def test_encode_numeric_overflow_nested(self):
class Nested(object):
x = 12839128391289382193812939
for _ in range(0, 100):
with pytest.raises(OverflowError):
ujson.encode(Nested())
def test_invalid_double_precision(self, invalid_val):
double_input = 30.12345678901234567890
expected_exception = (ValueError if isinstance(invalid_val, int)
else TypeError)
with pytest.raises(expected_exception):
ujson.encode(double_input, double_precision=invalid_val)
def test_array_reshaped(self, shape):
arr = np.arange(100)
arr = arr.reshape(shape)
tm.assert_numpy_array_equal(
np.array(ujson.decode(ujson.encode(arr))), arr)
tm.assert_numpy_array_equal(ujson.decode(
ujson.encode(arr), numpy=True), arr)
def test_array_basic(self):
arr = np.arange(96)
arr = arr.reshape((2, 2, 2, 2, 3, 2))
tm.assert_numpy_array_equal(
np.array(ujson.decode(ujson.encode(arr))), arr)
tm.assert_numpy_array_equal(ujson.decode(
ujson.encode(arr), numpy=True), arr)
def test_encode_big_set(self):
s = set()
for x in range(0, 100000):
s.add(x)
# Make sure no Exception is raised.
ujson.encode(s)
def test_encode_double_tiny_exponential(self):
num = 1e-40
assert num == ujson.decode(ujson.encode(num))
num = 1e-100
assert num == ujson.decode(ujson.encode(num))
num = -1e-45
assert num == ujson.decode(ujson.encode(num))
num = -1e-145
assert np.allclose(num, ujson.decode(ujson.encode(num)))
def test_series_nested(self, orient):
s = Series([10, 20, 30, 40, 50, 60], name="series",
index=[6, 7, 8, 9, 10, 15]).sort_values()
nested = {"s1": s, "s2": s.copy()}
kwargs = {} if orient is None else dict(orient=orient)
exp = {"s1": ujson.decode(ujson.encode(s, **kwargs)),
"s2": ujson.decode(ujson.encode(s, **kwargs))}
assert ujson.decode(ujson.encode(nested, **kwargs)) == exp
def test_dataframe_nested(self, orient):
df = DataFrame([[1, 2, 3], [4, 5, 6]], index=[
"a", "b"], columns=["x", "y", "z"])
nested = {"df1": df, "df2": df.copy()}
kwargs = {} if orient is None else dict(orient=orient)
exp = {"df1": ujson.decode(ujson.encode(df, **kwargs)),
"df2": ujson.decode(ujson.encode(df, **kwargs))}
assert ujson.decode(ujson.encode(nested, **kwargs)) == exp
def test_array_float(self):
dtype = np.float32
arr = np.arange(100.202, 200.202, 1, dtype=dtype)
arr = arr.reshape((5, 5, 4))
arr_out = np.array(ujson.decode(ujson.encode(arr)), dtype=dtype)
tm.assert_almost_equal(arr, arr_out)
arr_out = ujson.decode(ujson.encode(arr), numpy=True, dtype=dtype)
tm.assert_almost_equal(arr, arr_out)
def test_double_precision(self):
double_input = 30.012345678901234
output = ujson.encode(double_input, double_precision=15)
assert double_input == json.loads(output)
assert double_input == ujson.decode(output)
for double_precision in (3, 9):
output = ujson.encode(double_input,
double_precision=double_precision)
rounded_input = round(double_input, double_precision)
assert rounded_input == json.loads(output)
assert rounded_input == ujson.decode(output)
def test_encode_null_character(self):
wrapped_input = "31337 \x00 1337"
