def run_mssql_job():
where_clause_suffix = textwrap.dedent("""
('dbo')
""")
tmp_folder = '/var/tmp/amundsen/table_metadata'
node_files_folder = '{tmp_folder}/nodes/'.format(tmp_folder=tmp_folder)
relationship_files_folder = '{tmp_folder}/relationships/'.format(tmp_folder=tmp_folder)
job_config = ConfigFactory.from_dict({
#'extractor.mssql_metadata.{}'.format(MSSQLMetadataExtractor.WHERE_CLAUSE_SUFFIX_KEY):
# where_clause_suffix,
'extractor.mssql_metadata.{}'.format(MSSQLMetadataExtractor.USE_CATALOG_AS_CLUSTER_NAME):
True,
'extractor.mssql_metadata.extractor.sqlalchemy.{}'.format(SQLAlchemyExtractor.CONN_STRING):
connection_string(),
'loader.filesystem_csv_neo4j.{}'.format(FsNeo4jCSVLoader.NODE_DIR_PATH):
node_files_folder,
'loader.filesystem_csv_neo4j.{}'.format(FsNeo4jCSVLoader.RELATION_DIR_PATH):
relationship_files_folder,
'publisher.neo4j.{}'.format(neo4j_csv_publisher.NODE_FILES_DIR):
node_files_folder,
'publisher.neo4j.{}'.format(neo4j_csv_publisher.RELATION_FILES_DIR):
relationship_files_folder,
'publisher.neo4j.{}'.format(neo4j_csv_publisher.NEO4J_END_POINT_KEY):
neo4j_endpoint,
'publisher.neo4j.{}'.format(neo4j_csv_publisher.NEO4J_USER):
neo4j_user,
'publisher.neo4j.{}'.format(neo4j_csv_publisher.NEO4J_PASSWORD):
neo4j_password,
'publisher.neo4j.{}'.format(neo4j_csv_publisher.JOB_PUBLISH_TAG):
'unique_tag', # should use unique tag here like {ds}
})
job = DefaultJob(conf=job_config,
task=DefaultTask(extractor=MSSQLMetadataExtractor(), loader=FsNeo4jCSVLoader()),
publisher=Neo4jCsvPublisher())
return job
def test_extraction_with_single_result(self):
# type: () -> None
with patch.object(SQLAlchemyExtractor,
'_get_connection') as mock_connection:
connection = MagicMock()
mock_connection.return_value = connection
sql_execute = MagicMock()
connection.execute = sql_execute
table = {
'schema_name':
'test_schema',
'name':
'test_table',
'description':
'a table for testing',
'cluster':
self.conf['extractor.mssql_metadata.{}'.format(
MSSQLMetadataExtractor.CLUSTER_KEY)]
}
sql_execute.return_value = [
self._union(
{
'col_name': 'col_id1',
'col_type': 'bigint',
'col_description': 'description of id1',
'col_sort_order': 0
}, table),
self._union(
{
'col_name': 'col_id2',
'col_type': 'bigint',
'col_description': 'description of id2',
'col_sort_order': 1
}, table),
self._union(
{
'col_name': 'is_active',
'col_type': 'boolean',
'col_description': None,
'col_sort_order': 2
}, table),
self._union(
{
'col_name': 'source',
'col_type': 'varchar',
'col_description': 'description of source',
'col_sort_order': 3
}, table),
self._union(
{
'col_name': 'etl_created_at',
'col_type': 'timestamp',
'col_description': 'description of etl_created_at',
'col_sort_order': 4
}, table),
self._union(
{
'col_name': 'ds',
'col_type': 'varchar',
'col_description': None,
'col_sort_order': 5
}, table)
]
extractor = MSSQLMetadataExtractor()
extractor.init(self.conf)
actual = extractor.extract()
expected = TableMetadata(
'mssql', 'MY_CLUSTER', 'test_schema', 'test_table',
'a table for testing', [
ColumnMetadata('col_id1', 'description of id1', 'bigint',
0),
ColumnMetadata('col_id2', 'description of id2', 'bigint',
1),
ColumnMetadata('is_active', None, 'boolean', 2),
ColumnMetadata('source', 'description of source',
'varchar', 3),
ColumnMetadata('etl_created_at',
'description of etl_created_at',
'timestamp', 4),
ColumnMetadata('ds', None, 'varchar', 5)
], False, ['test_schema'])
self.assertEqual(expected.__repr__(), actual.__repr__())
self.assertIsNone(extractor.extract())
def test_extraction_with_multiple_result(self) -> None:
with patch.object(SQLAlchemyExtractor, '_get_connection') as mock_connection:
