def test_csv_row_serialization_schema(self): jvm = get_gateway().jvm JRow = jvm.org.apache.flink.types.Row j_row = JRow(3) j_row.setField(0, "BEGIN") j_row.setField(2, "END") def field_assertion(field_info, csv_value, value, field_delimiter): row_info = Types.ROW([Types.STRING(), field_info, Types.STRING()]) expected_csv = "BEGIN" + field_delimiter + csv_value + field_delimiter + "END\n" j_row.setField(1, value) csv_row_serialization_schema = CsvRowSerializationSchema.Builder(row_info)\ .set_escape_character('*').set_quote_character('\'')\ .set_array_element_delimiter(':').set_field_delimiter(';').build() csv_row_deserialization_schema = CsvRowDeserializationSchema.Builder(row_info)\ .set_escape_character('*').set_quote_character('\'')\ .set_array_element_delimiter(':').set_field_delimiter(';').build() csv_row_serialization_schema._j_serialization_schema.open( jvm.org.apache.flink.connector.testutils.formats. DummyInitializationContext()) csv_row_deserialization_schema._j_deserialization_schema.open( jvm.org.apache.flink.connector.testutils.formats. DummyInitializationContext()) serialized_bytes = csv_row_serialization_schema._j_serialization_schema.serialize( j_row) self.assertEqual(expected_csv, str(serialized_bytes, encoding='utf-8')) j_deserialized_row = csv_row_deserialization_schema._j_deserialization_schema\ .deserialize(expected_csv.encode("utf-8")) self.assertTrue(j_row.equals(j_deserialized_row)) field_assertion(Types.STRING(), "'123''4**'", "123'4*", ";") field_assertion(Types.STRING(), "'a;b''c'", "a;b'c", ";") field_assertion(Types.INT(), "12", 12, ";") test_j_row = JRow(2) test_j_row.setField(0, "1") test_j_row.setField(1, "hello") field_assertion(Types.ROW([Types.STRING(), Types.STRING()]), "'1:hello'", test_j_row, ";") test_j_row.setField(1, "hello world") field_assertion(Types.ROW([Types.STRING(), Types.STRING()]), "'1:hello world'", test_j_row, ";") field_assertion(Types.STRING(), "null", "null", ";")
def write_to_kafka(env): ds = env.from_collection([(1, 'hi'), (2, 'hello'), (3, 'hi'), (4, 'hello'), (5, 'hi'), (6, 'hello'), (6, 'hello')], type_info=Types.ROW([Types.INT(), Types.STRING()])) serialization_schema = AvroRowSerializationSchema(avro_schema_string=""" { "type": "record", "name": "TestRecord", "fields": [ {"name": "id", "type": "int"}, {"name": "name", "type": "string"} ] }""") kafka_producer = FlinkKafkaProducer( topic='test_avro_topic', serialization_schema=serialization_schema, producer_config={ 'bootstrap.servers': 'localhost:9092', 'group.id': 'test_group' }) # note that the output type of ds must be RowTypeInfo ds.add_sink(kafka_producer) env.execute()
def test_cassandra_sink(self): type_info = Types.ROW([Types.STRING(), Types.INT()]) ds = self.env.from_collection([('ab', 1), ('bdc', 2), ('cfgs', 3), ('deeefg', 4)], type_info=type_info) cassandra_sink_builder = CassandraSink.add_sink(ds) cassandra_sink = cassandra_sink_builder\ .set_host('localhost', 9876) \ .set_query('query') \ .enable_ignore_null_fields() \ .set_mapper_options(MapperOptions() .ttl(1) .timestamp(100) .tracing(True) .if_not_exists(False) .consistency_level(ConsistencyLevel.ANY) .save_null_fields(True)) \ .set_max_concurrent_requests(1000) \ .build() cassandra_sink.name('cassandra_sink').set_parallelism(3) plan = eval(self.env.get_execution_plan()) self.assertEqual("Sink: cassandra_sink", plan['nodes'][1]['type']) self.assertEqual(3, plan['nodes'][1]['parallelism'])
