Python string.ascii_letters.encode() Examples
The following are 30
code examples of string.ascii_letters.encode().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
string.ascii_letters
, or try the search function
.
.
Example #1
| Source File: _encoded_words.py From gimp-plugin-export-layers with GNU General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #2
| Source File: _encoded_words.py From ironpython3 with Apache License 2.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{}{}?{}?{}?=".format(charset, lang, encoding, encoded)
Example #3
| Source File: _encoded_words.py From cadquery-freecad-module with GNU Lesser General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #4
| Source File: _encoded_words.py From cadquery-freecad-module with GNU Lesser General Public License v3.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #5
| Source File: _encoded_words.py From addon with GNU General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #6
| Source File: _encoded_words.py From addon with GNU General Public License v3.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #7
| Source File: _encoded_words.py From blackmamba with MIT License | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #8
| Source File: _encoded_words.py From blackmamba with MIT License | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #9
| Source File: _encoded_words.py From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = ew.split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #10
| Source File: _encoded_words.py From Project-New-Reign---Nemesis-Main with GNU General Public License v3.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{}{}?{}?{}?=".format(charset, lang, encoding, encoded)
Example #11
| Source File: _encoded_words.py From odoo13-x64 with GNU General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = ew.split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #12
| Source File: _encoded_words.py From odoo13-x64 with GNU General Public License v3.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{}{}?{}?{}?=".format(charset, lang, encoding, encoded)
Example #13
| Source File: _encoded_words.py From verge3d-blender-addon with GNU General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #14
| Source File: _encoded_words.py From gimp-plugin-export-layers with GNU General Public License v3.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #15
| Source File: _encoded_words.py From arissploit with GNU General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #16
| Source File: _encoded_words.py From arissploit with GNU General Public License v3.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #17
| Source File: _encoded_words.py From Tautulli with GNU General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #18
| Source File: _encoded_words.py From Tautulli with GNU General Public License v3.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #19
| Source File: _encoded_words.py From Carnets with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = ew.split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #20
| Source File: _encoded_words.py From Carnets with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{}{}?{}?{}?=".format(charset, lang, encoding, encoded)
Example #21
| Source File: _encoded_words.py From V1EngineeringInc-Docs with Creative Commons Attribution Share Alike 4.0 International | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #22
| Source File: _encoded_words.py From V1EngineeringInc-Docs with Creative Commons Attribution Share Alike 4.0 International | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #23
| Source File: _encoded_words.py From android_universal with MIT License | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = ew.split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #24
| Source File: _encoded_words.py From android_universal with MIT License | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{}{}?{}?{}?=".format(charset, lang, encoding, encoded)
Example #25
| Source File: _encoded_words.py From misp42splunk with GNU Lesser General Public License v3.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #26
| Source File: _encoded_words.py From deepWordBug with Apache License 2.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #27
| Source File: _encoded_words.py From deepWordBug with Apache License 2.0 | 5 votes |
|
def encode(string, charset='utf-8', encoding=None, lang=''):
"""Encode string using the CTE encoding that produces the shorter result.
Produces an RFC 2047/2243 encoded word of the form:
=?charset*lang?cte?encoded_string?=
where '*lang' is omitted unless the 'lang' parameter is given a value.
Optional argument charset (defaults to utf-8) specifies the charset to use
to encode the string to binary before CTE encoding it. Optional argument
'encoding' is the cte specifier for the encoding that should be used ('q'
or 'b'); if it is None (the default) the encoding which produces the
shortest encoded sequence is used, except that 'q' is preferred if it is up
to five characters longer. Optional argument 'lang' (default '') gives the
RFC 2243 language string to specify in the encoded word.
"""
string = str(string)
if charset == 'unknown-8bit':
bstring = string.encode('ascii', 'surrogateescape')
else:
bstring = string.encode(charset)
if encoding is None:
qlen = _cte_encode_length['q'](bstring)
blen = _cte_encode_length['b'](bstring)
# Bias toward q. 5 is arbitrary.
encoding = 'q' if qlen - blen < 5 else 'b'
encoded = _cte_encoders[encoding](bstring)
if lang:
lang = '*' + lang
return "=?{0}{1}?{2}?{3}?=".format(charset, lang, encoding, encoded)
Example #28
| Source File: _encoded_words.py From misp42splunk with GNU Lesser General Public License v3.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #29
| Source File: _encoded_words.py From kgsgo-dataset-preprocessor with Mozilla Public License 2.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = str(ew).split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
Example #30
| Source File: _encoded_words.py From ironpython3 with Apache License 2.0 | 5 votes |
|
def decode(ew):
"""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.
"""
_, charset, cte, cte_string, _ = ew.split('?')
charset, _, lang = charset.partition('*')
cte = cte.lower()
# Recover the original bytes and do CTE decoding.
bstring = cte_string.encode('ascii', 'surrogateescape')
bstring, defects = _cte_decoders[cte](bstring)
# Turn the CTE decoded bytes into unicode.
try:
string = bstring.decode(charset)
except UnicodeError:
defects.append(errors.UndecodableBytesDefect("Encoded word "
"contains bytes not decodable using {} charset".format(charset)))
string = bstring.decode(charset, 'surrogateescape')
except LookupError:
string = bstring.decode('ascii', 'surrogateescape')
if charset.lower() != 'unknown-8bit':
defects.append(errors.CharsetError("Unknown charset {} "
"in encoded word; decoded as unknown bytes".format(charset)))
return string, charset, lang, defects
