ElasticSearch学习目录:
使用Java语言操作索引库
Elasticsearch相关的pom.xml坐标
<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>
1. 创建索引(Index)
Client:Java 客户端连接 Elasticsearch,对于ES包括下面两种形式:
- TransportClient:集群的外部访问者,它不加入群集,用于程序与集群的通信
- NodeClient:ES集群中的一个节点,知道整个集群状态,可以执行APIs
Settings相当于一个配置信息,主要用来配置集群的名称
put("cluster.name","my-elasticsearch") //配置集群名称
put("client.transport.sniff", true) //自动嗅探整个集群的状态,把集群中其它ES节点的ip添加到本地的客户端列表中,这样我们只需要配置一个节点就可以了
put("client.transport.ignore_cluster_name",true) //忽略连接节点集群名验证
put("client.transport.ping_timeout",10) //ping一个节点的响应时间 默认5秒
使用client对象创建索引库
client.admin().indices().prepareCreate("index_hello").get();
@Test
public void createIndex() throws Exception {
//1.创建一个Setting对象,相当于一个配置信息:主要配置集群的名称
Settings setting= Settings.builder()
.put("cluster.name","my-elasticsearch")
.put("client.transport.sniff", true)
.build();
//2.创建一个客户端Client对象
//TransportClient client =new PreBuiltTransportClient(Settings.EMPTY);//不设置索引信息
TransportClient client =new PreBuiltTransportClient(setting);
client.addTransportAddress(
//我们只需要配置一个节点就可以使用了,不过为了集群的安全可以配置多个节点
new InetSocketTransportAddress(
InetAddress.getByName("127.0.0.1"),9301));
// client.addTransportAddress(
// new InetSocketTransportAddress(
// InetAddress.getByName("127.0.0.1"),9302));
// client.addTransportAddress(
// new InetSocketTransportAddress(
// InetAddress.getByName("127.0.0.1"),9303));
//3.使用client对象创建索引库
client.admin().indices().prepareCreate("index_hello")
.get();
//4.关闭client对象
client.close();
}
JSON格式的数据
在进行索引库中数据存储时我们会采用JSON格式的数据,通过Java语言有几种不同的方式来产生JSON格式的文档(document):
- 手动方式,使用原生的byte[]或者String
- 使用Map方式,Map中的数据是key.value形式的,可以自动转换成与之等价的JSON
- 使用第三方库如Jackson,将javabean对象转换为json
- 使用内置的帮助类 XContentFactory.jsonBuilder()
2. 创建映射mapping
// 创建映射
PutMappingRequest mapping = Requests.putMappingRequest("index_hello")
.type("article").source(builder);
client.admin().indices().putMapping(mapping).get();
@Test
//创建映射
public void createMapping() throws Exception{
// 创建Client连接对象
Settings settings = Settings.builder().put("cluster.name", "my-elasticsearch").build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9301));
// 添加映射
/**
* 格式:
{
"mappings": {
"article": {
"properties": {
"id": {
"type": "long",
"store": true,
"index":"not_analyzed"
},
"title": {
"type": "text",
"store": true,
"index":"analyzed",
"analyzer":"standard"
},
"content": {
"type": "text",
"store": true,
"index":"analyzed",
"analyzer":"standard"
}
}
}
}
}
*/
XContentBuilder builder = XContentFactory.jsonBuilder()
.startObject()
.startObject("article")
.startObject("properties")
.startObject("id")
.field("type", "integer")
.field("store", "yes")
.endObject()
.startObject("title")
.field("type", "string")
.field("store", "yes")
.field("analyzer", "ik_smart")
.endObject()
.startObject("content")
.field("type", "string")
.field("store", "yes")
.field("analyzer", "ik_smart")
.endObject()
.endObject()
.endObject()
.endObject();
// 创建映射
PutMappingRequest mapping = Requests.putMappingRequest("index_hello")
.type("article").source(builder);
client.admin().indices().putMapping(mapping).get();
//释放资源
client.close();
}
4. 建立文档document
4.1 建立文档(通过XContentBuilder)
@Test
//创建文档(通过XContentBuilder)
public void testAddDocument1() throws Exception{
// 创建Client连接对象
Settings settings = Settings.builder().put("cluster.name", "my-elasticsearch").build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9301));
