Elasticsearch原生态
Posted lowerma
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了Elasticsearch原生态相关的知识，希望对你有一定的参考价值。
Elasticsearch 是一个分布式、RESTful 风格的搜索和数据分析引擎，能够解决不断涌现出的各种用例。 作为 Elastic Stack 的核心，它集中存储您的数据，帮助您发现意料之中以及意料之外的情况。
导入依赖
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
</dependency>
<dependency>
<groupId>org.elasticsearch</groupId>
<artifactId>elasticsearch</artifactId>
<version>5.6.8</version>
</dependency>
<dependency>
<groupId>org.elasticsearch.client</groupId>
<artifactId>transport</artifactId>
<version>5.6.8</version>
</dependency>
<!-- https://mvnrepository.com/artifact/com.alibaba/fastjson -->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.58</version>
</dependency>
<!-- https://mvnrepository.com/artifact/com.fasterxml.jackson.core/jackson-core -->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
<version>2.9.8</version>
</dependency>
<!-- https://mvnrepository.com/artifact/com.fasterxml.jackson.core/jackson-databind -->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>2.9.8</version>
</dependency>
<!-- https://mvnrepository.com/artifact/com.fasterxml.jackson.core/jackson-annotations -->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
<version>2.9.8</version>
</dependency>
连接所有方法都要用,提成公共方法
public TransportClient getClient() throws UnknownHostException {
//步骤一：创建一个Settings对象，指定集群名字
Settings settings = Settings.builder().put("cluster.name", "my-elasticsearch").build();
//步骤二：创建一个Client连接对象
TransportClient client = new PreBuiltTransportClient(settings);
//步骤三：连接到ES服务器
client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9300));
client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9301));
client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9302));
return client;
}
1.创建一个空的索引库
/**
* 创建空的索引库
*/
@Test
public void createNullIndex() throws UnknownHostException {
TransportClient client = getClient();
//创建一个空的索引库 admin()管理权限 indices()索引库 prepareCreate()创建一个索引库 get()执行之前的操作请求
client.admin().indices().prepareCreate("y2170").get();
//关闭client对象
client.close();
}
2.索引库指定Mapping信息
2.1 利用XContentBuilder对象拼接JSON字符串
2.2 手动用过字符串拼接得到JSON字符串
{
"hello":{
"properties":{
"id":{
"type":"long",
"store":true,
"index":"not_analyzed"
},
"title":{
"type":"text",
"store":true,
"index":"analyzed",
"analyzer":"ik_max_word"
},
"content":{
"type":"text",
"store":true,
"index":"analyzed",
"analyzer":"ik_max_word"
}
}
}
}
案例：
/**
* 指定索引库的Mapping信息
*/
@Test
public void createMappingByIndex() throws IOException {
TransportClient client = getClient();
//创建一个XContentBuilder对象，用于拼接JSON格式字符串
XContentBuilder xContentBuilder = XContentFactory.jsonBuilder();
xContentBuilder.startObject().startObject("hello").startObject("properties")
.startObject("id").field("type","long").field("store",true).field("index","not_analyzed").endObject()
.startObject("title").field("type","text").field("store",true).field("index","analyzed").field("analyzer","ik_max_word").endObject()
.startObject("content").field("type","text").field("store",true).field("index","analyzed").field("analyzer","ik_max_word").endObject()
.endObject().endObject().endObject();
//指定索引库以及Type类型的Mapping映射信息 preparePutMapping代表向哪一个索引库指定mpiing信息 setType代表该索引库下的TYPE，与上方JSON创建的Type保持一致
//setSource 指定JSON字符串的存储对象 get执行
client.admin().indices().preparePutMapping("y2170").setType("hello").setSource(xContentBuilder).get();
//关闭资源
client.close();
}
3.创建索引库同时指定Mapping信息
/**
* 创建索引库并且指定Mapping信息
*/
@Test
public void createIndexAndMapping() throws IOException {
TransportClient client = getClient();
//创建索引库
client.admin().indices().prepareCreate("wdksoft").get();
//创建Mapping信息
//创建一个XContentBuilder对象，用于拼接JSON格式字符串
XContentBuilder xContentBuilder = XContentFactory.jsonBuilder();
xContentBuilder.startObject().startObject("article").startObject("properties")
