usse/funda-scraper/venv/lib/python3.10/site-packages/mypyc/test-data/run-strings.test

638 lines
23 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Test cases for strings (compile and run)
[case testStrBasics]
from typing import Tuple
def f() -> str:
return 'some string'
def g() -> str:
return 'some\a \v \t \x7f " \n \0string 🐍'
def tostr(x: int) -> str:
return str(x)
def booltostr(x: bool) -> str:
return str(x)
def concat(x: str, y: str) -> str:
return x + y
def eq(x: str) -> int:
if x == 'foo':
return 0
elif x != 'bar':
return 1
return 2
def match(x: str, y: str) -> Tuple[bool, bool]:
return (x.startswith(y), x.endswith(y))
[file driver.py]
from native import f, g, tostr, booltostr, concat, eq, match
import sys
assert f() == 'some string'
assert f() is sys.intern('some string')
assert g() == 'some\a \v \t \x7f " \n \0string 🐍'
assert tostr(57) == '57'
assert concat('foo', 'bar') == 'foobar'
assert booltostr(True) == 'True'
assert booltostr(False) == 'False'
assert eq('foo') == 0
assert eq('zar') == 1
assert eq('bar') == 2
assert int(tostr(0)) == 0
assert int(tostr(20)) == 20
assert match('', '') == (True, True)
assert match('abc', '') == (True, True)
assert match('abc', 'a') == (True, False)
assert match('abc', 'c') == (False, True)
assert match('', 'abc') == (False, False)
[case testStringOps]
from typing import List, Optional
def do_split(s: str, sep: Optional[str] = None, max_split: Optional[int] = None) -> List[str]:
if sep is not None:
if max_split is not None:
return s.split(sep, max_split)
else:
return s.split(sep)
return s.split()
ss = "abc abcd abcde abcdef"
def test_split() -> None:
assert do_split(ss) == ["abc", "abcd", "abcde", "abcdef"]
assert do_split(ss, " ") == ["abc", "abcd", "abcde", "abcdef"]
assert do_split(ss, "-") == ["abc abcd abcde abcdef"]
assert do_split(ss, " ", -1) == ["abc", "abcd", "abcde", "abcdef"]
assert do_split(ss, " ", 0) == ["abc abcd abcde abcdef"]
assert do_split(ss, " ", 1) == ["abc", "abcd abcde abcdef"]
assert do_split(ss, " ", 2) == ["abc", "abcd", "abcde abcdef"]
def getitem(s: str, index: int) -> str:
return s[index]
from testutil import assertRaises
s = "abc"
def test_getitem() -> None:
assert getitem(s, 0) == "a"
assert getitem(s, 1) == "b"
assert getitem(s, 2) == "c"
assert getitem(s, -3) == "a"
assert getitem(s, -2) == "b"
assert getitem(s, -1) == "c"
with assertRaises(IndexError, "string index out of range"):
getitem(s, 4)
with assertRaises(IndexError, "string index out of range"):
getitem(s, -4)
def str_to_int(s: str, base: Optional[int] = None) -> int:
if base:
return int(s, base)
else:
return int(s)
def test_str_to_int() -> None:
assert str_to_int("1") == 1
assert str_to_int("10") == 10
assert str_to_int("a", 16) == 10
assert str_to_int("1a", 16) == 26
with assertRaises(ValueError, "invalid literal for int() with base 10: 'xyz'"):
str_to_int("xyz")
def test_slicing() -> None:
# Use dummy adds to avoid constant folding
zero = int()
two = zero + 2
s = "foobar" + str()
assert s[two:] == "obar"
assert s[:two] == "fo"
assert s[two:-two] == "ob"
assert s[two:two] == ""
assert s[two:two + 1] == "o"
assert s[-two:] == "ar"
assert s[:-two] == "foob"