output = ujson.encode(wrapped_input)
assert wrapped_input == json.loads(output)
assert output == json.dumps(wrapped_input)
assert wrapped_input == ujson.decode(output)
alone_input = "\x00"
output = ujson.encode(alone_input)
assert alone_input == json.loads(output)
assert output == json.dumps(alone_input)
assert alone_input == ujson.decode(output)
assert '" \\u0000\\r\\n "' == ujson.dumps(u(" \u0000\r\n "))
def test_datetime_index(self):
date_unit = "ns"
rng = date_range("1/1/2000", periods=20)
encoded = ujson.encode(rng, date_unit=date_unit)
decoded = DatetimeIndex(np.array(ujson.decode(encoded)))
tm.assert_index_equal(rng, decoded)
ts = Series(np.random.randn(len(rng)), index=rng)
decoded = Series(ujson.decode(ujson.encode(ts, date_unit=date_unit)))
idx_values = decoded.index.values.astype(np.int64)
decoded.index = DatetimeIndex(idx_values)
tm.assert_series_equal(ts, decoded)
def test_default_handler(self):
class _TestObject(object):
def __init__(self, val):
self.val = val
@property
def recursive_attr(self):
return _TestObject("recursive_attr")
def __str__(self):
return str(self.val)
msg = "Maximum recursion level reached"
with pytest.raises(OverflowError, match=msg):
ujson.encode(_TestObject("foo"))
assert '"foo"' == ujson.encode(_TestObject("foo"),
default_handler=str)
def my_handler(_):
return "foobar"
assert '"foobar"' == ujson.encode(_TestObject("foo"),
default_handler=my_handler)
def my_handler_raises(_):
raise TypeError("I raise for anything")
with pytest.raises(TypeError, match="I raise for anything"):
ujson.encode(_TestObject("foo"), default_handler=my_handler_raises)
def my_int_handler(_):
return 42
assert ujson.decode(ujson.encode(_TestObject("foo"),
default_handler=my_int_handler)) == 42
def my_obj_handler(_):
return datetime.datetime(2013, 2, 3)
assert (ujson.decode(ujson.encode(datetime.datetime(2013, 2, 3))) ==
ujson.decode(ujson.encode(_TestObject("foo"),
default_handler=my_obj_handler)))
obj_list = [_TestObject("foo"), _TestObject("bar")]
assert (json.loads(json.dumps(obj_list, default=str)) ==
ujson.decode(ujson.encode(obj_list, default_handler=str)))
def test_encode_set(self):
s = {1, 2, 3, 4, 5, 6, 7, 8, 9}
enc = ujson.encode(s)
dec = ujson.decode(enc)
for v in dec:
assert v in s
def test_encode_long_conversion(self):
long_input = 9223372036854775807
output = ujson.encode(long_input)
assert long_input == json.loads(output)
assert output == json.dumps(long_input)
assert long_input == ujson.decode(output)
def test_dataframe(self, orient, numpy):
if orient == "records" and numpy:
pytest.skip("Not idiomatic pandas")
df = DataFrame([[1, 2, 3], [4, 5, 6]], index=[
"a", "b"], columns=["x", "y", "z"])
encode_kwargs = {} if orient is None else dict(orient=orient)
decode_kwargs = {} if numpy is None else dict(numpy=numpy)
output = ujson.decode(ujson.encode(df, **encode_kwargs),
**decode_kwargs)
# Ensure proper DataFrame initialization.
if orient == "split":
dec = _clean_dict(output)
output = DataFrame(**dec)
else:
output = DataFrame(output)