.startObject("id").field("type","long").field("store",true).field("index","not_analyzed").endObject()
.startObject("title").field("type","text").field("store",true).field("index","analyzed").field("analyzer","ik_max_word").endObject()
.startObject("content").field("type","text").field("store",true).field("index","analyzed").field("analyzer","ik_max_word").endObject()
.endObject().endObject().endObject();
client.admin().indices().preparePutMapping("wdksoft").setType("article").setSource(xContentBuilder).get();
//关闭资源
client.close();
}
4.删除索引库
/**
* 删除索引库
*/
@Test
public void deleteIndex() throws UnknownHostException {
TransportClient client = getClient();
//删除索引库
client.admin().indices().prepareDelete("wdksoft").get();
//关闭资源
client.close();
}
5.创建文档-通过XContentBuilder对象拼接JSON格式字符串
( { ) 开头用.startObject()
( } )结尾用.endObject()
域用.field(键,值),多个就继续在后面追加
/**
* 创建文档-通过XContentBuilder对象拼接JSON字符串
*/
@Test
public void createDocumentByXC() throws IOException {
TransportClient client = getClient();
//构建文档信息
XContentBuilder xContentBuilder = XContentFactory.jsonBuilder();
xContentBuilder.startObject().field("id",1).field("title","Lucene是apache软件基金会4 jakarta项目组的一个子项目")
.field("content","Lucene是apache软件基金会4 jakarta项目组的一个子项目，是一个开放源代码的全文检索引擎工具包，但它不是一个完整的全文检索引擎，而是一个全文检索引擎的架构，提供了完整的")
.endObject();
//创建文档
client.prepareIndex("y2170","hello","1").setSource(xContentBuilder).get();
client.close();
}
6.创建文档-通过对象转换为JSON字符串
Hello类
public class Hello {
private Integer id; //属性要跟Type的域的名字一致
private String title;
private String content;
public Integer getId() {
return id;
}
public void setId(Integer id) {
this.id = id;
}
public String getTitle() {
return title;
}
public void setTitle(String title) {
this.title = title;
}
public String getContent() {
return content;
}
public void setContent(String content) {
this.content = content;
}
public Hello(Integer id, String title, String content) {
this.id = id;
this.title = title;
this.content = content;
}
public Hello() {
}
}
/**
* 创建文档-通过对象转换成JSON字符串
* fastjson String helloJson = JSON.toJSONString(hello);
* jackson
* ObjectMapper objectMapper=new ObjectMapper();
* String helloJson = objectMapper.writeValueAsString(hello);
*/
@Test
public void createDocumentByObject() throws UnknownHostException, JsonProcessingException {
TransportClient client = getClient();
//准备一个数据（文档）对象
Hello hello=new Hello(3,"ElasticSearch是一个基于Lucene的搜索服务器","ElasticSearch是一个基于Lucene的搜索服务器。它提供了一个分布式多用户能力的全文搜索引擎，基于RESTful web接口。Elasticsearch是用Java语言开发的，并作为Apache许可条款下的开放源码发布，是一种流行的企业级搜索引擎。ElasticSearch用");
//将对象转换为JSON格式字符串 fastjson
/*String helloJson = JSON.toJSONString(hello);
System.out.println(helloJson);*/
//利用jackson转换
ObjectMapper objectMapper=new ObjectMapper();
String helloJson = objectMapper.writeValueAsString(hello);
//向索引库中添加文档数据
client.prepareIndex("y2170","hello","3").setSource(helloJson, XContentType.JSON).get();
client.close();
}
7.删除文档
/**
* 删除文档
*/
@Test
public void deleteDocument() throws UnknownHostException, JsonProcessingException {
TransportClient client = getClient();
//删除文档
client.prepareDelete("y2170","hello","4").get();
client.close();
}
8.查询文档-根据文档ID查询
/**
* 根据文档ID进行查询
*/
@Test
public void getDocumentByID() throws UnknownHostException, JsonProcessingException {
TransportClient client = getClient();
//执行查询,可查询多个
SearchResponse searchResponse = client.prepareSearch("y2170").setTypes("hello").setQuery(
QueryBuilders.idsQuery().addIds("1", "2")
).get();
//获取到查询结果
SearchHits hits = searchResponse.getHits();
//如果返回数据较多，默认进行分页，默认10条数据
System.out.println("获取到文档数据条目数："+hits.getTotalHits());
//获取到文档数据
Iterator<SearchHit> iterator = hits.iterator();
while (iterator.hasNext()){
SearchHit hit = iterator.next();
System.out.println(hit.getSourceAsString());