assert s[:] == "foobar"
assert s[two:333] == "obar"
assert s[333:two] == ""
assert s[two:-333] == ""
assert s[-333:two] == "fo"
big_int: int = 1000 * 1000 * 1000 * 1000 * 1000 * 1000 * 1000
assert s[1:big_int] == "oobar"
assert s[big_int:] == ""
assert s[-big_int:-1] == "fooba"
def test_str_replace() -> None:
a = "foofoofoo"
assert a.replace("foo", "bar") == "barbarbar"
assert a.replace("foo", "bar", -1) == "barbarbar"
assert a.replace("foo", "bar", 1) == "barfoofoo"
assert a.replace("foo", "bar", 4) == "barbarbar"
assert a.replace("aaa", "bar") == "foofoofoo"
assert a.replace("ofo", "xyzw") == "foxyzwxyzwo"
def is_true(x: str) -> bool:
if x:
return True
else:
return False
def is_false(x: str) -> bool:
if not x:
return True
else:
return False
def test_str_to_bool() -> None:
assert is_false('')
assert not is_true('')
for x in 'a', 'foo', 'bar', 'some string':
assert is_true(x)
assert not is_false(x)
def test_str_min_max() -> None:
x: str = 'aaa'
y: str = 'bbb'
z: str = 'aa'
assert min(x, y) == 'aaa'
assert min(x, z) == 'aa'
assert max(x, y) == 'bbb'
assert max(x, z) == 'aaa'
[case testStringFormattingCStyle]
[typing fixtures/typing-full.pyi]
from typing import Tuple
var = 'mypyc'
num = 20
def test_basics() -> None:
assert 'Hello %s, this is a test' % var == "Hello mypyc, this is a test"
assert 'Hello %s %d, this is a test' % (var, num) == "Hello mypyc 20, this is a test"
t: Tuple[str, int] = (var, num)
assert 'Hello %s %d, this is a test' % t == "Hello mypyc 20, this is a test"
large_num = 2**65
assert 'number: %d' % large_num == 'number: 36893488147419103232'
neg_num = -3
assert 'negative integer: %d' % neg_num == 'negative integer: -3'
assert 'negative integer: %d' % (-large_num) == 'negative integer: -36893488147419103232'
bool_var1 = True
bool_var2 = False
assert 'bool: %s, %s' % (bool_var1, bool_var2) == 'bool: True, False'
float_num = 123.4
assert '%f' % float_num == '123.400000'
assert '%.2f' % float_num == '123.40'
assert '%.5f' % float_num == '123.40000'
assert '%10.2f' % float_num == ' 123.40'
assert '%10.5f' % float_num == ' 123.40000'
assert '%010.5f' % float_num == '0123.40000'
assert '%015.5f' % float_num == '000000123.40000'
assert '%e' % float_num == '1.234000e+02'
large_float = 1.23e30
large_float2 = 1234123412341234123400000000000000000
small_float = 1.23e-20
assert '%f, %f, %f' % (small_float, large_float, large_float2) == \
'0.000000, 1229999999999999959718843908096.000000, 1234123412341234169005079998930878464.000000'
assert '%s, %s, %s' % (small_float, large_float, large_float2) == \
'1.23e-20, 1.23e+30, 1234123412341234123400000000000000000'
assert '%d, %d, %d' % (small_float, large_float, large_float2) == \
'0, 1229999999999999959718843908096, 1234123412341234123400000000000000000'
nan_num = float('nan')
inf_num = float('inf')
assert '%s, %s' % (nan_num, inf_num) == 'nan, inf'
assert '%f, %f' % (nan_num, inf_num) == 'nan, inf'
[case testFStrings]
import decimal
from datetime import datetime
var = 'mypyc'
num = 20
def test_fstring_basics() -> None:
assert f'Hello {var}, this is a test' == "Hello mypyc, this is a test"
large_num = 2**65
assert f'number: {large_num}' == 'number: 36893488147419103232'
