[
https://issues.apache.org/jira/browse/RYA-303?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16119995#comment-16119995
]
ASF GitHub Bot commented on RYA-303:
------------------------------------
Github user meiercaleb commented on a diff in the pull request:
https://github.com/apache/incubator-rya/pull/172#discussion_r132173821
--- Diff:
extras/indexing/src/main/java/org/apache/rya/indexing/mongodb/pcj/MongoPcjIndexSetProvider.java
---
@@ -0,0 +1,125 @@
+/*
+ * 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.rya.indexing.mongodb.pcj;
+
+import static java.util.Objects.requireNonNull;
+
+import java.util.List;
+import java.util.Map;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.rya.api.RdfCloudTripleStoreConfiguration;
+import org.apache.rya.api.instance.RyaDetailsRepository;
+import
org.apache.rya.api.instance.RyaDetailsRepository.RyaDetailsRepositoryException;
+import org.apache.rya.indexing.external.tupleSet.ExternalTupleSet;
+import
org.apache.rya.indexing.pcj.matching.provider.AbstractPcjIndexSetProvider;
+import org.apache.rya.indexing.pcj.storage.PrecomputedJoinStorage;
+import org.apache.rya.indexing.pcj.storage.accumulo.PcjTableNameFactory;
+import org.apache.rya.indexing.pcj.storage.mongo.MongoPcjDocuments;
+import org.apache.rya.indexing.pcj.storage.mongo.MongoPcjStorage;
+import org.apache.rya.mongodb.MongoDBRdfConfiguration;
+import org.apache.rya.mongodb.instance.MongoRyaInstanceDetailsRepository;
+
+import com.google.common.collect.Lists;
+import com.google.common.collect.Maps;
+import com.mongodb.MongoClient;
+
+/**
+ * Implementation of {@link AbstractPcjIndexSetProvider} for MongoDB.
+ */
+public class MongoPcjIndexSetProvider extends AbstractPcjIndexSetProvider {
+ private final MongoClient client;
+ private final MongoDBRdfConfiguration mongoConf;
+
+ public MongoPcjIndexSetProvider(final Configuration conf, final
MongoClient client) {
+ super(conf);
+ this.client = client;
+ mongoConf = new MongoDBRdfConfiguration(conf);
+ }
+
+ public MongoPcjIndexSetProvider(final Configuration conf, final
List<ExternalTupleSet> indices, final MongoClient client) {
+ super(conf, indices);
+ this.client = client;
+ mongoConf = new MongoDBRdfConfiguration(conf);
+ }
+
+ @Override
+ protected List<ExternalTupleSet> getIndices() throws Exception {
+ requireNonNull(conf);
+ final MongoPcjDocuments pcjTables = new MongoPcjDocuments(client,
mongoConf.getMongoDBName());
+ final String pcjPrefix =
requireNonNull(conf.get(RdfCloudTripleStoreConfiguration.CONF_TBL_PREFIX));
+ List<String> tables = null;
+
+ tables = mongoConf.getPcjTables();
+ // this maps associates pcj table name with pcj sparql query
+ final Map<String, String> indexTables = Maps.newLinkedHashMap();
+
+ try(final PrecomputedJoinStorage storage = new
MongoPcjStorage(client, mongoConf.getMongoInstance(), null)) {
+ final PcjTableNameFactory pcjFactory = new
PcjTableNameFactory();
+
+ final boolean tablesProvided = tables != null &&
!tables.isEmpty();
+
+ if (tablesProvided) {
+ // if tables provided, associate table name with sparql
+ for (final String table : tables) {
+ indexTables.put(table,
storage.getPcjMetadata(pcjFactory.getPcjId(table)).getSparql());
+ }
+ } else if (hasRyaDetails(mongoConf.getMongoDBName())) {
+ // If this is a newer install of Rya, and it has PCJ
Details,
+ // then
+ // use those.
+ final List<String> ids = storage.listPcjs();
+ for (final String id : ids) {
+ indexTables.put(pcjFactory.makeTableName(pcjPrefix,
id), storage.getPcjMetadata(id).getSparql());
+ }
+ } else {
+ // Otherwise figure it out by getting document IDs.
+ tables = pcjTables.listPcjDocuments();
+ for (final String table : tables) {
+ if (table.startsWith(pcjPrefix + "INDEX")) {
+ indexTables.put(table,
pcjTables.getPcjMetadata(table).getSparql());
+ }
+ }
+ }
+ }
+
+ // use table name sparql map (indexTables) to create {@link
+ // AccumuloIndexSet}
--- End diff --
Why are you referencing AccumuloIndexSet here? Is this a C&P job :)
> Mongo PCJ indexer support
> -------------------------
>
> Key: RYA-303
> URL: https://issues.apache.org/jira/browse/RYA-303
> Project: Rya
> Issue Type: Improvement
> Reporter: Andrew Smith
> Assignee: Andrew Smith
>
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)