# Corrections to enable DataFrame comparison.
if orient == "values":
df.columns = [0, 1, 2]
df.index = [0, 1]
elif orient == "records":
df.index = [0, 1]
elif orient == "index":
df = df.transpose()
tm.assert_frame_equal(output, df, check_dtype=False)
def test_series(self, orient, numpy):
s = Series([10, 20, 30, 40, 50, 60], name="series",
index=[6, 7, 8, 9, 10, 15]).sort_values()
encode_kwargs = {} if orient is None else dict(orient=orient)
decode_kwargs = {} if numpy is None else dict(numpy=numpy)
output = ujson.decode(ujson.encode(s, **encode_kwargs),
**decode_kwargs)
if orient == "split":
dec = _clean_dict(output)
output = Series(**dec)
else:
output = Series(output)
if orient in (None, "index"):
s.name = None
output = output.sort_values()
s.index = ["6", "7", "8", "9", "10", "15"]
elif orient in ("records", "values"):
s.name = None
s.index = [0, 1, 2, 3, 4, 5]
tm.assert_series_equal(output, s, check_dtype=False)
def test_encode_string_conversion2(self):
string_input = "A string \\ / \b \f \n \r \t"
output = ujson.encode(string_input)
assert string_input == json.loads(output)
assert string_input == ujson.decode(output)
assert output == '"A string \\\\ \\/ \\b \\f \\n \\r \\t"'
def test_int_array(self, any_int_dtype):
arr = np.arange(100, dtype=np.int)
arr_input = arr.astype(any_int_dtype)
arr_output = np.array(ujson.decode(ujson.encode(arr_input)),
dtype=any_int_dtype)
tm.assert_numpy_array_equal(arr_input, arr_output)
def test_encode_control_escaping(self):
escaped_input = "\x19"
enc = ujson.encode(escaped_input)
dec = ujson.decode(enc)
assert escaped_input == dec
assert enc == json_unicode(escaped_input)
def test_encode_unicode_surrogate_pair(self):
surrogate_input = "\xf0\x90\x8d\x86"
enc = ujson.encode(surrogate_input)
dec = ujson.decode(enc)
assert enc == json_unicode(surrogate_input)
assert dec == json.loads(enc)
def test_encode_unicode_4bytes_utf8(self):
four_bytes_input = "\xf0\x91\x80\xb0TRAILINGNORMAL"
enc = ujson.encode(four_bytes_input)
dec = ujson.decode(enc)
assert enc == json_unicode(four_bytes_input)
assert dec == json.loads(enc)
def test_encode_datetime_conversion(self):
datetime_input = datetime.datetime.fromtimestamp(time.time())
output = ujson.encode(datetime_input, date_unit="s")
expected = calendar.timegm(datetime_input.utctimetuple())
assert int(expected) == json.loads(output)
assert int(expected) == ujson.decode(output)
def test_bool_array(self):
bool_array = np.array([
True, False, True, True,
False, True, False, False], dtype=np.bool)
output = np.array(ujson.decode(
ujson.encode(bool_array)), dtype=np.bool)
tm.assert_numpy_array_equal(bool_array, output)
def test_index(self):
i = Index([23, 45, 18, 98, 43, 11], name="index")
# Column indexed.
output = Index(ujson.decode(ujson.encode(i)), name="index")
tm.assert_index_equal(i, output)
output = Index(ujson.decode(ujson.encode(i), numpy=True), name="index")
tm.assert_index_equal(i, output)
dec = _clean_dict(ujson.decode(ujson.encode(i, orient="split")))
output = Index(**dec)
tm.assert_index_equal(i, output)
assert i.name == output.name
dec = _clean_dict(ujson.decode(ujson.encode(i, orient="split"),
numpy=True))
output = Index(**dec)
tm.assert_index_equal(i, output)
assert i.name == output.name
output = Index(ujson.decode(ujson.encode(i, orient="values")),
name="index")
tm.assert_index_equal(i, output)
