[ 
https://issues.apache.org/jira/browse/JENA-1305?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15926064#comment-15926064
 ] 

ASF GitHub Bot commented on JENA-1305:
--------------------------------------

Github user anujgandharv commented on a diff in the pull request:

    https://github.com/apache/jena/pull/227#discussion_r106152482
  
    --- Diff: 
jena-text/src/main/java/org/apache/jena/query/text/assembler/TextIndexESAssembler.java
 ---
    @@ -0,0 +1,129 @@
    +/**
    + * 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.jena.query.text.assembler;
    +
    +import org.apache.jena.assembler.Assembler;
    +import org.apache.jena.assembler.Mode;
    +import org.apache.jena.assembler.assemblers.AssemblerBase;
    +import org.apache.jena.query.text.*;
    +import org.apache.jena.rdf.model.RDFNode;
    +import org.apache.jena.rdf.model.Resource;
    +import org.apache.jena.rdf.model.Statement;
    +import org.apache.jena.sparql.util.graph.GraphUtils;
    +import org.slf4j.Logger;
    +import org.slf4j.LoggerFactory;
    +
    +import java.util.HashMap;
    +import java.util.Map;
    +
    +import static org.apache.jena.query.text.assembler.TextVocab.*;
    +
    +public class TextIndexESAssembler extends AssemblerBase {
    +
    +    private static Logger LOGGER      = 
LoggerFactory.getLogger(TextIndexESAssembler.class) ;
    +
    +    protected static final String COMMA = ",";
    +    protected static final String COLON = ":";
    +    /*
    +    <#index> a :TextIndexES ;
    +        text:serverList "127.0.0.1:9300,127.0.0.2:9400,127.0.0.3:9500" ; 
#Comma separated list of hosts:ports
    +        text:clusterName "elasticsearch"
    +        text:shards "1"
    +        text:replicas "1"
    +        text:entityMap <#endMap> ;
    +        .
    +    */
    +    
    +    @SuppressWarnings("resource")
    +    @Override
    +    public TextIndex open(Assembler a, Resource root, Mode mode) {
    +        try {
    +            String listOfHostsAndPorts = GraphUtils.getAsStringValue(root, 
pServerList) ;
    +            if(listOfHostsAndPorts == null || 
listOfHostsAndPorts.isEmpty()) {
    +                throw new TextIndexException("Mandatory property 
text:serverList (containing the comma-separated list of host:port) property is 
not specified. " +
    +                        "An example value for the property: 
127.0.0.1:9300");
    +            }
    +            String[] hosts = listOfHostsAndPorts.split(COMMA);
    +            Map<String,Integer> hostAndPortMapping = new HashMap<>();
    +            for(String host : hosts) {
    +                String[] hostAndPort = host.split(COLON);
    +                if(hostAndPort.length < 2) {
    +                    LOGGER.error("Either the host or the port value is 
missing.Please specify the property in host:port format. " +
    +                            "Both parts are mandatory. Ignoring this 
value. Moving to the next one.");
    +                    continue;
    +                }
    +                hostAndPortMapping.put(hostAndPort[0], 
Integer.valueOf(hostAndPort[1]));
    +            }
    +
    +            String clusterName = GraphUtils.getAsStringValue(root, 
pClusterName);
    +            if(clusterName == null || clusterName.isEmpty()) {
    +                LOGGER.warn("ClusterName property is not specified. 
Defaulting to 'elasticsearch'");
    +                clusterName = "elasticsearch";
    +            }
    +
    +            String numberOfShards = GraphUtils.getAsStringValue(root, 
pShards);
    +            if(numberOfShards == null || numberOfShards.isEmpty()) {
    +                LOGGER.warn("shards property is not specified. Defaulting 
to '1'");
    +                numberOfShards = "1";
    +            }
    +
    +            String replicationFactor = GraphUtils.getAsStringValue(root, 
pReplicas);
    +            if(replicationFactor == null || replicationFactor.isEmpty()) {
    +                LOGGER.warn("replicas property is not specified. 
Defaulting to '1'");
    +                replicationFactor = "1";
    +            }
    +
    +            String indexName = GraphUtils.getAsStringValue(root, 
pIndexName);
    +            if(indexName == null || indexName.isEmpty()) {
    +                LOGGER.warn("index Name property is not specified. 
Defaulting to 'test'");
    --- End diff --
    
    Done


> Elastic Search Support for Apache Jena Text 
> --------------------------------------------
>
>                 Key: JENA-1305
>                 URL: https://issues.apache.org/jira/browse/JENA-1305
>             Project: Apache Jena
>          Issue Type: New Feature
>          Components: Text
>    Affects Versions: Jena 3.2.0
>            Reporter: Anuj Kumar
>            Assignee: Osma Suominen
>              Labels: elasticsearch
>   Original Estimate: 240h
>  Remaining Estimate: 240h
>
> This Jira tracks the development of Jena Text ElasticSearch Implementation.
> The goal is to extend Jena Text capability to index, at scale, in 
> ElasticSearch. This implementation would be similar to the Lucene and Solr 
> implementations.
> We will use ES version 5.2.1 for the implementation.
> The following functionalities would be supported:
> * Indexing Literal values
> * Updating indexed values
> * Deleting Indexed values
> * Custom Analyzer Support
> * Configuration using Assembler as well as Java techniques.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Reply via email to