Repository navigation
Expand file tree
/
Copy pathbytes_decode_encoding.py
More file actions
75 lines (60 loc) · 2.12 KB
/
Copy pathbytes_decode_encoding.py
File metadata and controls
75 lines (60 loc) · 2.12 KB
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
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
# Test bytes.decode() and str.encode() with encoding parameter validation
# Check if decode method is available (requires MICROPY_CPYTHON_COMPAT)
try:
b"".decode()
except AttributeError:
print("SKIP")
raise SystemExit
# Test valid encodings for bytes.decode()
# utf-8 (default)
print(b"hello".decode("utf-8"))
print(b"hello".decode("utf8"))
# ascii (subset of utf-8)
print(b"hello".decode("ascii"))
# Test valid encoding for str.encode()
print("hello".encode("utf-8"))
print("hello".encode("utf8"))
print("hello".encode("ascii"))
# Test with bytearray
print(bytearray(b"test").decode("utf-8"))
# Test that UTF-8 still works correctly with non-ASCII characters
# © symbol (U+00A9)
print(b"\xc2\xa9".decode("utf-8"))
print("©".encode("utf-8"))
# Test emoji 👍 (U+1F44D)
print(b"\xf0\x9f\x91\x8d".decode("utf-8"))
print("👍".encode("utf-8"))
# Test ascii encode
print("abcde".encode("ascii"))
# Test invalid decoded code points in repr fallback path.
print(repr(b"\xf4\x90\x80\x80".decode("utf-8")))
print(repr(b"\xf5\x80\x80\x80".decode("utf-8")))
# Test invalid ASCII characters in decode
try:
print(repr(b"ni\xe5\xa5\xbd".decode("ascii")))
except UnicodeError:
print("UnicodeError")
# Test invalid encodings for bytes.decode()
# These should raise LookupError
invalid_encodings = ["latin-1", "latin1", "utf-16", "utf-32", "iso-8859-1", "cp1252"]
for encoding in invalid_encodings:
try:
b"hello".decode(encoding)
print("UNEXPECTED:", encoding, "should raise LookupError")
except LookupError as e:
print("LookupError:", encoding)
# Test bytes method accepting bytearray as argument (arg type normalization)
print(b"hello world".find(bytearray(b"world")))
print(bytearray(b"hello world").find(bytearray(b"world")))
# Test invalid encodings for str.encode()
for encoding in invalid_encodings:
try:
"hello".encode(encoding)
print("UNEXPECTED:", encoding, "should raise LookupError")
except LookupError as e:
print("LookupError:", encoding)
# Test invalid ascii characters in str.encode()
try:
"你好".encode("ascii")
except UnicodeError:
print("UnicodeError")