output = Index(ujson.decode(ujson.encode(i, orient="values"),
numpy=True), name="index")
tm.assert_index_equal(i, output)
output = Index(ujson.decode(ujson.encode(i, orient="records")),
name="index")
tm.assert_index_equal(i, output)
output = Index(ujson.decode(ujson.encode(i, orient="records"),
numpy=True), name="index")
tm.assert_index_equal(i, output)
output = Index(ujson.decode(ujson.encode(i, orient="index")),
name="index")
tm.assert_index_equal(i, output)
output = Index(ujson.decode(ujson.encode(i, orient="index"),
numpy=True), name="index")
tm.assert_index_equal(i, output)
def test_float_array(self, float_dtype):
arr = np.arange(12.5, 185.72, 1.7322, dtype=np.float)
float_input = arr.astype(float_dtype)
float_output = np.array(ujson.decode(
ujson.encode(float_input, double_precision=15)),
dtype=float_dtype)
tm.assert_almost_equal(float_input, float_output)
def test_encode_unicode_4bytes_utf8highest(self):
four_bytes_input = "\xf3\xbf\xbf\xbfTRAILINGNORMAL"
enc = ujson.encode(four_bytes_input)
dec = ujson.decode(enc)
assert enc == json_unicode(four_bytes_input)
assert dec == json.loads(enc)
def test_datetime_units(self):
val = datetime.datetime(2013, 8, 17, 21, 17, 12, 215504)
stamp = Timestamp(val)
roundtrip = ujson.decode(ujson.encode(val, date_unit='s'))
assert roundtrip == stamp.value // 10**9
roundtrip = ujson.decode(ujson.encode(val, date_unit='ms'))
assert roundtrip == stamp.value // 10**6
roundtrip = ujson.decode(ujson.encode(val, date_unit='us'))
assert roundtrip == stamp.value // 10**3
roundtrip = ujson.decode(ujson.encode(val, date_unit='ns'))
assert roundtrip == stamp.value
pytest.raises(ValueError, ujson.encode, val, date_unit='foo')
def test_encode_recursion_max(self):
# 8 is the max recursion depth
class O2(object):
member = 0
pass
class O1(object):
member = 0
pass
decoded_input = O1()
decoded_input.member = O2()
decoded_input.member.member = decoded_input
with pytest.raises(OverflowError):
ujson.encode(decoded_input)
def test_encode_to_utf8(self):
unencoded = "\xe6\x97\xa5\xd1\x88"
enc = ujson.encode(unencoded, ensure_ascii=False)
dec = ujson.decode(enc)
assert enc == json_unicode(unencoded, ensure_ascii=False)
assert dec == json.loads(enc)
def test_encode_as_null(self, decoded_input):
assert ujson.encode(decoded_input) == "null", "Expected null"
def test_float_max(self, float_dtype):
klass = np.dtype(float_dtype).type
num = klass(np.finfo(float_dtype).max / 10)
tm.assert_almost_equal(
klass(ujson.decode(ujson.encode(num, double_precision=15))), num)
def test_encode_unicode_4bytes_utf8_fail(self):
with pytest.raises(OverflowError):
ujson.encode("\xfd\xbf\xbf\xbf\xbf\xbf")
def test_encode_big_escape(self):
# Make sure no Exception is raised.
for _ in range(10):
base = '\u00e5'.encode("utf-8") if compat.PY3 else "\xc3\xa5"
escape_input = base * 1024 * 1024 * 2
ujson.encode(escape_input)
def test_encode_empty_set(self):
assert "[]" == ujson.encode(set())
def test_encode_timedelta_iso(self, td):
# GH 28256
result = ujson.encode(td, iso_dates=True)
expected = f'"{td.isoformat()}"'
assert result == expected
def test_encode_dict_with_unicode_keys(self, unicode_key):
unicode_dict = {unicode_key: "value1"}
assert unicode_dict == ujson.decode(ujson.encode(unicode_dict))
def test_encode_with_decimal(self):
decimal_input = 1.0
output = ujson.encode(decimal_input)
assert output == "1.0"
def test_encode_big_escape(self):