connection = MagicMock()
mock_connection.return_value = connection
sql_execute = MagicMock()
connection.execute = sql_execute
table = {'schema_name': 'test_schema1',
'name': 'test_table1',
'description': 'test table 1',
'cluster':
self.conf[f'extractor.mssql_metadata.{MSSQLMetadataExtractor.CLUSTER_KEY}']
}
table1 = {'schema_name': 'test_schema1',
'name': 'test_table2',
'description': 'test table 2',
'cluster':
self.conf[f'extractor.mssql_metadata.{MSSQLMetadataExtractor.CLUSTER_KEY}']
}
table2 = {'schema_name': 'test_schema2',
'name': 'test_table3',
'description': 'test table 3',
'cluster':
self.conf[f'extractor.mssql_metadata.{MSSQLMetadataExtractor.CLUSTER_KEY}']
}
sql_execute.return_value = [
self._union(
{'col_name': 'col_id1',
'col_type': 'bigint',
'col_description': 'description of col_id1',
'col_sort_order': 0}, table),
self._union(
{'col_name': 'col_id2',
'col_type': 'bigint',
'col_description': 'description of col_id2',
'col_sort_order': 1}, table),
self._union(
{'col_name': 'is_active',
'col_type': 'boolean',
'col_description': None,
'col_sort_order': 2}, table),
self._union(
{'col_name': 'source',
'col_type': 'varchar',
'col_description': 'description of source',
'col_sort_order': 3}, table),
self._union(
{'col_name': 'etl_created_at',
'col_type': 'timestamp',
'col_description': 'description of etl_created_at',
'col_sort_order': 4}, table),
self._union(
{'col_name': 'ds',
'col_type': 'varchar',
'col_description': None,
'col_sort_order': 5}, table),
self._union(
{'col_name': 'col_name',
'col_type': 'varchar',
'col_description': 'description of col_name',
'col_sort_order': 0}, table1),
self._union(
{'col_name': 'col_name2',
'col_type': 'varchar',
'col_description': 'description of col_name2',
'col_sort_order': 1}, table1),
self._union(
{'col_name': 'col_id3',
'col_type': 'varchar',
'col_description': 'description of col_id3',
'col_sort_order': 0}, table2),
self._union(
{'col_name': 'col_name3',
'col_type': 'varchar',
'col_description': 'description of col_name3',
'col_sort_order': 1}, table2)
]
extractor = MSSQLMetadataExtractor()
extractor.init(self.conf)
expected = TableMetadata(
'mssql',
self.conf[f'extractor.mssql_metadata.{MSSQLMetadataExtractor.CLUSTER_KEY}'],
'test_schema1', 'test_table1', 'test table 1',
[ColumnMetadata('col_id1', 'description of col_id1', 'bigint', 0),
ColumnMetadata('col_id2', 'description of col_id2', 'bigint', 1),
ColumnMetadata('is_active', None, 'boolean', 2),
ColumnMetadata('source', 'description of source', 'varchar', 3),
ColumnMetadata('etl_created_at', 'description of etl_created_at', 'timestamp', 4),
ColumnMetadata('ds', None, 'varchar', 5),
],
False, ['test_schema1']
)
actual = extractor.extract().__repr__()
self.assertEqual(expected.__repr__(), actual)
expected = TableMetadata(
'mssql',
self.conf[f'extractor.mssql_metadata.{MSSQLMetadataExtractor.CLUSTER_KEY}'],
'test_schema1', 'test_table2', 'test table 2',
[ColumnMetadata('col_name', 'description of col_name', 'varchar', 0),
ColumnMetadata('col_name2', 'description of col_name2', 'varchar', 1)],
False, ['test_schema1'])
actual = extractor.extract().__repr__()
self.assertEqual(expected.__repr__(), actual)
expected = TableMetadata(
'mssql',
self.conf[f'extractor.mssql_metadata.{MSSQLMetadataExtractor.CLUSTER_KEY}'],
'test_schema2', 'test_table3', 'test table 3',
[ColumnMetadata('col_id3', 'description of col_id3', 'varchar', 0),
ColumnMetadata('col_name3', 'description of col_name3',
'varchar', 1)],
False, ['test_schema2'])
actual = extractor.extract().__repr__()
self.assertEqual(expected.__repr__(), actual)
self.assertIsNone(extractor.extract())
self.assertIsNone(extractor.extract())
