3
\F! @ s d Z ddlZddlZddlZddlZddlmZmZ ddlm Z ddddd d
d d gZ
ej ej d
j
dd Zdd ZG dd deZe Zdeed< dd Zdd Zdd Zdd Zdd
ZeedZdd ZeedZeedZ d d d Z dS ) z Routines for manipulating RFC2047 encoded words.
This is currently a package-private API, but will be considered for promotion
to a public API if there is demand.
N)
ascii_lettersdigits)errorsdecode_qencode_qdecode_bencode_blen_qlen_bdecodeencodes =([a-fA-F0-9]{2})c C s t t| jddgS )N )bytesintgroup)m r ,/usr/lib64/python3.6/email/_encoded_words.pyA s r c C s | j dd} t| g fS )N _ )replace_q_byte_subber)encodedr r r r C s c @ s, e Zd Zdejd ejd Zdd ZdS ) _QByteMaps -!*+/asciic C s. || j krt|| |< ndj|| |< | | S )Nz={:02X})safechrformat)selfkeyr r r __missing__M s
z_QByteMap.__missing__N)__name__
__module__ __qualname__r r r r r" r r r r r I s r _ c C s dj dd | D S )N c s s | ]}t | V qd S )N) _q_byte_map).0xr r r Z s zencode_q..)join)bstringr r r r Y s c C s t dd | D S )Nc s s | ]}t t| V qd S )N)lenr) )r* r+ r r r r, ] s zlen_q..)sum)r. r r r r \ s c C s t | d }|r dd d| nd}y$tj| | dd|rDtj gng fS tjk
r ytj| ddtj gfS tjk
r y"tj| d ddtj tj gfS tjk
r | tj gfS X Y nX Y nX d S )N s === T)ZvalidateFs ==) r/ base64Z b64decoder ZInvalidBase64PaddingDefectbinasciiErrorZ InvalidBase64CharactersDefectZInvalidBase64LengthDefect)r Zpad_errZmissing_paddingr r r r d s c C s t j| jdS )Nr )r3 Z b64encoder )r. r r r r s c C s& t t| d\}}|d |r dnd S )N r1 r )divmodr/ )r. Z groups_of_3Zleftoverr r r r
s )qbc C s | j d\}}}}}|jd\}}}|j }|jdd}t| |\}}y|j|}W nv tk
r |jtj dj
| |j|d}Y nB t k
r |jdd}|j dkr|jtj dj
| Y nX ||||fS )a Decode encoded word and return (string, charset, lang, defects) tuple.
An RFC 2047/2243 encoded word has the form:
=?charset*lang?cte?encoded_string?=
where '*lang' may be omitted but the other parts may not be.
This function expects exactly such a string (that is, it does not check the
syntax and may raise errors if the string is not well formed), and returns
the encoded_string decoded first from its Content Transfer Encoding and
then from the resulting bytes into unicode using the specified charset. If
the cte-decoded string does not successfully decode using the specified
character set, a defect is added to the defects list and the unknown octets
are replaced by the unicode 'unknown' character \uFDFF.
The specified charset and language are returned. The default for language,
which is rarely if ever encountered, is the empty string.
?*r surrogateescapez:Encoded word contains bytes not decodable using {} charsetz unknown-8bitz sB $
&+