def test_rows_are_written(self):
client = mock.Mock()
table = bigquery.Table(tableReference=bigquery.TableReference(
projectId='project', datasetId='dataset', tableId='table'),
schema=bigquery.TableSchema())
client.tables.Get.return_value = table
write_disposition = beam.io.BigQueryDisposition.WRITE_APPEND
insert_response = mock.Mock()
insert_response.insertErrors = []
client.tabledata.InsertAll.return_value = insert_response
with beam.io.BigQuerySink(
'project:dataset.table',
write_disposition=write_disposition).writer(client) as writer:
writer.Write({'i': 1, 'b': True, 's': 'abc', 'f': 3.14})
sample_row = {'i': 1, 'b': True, 's': 'abc', 'f': 3.14}
expected_rows = []
json_object = bigquery.JsonObject()
for k, v in sample_row.iteritems():
json_object.additionalProperties.append(
bigquery.JsonObject.AdditionalProperty(key=k,
value=to_json_value(v)))
expected_rows.append(
bigquery.TableDataInsertAllRequest.RowsValueListEntry(
insertId='_1', # First row ID generated with prefix ''
json=json_object))
client.tabledata.InsertAll.assert_called_with(
bigquery.BigqueryTabledataInsertAllRequest(
projectId='project',
datasetId='dataset',
tableId='table',
tableDataInsertAllRequest=bigquery.TableDataInsertAllRequest(
rows=expected_rows)))
def _create_table(self, project_id, dataset_id, table_id, schema):
table = bigquery.Table(
tableReference=bigquery.TableReference(
projectId=project_id, datasetId=dataset_id, tableId=table_id),
schema=schema)
request = bigquery.BigqueryTablesInsertRequest(
projectId=project_id, datasetId=dataset_id, table=table)
response = self.client.tables.Insert(request)
# The response is a bigquery.Table instance.
return response
def test_table_with_write_disposition_append(self):
client = mock.Mock()
table = bigquery.Table(tableReference=bigquery.TableReference(
projectId='project', datasetId='dataset', tableId='table'),
schema=bigquery.TableSchema())
client.tables.Get.return_value = table
client.tables.Insert.return_value = table
write_disposition = beam.io.BigQueryDisposition.WRITE_APPEND
with beam.io.BigQuerySink(
'project:dataset.table',
write_disposition=write_disposition).writer(client):
pass
self.assertTrue(client.tables.Get.called)
self.assertFalse(client.tables.Delete.called)
self.assertFalse(client.tables.Insert.called)
def test_no_table_and_create_if_needed(self):
client = mock.Mock()
table = bigquery.Table(tableReference=bigquery.TableReference(
projectId='project', datasetId='dataset', tableId='table'),
schema=bigquery.TableSchema())
client.tables.Get.side_effect = HttpError(response={'status': '404'},
url='',
content='')
client.tables.Insert.return_value = table
create_disposition = beam.io.BigQueryDisposition.CREATE_IF_NEEDED
with beam.io.BigQuerySink(
'project:dataset.table',
schema='somefield:INTEGER',
create_disposition=create_disposition).writer(client):
pass
self.assertTrue(client.tables.Get.called)
self.assertTrue(client.tables.Insert.called)
def test_table_empty_and_write_disposition_empty(self):
client = mock.Mock()
table = bigquery.Table(tableReference=bigquery.TableReference(
projectId='project', datasetId='dataset', tableId='table'),
schema=bigquery.TableSchema())
client.tables.Get.return_value = table
client.tabledata.List.return_value = bigquery.TableDataList(
totalRows=0)
client.tables.Insert.return_value = table
write_disposition = beam.io.BigQueryDisposition.WRITE_EMPTY
with beam.io.BigQuerySink(
'project:dataset.table',
write_disposition=write_disposition).writer(client):
pass
self.assertTrue(client.tables.Get.called)
self.assertTrue(client.tabledata.List.called)
self.assertFalse(client.tables.Delete.called)
self.assertFalse(client.tables.Insert.called)
def test_table_not_empty_and_write_disposition_empty(
self, patched_time_sleep):
client = mock.Mock()
client.tables.Get.return_value = bigquery.Table(
tableReference=bigquery.TableReference(
projectId='project', datasetId='dataset', tableId='table'),
schema=bigquery.TableSchema())
client.tabledata.List.return_value = bigquery.TableDataList(totalRows=1)
write_disposition = beam.io.BigQueryDisposition.WRITE_EMPTY
with self.assertRaises(RuntimeError) as exn:
with beam.io.BigQuerySink(
'project:dataset.table',
write_disposition=write_disposition).writer(client):
pass
self.assertEqual(
exn.exception.message,
'Table project:dataset.table is not empty but write disposition is '
'WRITE_EMPTY.')