ReS) @ sP d Z d d l m Z d d l Z d d l m Z d Z d d d d
d d d
d i Z i Z d d Z d d Z
d d Z Gd d d e Z
e
d Z e
d Z e
d Z d d d Z d d Z e d d d! Z d d" d# Z d$ d% Z e d d& d' Z d( d) Z Gd* d+ d+ e Z Gd, d- d- e Z d S).a
webencodings
~~~~~~~~~~~~
This is a Python implementation of the `WHATWG Encoding standard
`. See README for details.
:copyright: Copyright 2012 by Simon Sapin
:license: BSD, see LICENSE for details.
)unicode_literalsN )LABELSz0.5.1z iso-8859-8-iz
iso-8859-8zx-mac-cyrillicz mac-cyrillic macintoshz mac-romanz windows-874cp874c C s | j d j j d S)a9 Transform (only) ASCII letters to lower case: A-Z is mapped to a-z.
:param string: An Unicode string.
:returns: A new Unicode string.
This is used for `ASCII case-insensitive
`_
matching of encoding labels.
The same matching is also used, among other things,
for `CSS keywords `_.
This is different from the :meth:`~py:str.lower` method of Unicode strings
which also affect non-ASCII characters,
sometimes mapping them into the ASCII range:
>>> keyword = u'Bac\N{KELVIN SIGN}ground'
>>> assert keyword.lower() == u'background'
>>> assert ascii_lower(keyword) != keyword.lower()
>>> assert ascii_lower(keyword) == u'bac\N{KELVIN SIGN}ground'
utf8)encodelowerdecode)string r /builddir/build/BUILDROOT/alt-python35-pip-20.2.4-5.el8.x86_64/opt/alt/python35/lib/python3.5/site-packages/pip/_vendor/webencodings/__init__.py ascii_lower# s r c C s t | j d } t j | } | d k r4 d St j | } | d k r | d k rn d d l m } n! t j | | } t j | } t
| | } | t | <| S)u<
Look for an encoding by its label.
This is the spec’s `get an encoding
`_ algorithm.
Supported labels are listed there.
:param label: A string.
:returns:
An :class:`Encoding` object, or :obj:`None` for an unknown label.
z
Nzx-user-definedr )
codec_info) r stripr getCACHEx_user_definedr PYTHON_NAMEScodecslookupEncoding)labelnameencodingr python_namer r r
r = s
r c C s? t | d r | St | } | d k r; t d | | S)z
Accept either an encoding object or label.
:param encoding: An :class:`Encoding` object or a label string.
:returns: An :class:`Encoding` object.
:raises: :exc:`~exceptions.LookupError` for an unknown label.
r NzUnknown encoding label: %r)hasattrr LookupError)encoding_or_labelr r r r
_get_encoding[ s r c @ s. e Z d Z d Z d d Z d d Z d S)r aO Reresents a character encoding such as UTF-8,
that can be used for decoding or encoding.
.. attribute:: name
Canonical name of the encoding
.. attribute:: codec_info
The actual implementation of the encoding,
a stdlib :class:`~codecs.CodecInfo` object.
See :func:`codecs.register`.
c C s | | _ | | _ d S)N)r r )selfr r r r r
__init__| s zEncoding.__init__c C s d | j S)Nz
)r )r r r r
__repr__ s zEncoding.__repr__N)__name__
__module__ __qualname____doc__r! r" r r r r
r m s r zutf-8zutf-16lezutf-16bereplacec C sG t | } t | \ } } | p' | } | j j | | d | f S)a
Decode a single string.
:param input: A byte string
:param fallback_encoding:
An :class:`Encoding` object or a label string.
The encoding to use if :obj:`input` does note have a BOM.
:param errors: Type of error handling. See :func:`codecs.register`.
:raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
:return:
A ``(output, encoding)`` tuple of an Unicode string
and an :obj:`Encoding`.
r )r _detect_bomr r
)inputfallback_encodingerrors bom_encodingr r r r
r
s r
c C ss | j d r# t | d d f S| j d rF t | d d f S| j d ri t | d d f Sd | f S)zBReturn (bom_encoding, input), with any BOM removed from the input.s Ns s )
startswith_UTF16LE_UTF16BEUTF8)r) r r r
r( s r( strictc C s t | j j | | d S)a;
Encode a single string.