neg_num = -3
assert f'negative integer: {neg_num}' == 'negative integer: -3'
assert f'negative integer: {-large_num}' == 'negative integer: -36893488147419103232'
bool_var1 = True
bool_var2 = False
assert f'bool: {bool_var1}, {bool_var2}' == 'bool: True, False'
x = bytes([1, 2, 3, 4])
# assert f'bytes: {x}' == "bytes: b'\\x01\\x02\\x03\\x04'"
# error: On Python 3 formatting "b'abc'" with "{}" produces "b'abc'", not "abc";
# use "{!r}" if this is desired behavior behavior
float_num = 123.4
assert f'{float_num}' == '123.4'
assert f'{float_num:.2f}' == '123.40'
assert f'{float_num:.5f}' == '123.40000'
assert f'{float_num:>10.2f}' == ' 123.40'
assert f'{float_num:>10.5f}' == ' 123.40000'
assert f'{float_num:>010.5f}' == '0123.40000'
assert f'{float_num:>015.5f}' == '000000123.40000'
assert f'{float_num:e}' == '1.234000e+02'
large_float = 1.23e30
large_float2 = 1234123412341234123400000000000000000
small_float = 1.23e-20
assert f'{small_float}, {large_float}, {large_float2}' == '1.23e-20, 1.23e+30, 1234123412341234123400000000000000000'
nan_num = float('nan')
inf_num = float('inf')
assert f'{nan_num}, {inf_num}' == 'nan, inf'
# F-strings would be translated into ''.join[string literals, format method call, ...] in mypy AST.
# Currently we are using a str.join specializer for f-string speed up. We might not cover all cases
# and the rest ones should fall back to a normal str.join method call.
# TODO: Once we have a new pipeline for f-strings, this test case can be moved to testStringOps.
def test_str_join() -> None:
var = 'mypyc'
num = 10
assert ''.join(['a', 'b', '{}'.format(var), 'c']) == 'abmypycc'
assert ''.join(['a', 'b', '{:{}}'.format(var, ''), 'c']) == 'abmypycc'
assert ''.join(['a', 'b', '{:{}}'.format(var, '>10'), 'c']) == 'ab mypycc'
assert ''.join(['a', 'b', '{:{}}'.format(var, '>{}'.format(num)), 'c']) == 'ab mypycc'
assert var.join(['a', '{:{}}'.format(var, ''), 'b']) == 'amypycmypycmypycb'
assert ','.join(['a', '{:{}}'.format(var, ''), 'b']) == 'a,mypyc,b'
assert ''.join(['x', var]) == 'xmypyc'
class A:
def __init__(self, name, age):
self.name = name
self.age = age
def __repr__(self):
return f'{self.name} is {self.age} years old.'
def test_fstring_datatype() -> None:
u = A('John Doe', 14)
assert f'{u}' == 'John Doe is 14 years old.'
d = {'name': 'John Doe', 'age': 14}
assert f'{d}' == "{'name': 'John Doe', 'age': 14}"
def test_fstring_escape() -> None:
assert f"{'inside'}" == 'inside'
assert f'{"inside"}' == 'inside'
assert f"""inside""" == 'inside'
assert f'''inside''' == 'inside'
assert f"\"{'inside'}\"" == '"inside"'
assert f'\'{"inside"}\'' == "'inside'"
assert f'{{10}}' == '{10}'
assert f'{{10 + 10}}' == '{10 + 10}'
assert f'{{{10 + 10}}}' == '{20}'
assert f'{{{{10 + 10}}}}' == '{{10 + 10}}'
def test_fstring_conversion() -> None:
assert f'Hello {var!r}' == "Hello 'mypyc'"
# repr() is equivalent to !r
assert f'Hello {repr(var)}' == "Hello 'mypyc'"
assert f'Hello {var!a}' == "Hello 'mypyc'"
# ascii() is equivalent to !a
assert f'Hello {ascii(var)}' == "Hello 'mypyc'"
tmp_str = """this
is a new line."""
assert f'Test: {tmp_str!a}' == "Test: 'this\\n is a new line.'"