# Make sure no Exception is raised.
for _ in range(10):
base = "\u00e5".encode()
escape_input = base * 1024 * 1024 * 2
ujson.encode(escape_input)
def test_bool(self, bool_input):
b = bool(bool_input)
assert ujson.decode(ujson.encode(b)) == b
def test_bool_array(self):
bool_array = np.array(
[True, False, True, True, False, True, False, False], dtype=bool)
output = np.array(ujson.decode(ujson.encode(bool_array)), dtype=bool)
tm.assert_numpy_array_equal(bool_array, output)
def test_int(self, any_int_dtype):
klass = np.dtype(any_int_dtype).type
num = klass(1)
assert klass(ujson.decode(ujson.encode(num))) == num
def test_encode_time_conversion_pytz(self):
# see gh-11473: to_json segfaults with timezone-aware datetimes
test = datetime.time(10, 12, 15, 343243, pytz.utc)
output = ujson.encode(test)
expected = '"{iso}"'.format(iso=test.isoformat())
assert expected == output
def test_double_long_numbers(self, long_number):
sut = {"a": long_number}
encoded = ujson.encode(sut, double_precision=15)
decoded = ujson.decode(encoded)
assert sut == decoded
def test_encode_time_conversion_dateutil(self):
# see gh-11473: to_json segfaults with timezone-aware datetimes
test = datetime.time(10, 12, 15, 343243, dateutil.tz.tzutc())
output = ujson.encode(test)
expected = f'"{test.isoformat()}"'
assert expected == output
def test_encode_time_conversion_basic(self, test):
output = ujson.encode(test)
expected = f'"{test.isoformat()}"'
assert expected == output
def test_encode_double_conversion(self, double_input):
output = ujson.encode(double_input)
assert round(double_input, 5) == round(json.loads(output), 5)
assert round(double_input, 5) == round(ujson.decode(output), 5)
def test_array_reshaped(self, shape):
arr = np.arange(100)
arr = arr.reshape(shape)
tm.assert_numpy_array_equal(np.array(ujson.decode(ujson.encode(arr))), arr)
tm.assert_numpy_array_equal(ujson.decode(ujson.encode(arr), numpy=True), arr)
def test_decimal_decode_test_precise(self):
sut = {"a": 4.56}
encoded = ujson.encode(sut)
decoded = ujson.decode(encoded, precise_float=True)
assert sut == decoded
def test_invalid_double_precision(self, invalid_val):
double_input = 30.12345678901234567890
expected_exception = ValueError if isinstance(invalid_val, int) else TypeError
with pytest.raises(expected_exception):
ujson.encode(double_input, double_precision=invalid_val)
def test_encode_builtin_values_conversion(self, builtin_value):
output = ujson.encode(builtin_value)
assert builtin_value == json.loads(output)
assert output == json.dumps(builtin_value)
assert builtin_value == ujson.decode(output)
def test_0d_array(self):
# gh-18878
msg = re.escape(
"array(1) (0d array) is not JSON serializable at the moment")
with pytest.raises(TypeError, match=msg):
ujson.encode(np.array(1))
def test_array_basic(self):
arr = np.arange(96)
arr = arr.reshape((2, 2, 2, 2, 3, 2))
tm.assert_numpy_array_equal(np.array(ujson.decode(ujson.encode(arr))), arr)
tm.assert_numpy_array_equal(ujson.decode(ujson.encode(arr), numpy=True), arr)
def test_encode_dict_conversion(self):
dict_input = {"k1": 1, "k2": 2, "k3": 3, "k4": 4}
output = ujson.encode(dict_input)
assert dict_input == json.loads(output)
assert dict_input == ujson.decode(output)
def test_0d_array(self):
with pytest.raises(TypeError):
ujson.encode(np.array(1))
def test_encode_num_conversion(self, num_input):
output = ujson.encode(num_input)
assert num_input == json.loads(output)
assert output == json.dumps(num_input)
assert num_input == ujson.decode(output)
def test_encode_numeric_overflow(self):
with pytest.raises(OverflowError):
ujson.encode(12839128391289382193812939)
def test_encode_unicode_conversion(self, unicode_input):
enc = ujson.encode(unicode_input)
dec = ujson.decode(enc)
assert enc == json.dumps(unicode_input)
assert dec == json.loads(enc)
def test_encode_time_conversion_basic(self, test):
output = ujson.encode(test)
expected = '"{iso}"'.format(iso=test.isoformat())
assert expected == output
def test_float(self, float_dtype):
klass = np.dtype(float_dtype).type
num = klass(256.2013)
assert klass(ujson.decode(ujson.encode(num))) == num
