def state_access_demo():
env = StreamExecutionEnvironment.get_execution_environment()
env.set_parallelism(1)
env.set_runtime_mode(RuntimeExecutionMode.BATCH)
seq_num_source = NumberSequenceSource(1, 10)
output_path = '/opt/examples/datastream/output/state_access'
file_sink = FileSink \
.for_row_format(output_path, Encoder.simple_string_encoder()) \
.with_output_file_config(OutputFileConfig.builder().with_part_prefix('pre').with_part_suffix('suf').build()) \
.build()
ds = env.from_source(
source=seq_num_source,
watermark_strategy=WatermarkStrategy.for_monotonous_timestamps(),
source_name='seq_num_source',
type_info=Types.LONG())
ds.map(lambda a: Row(a % 4, 1), output_type=Types.ROW([Types.LONG(), Types.LONG()])) \
.key_by(lambda a: a[0]) \
.map(MyMapFunction(), output_type=Types.ROW([Types.LONG(), Types.LONG()])) \
.key_by(lambda a: a[0]) \
.process(MyKeyedProcessFunction(), Types.LONG()) \
.sink_to(file_sink)
env.execute('11-data_stream_state_access')
def batch_seq_num_test():
env = StreamExecutionEnvironment.get_execution_environment()
env.set_parallelism(2)
env.set_runtime_mode(RuntimeExecutionMode.BATCH)
seq_num_source = NumberSequenceSource(1, 1000)
output_path = '/opt/examples/output/batch_seq_num'
file_sink = FileSink \
.for_row_format(output_path, Encoder.simple_string_encoder()) \
.with_output_file_config(OutputFileConfig.builder().with_part_prefix('pre').with_part_suffix('suf').build()) \
.build()
ds = env.from_source(
source=seq_num_source,
watermark_strategy=WatermarkStrategy.for_monotonous_timestamps(),
source_name='file_source',
type_info=Types.LONG())
ds.map(lambda a: Row(a % 4, 1), output_type=Types.ROW([Types.LONG(), Types.LONG()])) \
.key_by(lambda a: a[0]) \
.reduce(lambda a, b: Row(a[0], a[1] + b[1])) \
.sink_to(file_sink)
env.execute('9-data_stream_batch_seq_num')
def test_seq_source(self):
seq_source = NumberSequenceSource(1, 10)
seq_source_clz = load_java_class(
"org.apache.flink.api.connector.source.lib.NumberSequenceSource")
from_field = seq_source_clz.getDeclaredField("from")
from_field.setAccessible(True)
self.assertEqual(1, from_field.get(seq_source.get_java_function()))
to_field = seq_source_clz.getDeclaredField("to")
to_field.setAccessible(True)
self.assertEqual(10, to_field.get(seq_source.get_java_function()))