s = 'test: āĀēĒčČ..šŠūŪžŽ'
assert f'{s}' == 'test: āĀēĒčČ..šŠūŪžŽ'
assert f'{s!a}' == "'test: \\u0101\\u0100\\u0113\\u0112\\u010d\\u010c..\\u0161\\u0160\\u016b\\u016a\\u017e\\u017d'"
assert f'Hello {var!s}' == 'Hello mypyc'
assert f'Hello {num!s}' == 'Hello 20'
def test_fstring_align() -> None:
assert f'Hello {var:>20}' == "Hello mypyc"
assert f'Hello {var!r:>20}' == "Hello 'mypyc'"
assert f'Hello {var:>{num}}' == "Hello mypyc"
assert f'Hello {var!r:>{num}}' == "Hello 'mypyc'"
def test_fstring_multi() -> None:
assert f'Hello {var}, hello again {var}' == "Hello mypyc, hello again mypyc"
a = 'py'
s = f'my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}my{a}'
assert s == 'mypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypymypy'
def test_fstring_python_doc() -> None:
name = 'Fred'
assert f"He said his name is {name!r}." == "He said his name is 'Fred'."
assert f"He said his name is {repr(name)}." == "He said his name is 'Fred'."
width = 10
precision = 4
value = decimal.Decimal('12.34567')
assert f'result: {value:{width}.{precision}}' == 'result: 12.35' # nested field
today = datetime(year=2017, month=1, day=27)
assert f'{today:%B %d, %Y}' == 'January 27, 2017' # using date format specifier
number = 1024
assert f'{number:#0x}' == '0x400' # using integer format specifier
[case testStringFormatMethod]
from typing import Tuple
def test_format_method_basics() -> None:
x = str()
assert 'x{}'.format(x) == 'x'
assert 'ā{}'.format(x) == 'ā'
assert '😀{}'.format(x) == '😀'
assert ''.format() == ''
assert 'abc'.format() == 'abc'
assert '{}{}'.format(1, 2) == '12'
name = 'Eric'
age = 14
assert "My name is {name}, I'm {age}.".format(name=name, age=age) == "My name is Eric, I'm 14."
assert "My name is {A}, I'm {B}.".format(A=name, B=age) == "My name is Eric, I'm 14."
assert "My name is {}, I'm {B}.".format(name, B=age) == "My name is Eric, I'm 14."
bool_var1 = True
bool_var2 = False
assert 'bool: {}, {}'.format(bool_var1, bool_var2) == 'bool: True, False'
def test_format_method_empty_braces() -> None:
name = 'Eric'
age = 14
assert 'Hello, {}!'.format(name) == 'Hello, Eric!'
assert '{}'.format(name) == 'Eric'
assert '{}! Hi!'.format(name) == 'Eric! Hi!'
assert '{}, Hi, {}'.format(name, name) == 'Eric, Hi, Eric'
assert 'Hi! {}'.format(name) == 'Hi! Eric'
assert "Hi, I'm {}. I'm {}.".format(name, age) == "Hi, I'm Eric. I'm 14."
