本人现在使用的是elasticsearch 5.2.1的,服务器IP为192.168.5.182.所以在Java API和jar包中会有所不同.
常用的restful API如下:
http://192.168.5.182:9200/_cat/health?v 健康检查
http://192.168.5.182:9200/_cat/indices?v 查看索引
PUT http://192.168.5.182:9200/test_index?pretty 添加索引
DELETE http://192.168.5.182:9200/test_index 删除索引
PUT http://192.168.5.182:9200/ecommerce/product/1
BODY {
"name":"zhonghua yagao",
"desc":"caoben zhiwu",
"price":40,
"producer":"zhonghua producer",
"tags":["qingxin"]} 为索引添加数据,ecommerce索引,product type,1 ID
GET http://192.168.5.182:9200/ecommerce/product/1 查询数据
PUT http://192.168.5.182:9200/ecommerce/product/1
BODY {
"name":"jiaqiangban zhonghua yagao",
"desc":"caoben zhiwu",
"price":40,
"producer":"zhonghua producer",
"tags":["qingxin"]} 更新索引数据,方式一,必须带上所有数据
POST http://192.168.5.182:9200/ecommerce/product/1/_update
BODY {
"doc": {
"name":"gaolujie yagao"
}} 更新索引数据,方式二
DELETE http://192.168.5.182:9200/ecommerce/product/1 删除索引数据
GET http://192.168.5.182:9200/ecommerce/product/_search 搜索所有
GET http://192.168.5.182:9200/ecommerce/product/_search?q=name:yagao&sort=price:desc
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"query":{"match_all":{}}
}'
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{"query":{ "match":{ "name":"yagao" } }, "sort":[ {"price":"desc"} ]}' 排序查询
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"query":{"match_all":{}},
"from":1,
"size":1
}' 分页查询
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"query":{
"match_all":{}},
"_source":["name","price"]
}' 只查询指定的字段
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"query":{
"bool":{ "must":{ "match":{ "name":"yagao" } }, "filter":{ "range":{ "price":{ "gt":25 } } } }}
}' 查询yagao的price范围,大于25
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"query":{"match":{ "producer":"yagao producer" }}
}' 全文检索
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"query":{
"match_phrase":{
"producer":"yagao producer"
}}
}' 短语搜索
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"query":{ "match":{ "producer":"producer" } }, "highlight":{ "fields":{ "producer":{} } }}' 高亮显示
PUT http://192.168.5.182:9200/ecommerce/_mapping/product
BODY {
"properties":{
"tags":{
"type":"text",
"fielddata":true
}
}} 将文本field的fielddata属性设置为true
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"aggs":{ "group_by_tags":{ "terms":{ "field":"tags" } } }}' 对tags聚合,会显示明细
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{ "size":0,
"aggs":{
"group_by_tags":{
"terms":{
"field":"tags"
}
}
}}' 对tags聚合,不显示明细,只显示聚合
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"size":0,
"query":{"match":{ "name":"yagao" }},
"aggs":{"group_by_tags":{ "terms":{ "field":"tags" } }}
}' 搜索包含条件的聚合
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{"size":0, "aggs":{ "group_by_tags":{ "terms":{ "field":"tags" }, "aggs":{ "avg_price":{ "avg":{ "field":"price" } } } } }}' 聚合计算平均值
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"size":0, "aggs":{ "group_by_tags":{ "terms":{ "field":"tags", "order":{ "avg_price":"desc" } }, "aggs":{ "avg_price":{ "avg":{ "field":"price" } } } } }}' 聚合后降序排序
curl -XGET 'http://192.168.5.182:9200/ecommerce/product/_search' -d'
{
"size":0,
"aggs":{
"group_by_price":{
"range":{
"field":"price",
"ranges":[
{
"from":0,
"to":20
},
{
"from":20,
"to":40
},
{
"from":40,
"to":60
}
]
},
"aggs":{
"group_by_tags":{
"terms":{
"field":"tags"
},
"aggs":{
"average_price":{
"avg":{
"field":"price"
}
}
}
}
}
}}
}' 按照价格区间分组后再聚合tags平均价格
PUT http://192.168.5.182:9200/company
BODY {
"mappings": {
"employee": {
"properties": {
"age": {
"type": "long"
},
"country": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
},
"fielddata":true
},
"join_date": {
"type": "date"
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"position": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"salary": {
"type": "long"
}
}
}
}} 给country建立正排索引
在Java API中,我们需要先找到相应的jar包,maven中的配置如下(开始之前请先执行上面的给country建立正排索引的restful API)
org.elasticsearch.client
transport
5.2.1
5.2.1中只需要配这一个就可以了,当然不同的版本配置的都不同,高版本的需要配
org.elasticsearch
elasticsearch
我们依然在resources文件中做如下配置(注意restful API中使用的是9200端口,而Java API使用的是9300端口)
elasticsearch:
clusterName: aubin-cluster
clusterNodes: 192.168.5.182:9300
配置类如下
@Getter
@Setter
@Configuration
@ConfigurationProperties(prefix = "elasticsearch")
public class ElasticSearchConfig {
private String clusterName;
private String clusterNodes;
/**
* 使用elasticsearch实现类时才触发
*
* @return
*/@Bean
public TransportClient transportClient() {
// 设置集群名字
Settings settings = Settings.builder().put("cluster.name", this.clusterName).build();
TransportClient client = new PreBuiltTransportClient(settings);
try {
// 读取的ip列表是以逗号分隔的
for (String clusterNode : this.clusterNodes.split(",")) {
String ip = clusterNode.split(":")[0];
String port = clusterNode.split(":")[1];
client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName(ip), Integer.parseInt(port)));
}
} catch (UnknownHostException e) {
e.printStackTrace();
}
return client;}
}
在5.2.1中使用的是InetSocketTransportAddress,这是一个具体的类,而在高版本中此处为TransportAddress,这是一个接口.
