Github user mmiklavc commented on a diff in the pull request:
https://github.com/apache/metron/pull/1254#discussion_r236530583
--- Diff:
metron-platform/metron-elasticsearch/src/main/java/org/apache/metron/elasticsearch/bulk/ElasticsearchBulkDocumentWriter.java
---
@@ -0,0 +1,184 @@
+/**
+ * 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.metron.elasticsearch.bulk;
+
+import org.apache.commons.lang3.exception.ExceptionUtils;
+import org.apache.metron.elasticsearch.client.ElasticsearchClient;
+import org.apache.metron.indexing.dao.update.Document;
+import org.elasticsearch.action.DocWriteRequest;
+import org.elasticsearch.action.bulk.BulkItemResponse;
+import org.elasticsearch.action.bulk.BulkRequest;
+import org.elasticsearch.action.bulk.BulkResponse;
+import org.elasticsearch.action.index.IndexRequest;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.lang.invoke.MethodHandles;
+import java.util.ArrayList;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Optional;
+import java.util.stream.Collectors;
+
+/**
+ * Writes documents to an Elasticsearch index in bulk.
+ *
+ * @param <D> The type of document to write.
+ */
+public class ElasticsearchBulkDocumentWriter<D extends Document>
implements BulkDocumentWriter<D> {
+
+ /**
+ * A {@link Document} along with the index it will be written to.
+ */
+ private class Indexable {
+ D document;
+ String index;
+
+ public Indexable(D document, String index) {
+ this.document = document;
+ this.index = index;
+ }
+ }
+
+ private static final Logger LOG =
LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());
+ private Optional<SuccessListener> onSuccess;
+ private Optional<FailureListener> onFailure;
+ private ElasticsearchClient client;
+ private List<Indexable> documents;
+
+ public ElasticsearchBulkDocumentWriter(ElasticsearchClient client) {
+ this.client = client;
+ this.onSuccess = Optional.empty();
+ this.onFailure = Optional.empty();
+ this.documents = new ArrayList<>();
+ }
+
+ @Override
+ public void onSuccess(SuccessListener<D> onSuccess) {
+ this.onSuccess = Optional.of(onSuccess);
+ }
+
+ @Override
+ public void onFailure(FailureListener<D> onFailure) {
+ this.onFailure = Optional.of(onFailure);
+ }
+
+ @Override
+ public void addDocument(D document, String index) {
+ documents.add(new Indexable(document, index));
+ LOG.debug("Adding document to batch; document={}, index={}",
document, index);
+ }
+
+ @Override
+ public void write() {
+ try {
+ // create an index request for each document
+ List<DocWriteRequest> requests = documents
--- End diff --
Please be careful using streams. In general, but specifically here. Our ES
endpoints are typically where we bottleneck in any tuning exercise and adding
additional overhead may prove troublesome. I'd normally not stress too much on
"premature optimization" but I think we're safely very much post-premature at
this stage of the game with our Lucene stores.
https://jaxenter.com/java-performance-tutorial-how-fast-are-the-java-8-streams-118830.html
---
