def test_guess_encoding_no_chardet(self):
# Test that unicode strings are not allowed
tools.assert_raises(TypeError, misc.guess_encoding, self.u_spanish)
tools.ok_(misc.guess_encoding(self.utf8_spanish, disable_chardet=True) == 'utf-8')
tools.ok_(misc.guess_encoding(self.latin1_spanish, disable_chardet=True) == 'latin-1')
tools.ok_(misc.guess_encoding(self.utf8_japanese, disable_chardet=True) == 'utf-8')
tools.ok_(misc.guess_encoding(self.euc_jp_japanese, disable_chardet=True) == 'latin-1')
def test_guess_encoding_with_chardet(self):
# We go this slightly roundabout way because multiple encodings can
# output the same byte sequence. What we're really interested in is
# if we can get the original unicode string without knowing the
# converters beforehand
tools.ok_(to_unicode(self.utf8_spanish,
misc.guess_encoding(self.utf8_spanish)) == self.u_spanish)
tools.ok_(to_unicode(self.latin1_spanish,
misc.guess_encoding(self.latin1_spanish)) == self.u_spanish)
tools.ok_(to_unicode(self.utf8_japanese,
misc.guess_encoding(self.utf8_japanese)) == self.u_japanese)
def test_guess_encoding_with_chardet(self):
# We go this slightly roundabout way because multiple encodings can
# output the same byte sequence. What we're really interested in is
# if we can get the original unicode string without knowing the
# converters beforehand
tools.ok_(
to_unicode(self.utf8_spanish, misc.guess_encoding(
self.utf8_spanish)) == self.u_spanish)
tools.ok_(
to_unicode(self.latin1_spanish,
misc.guess_encoding(self.latin1_spanish)) ==
self.u_spanish)
tools.ok_(
to_unicode(self.utf8_japanese,
misc.guess_encoding(self.utf8_japanese)) ==
self.u_japanese)
def test_guess_encoding_no_chardet(self):
# Test that unicode strings are not allowed
tools.assert_raises(TypeError, misc.guess_encoding, self.u_spanish)
tools.ok_(
misc.guess_encoding(self.utf8_spanish, disable_chardet=True) ==
'utf-8')
tools.ok_(
misc.guess_encoding(self.latin1_spanish, disable_chardet=True) ==
'latin-1')
tools.ok_(
misc.guess_encoding(self.utf8_japanese, disable_chardet=True) ==
'utf-8')
tools.ok_(
misc.guess_encoding(self.euc_jp_japanese, disable_chardet=True) ==
'latin-1')
def test_guess_encoding_with_chardet_uninstalled(self):
if chardet:
raise SkipTest('chardet installed, euc_jp will not be mangled')
else:
tools.ok_(to_unicode(self.euc_jp_japanese,
misc.guess_encoding(self.euc_jp_japanese)) ==
self.u_mangled_euc_jp_as_latin1)
def guess_encoding_to_xml(string, output_encoding='utf-8', attrib=False,
control_chars='replace'):
'''Return a byte :class:`bytes` suitable for inclusion in xml
:arg string: :class:`str` or byte :class:`bytes` to be transformed into
a byte :class:`bytes` suitable for inclusion in xml. If string is
a byte :class:`bytes` we attempt to guess the encoding. If we cannot guess,
we fallback to ``latin-1``.
:kwarg output_encoding: Output encoding for the byte :class:`bytes`. This
should match the encoding of your xml file.
:kwarg attrib: If :data:`True`, escape the item for use in an xml
attribute. If :data:`False` (default) escape the item for use in
a text node.
:returns: :term:`utf-8` encoded byte :class:`bytes`
'''
# Unicode strings can just be run through unicode_to_xml()
if isunicodestring(string):
return unicode_to_xml(string, encoding=output_encoding,
attrib=attrib, control_chars=control_chars)
# Guess the encoding of the byte strings
input_encoding = guess_encoding(string)
# Return the new byte string
return byte_string_to_xml(string, input_encoding=input_encoding,
errors='replace', output_encoding=output_encoding,
attrib=attrib, control_chars=control_chars)
def guess_encoding_to_xml(string,
output_encoding='utf8',
attrib=False,
control_chars='replace'):
'''Return a byte string suitable for inclusion in xml
:arg string: unicode or byte string to be transformed into a byte string
suitable for inclusion in xml. If string is a byte string we attempt
to guess the encoding. If we cannot guess, we fallback to latin1.
:kwarg output_encoding: Output encoding for the byte string. This should
match the encoding of your xml file.
:kwarg attrib: If True, escape the item for use in an attribute. If False
default) escape the item for use in a text node.
:returns: utf8 encoded byte string
'''
# Unicode strings can just be run through unicode_to_xml()
if isinstance(string, unicode):
return unicode_to_xml(string,
encoding=output_encoding,
attrib=attrib,
control_chars=control_chars)
# Guess the encoding of the byte strings
input_encoding = guess_encoding(string)
# Return the new byte string
return byte_string_to_xml(string,
input_encoding=input_encoding,
errors='replace',
output_encoding=output_encoding,
attrib=attrib,
control_chars=control_chars)
def test_guess_encoding_with_chardet_uninstalled(self):
if chardet:
raise SkipTest('chardet installed, euc_jp will not be mangled')
else:
tools.ok_(
to_unicode(self.euc_jp_japanese,
misc.guess_encoding(self.euc_jp_japanese)) ==
self.u_mangled_euc_jp_as_latin1)
def test_guess_encoding_with_chardet_installed(self):
if chardet:
tools.ok_(
to_unicode(self.euc_jp_japanese,
misc.guess_encoding(self.euc_jp_japanese)) ==
self.u_japanese)
else:
raise SkipTest(
'chardet not installed, euc_jp will not be guessed correctly')
def test_guess_encoding_with_chardet_installed(self):
if chardet:
tools.ok_(to_unicode(self.euc_jp_japanese,
misc.guess_encoding(self.euc_jp_japanese)) == self.u_japanese)
else:
raise SkipTest('chardet not installed, euc_jp will not be guessed correctly')