def field_assertion(field_info, csv_value, value, field_delimiter): row_info = Types.ROW([Types.STRING(), field_info, Types.STRING()]) expected_csv = "BEGIN" + field_delimiter + csv_value + field_delimiter + "END\n" j_row.setField(1, value) csv_row_serialization_schema = CsvRowSerializationSchema.Builder(row_info)\ .set_escape_character('*').set_quote_character('\'')\ .set_array_element_delimiter(':').set_field_delimiter(';').build() csv_row_deserialization_schema = CsvRowDeserializationSchema.Builder(row_info)\ .set_escape_character('*').set_quote_character('\'')\ .set_array_element_delimiter(':').set_field_delimiter(';').build() csv_row_serialization_schema._j_serialization_schema.open( jvm.org.apache.flink.connector.testutils.formats. DummyInitializationContext()) csv_row_deserialization_schema._j_deserialization_schema.open( jvm.org.apache.flink.connector.testutils.formats. DummyInitializationContext()) serialized_bytes = csv_row_serialization_schema._j_serialization_schema.serialize( j_row) self.assertEqual(expected_csv, str(serialized_bytes, encoding='utf-8')) j_deserialized_row = csv_row_deserialization_schema._j_deserialization_schema\ .deserialize(expected_csv.encode("utf-8")) self.assertTrue(j_row.equals(j_deserialized_row))
def pandas_udaf(): env = StreamExecutionEnvironment.get_execution_environment() env.set_parallelism(1) t_env = StreamTableEnvironment.create(stream_execution_environment=env) # define the source with watermark definition ds = env.from_collection( collection=[ (Instant.of_epoch_milli(1000), 'Alice', 110.1), (Instant.of_epoch_milli(4000), 'Bob', 30.2), (Instant.of_epoch_milli(3000), 'Alice', 20.0), (Instant.of_epoch_milli(2000), 'Bob', 53.1), (Instant.of_epoch_milli(5000), 'Alice', 13.1), (Instant.of_epoch_milli(3000), 'Bob', 3.1), (Instant.of_epoch_milli(7000), 'Bob', 16.1), (Instant.of_epoch_milli(10000), 'Alice', 20.1) ], type_info=Types.ROW([Types.INSTANT(), Types.STRING(), Types.FLOAT()])) table = t_env.from_data_stream( ds, Schema.new_builder() .column_by_expression("ts", "CAST(f0 AS TIMESTAMP_LTZ(3))") .column("f1", DataTypes.STRING()) .column("f2", DataTypes.FLOAT()) .watermark("ts", "ts - INTERVAL '3' SECOND") .build() ).alias("ts, name, price") # define the sink t_env.create_temporary_table( 'sink', TableDescriptor.for_connector('print') .schema(Schema.new_builder() .column('name', DataTypes.STRING()) .column('total_price', DataTypes.FLOAT()) .column('w_start', DataTypes.TIMESTAMP_LTZ()) .column('w_end', DataTypes.TIMESTAMP_LTZ()) .build()) .build()) @udaf(result_type=DataTypes.FLOAT(), func_type="pandas") def mean_udaf(v): return v.mean() # define the tumble window operation table = table.window(Tumble.over(lit(5).seconds).on(col("ts")).alias("w")) \ .group_by(table.name, col('w')) \ .select(table.name, mean_udaf(table.price), col("w").start, col("w").end) # submit for execution table.execute_insert('sink') \ .wait()
def tumble_window_demo(): env = StreamExecutionEnvironment.get_execution_environment() env.set_parallelism(1) t_env = StreamTableEnvironment.create(stream_execution_environment=env) # define the source with watermark definition ds = env.from_collection( collection=[ (Instant.of_epoch_milli(1000), 'Alice', 110.1), (Instant.of_epoch_milli(4000), 'Bob', 30.2), (Instant.of_epoch_milli(3000), 'Alice', 20.0), (Instant.of_epoch_milli(2000), 'Bob', 53.1), (Instant.of_epoch_milli(5000), 'Alice', 13.1), (Instant.of_epoch_milli(3000), 'Bob', 3.1), (Instant.of_epoch_milli(7000), 'Bob', 16.1), (Instant.of_epoch_milli(10000), 'Alice', 20.1) ], type_info=Types.ROW([Types.INSTANT(), Types.STRING(), Types.FLOAT()])) table = t_env.from_data_stream( ds, Schema.new_builder() .column_by_expression("ts", "CAST(f0 