def test_create_do_with_side_text_file_write(self): input_path = self.create_temp_file('x\ny\n') elements = ['aa', 'bb'] output_buffer = [] executor.MapTaskExecutor().execute(make_map_task([ maptask.WorkerRead( inmemory.InMemorySource( elements=[pickler.dumps(e) for e in elements], start_index=0, end_index=2), output_coders=[self.OUTPUT_CODER]), maptask.WorkerDoFn( serialized_fn=pickle_with_side_inputs( ptransform.CallableWrapperDoFn( lambda x, side: ['%s:%s' % (x, s) for s in side]), tag_and_type=('textfile', pvalue.IterablePCollectionView, ())), output_tags=['out'], input=(0, 0), side_inputs=[ maptask.WorkerSideInputSource(fileio.TextFileSource( file_path=input_path, start_offset=None, end_offset=None, strip_trailing_newlines=True, coder=coders.StrUtf8Coder()), tag='textfile')], output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite(output_buffer=output_buffer, input=(1, 0), output_coders=(self.OUTPUT_CODER,))])) # The side source was specified as collection therefore we should see # all elements of the side source. self.assertEqual([u'aa:x', u'aa:y', u'bb:x', u'bb:y'], sorted(output_buffer))
def test_create_do_with_side_in_memory_write(self): elements = ['abc', 'def', 'ghi'] side_elements = ['x', 'y', 'z'] output_buffer = [] executor.MapTaskExecutor().execute(make_map_task([ maptask.WorkerRead( inmemory.InMemorySource( elements=[pickler.dumps(e) for e in elements], start_index=0, end_index=3), output_coders=[self.OUTPUT_CODER]), maptask.WorkerDoFn( serialized_fn=pickle_with_side_inputs( ptransform.CallableWrapperDoFn( lambda x, side: ['%s:%s' % (x, side)]), tag_and_type=('inmemory', pvalue.SingletonPCollectionView, (False, None))), output_tags=['out'], input=(0, 0), side_inputs=[ maptask.WorkerSideInputSource( inmemory.InMemorySource( elements=[pickler.dumps(e) for e in side_elements], start_index=None, end_index=None), tag='inmemory')], output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite( output_buffer=output_buffer, input=(1, 0), output_coders=(self.OUTPUT_CODER,))])) # The side source was specified as singleton therefore we should see # only the first element appended. self.assertEqual(['abc:x', 'def:x', 'ghi:x'], output_buffer)
def test_create_do_with_collection_side_bigquery_write(self): elements = ['aa', 'bb'] side_elements = ['x', 'y'] output_buffer = [] patch_target = 'google.cloud.dataflow.io.bigquery.BigQueryReader' with mock.patch(target=patch_target) as mock_class: # Setup the reader so it will yield the values in 'side_elements'. reader_mock = mock_class.return_value reader_mock.__enter__.return_value = reader_mock # Use a lambda so that multiple readers can be created, each reading the # entirety of the side elements. reader_mock.__iter__.side_effect = lambda: (x for x in side_elements) executor.MapTaskExecutor().execute( make_map_task([ maptask.WorkerRead(inmemory.InMemorySource( elements=[pickler.dumps(e) for e in elements], start_index=0, end_index=3), output_coders=[self.OUTPUT_CODER]), maptask. WorkerDoFn(serialized_fn=pickle_with_side_inputs( ptransform.CallableWrapperDoFn( lambda x, side: ['%s:%s' % (x, s) for s in side]), tag_and_type=('bigquery', pvalue.IterablePCollectionView, ())), output_tags=['out'], input=(0, 0), side_inputs=[ maptask.WorkerSideInputSource( bigquery.BigQuerySource( project='project', dataset='dataset', table='table', coder=get_bigquery_source_coder()), tag='bigquery') ], output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite( output_buffer=output_buffer, input=(1, 0), output_coders=(self.OUTPUT_CODER, )) ])) # The side source was specified as collection therefore we should see # all elements of the side source. self.assertEqual(['aa:x', 'aa:y', 'bb:x', 'bb:y'], sorted(output_buffer))
def test_in_memory_source_progress_reporting(self): elements = [101, 201, 301, 401, 501, 601, 701] output_buffer = [] source = ProgressRequestRecordingInMemorySource( elements=[pickler.dumps(e) for e in elements]) work_item = workitem.BatchWorkItem(None) work_item.map_task = make_map_task([ maptask.WorkerRead(source, output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite(output_buffer=output_buffer, input=(0, 0), output_coders=(self.OUTPUT_CODER, )) ]) executor.MapTaskExecutor(work_item.map_task).execute() self.assertEqual(elements, output_buffer) expected_progress_record = range(len(elements)) self.assertEqual(expected_progress_record, source.last_reader.progress_record)
