uni.py

#!/usr/bin/python

import re
import unicodedata
import codecs
import urllib2

if 2 == len( u'\U0001f4a9' ):
    length_ucs2 = len
else:
    def length_ucs2( string ):
        return len( string.encode( 'UTF-16LE' ) ) / 2

lm = re.compile("^[0-9a-fA-F]")
s=u""

#with open("./NamesList.txt") as f:
response = urllib2.urlopen('http://www.unicode.org/Public/5.2.0/ucd/NamesList.txt')
for line in response.read().split("\n"):
    if not lm.match(line):
        continue
    if line.find("\t<") > -1:
        continue
    s = s + unicodedata.lookup(line.strip().split("\t")[1])

print "length_ucs2: %d" % length_ucs2(s)
print "len:         %d" % len(s)
print "bytes:       %d" % len(bytearray(s, 'utf-8'))