def encode_for_xml(unicode_data, encoding='ascii'):
"""
Encode unicode_data for use as XML or HTML, with characters outside
of the encoding converted to XML numeric character references.
"""
try:
return unicode_data.encode(encoding, 'xmlcharrefreplace')
except ValueError:
# ValueError is raised if there are unencodable chars in the
# data and the 'xmlcharrefreplace' error handler is not found.
# Pre-2.3 Python doesn't support the 'xmlcharrefreplace' error
# handler, so we'll emulate it.
return _xmlcharref_encode(unicode_data, encoding)
def _xmlcharref_encode(unicode_data, encoding):
"""Emulate Python 2.3's 'xmlcharrefreplace' encoding error handler."""
chars = []
# Step through the unicode_data string one character at a time in
# order to catch unencodable characters:
for char in unicode_data:
try:
chars.append(char.encode(encoding, 'strict'))
except UnicodeError:
chars.append('&#%i;' % ord(char))
return ''.join(chars)
if __name__ == '__main__':
# demo
data = u'''\
Encoding Test
accented characters:
- \xe0 (a + grave)
- \xe7 (c + cedilla)
- \xe9 (e + acute)
- \xee (i + circumflex)
- \xf1 (n + tilde)
- \xfc (u + umlaut)
symbols:
- \xa3 (British pound)
- \xa2 (cent)
- \u20ac (Euro)
- \u221e (infinity)
- \xb0 (degree)
'''
print encode_for_xml(data, 'ascii')