Python pyarrow.string函数代码示例

def test_table_safe_casting():
    data = [
        pa.array(range(5), type=pa.int64()),
        pa.array([-10, -5, 0, 5, 10], type=pa.int32()),
        pa.array([1.0, 2.0, 3.0, 4.0, 5.0], type=pa.float64()),
        pa.array(['ab', 'bc', 'cd', 'de', 'ef'], type=pa.string())
    ]
    table = pa.Table.from_arrays(data, names=tuple('abcd'))

    expected_data = [
        pa.array(range(5), type=pa.int32()),
        pa.array([-10, -5, 0, 5, 10], type=pa.int16()),
        pa.array([1, 2, 3, 4, 5], type=pa.int64()),
        pa.array(['ab', 'bc', 'cd', 'de', 'ef'], type=pa.string())
    ]
    expected_table = pa.Table.from_arrays(expected_data, names=tuple('abcd'))

    target_schema = pa.schema([
        pa.field('a', pa.int32()),
        pa.field('b', pa.int16()),
        pa.field('c', pa.int64()),
        pa.field('d', pa.string())
    ])
    casted_table = table.cast(target_schema)

    assert casted_table.equals(expected_table)

def test_table_unsafe_casting():
    data = [
        pa.array(range(5), type=pa.int64()),
        pa.array([-10, -5, 0, 5, 10], type=pa.int32()),
        pa.array([1.1, 2.2, 3.3, 4.4, 5.5], type=pa.float64()),
        pa.array(['ab', 'bc', 'cd', 'de', 'ef'], type=pa.string())
    ]
    table = pa.Table.from_arrays(data, names=tuple('abcd'))

    expected_data = [
        pa.array(range(5), type=pa.int32()),
        pa.array([-10, -5, 0, 5, 10], type=pa.int16()),
        pa.array([1, 2, 3, 4, 5], type=pa.int64()),
        pa.array(['ab', 'bc', 'cd', 'de', 'ef'], type=pa.string())
    ]
    expected_table = pa.Table.from_arrays(expected_data, names=tuple('abcd'))

    target_schema = pa.schema([
        pa.field('a', pa.int32()),
        pa.field('b', pa.int16()),
        pa.field('c', pa.int64()),
        pa.field('d', pa.string())
    ])

    with pytest.raises(pa.ArrowInvalid,
                       match='Floating point value truncated'):
        table.cast(target_schema)

    casted_table = table.cast(target_schema, safe=False)
    assert casted_table.equals(expected_table)

def test_cast_from_null():
    in_data = [None] * 3
    in_type = pa.null()
    out_types = [
        pa.null(),
        pa.uint8(),
        pa.float16(),
        pa.utf8(),
        pa.binary(),
        pa.binary(10),
        pa.list_(pa.int16()),
        pa.decimal128(19, 4),
        pa.timestamp('us'),
        pa.timestamp('us', tz='UTC'),
        pa.timestamp('us', tz='Europe/Paris'),
        pa.struct([pa.field('a', pa.int32()),
                   pa.field('b', pa.list_(pa.int8())),
                   pa.field('c', pa.string())]),
        ]
    for out_type in out_types:
        _check_cast_case((in_data, in_type, in_data, out_type))

    out_types = [
        pa.dictionary(pa.int32(), pa.string()),
        pa.union([pa.field('a', pa.binary(10)),
                  pa.field('b', pa.string())], mode=pa.lib.UnionMode_DENSE),
        pa.union([pa.field('a', pa.binary(10)),
                  pa.field('b', pa.string())], mode=pa.lib.UnionMode_SPARSE),
        ]
    in_arr = pa.array(in_data, type=pa.null())
    for out_type in out_types:
        with pytest.raises(NotImplementedError):
            in_arr.cast(out_type)

def test_type_schema_pickling():
    cases = [
        pa.int8(),
        pa.string(),
        pa.binary(),
        pa.binary(10),
        pa.list_(pa.string()),
        pa.struct([
            pa.field('a', 'int8'),
            pa.field('b', 'string')
        ]),
        pa.time32('s'),
        pa.time64('us'),
        pa.date32(),
        pa.date64(),
        pa.timestamp('ms'),
        pa.timestamp('ns'),
        pa.decimal(12, 2),
        pa.field('a', 'string', metadata={b'foo': b'bar'})
    ]

    for val in cases:
        roundtripped = pickle.loads(pickle.dumps(val))
        assert val == roundtripped

    fields = []
    for i, f in enumerate(cases):
        if isinstance(f, pa.Field):
            fields.append(f)
        else:
            fields.append(pa.field('_f{}'.format(i), f))

