1 #!/usr/bin/env python 2 3 """ 4 Unicode objects. 5 6 Copyright (C) 2015, 2016 Paul Boddie <paul@boddie.org.uk> 7 8 This program is free software; you can redistribute it and/or modify it under 9 the terms of the GNU General Public License as published by the Free Software 10 Foundation; either version 3 of the License, or (at your option) any later 11 version. 12 13 This program is distributed in the hope that it will be useful, but WITHOUT 14 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS 15 FOR A PARTICULAR PURPOSE. See the GNU General Public License for more 16 details. 17 18 You should have received a copy of the GNU General Public License along with 19 this program. If not, see <http://www.gnu.org/licenses/>. 20 """ 21 22 from __builtins__.str import basestring 23 from posix.iconv import Converter 24 25 class utf8string(basestring): 26 27 "A character string representation based on UTF-8." 28 29 def encode(self, encoding): 30 31 "Encode the string to the given 'encoding'." 32 33 from_utf8 = Converter("UTF-8", encoding) 34 try: 35 from_utf8.feed(self) 36 return str(from_utf8) 37 finally: 38 from_utf8.close() 39 40 def unicode(s, encoding): 41 42 "Convert 's' to a Unicode object, interpreting 's' as using 'encoding'." 43 44 if isinstance(s, utf8string): 45 return s 46 47 # Obtain a string representation. 48 49 s = s.__str__() 50 51 # Convert the string to UTF-8. 52 53 to_utf8 = Converter(encoding, "UTF-8") 54 try: 55 to_utf8.feed(s) 56 return utf8string(str(to_utf8)) 57 finally: 58 to_utf8.close() 59 60 # vim: tabstop=4 expandtab shiftwidth=4