test_unicode_ffff_plus_chars.py

# encoding: utf-8


def to_bin(x):
    return ' '.join('{:08b}'.format(ord(i)) for i in x)

embeded_unicode = u'💩'
char_in_unicode = u'\U0001f4a9'

assert(embeded_unicode == char_in_unicode)

print('len(char_in_unicode)')
print(len(char_in_unicode))

print('len(embeded_unicode)')
print(len(embeded_unicode))

print('\nto_bin(char_in_unicode.encode(utf-8))')
print(to_bin(char_in_unicode.encode('utf-8')))


print('\nto_bin(embeded_unicode.encode(utf-8))')
print(to_bin(embeded_unicode.encode('utf-8')))

print('\nto_bin(char_in_unicode[0].encode(utf-8))')
print(to_bin(char_in_unicode[0].encode('utf-8')))

print('\nto_bin(char_in_unicode[1].encode(utf-8))')
print(to_bin(char_in_unicode[1].encode('utf-8')))

assert(char_in_unicode[0].encode('utf-8') + char_in_unicode[1].encode('utf-8') != char_in_unicode.encode('utf-8'))


## lxml
from lxml import etree
x = etree.XML('<root/>')
x.text = u'char: [' + char_in_unicode + u']'
print('xml.text')
print(x.text)

print('etree.tostring(x, utf-8)')
print(etree.tostring(x, encoding='utf-8'))

print('etree.tostring(x, ascii)')
print(etree.tostring(x, encoding='ascii'))