AS TIMESTAMP(3))") .column("f1", DataTypes.STRING()) .column("f2", DataTypes.FLOAT()) .watermark("ts", "ts - INTERVAL '3' SECOND") .build() ).alias("ts", "name", "price") # define the sink t_env.create_temporary_table( 'sink', TableDescriptor.for_connector('print') .schema(Schema.new_builder() .column('name', DataTypes.STRING()) .column('total_price', DataTypes.FLOAT()) .build()) .build()) # define the over window operation table = table.over_window( Over.partition_by(col("name")) .order_by(col("ts")) .preceding(row_interval(2)) .following(CURRENT_ROW) .alias('w')) \ .select(table.name, table.price.max.over(col('w'))) # submit for execution table.execute_insert('sink') \ .wait()
def read_from_kafka(env): deserialization_schema = JsonRowDeserializationSchema.Builder() \ .type_info(Types.ROW([Types.INT(), Types.STRING()])) \ .build() kafka_consumer = FlinkKafkaConsumer( topics='test_csv_topic', deserialization_schema=deserialization_schema, properties={'bootstrap.servers': 'localhost:9092', 'group.id': 'test_group_1'} ) kafka_consumer.set_start_from_earliest() env.add_source(kafka_consumer).print() env.execute()
def write_to_kafka(env): type_info = Types.ROW([Types.INT(), Types.STRING()]) ds = env.from_collection([ (1, 'hi'), (2, 'hello'), (3, 'hi'), (4, 'hello'), (5, 'hi'), (6, 'hello'), (6, 'hello')], type_info=type_info) serialization_schema = CsvRowSerializationSchema.Builder(type_info).build() kafka_producer = FlinkKafkaProducer( topic='test_csv_topic', serialization_schema=serialization_schema, producer_config={'bootstrap.servers': 'localhost:9092', 'group.id': 'test_group'} ) # note that the output type of ds must be RowTypeInfo ds.add_sink(kafka_producer) env.execute()
def test_jdbc_sink(self): ds = self.env.from_collection([('ab', 1), ('bdc', 2), ('cfgs', 3), ('deeefg', 4)], type_info=Types.ROW( [Types.STRING(), Types.INT()])) jdbc_connection_options = JdbcConnectionOptions.JdbcConnectionOptionsBuilder()\ .with_driver_name('com.mysql.jdbc.Driver')\ .with_user_name('root')\ .with_password('password')\ .with_url('jdbc:mysql://server-name:server-port/database-name').build() jdbc_execution_options = JdbcExecutionOptions.builder().with_batch_interval_ms(2000)\ .with_batch_size(100).with_max_retries(5).build() jdbc_sink = JdbcSink.sink("insert into test table", ds.get_type(), jdbc_connection_options, jdbc_execution_options) ds.add_sink(jdbc_sink).name('jdbc sink') plan = eval(self.env.get_execution_plan()) self.assertEqual('Sink: jdbc sink', plan['nodes'][1]['type']) j_output_format = get_field_value(jdbc_sink.get_java_function(), 'outputFormat') connection_options = JdbcConnectionOptions( get_field_value( get_field_value(j_output_format, 'connectionProvider'), 'jdbcOptions')) self.assertEqual(jdbc_connection_options.get_db_url(), connection_options.get_db_url()) self.assertEqual(jdbc_connection_options.get_driver_name(), connection_options.get_driver_name()) self.assertEqual(jdbc_connection_options.get_password(), connection_options.get_password()) self.assertEqual(jdbc_connection_options.get_user_name(), connection_options.get_user_name()) exec_options = JdbcExecutionOptions( get_field_value(j_output_format, 'executionOptions')) self.assertEqual(jdbc_execution_options.get_batch_interval_ms(), exec_options.get_batch_interval_ms()) self.assertEqual(jdbc_execution_options.get_batch_size(), exec_options.get_batch_size()) self.assertEqual(jdbc_execution_options.get_max_retries(), exec_options.get_max_retries())
