fapaul commented on a change in pull request #17363: URL: https://github.com/apache/flink/pull/17363#discussion_r718235473
########## File path: flink-connectors/flink-connector-elasticsearch7/src/main/java/org/apache/flink/connector/elasticsearch/sink/ElasticsearchSink.java ########## @@ -0,0 +1,124 @@ +/* + * 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. + */ + +package org.apache.flink.connector.elasticsearch.sink; + +import org.apache.flink.annotation.PublicEvolving; +import org.apache.flink.api.connector.sink.Committer; +import org.apache.flink.api.connector.sink.GlobalCommitter; +import org.apache.flink.api.connector.sink.Sink; +import org.apache.flink.api.connector.sink.SinkWriter; +import org.apache.flink.connector.base.DeliveryGuarantee; +import org.apache.flink.core.io.SimpleVersionedSerializer; + +import org.apache.http.HttpHost; + +import java.io.IOException; +import java.util.List; +import java.util.Optional; + +import static org.apache.flink.util.Preconditions.checkNotNull; +import static org.apache.flink.util.Preconditions.checkState; + +/** + * Flink Sink to produce or update data in an Elasticsearch index. The sink supports the following + * delivery guarantees. + * + * <ul> + * <li>{@link DeliveryGuarantee#NONE} does not provide any guarantees: actions are flushed to + * Elasticsearch only depending on the configurations of the bulk processor. In case of a + * failure it might happen that actions are lost if the bulk processor still has buffered + * actions. + * <li>{@link DeliveryGuarantee#AT_LEAST_ONCE} on a checkpoint the sink will wait until all + * buffered actions are flushed to and acknowledged by Elasticsearch. No actions will be lost + * but actions might be sent to Elasticsearch multiple times when Flink restarts. + * </ul> + * + * @param <IN> type of the records converted to Elasticsearch actions + * @see ElasticsearchSinkBuilder on how to construct a ElasticsearchSink + */ +@PublicEvolving +public class ElasticsearchSink<IN> implements Sink<IN, Void, Void, Void> { + + private final List<HttpHost> hosts; + private final ElasticsearchProcessor<IN> processor; + private final BulkProcessorConfig buildBulkProcessorConfig; + private final NetworkClientConfig networkClientConfig; + private final DeliveryGuarantee deliveryGuarantee; + + ElasticsearchSink( + List<HttpHost> hosts, + ElasticsearchProcessor<IN> processor, + DeliveryGuarantee deliveryGuarantee, + BulkProcessorConfig buildBulkProcessorConfig, + NetworkClientConfig networkClientConfig) { + this.hosts = checkNotNull(hosts); + checkState(!hosts.isEmpty(), "Hosts cannot be empty."); Review comment: I am still surprised when to use which precondition ... :) -- 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]
