def test_netbytes2str(self):
from mobilize.httputil import netbytes2str
kungfu = '功夫' # b'\xe5\x8a\x9f\xe5\xa4\xab'
src = b'<html><body><p>\xe5\x8a\x9f\xe5\xa4\xab means:\r\n<ul>\r\n<li>hard work</li>\r\n<li>great skill</li>\r\n</ul>'
expected = '<html><body><p>功夫 means:\n<ul>\n<li>hard work</li>\n<li>great skill</li>\n</ul>'
actual = netbytes2str(src, 'utf-8')
self.assertEquals(expected, actual)
def test_netbytes2str_wrongencoding(self):
'''Test for when the guessed encoding is wrong, and we need to automatically try different ones'''
from mobilize.httputil import netbytes2str
# iso-8859-1 encoding, but we'll initially parse it as utf-8
kungfu = '功夫' # b'\xe5\x8a\x9f\xe5\xa4\xab'
src = b'<p>a \xa0 b</p>'
expected = '<p>a b</p>'
actual = netbytes2str(src, 'utf-8')
self.assertEquals(expected, actual)