def test_text_zero_chunks_valid(self):
validate_table_metadata(
pyarrow.Table.from_batches([],
pyarrow.schema([("A", pyarrow.string())
])),
TableMetadata(0, [Text("A")]),
)
def test_duplicate_column_name(self):
with self.assertRaises(DuplicateColumnName):
validate_table_metadata(
pyarrow.Table.from_arrays(
[pyarrow.array(["a"]),
pyarrow.array(["b"])], ["A", "A"]),
TableMetadata(1, [Text("A"), Text("A")]),
)
def test_column_name_mismatch(self):
with self.assertRaises(WrongColumnName):
validate_table_metadata(
pyarrow.table({
"A": ["a"],
"B": ["b"]
}),
TableMetadata(1, [Text("A"), Text("B2")]),
)
def test_text_dictionary_zero_chunks_is_valid(self):
validate_table_metadata(
pyarrow.Table.from_batches(
[],
pyarrow.schema([("A",
pyarrow.dictionary(pyarrow.int32(),
pyarrow.string()))]),
),
TableMetadata(0, [Text("A")]),
)
def test_table_not_one_batch(self):
with self.assertRaises(TableHasTooManyRecordBatches):
validate_table_metadata(
pyarrow.Table.from_batches([
pyarrow.RecordBatch.from_arrays([pyarrow.array(["a"])],
["A"]),
pyarrow.RecordBatch.from_arrays([pyarrow.array(["b"])],
["A"]),
]),
TableMetadata(2, [Text("A")]),
)
def test_column_datetime_must_be_ns_resolution(self):
# [2019-09-17] Pandas only supports datetime64[ns]
# https://github.com/pandas-dev/pandas/issues/7307#issuecomment-224180563
with self.assertRaises(DatetimeUnitNotAllowed):
validate_table_metadata(
pyarrow.table({
"A":
pyarrow.array([5298375234],
type=pyarrow.timestamp("us", tz=None))
}),
TableMetadata(1, [Datetime("A")]),
)
def test_column_datetime_should_be_tz_naive(self):
with self.assertRaises(DatetimeTimezoneNotAllowed):
validate_table_metadata(
pyarrow.table({
"A":
pyarrow.array(
[5298375234123],
type=pyarrow.timestamp("ns", "America/New_York"),
)
}),
TableMetadata(1, [Datetime("A")]),
)
def test_table_wrong_number_of_rows(self):
with self.assertRaises(WrongRowCount):
validate_table_metadata(pyarrow.Table.from_pydict({"A": ["x"]}),
TableMetadata(2, [Text("A")]))
def test_table_not_none_when_should_be_none(self):
with self.assertRaises(TableShouldBeNone):
validate_table_metadata(pyarrow.Table.from_arrays([]),
TableMetadata(2, []))
def test_table_none_when_should_be_set(self):
with self.assertRaises(WrongColumnCount):
validate_table_metadata(None, TableMetadata(2, [Text("A")]))
def test_happy_path_table_is_none(self):
validate_table_metadata(None, TableMetadata(2, []))
def test_column_str_should_be_datetime(self):
with self.assertRaises(WrongColumnType):
validate_table_metadata(pyarrow.table({"A": ["x"]}),
TableMetadata(1, [Datetime("A")]))
def test_column_int_should_be_text(self):
with self.assertRaises(WrongColumnType):
validate_table_metadata(pyarrow.table({"A": [1]}),
TableMetadata(1, [Text("A")]))