//创建文档信息
XContentBuilder builder = XContentFactory.jsonBuilder()
.startObject()
.field("id", 1)
.field("title", "ElasticSearch是一个基于Lucene的搜索服务器")
.field("content",
"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开发的,并作为Apache许可条款下的开放源码发布,是当前流行的企业级搜索引擎。设计用于云计算中,能够达到实时搜索,稳定,可靠,快速,安装使用方便。")
.endObject();
// 建立文档对象
/**
* 参数一blog1:表示索引对象
* 参数二article:类型
* 参数三1:建立id
*/
client.prepareIndex("index_hello", "article", "1").setSource(builder).get();
//释放资源
client.close();
}
4.2 建立文档(使用Jackson转换实体)
json转换相关的pom.xml坐标
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
<version>2.8.1</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>2.8.1</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
<version>2.8.1</version>
</dependency>
1. 创建Article实体
public class Article {
private Integer id;
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;
}
}
3. 代码实现
@Test
//创建文档(通过实体转json)
public void testAddDocument2() throws Exception{
// 创建Client连接对象
Settings settings = Settings.builder().put("cluster.name", "my-elasticsearch").build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9301));
// 描述json 数据
//{id:xxx, title:xxx, content:xxx}
Article article = new Article();
article.setId(2);
article.setTitle("搜索工作其实很快乐");
article.setContent("我们希望我们的搜索解决方案要快,我们希望有一个零配置和一个完全免费的搜索模式,我们希望能够简单地使用JSON通过HTTP的索引数据,我们希望我们的搜索服务器始终可用,我们希望能够一台开始并扩展到数百,我们要实时搜索,我们要简单的多租户,我们希望建立一个云的解决方案。Elasticsearch旨在解决所有这些问题和更多的问题。");
ObjectMapper objectMapper = new ObjectMapper();
// 建立文档
client.prepareIndex("index_hello", "article", article.getId().toString())
//.setSource(objectMapper.writeValueAsString(article)).get();
// .setSource(objectMapper.writeValueAsString(article), XContentType.JSON).get();
.setSource(objectMapper.writeValueAsString(article).getBytes(), XContentType.JSON).get();
//释放资源
client.close();
}
5. 查询文档操作
对于测试查询文档,我们可以将重复的代码提取出来,方便测试
private void search(QueryBuilder queryBuilder) throws Exception{
//1、创建es客户端连接对象
Settings settings = Settings.builder().put("cluster.name", "my-elasticsearch").build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9301));
//client对象为TransportClient对象
SearchResponse response = client.prepareSearch("index_hello")
.setTypes("article")
//设置要查询的id
.setQuery(queryBuilder)
//执行查询
.get();
//取查询结果
SearchHits searchHits = response.getHits();
//取查询结果总记录数
System.out.println(searchHits.getTotalHits());
Iterator<SearchHit> hitIterator = searchHits.iterator();
while(hitIterator.hasNext()) {
SearchHit searchHit = hitIterator.next();
//打印整行数据
System.out.println(searchHit.getSourceAsString());
//取文档的属性
System.out.println("取文档属性");
Map<String,Object> document=searchHit.getSource();
System.out.println(document.get("id"));
System.out.println(document.get("title"));
System.out.println(document.get("content"));
}
client.close();
}
5.1关键词查询
@Test
//关键词查询
public void testTermQuery() throws Exception{
QueryBuilder queryBuilder=QueryBuilders.termQuery("content", "搜索");
search(queryBuilder);
}
5.2 字符串查询
//字符串查询
@Test
public void testStringQuery() throws Exception{
//QueryBuilder queryBuilder=QueryBuilders.queryStringQuery("搜索");
QueryBuilder queryBuilder=QueryBuilders.queryStringQuery("搜索").defaultField("title");
search(queryBuilder);
}
5.2 使用文档ID查询文档
//使用文档ID查询文档
@Test
public void testIdQuery() throws Exception {
QueryBuilder queryBuilder=QueryBuilders.idsQuery().addIds("1","2");
search(queryBuilder);
