def test_hash(self):
schema = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
schema2 = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
self.assertEqual(hash(schema2), hash(schema))
def test_hash(self):
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
schema2 = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
assert hash(schema) == hash(schema2)
def get_schema(self) -> 'TableSchema':
"""
Returns the :class:`~pyflink.table.TableSchema` of this table.
:return: The schema of this table.
"""
return TableSchema(j_table_schema=self._j_table.getSchema())
def get_schema(self):
"""
Returns the :class:`TableSchema` of this table.
:return: The schema of this table.
"""
return TableSchema(j_table_schema=self._j_table.getSchema())
def test_get_field_count(self):
schema = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
count = schema.get_field_count()
self.assertEqual(3, count)
def get_schema(self):
"""
Get the schema of the table.
:return: Schema of the table/view.
"""
return TableSchema(j_table_schema=self._j_catalog_base_table.getSchema())
def test_get_field_names(self):
schema = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
names = schema.get_field_names()
self.assertEqual(["a", "b", "c"], names)
def test_get_schema(self):
t = self.t_env.from_elements([(1, 'Hi', 'Hello')], ['a', 'b', 'c'])
result = t.group_by(t.c).select(t.a.sum.alias('a'), t.c.alias('b'))
schema = result.get_schema()
assert schema == TableSchema(
["a", "b"],
[DataTypes.BIGINT(), DataTypes.STRING()])
def test_copy(self):
schema = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
copied_schema = schema.copy()
self.assertEqual(schema, copied_schema)
copied_schema._j_table_schema = None
self.assertNotEqual(schema, copied_schema)
def test_get_field_name(self):
schema = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
field_name = schema.get_field_name(2)
field_name_not_exist = schema.get_field_name(3)
self.assertEqual("c", field_name)
self.assertIsNone(field_name_not_exist)
def test_repr(self):
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
assert repr(
schema) == "root\n |-- a: INT\n |-- b: BIGINT\n |-- c: STRING\n"
def get_table_schema(self):
"""
Get the schema of result.
:return: The schema of result.
:rtype: pyflink.table.TableSchema
"""
return TableSchema(
j_table_schema=self._j_table_result.getTableSchema())
def test_init(self):
schema = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
self.assertEqual(3, schema.get_field_count())
self.assertEqual(["a", "b", "c"], schema.get_field_names())
self.assertEqual([DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()],
schema.get_field_data_types())
def test_repr(self):
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
expected = "root\n |-- a: INT\n |-- b: BIGINT\n |-- c: STRING\n"
self.assertEqual(expected, repr(schema))
def get_table_schema(self):
"""
Get the schema of result.
:return: The schema of result.
:rtype: pyflink.table.TableSchema
.. versionadded:: 1.11.0
"""
return TableSchema(j_table_schema=self._j_table_result.getTableSchema())
def test_get_field_names():
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
names = schema.get_field_names()
assert names == ["a", "b", "c"]
def test_get_field_count():
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
count = schema.get_field_count()
assert count == 3
def test_to_row_data_type(self):
schema = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
row_type = schema.to_row_data_type()
expected = DataTypes.ROW([DataTypes.FIELD("a", DataTypes.INT()),
DataTypes.FIELD("b", DataTypes.BIGINT()),
DataTypes.FIELD("c", DataTypes.STRING())])
self.assertEqual(expected, row_type)
def test_schema(self):
table_schema = TableSchema(["a", "b"], [DataTypes.INT(), DataTypes.STRING()])
schema = Schema().schema(table_schema)
properties = schema.to_properties()
expected = {'schema.0.name': 'a',
'schema.0.data-type': 'INT',
'schema.1.name': 'b',
'schema.1.data-type': 'VARCHAR(2147483647)'}
self.assertEqual(expected, properties)
def test_builder(self):
schema_builder = TableSchema.builder()
schema = schema_builder \
.field("a", DataTypes.INT())\
.field("b", DataTypes.BIGINT())\
.field("c", DataTypes.STRING()).build()
expected = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
self.assertEqual(expected, schema)
def test_get_field_name(self):
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
field_name = schema.get_field_name(2)
field_name_not_exist = schema.get_field_name(3)
assert field_name == "c"
assert field_name_not_exist is None
def test_copy(self):
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
copied_schema = schema.copy()
assert schema == copied_schema
copied_schema._j_table_schema = None
assert schema != copied_schema
def get_schema(self) -> TableSchema:
"""
Get the schema of the table.
:return: Schema of the table/view.
. note:: Deprecated in 1.14. This method returns the deprecated TableSchema class. The old
class was a hybrid of resolved and unresolved schema information. It has been replaced by
the new Schema which is always unresolved and will be resolved by the framework later.
"""
return TableSchema(
j_table_schema=self._j_catalog_base_table.getSchema())
def test_schema():
schema = Schema()
table_schema = TableSchema(["a", "b"], [DataTypes.INT(), DataTypes.STRING()])
schema = schema.schema(table_schema)
properties = schema.to_properties()
expected = {'schema.0.name': 'a',
'schema.0.type': 'INT',
'schema.1.name': 'b',
'schema.1.type': 'VARCHAR'}
assert properties == expected
def test_get_schema(self):
t_env = self.t_env
t = t_env.from_elements([(1, 'Hi', 'Hello'), (2, 'Hello', 'Hello'), (2, 'Hello', 'Hello')],
['a', 'b', 'c'])
field_names = ["a", "b"]
field_types = [DataTypes.BIGINT(), DataTypes.STRING()]
t_env.register_table_sink(
"Results",
field_names, field_types, source_sink_utils.TestRetractSink())
result = t.group_by("c").select("a.sum as a, c as b")
schema = result.get_schema()
assert schema == TableSchema(["a", "b"], [DataTypes.BIGINT(), DataTypes.STRING()])
def test_init(self):
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
assert schema.get_field_count() == 3
assert schema.get_field_names() == ["a", "b", "c"]
assert schema.get_field_data_types() == [
DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()
]
def test_get_field_data_types(self):
schema = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
types = schema.get_field_data_types()
assert types == [
DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()
]
def test_builder():
schema_builder = TableSchema.builder()
schema = schema_builder \
.field("a", DataTypes.INT())\
.field("b", DataTypes.BIGINT())\
.field("c", DataTypes.STRING()).build()
expected = TableSchema(
["a", "b", "c"],
[DataTypes.INT(),
DataTypes.BIGINT(),
DataTypes.STRING()])
assert schema == expected
def test_get_field_data_type(self):
schema = TableSchema(["a", "b", "c"],
[DataTypes.INT(), DataTypes.BIGINT(), DataTypes.STRING()])
type_by_name = schema.get_field_data_type("b")
type_by_index = schema.get_field_data_type(2)
type_by_name_not_exist = schema.get_field_data_type("d")
type_by_index_not_exist = schema.get_field_data_type(6)
with self.assertRaises(TypeError):
schema.get_field_data_type(None)
self.assertEqual(DataTypes.BIGINT(), type_by_name)
self.assertEqual(DataTypes.STRING(), type_by_index)
self.assertIsNone(type_by_name_not_exist)
self.assertIsNone(type_by_index_not_exist)
def test_schema(self):
csv = OldCsv()
schema = TableSchema(["a", "b"], [DataTypes.INT(), DataTypes.STRING()])
csv = csv.schema(schema)
properties = csv.to_properties()
expected = {'format.fields.0.name': 'a',
'format.fields.0.data-type': 'INT',
'format.fields.1.name': 'b',
'format.fields.1.data-type': 'VARCHAR(2147483647)',
'format.type': 'csv',
'format.property-version': '1'}
self.assertEqual(expected, properties)