    schema = pa.schema(fields, metadata={b'foo': b'bar'})
    roundtripped = pickle.loads(pickle.dumps(schema))
    assert schema == roundtripped

def test_orcfile_empty():
    from pyarrow import orc
    f = orc.ORCFile(path_for_orc_example('TestOrcFile.emptyFile'))
    table = f.read()
    assert table.num_rows == 0
    schema = table.schema
    expected_schema = pa.schema([
        ('boolean1', pa.bool_()),
        ('byte1', pa.int8()),
        ('short1', pa.int16()),
        ('int1', pa.int32()),
        ('long1', pa.int64()),
        ('float1', pa.float32()),
        ('double1', pa.float64()),
        ('bytes1', pa.binary()),
        ('string1', pa.string()),
        ('middle', pa.struct([
            ('list', pa.list_(pa.struct([
                ('int1', pa.int32()),
                ('string1', pa.string()),
                ]))),
            ])),
        ('list', pa.list_(pa.struct([
            ('int1', pa.int32()),
            ('string1', pa.string()),
            ]))),
        ('map', pa.list_(pa.struct([
            ('key', pa.string()),
            ('value', pa.struct([
                ('int1', pa.int32()),
                ('string1', pa.string()),
                ])),
            ]))),
        ])
    assert schema == expected_schema

def test_schema():
    fields = [
        pa.field('foo', pa.int32()),
        pa.field('bar', pa.string()),
        pa.field('baz', pa.list_(pa.int8()))
    ]
    sch = pa.schema(fields)

    assert sch.names == ['foo', 'bar', 'baz']
    assert sch.types == [pa.int32(), pa.string(), pa.list_(pa.int8())]

    assert len(sch) == 3
    assert sch[0].name == 'foo'
    assert sch[0].type == fields[0].type
    assert sch.field_by_name('foo').name == 'foo'
    assert sch.field_by_name('foo').type == fields[0].type

    assert repr(sch) == """\
foo: int32
bar: string
baz: list<item: int8>
  child 0, item: int8"""

    with pytest.raises(TypeError):
        pa.schema([None])

    def test_custom_nulls(self):
        # Infer nulls with custom values
        opts = ConvertOptions(null_values=['Xxx', 'Zzz'])
        rows = b"a,b,c,d\nZzz,Xxx,1,2\nXxx,#N/A,,Zzz\n"
        table = self.read_bytes(rows, convert_options=opts)
        schema = pa.schema([('a', pa.null()),
                            ('b', pa.string()),
                            ('c', pa.string()),
                            ('d', pa.int64())])
        assert table.schema == schema
        assert table.to_pydict() == {
            'a': [None, None],
            'b': [u"Xxx", u"#N/A"],
            'c': [u"1", u""],
            'd': [2, None],
            }

        opts = ConvertOptions(null_values=[])
        rows = b"a,b\n#N/A,\n"
        table = self.read_bytes(rows, convert_options=opts)
        schema = pa.schema([('a', pa.string()),
                            ('b', pa.string())])
        assert table.schema == schema
        assert table.to_pydict() == {
            'a': [u"#N/A"],
            'b': [u""],
            }

def test_is_binary_string():
    assert types.is_binary(pa.binary())
    assert not types.is_binary(pa.string())

    assert types.is_string(pa.string())
    assert types.is_unicode(pa.string())
    assert not types.is_string(pa.binary())

    assert types.is_fixed_size_binary(pa.binary(5))
    assert not types.is_fixed_size_binary(pa.binary())

def test_sequence_utf8_to_unicode():
    # ARROW-1225
    data = [b'foo', None, b'bar']
    arr = pa.array(data, type=pa.string())
    assert arr[0].as_py() == u'foo'

    # test a non-utf8 unicode string
    val = (u'mañana').encode('utf-16-le')
    with pytest.raises(pa.ArrowInvalid):
        pa.array([val], type=pa.string())

def test_convert_options():
    cls = ConvertOptions
    opts = cls()

    assert opts.check_utf8 is True
    opts.check_utf8 = False
    assert opts.check_utf8 is False

    assert opts.strings_can_be_null is False
    opts.strings_can_be_null = True
    assert opts.strings_can_be_null is True

    assert opts.column_types == {}
    # Pass column_types as mapping
    opts.column_types = {'b': pa.int16(), 'c': pa.float32()}
    assert opts.column_types == {'b': pa.int16(), 'c': pa.float32()}
    opts.column_types = {'v': 'int16', 'w': 'null'}
    assert opts.column_types == {'v': pa.int16(), 'w': pa.null()}
    # Pass column_types as schema
    schema = pa.schema([('a', pa.int32()), ('b', pa.string())])
    opts.column_types = schema
    assert opts.column_types == {'a': pa.int32(), 'b': pa.string()}
    # Pass column_types as sequence
    opts.column_types = [('x', pa.binary())]
    assert opts.column_types == {'x': pa.binary()}

