def test_html_entities_unescape(self):
tools.assert_raises(TypeError, misc.html_entities_unescape, b'byte string')
tools.ok_(misc.html_entities_unescape(self.u_entity_escape) == self.u_entity)
tools.ok_(misc.html_entities_unescape('<tag>%s</tag>'
% self.u_entity_escape) == self.u_entity)
tools.ok_(misc.html_entities_unescape('a�b') == 'a�b')
tools.ok_(misc.html_entities_unescape('a�b') == 'a\ufffdb')
tools.ok_(misc.html_entities_unescape('a�b') == 'a\ufffdb')
def test_html_entities_unescape(self):
tools.assert_raises(TypeError, misc.html_entities_unescape,
'byte string')
tools.ok_(
misc.html_entities_unescape(self.u_entity_escape) == self.u_entity)
tools.ok_(
misc.html_entities_unescape(u'<tag>%s</tag>' %
self.u_entity_escape) == self.u_entity)
tools.ok_(
misc.html_entities_unescape(u'a�b') ==
u'a�b')
tools.ok_(misc.html_entities_unescape(u'a�b') == u'a\ufffdb')
tools.ok_(misc.html_entities_unescape(u'a�b') == u'a\ufffdb')
def xml_to_unicode(byte_string, encoding='utf8', errors='replace'):
'''Transform a byte string from an xml file into unicode
:arg byte_string: byte string to decode
:kwarg encoding: encoding that the byte string is in
:kwarg errors: What to do if not every character is decodable using
:attr:`encoding`. See the :func:`to_unicode` docstring for
legal values.
:returns: unicode string decoded from :attr:`byte_string`
This function attempts to reverse what :func:`unicode_to_xml` does.
It takes a byte string (presumably read in from an xml file) and expands
all the html entities into unicode characters and decodes the bytes into
a unicode string. One thing it cannot do is restore any control
characters that were removed prior to inserting into the file. If you
need to keep such characters you need to use func:`xml_to_bytes` and
:func:`bytes_to_xml` instead.
'''
string = to_unicode(byte_string, encoding=encoding, errors=errors)
string = html_entities_unescape(string)
return string
def xml_to_unicode(byte_string, encoding='utf-8', errors='replace'):
'''Transform a byte :class:`bytes` from an xml file into a :class:`str`
string
:arg byte_string: byte :class:`bytes` to decode
:kwarg encoding: encoding that the byte :class:`bytes` is in
:kwarg errors: What to do if not every character is valid in
:attr:`encoding`. See the :func:`to_unicode` documentation for legal
values.
:rtype: :class:`str` string
:returns: string decoded from :attr:`byte_string`
This function attempts to reverse what :func:`unicode_to_xml` does. It
takes a byte :class:`bytes` (presumably read in from an xml file) and
expands all the html entities into unicode characters and decodes the byte
:class:`bytes` into a :class:`str` string. One thing it cannot do is
restore any :term:`control characters` that were removed prior to
inserting into the file. If you need to keep such characters you need to
use :func:`xml_to_bytes` and :func:`bytes_to_xml` or use on of the
strategies documented in :func:`unicode_to_xml` instead.
'''
string = to_unicode(byte_string, encoding=encoding, errors=errors)
string = html_entities_unescape(string)
return string