def test_create_do_with_side_avro_file_write(self): input_path1 = self.create_temp_file('%s\n' % pickler.dumps('x')) input_path2 = self.create_temp_file('%s\n' % pickler.dumps('y')) elements = ['aa', 'bb'] output_buffer = [] executor.MapTaskExecutor().execute( make_map_task([ maptask.WorkerRead(inmemory.InMemorySource( elements=[pickler.dumps(e) for e in elements], start_index=0, end_index=2), output_coders=[self.OUTPUT_CODER]), maptask.WorkerDoFn( serialized_fn=pickle_with_side_inputs( ptransform.CallableWrapperDoFn( lambda x, side: ['%s:%s' % (x, s) for s in side]), tag_and_type=('sometag', pvalue.IterablePCollectionView, ())), output_tags=['out'], input=(0, 0), # Note that the two side inputs have the same tag. This is quite # common for intermediary PCollections used as side inputs that # are saved as AVRO files. The files will contain the sharded # PCollection. side_inputs=[ maptask.WorkerSideInputSource(fileio.TextFileSource( file_path=input_path1, coder=coders.Base64PickleCoder()), tag='sometag'), maptask.WorkerSideInputSource(fileio.TextFileSource( file_path=input_path2, coder=coders.Base64PickleCoder()), tag='sometag') ], output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite( output_buffer=output_buffer, input=(1, 0), output_coders=(self.OUTPUT_CODER, )) ])) # The side source was specified as collection therefore we should see # all three elements of the side source. self.assertEqual([u'aa:x', u'aa:y', u'bb:x', u'bb:y'], sorted(output_buffer))
def test_pgbk(self): elements = [('a', 1), ('b', 2), ('a', 3), ('a', 4)] output_buffer = [] executor.MapTaskExecutor().execute(make_map_task([ maptask.WorkerRead( inmemory.InMemorySource(elements=[pickler.dumps(e) for e in elements ], start_index=0, end_index=100), output_coders=[self.OUTPUT_CODER]), maptask.WorkerPartialGroupByKey( combine_fn=None, input=(0, 0), output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite(output_buffer=output_buffer, input=(1, 0), output_coders=(self.OUTPUT_CODER,)) ])) self.assertEqual([('a', [1, 3, 4]), ('b', [2])], sorted(output_buffer))
def test_combine(self): elements = [('a', [1, 2, 3]), ('b', [10])] output_buffer = [] executor.MapTaskExecutor().execute(make_map_task([ maptask.WorkerRead( inmemory.InMemorySource( elements=[pickler.dumps(e) for e in elements], start_index=0, end_index=100), output_coders=[self.OUTPUT_CODER]), maptask.WorkerCombineFn(serialized_fn=pickle_with_side_inputs( ptransform.CombineFn.from_callable(sum)), phase='all', input=(0, 0), output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite(output_buffer=output_buffer, input=(1, 0), output_coders=(self.OUTPUT_CODER,)) ])) self.assertEqual([('a', 6), ('b', 10)], output_buffer)
def test_in_memory_source_progress_reporting(self): elements = [101, 201, 301, 401, 501, 601, 701] output_buffer = [] source = ProgressRequestRecordingInMemorySource( elements=[pickler.dumps(e) for e in elements]) executor.MapTaskExecutor().execute(make_map_task([ maptask.WorkerRead(source, output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite(output_buffer=output_buffer, input=(0, 0), output_coders=(self.OUTPUT_CODER,)) ])) self.assertEqual(elements, output_buffer) expected_progress_record = [] len_elements = len(elements) for i in range(len_elements): expected_progress_record.append(float(i + 1) / len_elements) self.assertEqual(expected_progress_record, source.last_reader.progress_record)
def test_create_do_with_singleton_side_bigquery_write(self): elements = ['abc', 'def', 'ghi'] side_elements = ['x', 'y', 'z'] output_buffer = [] patch_target = 'google.cloud.dataflow.io.bigquery.BigQueryReader' with mock.patch(target=patch_target) as mock_class: # Setup the reader so it will yield the values in 'side_elements'. reader_mock = mock_class.return_value reader_mock.__enter__.return_value = reader_mock reader_mock.__iter__.return_value = (x for x in side_elements) pickled_elements = [pickler.dumps(e) for e in elements] executor.MapTaskExecutor().execute(make_map_task([ maptask.WorkerRead( inmemory.InMemorySource(elements=pickled_elements, start_index=0, end_index=3), output_coders=[self.OUTPUT_CODER]), maptask.WorkerDoFn( serialized_fn=pickle_with_side_inputs( ptransform.CallableWrapperDoFn( lambda x, side: ['%s:%s' % (x, side)]), tag_and_type=('bigquery', pvalue.SingletonPCollectionView, (False, None))), output_tags=['out'], input=(0, 0), side_inputs=[ maptask.WorkerSideInputSource( bigquery.BigQuerySource( project='project', dataset='dataset', table='table', coder=get_bigquery_source_coder()), tag='bigquery')], output_coders=[self.OUTPUT_CODER]), maptask.WorkerInMemoryWrite( output_buffer=output_buffer, input=(1, 0), output_coders=(self.OUTPUT_CODER,))])) # The side source was specified as singleton therefore we should see # only the first element appended. self.assertEqual(['abc:x', 'def:x', 'ghi:x'], output_buffer)