Skip to content

Instantly share code, notes, and snippets.

@philikon
Created February 8, 2011 08:22
Show Gist options
  • Save philikon/816088 to your computer and use it in GitHub Desktop.
Save philikon/816088 to your computer and use it in GitHub Desktop.
WTF-8 codec for Python
# wtf8.py
import codecs
def encode(input, errors='strict'):
return input.encode('utf-8', errors).decode('latin-1', errors).encode('utf-8', errors), len(input)
def decode(input, errors='strict'):
return input.decode('utf-8', errors).encode('latin-1', errors).decode('utf-8', errors), len(input)
class StreamWriter(codecs.StreamWriter):
encode = encode
class StreamReader(codecs.StreamReader):
decode = decode
def find_codec(codec_name):
if codec_name.lower() == 'wtf-8':
return (encode, decode, StreamReader, StreamWriter)
return None
codecs.register(find_codec)
if __name__ == "__main__":
msg = u"I \u2665 Unicode"
print "In your terminal's encoding:", msg
print "In glorious WTF-8:", msg.encode('wtf-8')
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment