使用java restclient连接elasticsearch
java连接es方式有transport、rest client、java client方式。官方最新标的transport和rest client方式都已经过时了，这里用的es7 还是以rest client方式进行连接测试。java client 是es7.15之后推出的。下面开始使用High Level Java REST Client。maven依赖
-
org.elasticsearch.client:elasticsearch-rest-client
-
org.elasticsearch:elasticsearch
maven配置<properties> <elasticsearch.version>7.12.1</elasticsearch.version> </properties> <dependencies> <dependency> <groupId>org.elasticsearch</groupId> <artifactId>elasticsearch</artifactId> <version>${elasticsearch.version}</version> </dependency> <dependency> <groupId>org.elasticsearch.client</groupId> <artifactId>elasticsearch-rest-client</artifactId> <version>${elasticsearch.version}</version> </dependency> <dependency> <groupId>org.elasticsearch.client</groupId> <artifactId>elasticsearch-rest-high-level-client</artifactId> <version>${elasticsearch.version}</version> </dependency> <dependency> <groupId>commons-logging</groupId> <artifactId>commons-logging</artifactId> <version>1.2</version> </dependency> <dependency> <groupId>com.alibaba</groupId> <artifactId>fastjson</artifactId> </dependency> <dependency> <groupId>junit</groupId> <artifactId>junit</artifactId> <scope>test</scope> </dependency> <dependency> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> </dependency> </dependencies>
准备条件
还是基于上篇文章预先创建一个测试用的test索引,mapping字段信息如下：
"mappings":{
"properties": {
"title":{
"type":"text",
"analyzer": "ik_max_word",
"search_analyzer": "ik_smart"
},
"actor":{
"type": "text",
"analyzer": "ik_max_word",
"search_analyzer": "ik_smart"
},
"score":{
"type":"double"
}
}
}
创建一个数据对象
@Data
@NoArgsConstructor
@AllArgsConstructor
public class Film implements Serializable {
private String title;
private double score;
private String actor;
}
建立连接
这里使用junit进行测试，定义一个公共的RestHighLevelClient类型client连接。后续测试查询执行都基于该连接下。
//连接变量
RestHighLevelClient client;
//测试索引名称
public static String INDEX_NAME = "test";
@Before
public void init(){
client = new RestHighLevelClient(RestClient.builder(
//可以放置多个es地址
new HttpHost("localhost",9200,"http"))
);
索引操作就不练习了，一般在可视化工具里初始化好，这里只练习查询操作。
添加文档 (IndexRequest)
@Test
public void index1() throws IOException {
//指定索引 和文档ID
IndexRequest request = new IndexRequest(INDEX_NAME).id("1");
Film f = new Film("大话西游",9.5,"周星驰，吴孟达，朱茵");
request.source(JSON.toJSONString(f), XContentType.JSON);
IndexResponse response = client.index(request, RequestOptions.DEFAULT);
//执行结果 存在返回created，不存在updated
System.out.println(response.getResult().getLowercase());
RestStatus status = response.status();
Assert.assertEquals(200,status.getStatus());
}
按ID查询文档（GetRequest）
@Test
public void get1() throws IOException {
//指定索引和id
GetRequest request = new GetRequest(INDEX_NAME,"1");
// request.version(11);
GetResponse response = client.get(request, RequestOptions.DEFAULT);
//文档是否存在
if(response.isExists()){
//输出source内容
System.out.println(response.getSourceAsMap());
}else{
System.out.println("not exists");
}
}
/**
输出：{actor=周星驰，吴孟达，朱茵, score=9.5, title=大话西游}
*/
@Test
public void get2() throws IOException {
GetRequest request = new GetRequest(INDEX_NAME,"1");
//只获取指定的field
FetchSourceContext fetchSource = new FetchSourceContext(true,new String[]{"title"},null);
request.fetchSourceContext(fetchSource);
GetResponse response = client.get(request, RequestOptions.DEFAULT);
if(response.isExists()){
System.out.println(response.getSourceAsMap());
}else{
System.out.println("not exists");
}
}
/**
输出：{title=大话西游}
*/
@Test
public void exists() throws IOException {
GetRequest request = new GetRequest(INDEX_NAME,"11");
//判断是否存在
boolean exists = client.exists(request, RequestOptions.DEFAULT);
System.out.println(exists);
}
更新文档（UpdateRequest）
UpdateRequest request = new UpdateRequest(INDEX_NAME,"1");
// key value形式
request.doc("score",9.6,"title","大话西游1");
//json map
Map<String, Object> jsonMap = new HashMap<>();
jsonMap.put("score", 9.7);
jsonMap.put("title", "大话西游2");
request.doc(jsonMap);
UpdateResponse response = client.update(request, RequestOptions.DEFAULT);
Assert.assertEquals(200,response.status().getStatus());
删除文档（DeleteRequest）
DeleteRequest request = new DeleteRequest(INDEX_NAME,"1");
DeleteResponse response = client.delete(request, RequestOptions.DEFAULT);
Assert.assertEquals(200,response.status().getStatus());
按条件删除（DeleteByQueryRequest）
DeleteByQueryRequest request = new DeleteByQueryRequest(INDEX_NAME);
request.setQuery(new TermQueryBuilder("title","大话"));
BulkByScrollResponse response = client.deleteByQuery(request, RequestOptions.DEFAULT);
System.out.println(response.getStatus().getDeleted());
bulk批量操作（BulkRequest）
就是把多个indexrequest、updaterequest、deleterequest放到bulkrequest
BulkRequest request = new BulkRequest();
request.add(new IndexRequest(INDEX_NAME).id("1").source(JSON.toJSONString(new Film("大话西游1",9.3,"周星驰")),XContentType.JSON))
.add(new IndexRequest(INDEX_NAME).id("2").source(JSON.toJSONString(new Film("大话西游2",9.5,"周星驰")),XContentType.JSON))
.add(new DeleteRequest(INDEX_NAME).id("3"));
BulkResponse responses = client.bulk(request, RequestOptions.DEFAULT);
//是否有执行失败
System.out.println(responses.hasFailures());
responses.forEach(bulkItemResponse -> {
System.out.println(bulkItemResponse.getOpType().name()+"-"+ bulkItemResponse.getResponse().getResult().getLowercase() +"-"+bulkItemResponse.getResponse().status().getStatus());
//按操作类型转执行结果
switch (bulkItemResponse.getOpType()){
case INDEX:
case CREATE:
IndexResponse indexResp = bulkItemResponse.getResponse();
break;
case DELETE:
DeleteResponse delResp = bulkItemResponse.getResponse();
break;
case UPDATE:
UpdateResponse updateResp = bulkItemResponse.getResponse();
}
});
检索（SearchRequest）
检索使用一个公共的SearchRequest请求。可以设置不同的querybuilder进行不同的条件查询。
1、matchAllQuery
SearchRequest request = new SearchRequest(INDEX_NAME);
SearchSourceBuilder builder = new SearchSourceBuilder();
builder.query(QueryBuilders.matchAllQuery());
request.source(builder);
SearchResponse response = client.search(request, RequestOptions.DEFAULT);
System.out.println(response.status().getStatus());
response.getHits().forEach(hit ->{
System.out.println(hit.getSourceAsMap());
});
/**
输出：这是全量测试数据，下面查询输出都针对这个数据基础检索
4:{actor=韩庚/唐嫣/吴京/莫文蔚, score=4.1, title=大话西游3}
5:{actor=六小龄童/迟重瑞/马德华/徐少华, score=9.7, title=西游记}
6:{actor=周星驰/元秋/元华/黄圣依/梁小龙/陈国坤, score=8.8, title=功夫}
7:{actor=周星驰/袁咏仪/罗家英/陈宝莲, score=8.7, title=国产凌凌漆}
8:{actor=周星驰, score=8.7, title=西游大话}
1:{actor=周星驰，吴孟达，朱茵, score=9.5, title=大话西游}
11:{actor=大话西游前传，周星驰, score=7.5, title=西游篇之1}
9:{actor=黄渤，文章, score=7.5, title=大话之西游}
2:{actor=黄渤，文章, score=8.7, title=西游降魔篇}
*/
2、TermQuery
SearchRequest request = new SearchRequest(INDEX_NAME);
SearchSourceBuilder builder = new SearchSourceBuilder();
//Term Query 精确匹配，不会再分词，就是一个固定token去索引里匹配
builder.query(new TermQueryBuilder("actor","周星驰"));
//设置查询条数 从第几条到开始取多少条 分页
builder.from(0).size(5);
//设置查询超时时间
builder.timeout(new TimeValue(60, TimeUnit.SECONDS));
request.source(builder);
SearchResponse response = client.search(request, RequestOptions.DEFAULT);
System.out.println(response.status().getStatus());
response.getHits().forEach(hit ->{
System.out.println(hit.getSourceAsMap());
});
/**
输出：
{actor=周星驰, score=8.7, title=西游大话}
{actor=周星驰，吴孟达，朱茵, score=9.5, title=大话西游}
{actor=周星驰/袁咏仪/罗家英/陈宝莲, score=8.7, title=国产凌凌漆}
{actor=大话西游前传，周星驰, score=7.5, title=西游篇之1}
{actor=周星驰/元秋/元华/黄圣依/梁小龙/陈国坤, score=8.8, title=功夫}
*/
3、matchQuery
SearchRequest request = new SearchRequest(INDEX_NAME);
SearchSourceBuilder builder = new SearchSourceBuilder();
//match query 分词匹配 operator指定多个分词匹配方式
builder.query(QueryBuilders.matchQuery("title","大话西游").operator(Operator.OR));
/**
* 设置排序
* ScoreSortBuilder 设置评分排序
* FieldSortBuilder 设置某个字段排序
* 默认按score降序，id升序
*/
builder.sort(new FieldSortBuilder("score").order(SortOrder.DESC));
//builder.trackTotalHits(true);
builder.size(2);
//设置返回字段和不返回的字段
builder.fetchSource(new String[]{"title","score"},null);
request.source(builder);
SearchResponse response = client.search(request, RequestOptions.DEFAULT);
System.out.println(response.status().getStatus());
//命中总条数 可以当分页总条数。好像这个又有最大限制，后面再研究
System.out.println(response.getHits().getTotalHits().value);
response.getHits().forEach(hit ->{
System.out.println(hit.getScore()+":"+hit.getSourceAsMap());
});
/** 因为加了sort，score没有值
输出：
NaN:{score=9.5, title=大话西游}
NaN:{score=4.1, title=大话西游3}
*/
这里 检索大话西游 为什么西游记没有查出呢。因为title字段定义的时候是这样
"title":{
"type":"text",
"analyzer": "ik_max_word",
"search_analyzer": "ik_smart"
}
analyzer 指定索引创建时候使用ik_max_word，search_analyzer指定检索的时候使用ik_smart分词器。 _analyze执行下会发现ik_smart分词器对 大话西游的分词结果只有一个{大话西游 }词条。所以无法检索出西游记。ik_max_word分词结果是{大话西游、大话、西游}三个词条。
4、multiMatchQuery
多列匹配，检索关键字去匹配多个列字段
SearchRequest request = new SearchRequest(INDEX_NAME);
SearchSourceBuilder builder = new SearchSourceBuilder();
/**
* multiMatchQuery:
* 关键字匹配多个字段。
* 这里 “大话西游” 去匹配 title和actor两个字段
*/
MultiMatchQueryBuilder multiMatchQuery = QueryBuilders.multiMatchQuery("大话西游", "title", "actor");
builder.query(multiMatchQuery);
request.source(builder);
SearchResponse response = client.search(request, RequestOptions.DEFAULT);
System.out.println(response.status().getStatus());
//命中总条数
System.out.println(response.getHits().getTotalHits().value);
response.getHits().forEach(hit ->{
System.out.println(hit.getScore()+":"+hit.getSourceAsMap());
});
/**
输出：actor和title包含 大话西游的都可以查出
1.9787104:{actor=大话西游前传，周星驰, score=7.5, title=西游篇之1}
1.1451323:{actor=周星驰，吴孟达，朱茵, score=9.5, title=大话西游}
1.0077165:{actor=韩庚/唐嫣/吴京/莫文蔚, score=4.1, title=大话西游3}
*/
5、boolQuery
多条件组合查询
SearchRequest request = new SearchRequest(INDEX_NAME);
SearchSourceBuilder builder = new SearchSourceBuilder();
/**
* boolQuery:
*
* must：文档中一定包含的内容
* mustNot：一定不包含内容
* filter：满足其它检索条件基础上添加过滤条件
* should：不一定包含的查询条件
* minimumShouldMatch：should条件最小命中数
*/
BoolQueryBuilder boolQuery = QueryBuilders.boolQuery();
boolQuery.must(QueryBuilders.matchQuery("title","大话西游"))
.filter(QueryBuilders.rangeQuery("score").gte(8d))
.should(QueryBuilders.matchQuery("actor","周星驰"))
.minimumShouldMatch(1);
builder.query(boolQuery);
request.source(builder);
SearchResponse response = client.search(request, RequestOptions.DEFAULT);
System.out.println(response.status().getStatus());
//命中总条数
System.out.println(response.getHits().getTotalHits().value);
response.getHits().forEach(hit ->{
System.out.println(hit.getScore()+":"+hit.getSourceAsMap());
});
/**
输出：
1.7510496:{actor=周星驰，吴孟达，朱茵, score=9.5, title=大话西游}
*/
6、matchPhraseQuery
SearchRequest request = new SearchRequest(INDEX_NAME);
SearchSourceBuilder builder = new SearchSourceBuilder();
/**
* matchPhraseQuery:
* 分词的每个词条都要匹配，并且词条连续出现
* 西游之大话，西游大话都匹配不到
*/
MatchPhraseQueryBuilder matchPhraseQuery = QueryBuilders.matchPhraseQuery("title", "大话西游");
builder.query(matchPhraseQuery);
request.source(builder);
SearchResponse response = client.search(request, RequestOptions.DEFAULT);
System.out.println(response.status().getStatus());
//命中总条数
System.out.println(response.getHits().getTotalHits().value);
response.getHits().forEach(hit ->{
System.out.println(hit.getScore()+":"+hit.getSourceAsMap());
});
/**
输出：
1.1451323:{actor=周星驰，吴孟达，朱茵, score=9.5, title=大话西游}
1.0077165:{actor=韩庚/唐嫣/吴京/莫文蔚, score=4.1, title=大话西游3}
*/
7、matchquery 高亮显示
命中关键词添加标签高亮显示
SearchRequest request = new SearchRequest(INDEX_NAME);
SearchSourceBuilder builder = new SearchSourceBuilder();
//match query 分词匹配 operator指定多个分词匹配方式
builder.query(QueryBuilders.matchQuery("title","大话西游").operator(Operator.OR));
HighlightBuilder highlightBuilder = new HighlightBuilder();
highlightBuilder.highlighterType("unified")
//设置标签
.preTags("<font color='red'>").postTags("</font>")
.field("title");
builder.highlighter(highlightBuilder);
request.source(builder);
SearchResponse response = client.search(request, RequestOptions.DEFAULT);
System.out.println(response.status().getStatus());
response.getHits().forEach(hit ->{
// 命中信息
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
//System.out.println(highlightFields);
//替换元素sourcemap数据为加标签后
highlightFields.forEach( (s, highlightField) -> {
String text = "";
for (Text fragment : highlightField.fragments()) {
text += fragment;
}
hit.getSourceAsMap().put(s,text);
});
System.out.println(hit.getScore()+":"+hit.getSourceAsMap());
});
/**
输出：匹配关键词 大话西游 添加了font标签
1.1451323:{actor=周星驰，吴孟达，朱茵, score=9.5, title=<font color='red'>大话西游</font>}
1.0077165:{actor=韩庚/唐嫣/吴京/莫文蔚, score=4.1, title=<font color='red'>大话西游</font>3}
*/
还有一些查询，这里就测试到这里，更多参考官方文档
https://www.elastic.co/guide/en/elasticsearch/client/java-rest/7.17/java-rest-high.html
