1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
|
# Test a UTF-8 encoded literal
s = "asdf©qwer"
for i in range(len(s)):
print("s[%d]: %s %X"%(i, s[i], ord(s[i])))
# Test all three forms of Unicode escape, and
# all blocks of UTF-8 byte patterns
s = "a\xA9\xFF\u0123\u0800\uFFEE\U0001F44C"
for i in range(-len(s), len(s)):
print("s[%d]: %s %X"%(i, s[i], ord(s[i])))
print("s[:%d]: %d chars, '%s'"%(i, len(s[:i]), s[:i]))
for j in range(i, len(s)):
print("s[%d:%d]: %d chars, '%s'"%(i, j, len(s[i:j]), s[i:j]))
print("s[%d:]: %d chars, '%s'"%(i, len(s[i:]), s[i:]))
# Test UTF-8 encode and decode
enc = s.encode()
print(enc, enc.decode() == s)
# printing of unicode chars using repr
# NOTE: for some characters (eg \u10ff) we differ to CPython
print(repr('a\uffff'))
print(repr('a\U0001ffff'))
# test invalid escape code
try:
eval('"\\U00110000"')
except SyntaxError:
print('SyntaxError')
# test unicode string given to int
try:
int('\u0200')
except ValueError:
print('ValueError')
|