:param input: An Unicode string.
:param encoding: An :class:`Encoding` object or a label string.
:param errors: Type of error handling. See :func:`codecs.register`.
:raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
:return: A byte string.
r )r r r )r) r r+ r r r
r s r c C s4 t | | } t | | } t | } | | f S)a
"Pull"-based decoder.
:param input:
An iterable of byte strings.
The input is first consumed just enough to determine the encoding
based on the precense of a BOM,
then consumed on demand when the return value is.
:param fallback_encoding:
An :class:`Encoding` object or a label string.
The encoding to use if :obj:`input` does note have a BOM.
:param errors: Type of error handling. See :func:`codecs.register`.
:raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
:returns:
An ``(output, encoding)`` tuple.
:obj:`output` is an iterable of Unicode strings,
:obj:`encoding` is the :obj:`Encoding` that is being used.
)IncrementalDecoder_iter_decode_generatornext)r) r* r+ decoder generatorr r r r
iter_decode s r9 c c s | j } t | } x | D]; } | | } | r | j d k sI t | j V| VPq W| d d d } | j d k s t | j V| r | Vd Sx% | D] } | | } | r | Vq W| d d d } | r | Vd S)zqReturn a generator that first yields the :obj:`Encoding`,
then yields output chukns as Unicode strings.
N finalT)r
iterr AssertionError)r) r7 r
chunckoutputr r r
r5 s,
r5 c C s t | | j } t | | S)uY
“Pull”-based encoder.
:param input: An iterable of Unicode strings.
:param encoding: An :class:`Encoding` object or a label string.
:param errors: Type of error handling. See :func:`codecs.register`.
:raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
:returns: An iterable of byte strings.
)IncrementalEncoderr _iter_encode_generator)r) r r+ r r r r
iter_encode s rB c c sI x% | D] } | | } | r | Vq W| d d d } | rE | Vd S)N r; Tr )r) r r> r? r r r
rA s
rA c @ s4 e Z d Z d Z d d d Z d d d Z d S) r4 uO
“Push”-based decoder.
:param fallback_encoding:
An :class:`Encoding` object or a label string.
The encoding to use if :obj:`input` does note have a BOM.
:param errors: Type of error handling. See :func:`codecs.register`.
:raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
r' c C s7 t | | _ | | _ d | _ d | _ d | _ d S)Nr: )r _fallback_encoding_errors_buffer_decoderr )r r* r+ r r r
r! s
zIncrementalDecoder.__init__Fc C s | j } | d k r" | | | S| j | } t | \ } } | d k r| t | d k rs | rs | | _ d S| j } | j j | j j } | | _ | | _ | | | S)zDecode one chunk of the input.
:param input: A byte string.
:param final:
Indicate that no more input is available.
Must be :obj:`True` if this is the last call.
:returns: An Unicode string.
Nr. rC )
rG rF r( lenrD r incrementaldecoderrE r
r )r r) r; r7 r r r r
r
' s
zIncrementalDecoder.decodeN)r# r$ r% r& r! r
r r r r
r4 s
r4 c @ s( e Z d Z d Z e d d d Z d S)r@ u
“Push”-based encoder.
:param encoding: An :class:`Encoding` object or a label string.
:param errors: Type of error handling. See :func:`codecs.register`.
:raises: :exc:`~exceptions.LookupError` for an unknown encoding label.
.. method:: encode(input, final=False)
:param input: An Unicode string.
:param final:
Indicate that no more input is available.
Must be :obj:`True` if this is the last call.
:returns: A byte string.
r3 c C s( t | } | j j | j | _ d S)N)r r incrementalencoderr )r r r+ r r r
r! T s zIncrementalEncoder.__init__N)r# r$ r% r& r2 r! r r r r
r@ C s r@ )r&
__future__r r labelsr VERSIONr r r r r objectr r2 r0 r1 r
r( r r9 r5 rB rA r4 r@ r r r r
s2
3