    with pytest.raises(TypeError, match='DataType expected'):
        opts.column_types = {'a': None}
    with pytest.raises(TypeError):
        opts.column_types = 0

    assert isinstance(opts.null_values, list)
    assert '' in opts.null_values
    assert 'N/A' in opts.null_values
    opts.null_values = ['xxx', 'yyy']
    assert opts.null_values == ['xxx', 'yyy']

    assert isinstance(opts.true_values, list)
    opts.true_values = ['xxx', 'yyy']
    assert opts.true_values == ['xxx', 'yyy']

    assert isinstance(opts.false_values, list)
    opts.false_values = ['xxx', 'yyy']
    assert opts.false_values == ['xxx', 'yyy']

    opts = cls(check_utf8=False, column_types={'a': pa.null()},
               null_values=['N', 'nn'], true_values=['T', 'tt'],
               false_values=['F', 'ff'], strings_can_be_null=True)
    assert opts.check_utf8 is False
    assert opts.column_types == {'a': pa.null()}
    assert opts.null_values == ['N', 'nn']
    assert opts.false_values == ['F', 'ff']
    assert opts.true_values == ['T', 'tt']
    assert opts.strings_can_be_null is True

def test_schema_equals_propagates_check_metadata():
    # ARROW-4088
    schema1 = pa.schema([
        pa.field('foo', pa.int32()),
        pa.field('bar', pa.string())
    ])
    schema2 = pa.schema([
        pa.field('foo', pa.int32()),
        pa.field('bar', pa.string(), metadata={'a': 'alpha'}),
    ])
    assert not schema1.equals(schema2)
    assert schema1.equals(schema2, check_metadata=False)

def test_table_pickle():
    data = [
        pa.chunked_array([[1, 2], [3, 4]], type=pa.uint32()),
        pa.chunked_array([["some", "strings", None, ""]], type=pa.string()),
    ]
    schema = pa.schema([pa.field('ints', pa.uint32()),
                        pa.field('strs', pa.string())],
                       metadata={b'foo': b'bar'})
    table = pa.Table.from_arrays(data, schema=schema)

    result = pickle.loads(pickle.dumps(table))
    result._validate()
    assert result.equals(table)

def test_array_mixed_unicode_bytes():
    values = [u'qux', b'foo', bytearray(b'barz')]
    b_values = [b'qux', b'foo', b'barz']
    u_values = [u'qux', u'foo', u'barz']

    arr = pa.array(values)
    expected = pa.array(b_values, type=pa.binary())
    assert arr.type == pa.binary()
    assert arr.equals(expected)

    arr = pa.array(values, type=pa.string())
    expected = pa.array(u_values, type=pa.string())
    assert arr.type == pa.string()
    assert arr.equals(expected)

 def test_unicode(self):
     data = [u("foo"), u("bar"), None, u("arrow")]
     arr = pyarrow.from_pylist(data)
     assert len(arr) == 4
     assert arr.null_count == 1
     assert arr.type == pyarrow.string()
     assert arr.to_pylist() == [u("foo"), u("bar"), None, u("arrow")]

def test_struct_from_tuples():
    ty = pa.struct([pa.field('a', pa.int32()),
                    pa.field('b', pa.string()),
                    pa.field('c', pa.bool_())])

    data = [(5, 'foo', True),
            (6, 'bar', False)]
    expected = [{'a': 5, 'b': 'foo', 'c': True},
                {'a': 6, 'b': 'bar', 'c': False}]
    arr = pa.array(data, type=ty)

    data_as_ndarray = np.empty(len(data), dtype=object)
    data_as_ndarray[:] = data
    arr2 = pa.array(data_as_ndarray, type=ty)
    assert arr.to_pylist() == expected

    assert arr.equals(arr2)

    # With omitted values
    data = [(5, 'foo', None),
            None,
            (6, None, False)]
    expected = [{'a': 5, 'b': 'foo', 'c': None},
                None,
                {'a': 6, 'b': None, 'c': False}]
    arr = pa.array(data, type=ty)
    assert arr.to_pylist() == expected

    # Invalid tuple size
    for tup in [(5, 'foo'), (), ('5', 'foo', True, None)]:
        with pytest.raises(ValueError, match="(?i)tuple size"):
            pa.array([tup], type=ty)