ElasticSearch_JavaAPI

在官方文档中主要还是已RESTFUL API来说明较多，本文主要是来介绍ES的Java API的使用，在实验室环境使用的ES版本为5.5.1

Client

TransportClient

TransportClient是通过transport module来远程连接ES cluster。 TransportClient不是加入集群，而是获取初始交换层地址。

Client API

//初始化
public static TransportClient getClient() {  
         if(client!=null){  
             return client;  
         }  
         //设置集群名称
         Settings settings = Settings.builder().put("cluster.name", "ubuntu").build();  
         try {  
             client = new PreBuiltTransportClient(settings) 
                     .addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("ubuntu1"), 9300)) 
                     .addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("ubuntu2"), 9300))  
                     .addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("ubuntu3"), 9300))  
                     .addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("ubuntu4"), 9300));  
         } catch (UnknownNamedObjectException | UnknownHostException e) {  
             e.printStackTrace();  
         }  
         return client;  
   }

Index API

 //在index=twitter,type=tweet,id=1
 public void add() throws IOException{
     IndexResponse response = getClient().prepareIndex("twitter", "tweet", "1")
                .setSource(XContentFactory.jsonBuilder()
                        .startObject()
                        .field("user", "kimchy")
                        .field("postDate", new Date())
                        .field("message", "trying out Elasticsearch")
                    .endObject())
                .get();
    // Index name
     String _index = response.getIndex();
     // Type name
     String _type = response.getType();
     // Document ID (generated or not)
     String _id = response.getId();
     // Version (if it's the first time you index this document, you will get: 1)
     long _version = response.getVersion();
     // status has stored current instance statement.
     RestStatus status = response.status();
 }

Get API

//通过id号get document
 public void getIndex(){
     GetResponse response = getClient().prepareGet("twitter", "tweet", "1").get();
     for(Entry<String, Object> entry : response.getSource().entrySet()){
         System.out.println(entry.getKey() +"===="+entry.getValue());
     }
 }

Delete API

//根据document删除(同步操作)
 public void deleteByDocument(){
     BulkByScrollResponse response =
                DeleteByQueryAction.INSTANCE.newRequestBuilder(getClient())
                    //query
                    .filter(QueryBuilders.matchQuery("user", "kimchy")) 
                    //index
                    .source("twitter")   
                    //execute the operation
                    .get();                                             
     //number of deleted documents
     long deleted = response.getDeleted();
     System.out.println(deleted);
 }


// 异步删除
 public void deleteByDocumentInAsy(){
     DeleteByQueryAction.INSTANCE.newRequestBuilder(getClient())
        .filter(QueryBuilders.matchQuery("user", "kimchy"))    
        //index
        .source("twitter")
        //监听器
        .execute(new ActionListener<BulkByScrollResponse>() {       
            //删除的文档数
            @Override
            public void onResponse(BulkByScrollResponse response) {
                long deleted = response.getDeleted();                        
            }
            @Override
            public void onFailure(Exception e) {
            }
        });
 }

Update API

//更新document，同时可以再对应id下再增加数据
 public void update(){
     try {
        UpdateResponse response = getClient().prepareUpdate("twitter", "tweet", "1")
         .setDoc(XContentFactory.jsonBuilder()               
             .startObject()
                 .field("gender", "male")
             .endObject())
         .get();
    } catch (IOException e) {
        e.printStackTrace();
    }
 }

//如果之前没有document可以使用upsert方法添加，若有，则可以只update需要update的document
IndexRequest indexRequest = new IndexRequest("index", "type", "1")
        .source(jsonBuilder()
            .startObject()
                .field("name", "Joe Smith")
                .field("gender", "male")
            .endObject());
UpdateRequest updateRequest = new UpdateRequest("index", "type", "1")
        .doc(jsonBuilder()
            .startObject()
                .field("gender", "male")
            .endObject())
        .upsert(indexRequest);              
client.update(updateRequest).get();

Bulk API 可以一次性多次进行index操作和delete操作

BulkRequestBuilder bulkRequest = client.prepareBulk();

// either use client#prepare, or use Requests# to directly build index/delete requests
bulkRequest.add(client.prepareIndex("twitter", "tweet", "1")
        .setSource(jsonBuilder()
                    .startObject()
                        .field("user", "kimchy")
                        .field("postDate", new Date())
                        .field("message", "trying out Elasticsearch")
                    .endObject()
                  )
        );

bulkRequest.add(client.prepareIndex("twitter", "tweet", "2")
        .setSource(jsonBuilder()
                    .startObject()
                        .field("user", "kimchy")
                        .field("postDate", new Date())
                        .field("message", "another post")
                    .endObject()
                  )
        );

BulkResponse bulkResponse = bulkRequest.get();

EL建表说明

EL建Field的限制，EL限制最多只能有1000个Field

请求参数方式查询

http://ubuntu1:9200/el/28s/_search?q=*&pretty

TermQuery查询大‘Bug’

QueryBuilders.termQuery(colum, value)

对于英文检索value时，即使数据存储的是如‘Benz’，但是查询时value为‘Benz’是查询不到结果的，必须为小写‘benz’才可以查询到结果

原因： String类型分为text和keyword,text是要被分词的，keyword类似于es2.3的not_analyzed,String默认为text,默认分词器为standard analyzer。”Quick Brown Fox!”会被分解成[quick,brown,fox]写入倒排索引,所以检索时大写字母检索不到

解决方法： 为了应对中文的分词，需要使用ik分词器，大小写情况ik分词器还没有解决

分词查看

http://ubuntu1:9200/_analyze?&pretty=true&text=内容

使用ik分词器对中文进行分词

http://ubuntu1:9200/_analyze?analyzer=ik_smart&pretty=true&text=内容

查看Field属性

http://ubuntu1:9200/el/28s/_mapping

查看index的analyzer

GET kg/_settings

查看index中type的search

GET kg/28s/_search

matchQuery和termQuery的区别

两个query都是从分词后的token组中查询，termQuery是完全匹配，matchQuery可以匹配大小写

Join Query中的Has Child Query和Has Parent Query

两个Type做Join