfe
ddfe
ddfe
e
dfe e
dfdœZdddddddddddddddddddddd d d
d œZd d dd!œZd,d"d#„Zd$d%„ Zd&d'„ Zd(d)„ ZG d*d+„ d+ƒZdS )-)ÚCharsetÚ add_aliasÚ add_charsetÚ add_codecé )ÚpartialN)Úerrors)Úencode_7or8bité é é é úus-asciiz unknown-8bitÚ )NNNú iso-2022-jpúutf-8)ú
iso-8859-1ú
iso-8859-2ú
iso-8859-3ú
iso-8859-4ú
iso-8859-9ú iso-8859-10ú iso-8859-13ú iso-8859-14ú iso-8859-15ú iso-8859-16z windows-1252Zvisciir
Úbig5Úgb2312úeuc-jpÚ shift_jisr zkoi8-rr r r r r r r r r r r zks_c_5601-1987r zeuc-kr)Úlatin_1zlatin-1Zlatin_2zlatin-2Zlatin_3zlatin-3Zlatin_4zlatin-4Zlatin_5zlatin-5Zlatin_6zlatin-6Zlatin_7zlatin-7Zlatin_8zlatin-8Zlatin_9zlatin-9Zlatin_10zlatin-10Úcp949Úeuc_jpÚeuc_krÚasciiÚ eucgb2312_cnÚbig5_tw)r r r
c C s" |t krtdƒ‚|||ft| < dS )a> 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.
z!SHORTEST not allowed for body_encN)ÚSHORTESTÚ
ValueErrorÚCHARSETS)ÚcharsetZ
header_encZbody_encÚoutput_charset© r+ ú2/opt/alt/python39/lib64/python3.9/email/charset.pyr m s r c C s |t | < dS )zAdd 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)ÚALIASES)ÚaliasZ canonicalr+ r+ r, r ‰ s r c C s |t | < dS )a$ 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)Ú CODEC_MAP)r) Z codecnamer+ r+ r, r ’ s r c C s" |t kr| dd¡S | |¡S d S )Nr# Úsurrogateescape)Ú UNKNOWN8BITÚencode)ÚstringÚcodecr+ r+ r, Ú_encodeŸ s r5 c @ s\ e Zd ZdZefdd„Zdd„ Zdd„ Zdd „ Zd
d „ Z d d
„ Z
dd„ Z dd„ Z dd„ Z
dS )r a@ 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 s¾ z$t |tƒr| d¡ n
t|dƒ}W n ty@ t |¡‚Y n0 | ¡ }t ||¡| _ t
| j t t d f¡\}}}|s|| j }|| _
|| _t ||¡| _t | j | j ¡| _t | j| j¡| _d S )Nr# )Ú
isinstanceÚstrr2 Ú UnicodeErrorr Z CharsetErrorÚlowerr- ÚgetÚ
input_charsetr( r& ÚBASE64Úheader_encodingÚ
body_encodingr* r/ Z input_codecÚ output_codec)Úselfr; ZhencZbencZconvr+ r+ r, Ú__init__Ó s,
ÿ
ÿÿzCharset.__init__c C s
| j ¡ S ©N)r; r9 ©r@ r+ r+ r, Ú__repr__ô s zCharset.__repr__c C s t | ƒt |ƒ ¡ kS rB )r7 r9 )r@ Úotherr+ r+ r, Ú__eq__÷ s zCharset.__eq__c C s$ | j tkrdS | j tkr dS tS dS )aP 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 conversion function otherwise.
zquoted-printableÚbase64N)r> ÚQPr< r rC r+ r+ r, Úget_body_encodingú s
zCharset.get_body_encodingc C s | j p
| jS )zReturn the output character set.
This is self.output_charset if that is not None, otherwise it is
self.input_charset.
)r* r; rC r+ r+ r, Úget_output_charset s zCharset.get_output_charsetc C s6 | j pd}t||ƒ}| |¡}|du r*|S | ||¡S )až Header-encode a string by converting it first to bytes.
The type of encoding (base64 or quoted-printable) will be based on
this charset's `header_encoding`.
:param string: A unicode string for the header. It must be possible
to encode this string to bytes using the character set's
output codec.
:return: The encoded string, with RFC 2047 chrome.
r
N)r? r5 Ú _get_encoderÚ
header_encode)r@ r3 r4 Ú header_bytesÚencoder_moduler+ r+ r, rL s
zCharset.header_encodec C s | j pd}t||ƒ}| |¡}t|j|d}| ¡ }t|ƒt }g } g }
t|ƒ| } |D ]Œ} |
| ¡ t
|
¡}
| t|
|ƒ¡}|| krX|
¡ | s¤|
s¤| d¡ n.| r¬dnd}t
|
¡}t||ƒ}| ||ƒ¡ | g}
t|ƒ| } qXt
|
¡}t||ƒ}| ||ƒ¡ | S )af Header-encode a string by converting it first to bytes.
This is similar to `header_encode()` except that the string is fit
into maximum line lengths as given by the argument.
:param string: A unicode string for the header. It must be possible
to encode this string to bytes using the character set's
output codec.
:param maxlengths: Maximum line length iterator. Each element
returned from this iterator will provide the next maximum line
length. This parameter is used as an argument to built-in next()
and should never be exhausted. The maximum line lengths should
not count the RFC 2047 chrome. These line lengths are only a
hint; the splitter does the best it can.
:return: Lines of encoded strings, each with RFC 2047 chrome.
r
)r) Nú r )r? r5 rK r rL rJ ÚlenÚRFC2047_CHROME_LENÚnextÚappendÚ EMPTYSTRINGÚjoinÚ
header_lengthÚpop)r@ r3 Z
maxlengthsr4 rM rN Úencoderr) ZextraÚlinesZ current_lineÚmaxlenÚ characterZ this_lineZlengthZ separatorZ joined_liner+ r+ r, Úheader_encode_lines* s6
zCharset.header_encode_linesc C s` | j tkrtjS | j tkr tjS | j tkrXtj |¡}tj |¡}||k rPtjS tjS nd S d S rB )r= r< ÚemailÚ
base64mimerH Ú
quoprimimer& rV )r@ rM Zlen64Zlenqpr+ r+ r, rK h s
zCharset._get_encoderc C sŽ |s|S | j tu r4t|tƒr(| | j¡}tj |¡S | j t u rjt|tƒrT| | j¡}|
d¡}tj |¡S t|tƒr†| | j¡
d¡}|S dS )av Body-encode a string by converting it first to bytes.
The type of encoding (base64 or quoted-printable) will be based on
self.body_encoding. If body_encoding is None, we assume the
output charset is a 7bit encoding, so re-encoding the decoded
string using the ascii codec produces the correct string version
of the content.
Úlatin1r# N) r> r< r6 r7 r2 r* r] r^ Ú body_encoderH Údecoder_ )r@ r3 r+ r+ r, ra w s
zCharset.body_encodeN)Ú__name__Ú
__module__Ú __qualname__Ú__doc__ÚDEFAULT_CHARSETrA rD rF rI rJ rL r\ rK ra r+ r+ r+ r, r § s + !>r )NNN)Ú__all__Ú functoolsr Zemail.base64mimer] Zemail.quoprimimer Zemail.encodersr rH r< r& rQ rg r1 rT r( r- r/ r r r r5 r r+ r+ r+ r, Ú s† æ è ú