assert '{{}}'.format() == '{}'
assert '{{{{}}}}'.format() == '{{}}'
assert '{{}}{}'.format(name) == '{}Eric'
assert 'Hi! {{{}}}'.format(name) == 'Hi! {Eric}'
assert 'Hi! {{ {}'.format(name) == 'Hi! { Eric'
assert 'Hi! {{ {} }}}}'.format(name) == 'Hi! { Eric }}'
def test_format_method_numbers() -> None:
s = 'int: {0:d}; hex: {0:x}; oct: {0:o}; bin: {0:b}'.format(-233)
assert s == 'int: -233; hex: -e9; oct: -351; bin: -11101001'
num = 2**65
s = 'int: {0:d}; hex: {0:x}; oct: {0:o}; bin: {0:b}'.format(num)
assert s == 'int: 36893488147419103232; hex: 20000000000000000; oct: 4000000000000000000000; bin: 100000000000000000000000000000000000000000000000000000000000000000'
s = 'int: {0:d}; hex: {0:x}; oct: {0:o}; bin: {0:b}'.format(-num)
assert s == 'int: -36893488147419103232; hex: -20000000000000000; oct: -4000000000000000000000; bin: -100000000000000000000000000000000000000000000000000000000000000000'
large_num = 2**65
assert 'number: {}'.format(large_num) == 'number: 36893488147419103232'
neg_num = -3
assert 'negative integer: {}'.format(neg_num) == 'negative integer: -3'
assert 'negative integer: {}'.format(-large_num) == 'negative integer: -36893488147419103232'
large_float = 1.23e30
large_float2 = 1234123412341234123400000000000000000
small_float = 1.23e-20
assert '{}, {}, {}'.format(small_float, large_float, large_float2) == '1.23e-20, 1.23e+30, 1234123412341234123400000000000000000'
nan_num = float('nan')
inf_num = float('inf')
assert '{}, {}'.format(nan_num, inf_num) == 'nan, inf'
def format_args(*args: int) -> str:
return 'x{}y{}'.format(*args)
def format_kwargs(**kwargs: int) -> str:
return 'c{x}d{y}'.format(**kwargs)
def format_args_self(*args: int) -> str:
return '{}'.format(args)
def format_kwargs_self(**kwargs: int) -> str:
return '{}'.format(kwargs)
def test_format_method_args() -> None:
assert format_args(10, 2) == 'x10y2'
assert format_args_self(10, 2) == '(10, 2)'
assert format_kwargs(x=10, y=2) == 'c10d2'
assert format_kwargs(x=10, y=2, z=1) == 'c10d2'
assert format_kwargs_self(x=10, y=2, z=1) == "{'x': 10, 'y': 2, 'z': 1}"
def test_format_method_different_kind() -> None:
s1 = "Literal['😀']"
assert 'Revealed type is {}'.format(s1) == "Revealed type is Literal['😀']"
s2 = "Revealed type is"
assert "{} Literal['😀']".format(s2) == "Revealed type is Literal['😀']"
s3 = "测试:"
assert "{}{} {}".format(s3, s2, s1) == "测试Revealed type is Literal['😀']"
assert "Test: {}{}".format(s3, s1) == "Test: 测试Literal['😀']"
assert "Test: {}{}".format(s3, s2) == "Test: 测试Revealed type is"
def test_format_method_nested() -> None:
var = 'mypyc'
num = 10
assert '{:{}}'.format(var, '') == 'mypyc'
assert '{:{}}'.format(var, '>10') == ' mypyc'
assert '{:{}}'.format(var, '>{}'.format(num)) == ' mypyc'
class Point:
def __init__(self, x, y):
self.x, self.y = x, y
def __str__(self):
return 'Point({self.x}, {self.y})'.format(self=self)
# Format examples from Python doc
# https://docs.python.org/3/library/string.html#formatexamples
def test_format_method_python_doc() -> None:
# Accessing arguments by position:
assert '{0}, {1}, {2}'.format('a', 'b', 'c') == 'a, b, c'
assert '{}, {}, {}'.format('a', 'b', 'c') == 'a, b, c'
assert '{2}, {1}, {0}'.format('a', 'b', 'c') == 'c, b, a'