}
6. 查询文档分页操作
6.1 批量插入数据
//批量插入数据
@Test
//批量插入100条数据
public void testAddDocument3() throws Exception{
// 创建Client连接对象
Settings settings = Settings.builder().put("cluster.name", "my-elasticsearch").build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9300));
ObjectMapper objectMapper = new ObjectMapper();
for (int i = 1; i <= 100; i++) {
// 描述json 数据
Article article = new Article();
article.setId(i);
article.setTitle(i + "搜索工作其实很快乐");
article.setContent(i
+ "我们希望我们的搜索解决方案要快,我们希望有一个零配置和一个完全免费的搜索模式,我们希望能够简单地使用JSON通过HTTP的索引数据,我们希望我们的搜索服务器始终可用,我们希望能够一台开始并扩展到数百,我们要实时搜索,我们要简单的多租户,我们希望建立一个云的解决方案。Elasticsearch旨在解决所有这些问题和更多的问题。");
// 建立文档
client.prepareIndex("index_hello", "article", article.getId().toString())
//.setSource(objectMapper.writeValueAsString(article)).get();
.setSource(objectMapper.writeValueAsString(article).getBytes(),XContentType.JSON).get();
}
//释放资源
client.close();
}
6.2 分页查询
@Test
//分页查询
public void testQueryStringQuery() throws Exception{
// 创建Client连接对象
Settings settings = Settings.builder().put("cluster.name", "my-elasticsearch").build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9301));
// 搜索数据
SearchRequestBuilder searchRequestBuilder = client.prepareSearch("index_hello").setTypes("article")
.setQuery(QueryBuilders.matchAllQuery());//默认每页10条记录
// 查询第2页数据,每页20条
//setFrom():从第几条开始检索,默认是0。
//setSize():每页最多显示的记录数。
searchRequestBuilder.setFrom(0).setSize(5);
SearchResponse searchResponse = searchRequestBuilder.get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数,查询结果有多少对象
System.out.println("查询结果有:" + hits.getTotalHits() + "条");
Iterator<SearchHit> iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit searchHit = iterator.next(); // 每个查询对象
System.out.println(searchHit.getSourceAsString()); // 获取字符串格式打印
System.out.println("id:" + searchHit.getSource().get("id"));
System.out.println("title:" + searchHit.getSource().get("title"));
System.out.println("content:" + searchHit.getSource().get("content"));
System.out.println("-----------------------------------------");
}
//释放资源
client.close();
}
7. 高亮显示
在进行关键字搜索时,搜索出的内容中的关键字会显示不同的颜色,称之为高亮。ElasticSearch可以对查询出的内容中关键字部分进行标签和样式的设置,但是你需要告诉ElasticSearch使用什么标签对高亮关键字进行包裹。
代码实现:
@Test
//高亮查询
public void testSearch() throws Exception{
// 创建Client连接对象
Settings settings = Settings.builder().put("cluster.name", "my-elasticsearch").build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("127.0.0.1"), 9301));
// 搜索数据
SearchRequestBuilder searchRequestBuilder = client
.prepareSearch("index_hello").setTypes("article")
.setQuery(QueryBuilders.termQuery("title", "搜索"));
//设置高亮数据
HighlightBuilder hiBuilder=new HighlightBuilder();
hiBuilder.preTags("<font style='color:red'>");
hiBuilder.postTags("</font>");
hiBuilder.field("title");
searchRequestBuilder.highlighter(hiBuilder);
//获得查询结果数据
SearchResponse searchResponse = searchRequestBuilder.get();
//获取查询结果集
SearchHits searchHits = searchResponse.getHits();
System.out.println("共搜到:"+searchHits.getTotalHits()+"条结果!");
//遍历结果
for(SearchHit hit:searchHits){
System.out.println("String方式打印文档搜索内容:");
System.out.println(hit.getSourceAsString());
System.out.println("Map方式打印高亮内容");
System.out.println(hit.getHighlightFields());
System.out.println("遍历高亮集合,打印高亮片段:");
Text[] text = hit.getHighlightFields().get("title").getFragments();
for (Text str : text) {
System.out.println(str);
}
}
//释放资源
client.close();
}