2016-12-14 | Paul Boddie | raw annotate files changeset graph | Added a UTF-8 character counting native function to support the __len__ method on Unicode objects, introducing a bytelength method on strings so that byte-level operations, such as conversion between encodings, can still work with Unicode objects (since __len__ returning characters would be inappropriate for such purposes). |
1 def f(): 2 s = "test" 3 m = s.__len__ 4 n = "test".__len__ 5 print m # __builtins__.str.basestring.__len__ 6 print m() # 4 7 print n # __builtins__.str.basestring.__len__ 8 print n() 9 10 def g(): 11 l = [1, 2] 12 m = l.__len__ 13 n = [1, 2].__len__ 14 print l # [1, 2] 15 print m # __builtins__.list.list.__len__ 16 print m() # 2 17 print n # __builtins__.list.list.__len__ 18 print n() # 2 19 20 f() 21 g()