assert '{2}, {1}, {0}'.format(*'abc') == 'c, b, a' # unpacking argument sequence
# assert '{0}{1}{0}'.format('abra', 'cad') = 'abracadabra' # arguments' indices can be repeated
# Accessing arguments by name:
s = 'Coordinates: {latitude}, {longitude}'.format(latitude='37.24N', longitude='-115.81W')
assert s == 'Coordinates: 37.24N, -115.81W'
coord = {'latitude': '37.24N', 'longitude': '-115.81W'}
assert 'Coordinates: {latitude}, {longitude}'.format(**coord) == 'Coordinates: 37.24N, -115.81W'
# Accessing arguments attributes:
assert str(Point(4, 2)) == 'Point(4, 2)'
# Accessing arguments items:
coord2 = (3, 5)
assert 'X: {0[0]}; Y: {0[1]}'.format(coord2) == 'X: 3; Y: 5'
# Replacing %s and %r:
s = "repr() shows quotes: {!r}; str() doesn't: {!s}".format('test1', 'test2')
assert s == "repr() shows quotes: 'test1'; str() doesn't: test2"
# Aligning the text and specifying a width:
assert '{:<30}'.format('left aligned') == 'left aligned '
assert '{:>30}'.format('right aligned') == ' right aligned'
assert '{:^30}'.format('centered') == ' centered '
assert '{:*^30}'.format('centered') == '***********centered***********' # use '*' as a fill char
# Replacing %+f, %-f, and % f and specifying a sign:
assert '{:+f}; {:+f}'.format(3.14, -3.14) == '+3.140000; -3.140000' # show it always
assert '{: f}; {: f}'.format(3.14, -3.14) == ' 3.140000; -3.140000' # show a space for positive numbers
assert '{:-f}; {:-f}'.format(3.14, -3.14) == '3.140000; -3.140000' # show only the minus -- same as '{:f}; {:f}'
# Replacing %x and %o and converting the value to different bases:
s = 'int: {0:d}; hex: {0:x}; oct: {0:o}; bin: {0:b}'.format(42) # format also supports binary numbers
assert s == 'int: 42; hex: 2a; oct: 52; bin: 101010'
s = 'int: {0:d}; hex: {0:#x}; oct: {0:#o}; bin: {0:#b}'.format(42) # with 0x, 0o, or 0b as prefix:
assert s == 'int: 42; hex: 0x2a; oct: 0o52; bin: 0b101010'
# Using the comma as a thousands separator:
assert '{:,}'.format(1234567890) == '1,234,567,890'
# Expressing a percentage:
points = 19.0
total = 22.0
assert 'Correct answers: {:.2%}'.format(points/total) == 'Correct answers: 86.36%'
# Using type-specific formatting:
import datetime
d = datetime.datetime(2010, 7, 4, 12, 15, 58)
assert '{:%Y-%m-%d %H:%M:%S}'.format(d) == '2010-07-04 12:15:58'
# Nesting arguments and more complex examples:
tmp_strs = []
for align, text in zip('<^>', ['left', 'center', 'right']):
tmp_strs.append('{0:{fill}{align}16}'.format(text, fill=align, align=align))
assert tmp_strs == ['left<<<<<<<<<<<<', '^^^^^center^^^^^', '>>>>>>>>>>>right']
octets = [192, 168, 0, 1]
assert '{:02X}{:02X}{:02X}{:02X}'.format(*octets) == 'C0A80001'
width = 5
tmp_strs = []
for num in range(5,12):
tmp_str = ''
for base in 'dXob':
tmp_str += ('{0:{width}{base}}'.format(num, base=base, width=width))
tmp_strs.append(tmp_str)
assert tmp_strs == [' 5 5 5 101',\
' 6 6 6 110',\
' 7 7 7 111',\
' 8 8 10 1000',\
' 9 9 11 1001',\
' 10 A 12 1010',\
' 11 B 13 1011']
[case testChr]
# Some test cases are from https://docs.python.org/3/howto/unicode.html
def try_invalid(x: int) -> bool:
try:
chr(x + int())
return False
except ValueError:
return True
def test_chr() -> None:
assert chr(57344) == '\ue000'
assert chr(0) == '\x00'
assert chr(65) == 'A'
assert chr(150) == '\x96'
try:
chr(-1)
assert False
except ValueError:
pass
try:
chr(1114112)
assert False
except ValueError:
pass
assert chr(1114111) == '\U0010ffff'
x = 0
assert chr(x + int()) == '\x00'
x = 100
assert chr(x + int()) == 'd'
x = 150
assert chr(x + int()) == '\x96'
x = 257
assert chr(x + int()) == 'ā'
x = 65537
assert chr(x + int()) == '𐀁'
assert try_invalid(-1)
assert try_invalid(1114112)
[case testOrd]
def test_ord() -> None:
assert ord('\ue000') == 57344
s = "a\xac\u1234\u20ac\U00008000"
# ^^^^ two-digit hex escape
# ^^^^^^ four-digit Unicode escape
# ^^^^^^^^^^ eight-digit Unicode escape
l1 = [ord(c) for c in s]
assert l1 == [97, 172, 4660, 8364, 32768]
u = 'abcdé'
assert ord(u[-1]) == 233
assert ord(b'a') == 97
assert ord(b'a' + bytes()) == 97
u2 = '\U0010ffff'
assert ord(u2) == 1114111
try:
ord('aa')
assert False
except TypeError:
pass
[case testDecode]
def test_decode() -> None:
assert "\N{GREEK CAPITAL LETTER DELTA}" == '\u0394'
assert "\u0394" == "\u0394"
assert "\U00000394" == '\u0394'
assert b'\x80abc'.decode('utf-8', 'replace') == '\ufffdabc'
assert b'\x80abc'.decode('utf-8', 'backslashreplace') == '\\x80abc'
assert b'abc'.decode() == 'abc'
assert b'abc'.decode('utf-8') == 'abc'
assert b'\x80abc'.decode('utf-8', 'ignore') == 'abc'
assert b'\x80abc'.decode('UTF-8', 'ignore') == 'abc'
assert b'\x80abc'.decode('Utf-8', 'ignore') == 'abc'
assert b'\x80abc'.decode('utf_8', 'ignore') == 'abc'
assert b'\x80abc'.decode('latin1', 'ignore') == '\x80abc'
assert b'\xd2\xbb\xb6\xfe\xc8\xfd'.decode('gbk', 'ignore') == '一二三'
assert b'\xd2\xbb\xb6\xfe\xc8\xfd'.decode('latin1', 'ignore') == 'Ò»¶þÈý'
assert b'Z\xc3\xbcrich'.decode("utf-8") == 'Zürich'
try:
b'Z\xc3\xbcrich'.decode('ascii')
assert False
except UnicodeDecodeError:
pass
assert bytearray(range(5)).decode() == '\x00\x01\x02\x03\x04'
b = bytearray(b'\xe4\xbd\xa0\xe5\xa5\xbd')
assert b.decode() == '你好'
assert b.decode('gbk') == '浣犲ソ'
assert b.decode('latin1') == 'ä½\xa0好'
[case testEncode]
from testutil import assertRaises
def test_encode() -> None:
u = chr(40960) + 'abcd' + chr(1972)
assert u.encode() == b'\xea\x80\x80abcd\xde\xb4'
assert u.encode('utf-8') == b'\xea\x80\x80abcd\xde\xb4'
with assertRaises(UnicodeEncodeError):
u.encode('ascii')
with assertRaises(LookupError):
u.encode('aaa')
assert u.encode('utf-8', 'aaaaaa') == b'\xea\x80\x80abcd\xde\xb4'
assert u.encode('ascii', 'ignore') == b'abcd'
assert u.encode('ASCII', 'ignore') == b'abcd'
assert u.encode('ascii', 'replace') == b'?abcd?'
assert u.encode('ascii', 'xmlcharrefreplace') == b'&#40960;abcd&#1972;'
assert u.encode('ascii', 'backslashreplace') == b'\\ua000abcd\\u07b4'
assert u.encode('ascii', 'namereplace') == b'\\N{YI SYLLABLE IT}abcd\\u07b4'
assert 'pythön!'.encode() == b'pyth\xc3\xb6n!'
assert '一二三'.encode('gbk') == b'\xd2\xbb\xb6\xfe\xc8\xfd'
assert u.encode('UTF-8', 'ignore') == b'\xea\x80\x80abcd\xde\xb4'
assert u.encode('Utf_8') == b'\xea\x80\x80abcd\xde\xb4'
assert u.encode('UTF_8') == b'\xea\x80\x80abcd\xde\xb4'
assert u'\u00E1'.encode('latin1') == b'\xe1'
with assertRaises(UnicodeEncodeError):
u.encode('latin1')