def test_rabbitmq_connectors(self): connection_config = RMQConnectionConfig.Builder() \ .set_host('localhost') \ .set_port(5672) \ .set_virtual_host('/') \ .set_user_name('guest') \ .set_password('guest') \ .build() type_info = Types.ROW([Types.INT(), Types.STRING()]) deserialization_schema = JsonRowDeserializationSchema.builder() \ .type_info(type_info=type_info).build() rmq_source = RMQSource( connection_config, 'source_queue', True, deserialization_schema) self.assertEqual( get_field_value(rmq_source.get_java_function(), 'queueName'), 'source_queue') self.assertTrue(get_field_value(rmq_source.get_java_function(), 'usesCorrelationId')) serialization_schema = JsonRowSerializationSchema.builder().with_type_info(type_info) \ .build() rmq_sink = RMQSink(connection_config, 'sink_queue', serialization_schema) self.assertEqual( get_field_value(rmq_sink.get_java_function(), 'queueName'), 'sink_queue')
def test_pulsar_sink(self): ds = self.env.from_collection([('ab', 1), ('bdc', 2), ('cfgs', 3), ('deeefg', 4)], type_info=Types.ROW( [Types.STRING(), Types.INT()])) TEST_OPTION_NAME = 'pulsar.producer.chunkingEnabled' pulsar_sink = PulsarSink.builder() \ .set_service_url('pulsar://localhost:6650') \ .set_admin_url('http://localhost:8080') \ .set_producer_name('fo') \ .set_topics('ada') \ .set_serialization_schema( PulsarSerializationSchema.flink_schema(SimpleStringSchema())) \ .set_delivery_guarantee(DeliveryGuarantee.AT_LEAST_ONCE) \ .set_topic_routing_mode(TopicRoutingMode.ROUND_ROBIN) \ .delay_sending_message(MessageDelayer.fixed(Duration.of_seconds(12))) \ .set_config(TEST_OPTION_NAME, True) \ .set_properties({'pulsar.producer.batchingMaxMessages': '100'}) \ .build() ds.sink_to(pulsar_sink).name('pulsar sink') plan = eval(self.env.get_execution_plan()) self.assertEqual('pulsar sink: Writer', plan['nodes'][1]['type']) configuration = get_field_value(pulsar_sink.get_java_function(), "sinkConfiguration") self.assertEqual( configuration.getString( ConfigOptions.key('pulsar.client.serviceUrl').string_type(). no_default_value()._j_config_option), 'pulsar://localhost:6650') self.assertEqual( configuration.getString( ConfigOptions.key('pulsar.admin.adminUrl').string_type(). no_default_value()._j_config_option), 'http://localhost:8080') self.assertEqual( configuration.getString( ConfigOptions.key('pulsar.producer.producerName').string_type( ).no_default_value()._j_config_option), 'fo - %s') j_pulsar_serialization_schema = get_field_value( pulsar_sink.get_java_function(), 'serializationSchema') j_serialization_schema = get_field_value(j_pulsar_serialization_schema, 'serializationSchema') self.assertTrue( is_instance_of( j_serialization_schema, 'org.apache.flink.api.common.serialization.SimpleStringSchema') ) self.assertEqual( configuration.getString( ConfigOptions.key('pulsar.sink.deliveryGuarantee').string_type( ).no_default_value()._j_config_option), 'at-least-once') j_topic_router = get_field_value(pulsar_sink.get_java_function(), "topicRouter") self.assertTrue( is_instance_of( j_topic_router, 'org.apache.flink.connector.pulsar.sink.writer.router.RoundRobinTopicRouter' )) j_message_delayer = get_field_value(pulsar_sink.get_java_function(), 'messageDelayer') delay_duration = get_field_value(j_message_delayer, 'delayDuration') self.assertEqual(delay_duration, 12000) test_option = ConfigOptions.key( TEST_OPTION_NAME).boolean_type().no_default_value() self.assertEqual( configuration.getBoolean(test_option._j_config_option), True) self.assertEqual( configuration.getLong( ConfigOptions.key('pulsar.producer.batchingMaxMessages'). long_type().no_default_value()._j_config_option), 100)