113 lines
4.4 KiB
Python
113 lines
4.4 KiB
Python
from webencodings import UTF8, decode, lookup
|
|
|
|
from .parser import parse_stylesheet
|
|
|
|
|
|
def decode_stylesheet_bytes(css_bytes, protocol_encoding=None,
|
|
environment_encoding=None):
|
|
"""Determine the character encoding of a CSS stylesheet and decode it.
|
|
|
|
This is based on the presence of a ,
|
|
an ``@charset`` rule,
|
|
and encoding meta-information.
|
|
|
|
:param css_bytes: A byte string.
|
|
:param protocol_encoding:
|
|
The encoding label, if any, defined by HTTP or equivalent protocol.
|
|
(e.g. via the ``charset`` parameter of the ``Content-Type`` header.)
|
|
:param environment_encoding:
|
|
A :class:`webencodings.Encoding` object
|
|
for the `environment encoding
|
|
<http://www.w3.org/TR/css-syntax/#environment-encoding>`_,
|
|
if any.
|
|
:returns:
|
|
A 2-tuple of a decoded Unicode string
|
|
and the :class:`webencodings.Encoding` object that was used.
|
|
|
|
"""
|
|
# http://dev.w3.org/csswg/css-syntax/#the-input-byte-stream
|
|
if protocol_encoding:
|
|
fallback = lookup(protocol_encoding)
|
|
if fallback:
|
|
return decode(css_bytes, fallback)
|
|
if css_bytes.startswith(b'@charset "'):
|
|
# 10 is len(b'@charset "')
|
|
# 100 is arbitrary so that no encoding label is more than 100-10 bytes.
|
|
end_quote = css_bytes.find(b'"', 10, 100)
|
|
if end_quote != -1 and css_bytes.startswith(b'";', end_quote):
|
|
fallback = lookup(css_bytes[10:end_quote].decode('latin1'))
|
|
if fallback:
|
|
if fallback.name in ('utf-16be', 'utf-16le'):
|
|
return decode(css_bytes, UTF8)
|
|
return decode(css_bytes, fallback)
|
|
if environment_encoding:
|
|
return decode(css_bytes, environment_encoding)
|
|
return decode(css_bytes, UTF8)
|
|
|
|
|
|
def parse_stylesheet_bytes(css_bytes, protocol_encoding=None,
|
|
environment_encoding=None,
|
|
skip_comments=False, skip_whitespace=False):
|
|
"""Parse :diagram:`stylesheet` from bytes,
|
|
determining the character encoding as web browsers do.
|
|
|
|
This is used when reading a file or fetching an URL.
|
|
The character encoding is determined from the initial bytes
|
|
(a :abbr:`BOM (Byte Order Mark)` or an ``@charset`` rule)
|
|
as well as the parameters.
|
|
The ultimate fallback is UTF-8.
|
|
|
|
:param css_bytes: A byte string.
|
|
:param protocol_encoding:
|
|
A string.
|
|
The encoding label, if any, defined by HTTP or equivalent protocol.
|
|
(e.g. via the ``charset`` parameter of the ``Content-Type`` header.)
|
|
:param environment_encoding:
|
|
A :class:`webencodings.Encoding` object
|
|
for the `environment encoding`_,
|
|
if any.
|
|
:param skip_comments:
|
|
Ignore CSS comments at the top-level of the stylesheet.
|
|
If the input is a string, ignore all comments.
|
|
:param skip_whitespace:
|
|
Ignore whitespace at the top-level of the stylesheet.
|
|
Whitespace is still preserved
|
|
in the :attr:`~tinycss2.ast.QualifiedRule.prelude`
|
|
and the :attr:`~tinycss2.ast.QualifiedRule.content` of rules.
|
|
:returns:
|
|
A ``(rules, encoding)`` tuple.
|
|
|
|
* :obj:`rules` is a list of
|
|
:class:`~tinycss2.ast.QualifiedRule`,
|
|
:class:`~tinycss2.ast.AtRule`,
|
|
:class:`~tinycss2.ast.Comment` (if ``skip_comments`` is false),
|
|
:class:`~tinycss2.ast.WhitespaceToken`
|
|
(if ``skip_whitespace`` is false),
|
|
and :class:`~tinycss2.ast.ParseError` objects.
|
|
* :obj:`encoding` is the :class:`webencodings.Encoding` object
|
|
that was used.
|
|
If ``rules`` contains an ``@import`` rule, this is
|
|
the `environment encoding`_ for the imported stylesheet.
|
|
|
|
.. _environment encoding:
|
|
http://www.w3.org/TR/css-syntax/#environment-encoding
|
|
|
|
.. code-block:: python
|
|
|
|
response = urlopen('http://example.net/foo.css')
|
|
rules, encoding = parse_stylesheet_bytes(
|
|
css_bytes=response.read(),
|
|
# Python 3.x
|
|
protocol_encoding=response.info().get_content_type().get_param('charset'),
|
|
# Python 2.x
|
|
protocol_encoding=response.info().gettype().getparam('charset'),
|
|
)
|
|
for rule in rules:
|
|
...
|
|
|
|
"""
|
|
css_unicode, encoding = decode_stylesheet_bytes(
|
|
css_bytes, protocol_encoding, environment_encoding)
|
|
stylesheet = parse_stylesheet(css_unicode, skip_comments, skip_whitespace)
|
|
return stylesheet, encoding
|