hailin0 commented on code in PR #2783: URL: https://github.com/apache/incubator-seatunnel/pull/2783#discussion_r974045985
########## seatunnel-e2e/seatunnel-flink-connector-v2-e2e/connector-kafka-flink-e2e/src/test/resources/kafka/kafkasouce_to_console.conf: ########## @@ -0,0 +1,56 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +###### +###### This config file is a demonstration of streaming processing in seatunnel config +###### + +env { + # You can set flink configuration here + execution.parallelism = 1 + #execution.checkpoint.interval = 10000 + #execution.checkpoint.data-uri = "hdfs://localhost:9000/checkpoint" +} + +source { + Kafka { + result_table_name = "kafka" + schema = { + fields { + name = "string" + age = "int" + } + } + topic = "test_csv" + bootstrap.server = "hadoop101:9092,hadoop102:9092,hadoop103:9092" + } + + # If you would like to get more information about how to configure seatunnel and see full list of source plugins, + # please go to https://seatunnel.apache.org/docs/connector-v2/source/KafkaSource +} + +transform { + sql { + sql = "select name,age from kafka" + } + + # If you would like to get more information about how to configure seatunnel and see full list of transform plugins, + # please go to https://seatunnel.apache.org/docs/transform/sql +} + +sink { + Console {} Review Comment: Add `Assert` check row data type? reference https://github.com/apache/incubator-seatunnel/blob/dev/seatunnel-e2e/seatunnel-flink-connector-v2-e2e/connector-iceberg-flink-e2e/src/test/resources/iceberg/iceberg_source.conf#L61 ########## seatunnel-e2e/seatunnel-flink-connector-v2-e2e/connector-kafka-flink-e2e/src/test/resources/kafka/kafkasouce_to_console.conf: ########## @@ -0,0 +1,56 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +###### +###### This config file is a demonstration of streaming processing in seatunnel config +###### + +env { + # You can set flink configuration here + execution.parallelism = 1 + #execution.checkpoint.interval = 10000 + #execution.checkpoint.data-uri = "hdfs://localhost:9000/checkpoint" +} + +source { + Kafka { + result_table_name = "kafka" + schema = { + fields { + name = "string" + age = "int" + } Review Comment: test all datatype? reference https://github.com/apache/incubator-seatunnel/blob/dev/seatunnel-e2e/seatunnel-flink-connector-v2-e2e/connector-iceberg-flink-e2e/src/test/resources/iceberg/iceberg_source.conf#L29 ########## seatunnel-e2e/seatunnel-spark-connector-v2-e2e/connector-kafka-spark-e2e/src/test/resources/kafka/kafkasource_to_console.conf: ########## @@ -0,0 +1,60 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +###### +###### This config file is a demonstration of streaming processing in seatunnel config +###### + +env { + # You can set spark configuration here + # see available properties defined by spark: https://spark.apache.org/docs/latest/configuration.html#available-properties + spark.app.name = "SeaTunnel" + spark.executor.instances = 2 + spark.executor.cores = 1 + spark.executor.memory = "1g" + spark.master = local +} + +source { + Kafka { + result_table_name = "kafka" + schema = { + fields { + name = "string" Review Comment: as above ########## seatunnel-e2e/seatunnel-spark-connector-v2-e2e/connector-kafka-spark-e2e/src/test/resources/kafka/kafkasource_to_console.conf: ########## @@ -0,0 +1,60 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +###### +###### This config file is a demonstration of streaming processing in seatunnel config +###### + +env { + # You can set spark configuration here + # see available properties defined by spark: https://spark.apache.org/docs/latest/configuration.html#available-properties + spark.app.name = "SeaTunnel" + spark.executor.instances = 2 + spark.executor.cores = 1 + spark.executor.memory = "1g" + spark.master = local +} + +source { + Kafka { + result_table_name = "kafka" + schema = { + fields { + name = "string" + age = "int" + } + } + topic = "test_csv" + bootstrap.server = "hadoop101:9092,hadoop102:9092,hadoop103:9092" Review Comment: as above ########## seatunnel-e2e/seatunnel-flink-connector-v2-e2e/connector-kafka-flink-e2e/src/test/resources/kafka/kafkasouce_to_console.conf: ########## @@ -0,0 +1,56 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +###### +###### This config file is a demonstration of streaming processing in seatunnel config +###### + +env { + # You can set flink configuration here + execution.parallelism = 1 + #execution.checkpoint.interval = 10000 + #execution.checkpoint.data-uri = "hdfs://localhost:9000/checkpoint" +} + +source { + Kafka { + result_table_name = "kafka" + schema = { + fields { + name = "string" + age = "int" + } + } + topic = "test_csv" + bootstrap.server = "hadoop101:9092,hadoop102:9092,hadoop103:9092" + } + + # If you would like to get more information about how to configure seatunnel and see full list of source plugins, + # please go to https://seatunnel.apache.org/docs/connector-v2/source/KafkaSource +} + +transform { + sql { + sql = "select name,age from kafka" + } Review Comment: remove or use `select * from kafka` selected all fields ########## seatunnel-e2e/seatunnel-flink-connector-v2-e2e/connector-kafka-flink-e2e/src/test/resources/kafka/kafkasouce_to_console.conf: ########## @@ -0,0 +1,56 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +###### +###### This config file is a demonstration of streaming processing in seatunnel config +###### + +env { + # You can set flink configuration here + execution.parallelism = 1 + #execution.checkpoint.interval = 10000 + #execution.checkpoint.data-uri = "hdfs://localhost:9000/checkpoint" +} + +source { + Kafka { + result_table_name = "kafka" + schema = { + fields { + name = "string" + age = "int" + } + } + topic = "test_csv" + bootstrap.server = "hadoop101:9092,hadoop102:9092,hadoop103:9092" Review Comment: 1. You need to start the kafka test container in the test case 2. Connect your test container and initialize the data 3. Test your logic reference https://github.com/apache/incubator-seatunnel/blob/dev/seatunnel-e2e/seatunnel-flink-connector-v2-e2e/connector-mongodb-flink-e2e/src/test/java/org/apache/seatunnel/e2e/flink/v2/mongodb/MongodbSourceToConsoleIT.java#L70 https://github.com/apache/incubator-seatunnel/blob/dev/seatunnel-e2e/seatunnel-flink-connector-v2-e2e/connector-mongodb-flink-e2e/src/test/resources/mongodb/mongodb_to_console.conf#L33 ########## seatunnel-e2e/seatunnel-spark-connector-v2-e2e/connector-kafka-spark-e2e/src/test/resources/kafka/kafkasource_to_console.conf: ########## @@ -0,0 +1,60 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +###### +###### This config file is a demonstration of streaming processing in seatunnel config +###### + +env { + # You can set spark configuration here + # see available properties defined by spark: https://spark.apache.org/docs/latest/configuration.html#available-properties + spark.app.name = "SeaTunnel" + spark.executor.instances = 2 + spark.executor.cores = 1 + spark.executor.memory = "1g" + spark.master = local +} + +source { + Kafka { + result_table_name = "kafka" + schema = { + fields { + name = "string" + age = "int" + } + } + topic = "test_csv" + bootstrap.server = "hadoop101:9092,hadoop102:9092,hadoop103:9092" + } + + # If you would like to get more information about how to configure seatunnel and see full list of source plugins, + # please go to https://seatunnel.apache.org/docs/connector-v2/source/KafkaSource +} + +transform { + sql { + sql = "select name,age from kafka" Review Comment: as above ########## seatunnel-e2e/seatunnel-spark-connector-v2-e2e/connector-kafka-spark-e2e/src/test/resources/kafka/kafkasource_to_console.conf: ########## @@ -0,0 +1,60 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +###### +###### This config file is a demonstration of streaming processing in seatunnel config +###### + +env { + # You can set spark configuration here + # see available properties defined by spark: https://spark.apache.org/docs/latest/configuration.html#available-properties + spark.app.name = "SeaTunnel" + spark.executor.instances = 2 + spark.executor.cores = 1 + spark.executor.memory = "1g" + spark.master = local +} + +source { + Kafka { + result_table_name = "kafka" + schema = { + fields { + name = "string" + age = "int" + } + } + topic = "test_csv" + bootstrap.server = "hadoop101:9092,hadoop102:9092,hadoop103:9092" + } + + # If you would like to get more information about how to configure seatunnel and see full list of source plugins, + # please go to https://seatunnel.apache.org/docs/connector-v2/source/KafkaSource +} + +transform { + sql { + sql = "select name,age from kafka" + } + + # If you would like to get more information about how to configure seatunnel and see full list of transform plugins, + # please go to https://seatunnel.apache.org/docs/transform/sql +} + + +sink { + Console {} +} Review Comment: as above ########## seatunnel-connectors-v2/connector-kafka/src/main/java/org/apache/seatunnel/connectors/seatunnel/kafka/source/KafkaSource.java: ########## @@ -122,4 +124,27 @@ public SourceSplitEnumerator<KafkaSourceSplit, KafkaSourceState> restoreEnumerat public void setJobContext(JobContext jobContext) { this.jobContext = jobContext; } + + private void setDeserialization(Config config) { + if (config.hasPath(SCHEMA)) { + Config schema = config.getConfig(SCHEMA); + typeInfo = SeaTunnelSchema.buildWithConfig(schema).getSeaTunnelRowType(); + } else { + typeInfo = SeaTunnelSchema.buildSimpleTextSchema(); + } + // TODO: use format SPI + // default use json format + String format; + if(config.hasPath(FORMAT)){ + if(DEFAULT_FORMAT.equals(config.getString(FORMAT))){ + deserializationSchema = new JsonDeserializationSchema(false, false, typeInfo); + }else{ + format = config.getString(FORMAT); + this.deserializationSchema = null; + } + }else { Review Comment: check codestyle -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