System.out.println("content:"+hit.getSource().get("content"));
}
client.close();
}
9.查询文档-根据Term关键词查询
/**
* 根据Term分词进行查询
*/
@Test
public void getDocumentByTerm() throws UnknownHostException, JsonProcessingException {
TransportClient client = getClient();
//执行查询,可查询多个
SearchResponse searchResponse = client.prepareSearch("y2170").setTypes("hello").setQuery(
QueryBuilders.termQuery("title","服务器")
).get();
//获取到查询结果
SearchHits hits = searchResponse.getHits();
//如果返回数据较多，默认进行分页，默认10条数据
System.out.println("获取到文档数据条目数："+hits.getTotalHits());
//获取到文档数据
Iterator<SearchHit> iterator = hits.iterator();
while (iterator.hasNext()){
SearchHit hit = iterator.next();
System.out.println(hit.getSourceAsString());
System.out.println("content:"+hit.getSource().get("content"));
}
client.close();
}
10.查询文档-根据QueryString查询文档
@Test
public void getDocumentByQueryString() throws UnknownHostException, JsonProcessingException {
TransportClient client = getClient();
//执行查询
SearchResponse searchResponse = client.prepareSearch("y2170").setTypes("hello").setQuery(
QueryBuilders.queryStringQuery("Solr是一个独立的企业级搜索应用服务器")
).get();
//获取到查询结果
SearchHits hits = searchResponse.getHits();
//如果返回数据较多，默认进行分页，默认10条数据
System.out.println("获取到文档数据条目数："+hits.getTotalHits());
//获取到文档数据
Iterator<SearchHit> iterator = hits.iterator();
while (iterator.hasNext()){
SearchHit hit = iterator.next();
System.out.println(hit.getSourceAsString());
System.out.println("content:"+hit.getSource().get("content"));
}
client.close();
11.查询数据的分页检索
ES当中默认检索数据是10条
/**
* 分页
*/
@Test
public void getDocumentByQueryStringlimit() throws UnknownHostException, JsonProcessingException {
TransportClient client = getClient();
//设置查询条件
SearchRequestBuilder searchRequestBuilder = client.prepareSearch("y2170").setTypes("hello").setQuery(
QueryBuilders.queryStringQuery("服务器")
);
//加入分页规则 setFrom代表从那一条数据开始获取
searchRequestBuilder.setFrom(0).setSize(5);
SearchResponse searchResponse = searchRequestBuilder.get();
//获取到查询结果
SearchHits hits = searchResponse.getHits();
//如果返回数据较多，默认进行分页，默认10条数据
System.out.println("获取到文档数据条目数：" + hits.getTotalHits());
//获取到文档数据
Iterator<SearchHit> iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit hit = iterator.next();
System.out.println(hit.getSourceAsString());
System.out.println("content:" + hit.getSource().get("content"));
}
client.close();
}
12.查询数据的高亮显示
执行查询数据之前设置高亮显示规则
1.设置高亮显示的域
2.设置高亮显示前缀
3.设置高亮显示后缀
执行查询
获取到高亮显示的数据
/**
* 高亮显示
*/
@Test
public void getDocumentByQueryHight() throws UnknownHostException, JsonProcessingException {
TransportClient client = getClient();
//设置查询条件
SearchRequestBuilder searchRequestBuilder = client.prepareSearch("y2170").setTypes("hello").setQuery(
QueryBuilders.termQuery("title", "服务器")
);
//加入分页规则 setFrom代表从那一条数据开始获取
searchRequestBuilder.setFrom(0).setSize(5);
//设置高亮规则
HighlightBuilder highlightBuilder=new HighlightBuilder();
//指定高亮显示的域
highlightBuilder.field("title");
highlightBuilder.preTags("<span style=‘color:red‘>");
highlightBuilder.postTags("</span>");
searchRequestBuilder.highlighter(highlightBuilder);
//执行查询
SearchResponse searchResponse = searchRequestBuilder.get();
//获取到查询结果
SearchHits hits = searchResponse.getHits();
//如果返回数据较多，默认进行分页，默认10条数据
System.out.println("获取到文档数据条目数：" + hits.getTotalHits());
//获取到文档数据
Iterator<SearchHit> iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit hit = iterator.next();
System.out.println(hit.getSourceAsString());
/* System.out.println("content:" + hit.getSource().get("content"));*/
//获取高亮结果
Text[] titles = hit.getHighlightFields().get("title").getFragments();
for(Text text:titles){
System.out.println("高亮显示数据为："+text);
}
}
client.close();
}
以上是关于Elasticsearch原生态的主要内容，如果未能解决你的问题，请参考以下文章
Elasticsearch 实战与原理解析 - 第 10 章 Elasticsearch 生态圈