archlinux

cscorley@geogaddi: ~
% python2
Python 2.7.8 (default, Jul  1 2014, 17:30:21)
[GCC 4.9.0 20140604 (prerelease)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> s = u"test💩word"
>>> s
u'test\U0001f4a9word'
>>> type(s)
<type 'unicode'>
>>> len(s)
9
>>> for each in s:
...    print(each)
...
t
e
s
t
💩
w
o
r
d
>>>

cscorley@geogaddi: ~
% locale
LANG=en_US.utf8
LC_CTYPE=en_US.utf8
LC_NUMERIC="en_US.utf8"
LC_TIME="en_US.utf8"
LC_COLLATE="en_US.utf8"
LC_MONETARY="en_US.utf8"
LC_MESSAGES="en_US.utf8"
LC_PAPER="en_US.utf8"
LC_NAME="en_US.utf8"
LC_ADDRESS="en_US.utf8"
LC_TELEPHONE="en_US.utf8"
LC_MEASUREMENT="en_US.utf8"
LC_IDENTIFICATION="en_US.utf8"
LC_ALL=

osx

cscorley@bocmaxima: ~
% python2
Python 2.7.8 (default, Jul  2 2014, 10:14:46)
[GCC 4.2.1 Compatible Apple LLVM 5.1 (clang-503.0.40)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> s = u"test💩word"
>>> s
u'test\U0001f4a9word'
>>> type(s)
<type 'unicode'>
>>> len(s)
10
>>> for each in s:
...    print(each)
...
t
e
s
t
�
�
w
o
r
d
>>>

cscorley@bocmaxima: ~
% locale
LANG="en_US.UTF-8"
LC_COLLATE="en_US.UTF-8"
LC_CTYPE="en_US.UTF-8"
LC_MESSAGES="en_US.UTF-8"
LC_MONETARY="en_US.UTF-8"
LC_NUMERIC="en_US.UTF-8"
LC_TIME="en_US.UTF-8"
LC_ALL=

osx-withnormalize

cscorley@bocmaxima: ~
% python2
Python 2.7.8 (default, Jul  2 2014, 10:14:46)
[GCC 4.2.1 Compatible Apple LLVM 5.1 (clang-503.0.40)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> s = u"test💩word"
>>> import unicodedata
>>> unicodedata.normalize('NFC', s)
u'test\U0001f4a9word'
>>> s
u'test\U0001f4a9word'
>>> len(unicodedata.normalize('NFC', s))
10
>>> for char in unicodedata.normalize('NFC', s):
...    print(char)
...
t
e
s
t
�
�
w
o
r
d
>>> len(unicodedata.normalize('NFKC', s))
10
>>> len(unicodedata.normalize('NFD', s))
10
>>> len(unicodedata.normalize('NFKD', s))
10
>>>