Created
August 3, 2013 23:23
-
-
Save juandebravo/6148367 to your computer and use it in GitHub Desktop.
Check the representation of a set of characters using different encodings
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import sys | |
if len(sys.argv) > 1: | |
code_points = [unicode(c, 'utf-8') for c in sys.argv[1:]] | |
else: | |
# Testing values | |
code_points = [u'\U0001F37A\U00000045\U0000039B', u'\U0001F37A'] | |
#code_points = [unicode('❯❯', 'utf-8')] | |
def handle_encoding(encoding, code_point): | |
try: | |
values = ['{:>15}'.format(encoding), | |
' ---> ', | |
':'.join('{0:x}'.format(ord(c)) for c in | |
code_point.encode(encoding)), | |
' (', str(len(code_point.encode(encoding))), ')'] | |
print ''.join(values) | |
except Exception as ex: | |
values = ['{:>15}'.format(encoding), | |
' ---> ', | |
'Unable to encode the codepoint in {0}'.format(encoding)] | |
print ''.join(values) | |
for code_point in code_points: | |
print '{:>15}'.format('character') + ' ---> ' + code_point | |
print '{:>15}'.format('code points') + ' ---> ' + repr(code_point) | |
for coding in ('ascii', 'latin-1', 'utf-8', 'utf-16', 'utf-16be', 'utf-16le'): | |
handle_encoding(coding, code_point) | |
# python encoding_info.py | |
# character ---> 🍺EΛ | |
# code points ---> u'\U0001f37aE\u039b' | |
# ascii ---> Unable to encode the codepoint in ascii | |
# latin-1 ---> Unable to encode the codepoint in latin-1 | |
# utf-8 ---> f0:9f:8d:ba:45:ce:9b (7) | |
# utf-16 ---> ff:fe:3c:d8:7a:df:45:0:9b:3 (10) | |
# utf-16be ---> d8:3c:df:7a:0:45:3:9b (8) | |
# utf-16le ---> 3c:d8:7a:df:45:0:9b:3 (8) | |
# character ---> 🍺 | |
# code points ---> u'\U0001f37a' | |
# ascii ---> Unable to encode the codepoint in ascii | |
# latin-1 ---> Unable to encode the codepoint in latin-1 | |
# utf-8 ---> f0:9f:8d:ba (4) | |
# utf-16 ---> ff:fe:3c:d8:7a:df (6) | |
# utf-16be ---> d8:3c:df:7a (4) | |
# utf-16le ---> 3c:d8:7a:df (4) | |
# python encoding_info.py "OLA KE ASE KOMO VA KE ASE" | |
# character ---> OLA KE ASE KOMO VA KE ASE | |
# code points ---> u'OLA KE ASE KOMO VA KE ASE' | |
# ascii ---> 4f:4c:41:20:4b:45:20:41:53:45:20:4b:4f:4d:4f:20:56:41:20:4b:45:20:41:53:45 (25) | |
# latin-1 ---> 4f:4c:41:20:4b:45:20:41:53:45:20:4b:4f:4d:4f:20:56:41:20:4b:45:20:41:53:45 (25) | |
# utf-8 ---> 4f:4c:41:20:4b:45:20:41:53:45:20:4b:4f:4d:4f:20:56:41:20:4b:45:20:41:53:45 (25) | |
# utf-16 ---> ff:fe:4f:0:4c:0:41:0:20:0:4b:0:45:0:20:0:41:0:53:0:45:0:20:0:4b:0:4f:0:4d:0:4f:0:20:0:56:0:41:0:20:0:4b:0:45:0:20:0:41:0:53:0:45:0 (52) | |
# utf-16be ---> 0:4f:0:4c:0:41:0:20:0:4b:0:45:0:20:0:41:0:53:0:45:0:20:0:4b:0:4f:0:4d:0:4f:0:20:0:56:0:41:0:20:0:4b:0:45:0:20:0:41:0:53:0:45 (50) | |
# utf-16le ---> 4f:0:4c:0:41:0:20:0:4b:0:45:0:20:0:41:0:53:0:45:0:20:0:4b:0:4f:0:4d:0:4f:0:20:0:56:0:41:0:20:0:4b:0:45:0:20:0:41:0:53:0:45:0 (50) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment