You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
53 lines
1.3 KiB
53 lines
1.3 KiB
# 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")
|
|
|
|
# test invalid UTF-8 string
|
|
try:
|
|
str(b"ab\xa1", "utf8")
|
|
except UnicodeError:
|
|
print("UnicodeError")
|
|
try:
|
|
str(b"ab\xf8", "utf8")
|
|
except UnicodeError:
|
|
print("UnicodeError")
|
|
try:
|
|
str(bytearray(b"ab\xc0a"), "utf8")
|
|
except UnicodeError:
|
|
print("UnicodeError")
|
|
try:
|
|
str(b"\xf0\xe0\xed\xe8", "utf8")
|
|
except UnicodeError:
|
|
print("UnicodeError")
|
|
|