我们做一个数据类
@Component
public class DataEs {
@Autowired
private TransportClient transportClient;
/**
* 添加原始数据
* @throws IOException
*/
@PostConstruct
private void init() throws IOException {
transportClient.prepareIndex("company","employee","1").setSource(XContentFactory.jsonBuilder().startObject()
.field("name","jack")
.field("age",27)
.field("position","technique software")
.field("country","China")
.field("join_date","2018-01-01")
.field("salary",10000)
.endObject()).get();
transportClient.prepareIndex("company","employee","2").setSource(XContentFactory.jsonBuilder().startObject()
.field("name","marry")
.field("age",35)
.field("position","technique manager")
.field("country","China")
.field("join_date","2018-01-01")
.field("salary",12000)
.endObject()).get();
transportClient.prepareIndex("company","employee","3").setSource(XContentFactory.jsonBuilder().startObject()
.field("name","tom")
.field("age",32)
.field("position","senior technique software")
.field("country","China")
.field("join_date","2017-01-01")
.field("salary",11000)
.endObject()).get();
transportClient.prepareIndex("company","employee","4").setSource(XContentFactory.jsonBuilder().startObject()
.field("name","jen")
.field("age",25)
.field("position","junior finance")
.field("country","USA")
.field("join_date","2017-01-01")
.field("salary",7000)
.endObject()).get();
transportClient.prepareIndex("company","employee","5").setSource(XContentFactory.jsonBuilder().startObject()
.field("name","mike")
.field("age",37)
.field("position","finance manager")
.field("country","USA")
.field("join_date","2016-01-01")
.field("salary",15000)
.endObject()).get();
}
/**
* 员工搜索应用程序
* 搜索职位中包含technique的员工
* 同时要求age在30到40岁之间
* 分页查询,查找第一页
*/
public void executeSearch() {
SearchResponse searchResponse = transportClient.prepareSearch("company")
.setTypes("employee")
.setQuery(QueryBuilders.matchQuery("position", "technique"))
.setPostFilter(QueryBuilders.rangeQuery("age").from(30).to(40))
.setFrom(0).setSize(1)
.get();
SearchHit[] hits = searchResponse.getHits().getHits();
for (int i = 0;i < hits.length;i++) {
System.out.println(hits[i].getSourceAsString());
}
}
/**
* 员工聚合分析应用程序
* 首先按照country国家来进行分组
* 然后在每个country分组内,再按照入职年限进行分组
* 最后计算每个分组内的平均薪资
*/
public void executeAggregation() {
SearchResponse searchResponse = transportClient.prepareSearch("company")
.addAggregation(AggregationBuilders.terms("group_by_country").field("country")
.subAggregation(AggregationBuilders.dateHistogram("group_by_join_date")
.field("join_date").dateHistogramInterval(DateHistogramInterval.YEAR)
.subAggregation(AggregationBuilders.avg("avg_salary").field("salary"))))
.execute().actionGet();
Map<String,Aggregation> aggrMap = searchResponse.getAggregations().asMap();
StringTerms groupByCountry = (StringTerms) aggrMap.get("group_by_country");
Iterator<StringTerms.Bucket> groupByCountryBucketIterator = groupByCountry.getBuckets().iterator();
while (groupByCountryBucketIterator.hasNext()) {
StringTerms.Bucket groupByCountryBucket = groupByCountryBucketIterator.next();
System.out.println(groupByCountryBucket.getKey() + ":" + groupByCountryBucket.getDocCount());
Histogram groupByJoinDate = (Histogram) groupByCountryBucket.getAggregations().asMap().get("group_by_join_date");
Iterator<? extends Histogram.Bucket> groupByJoinDateIterator = groupByJoinDate.getBuckets().iterator();
while (groupByJoinDateIterator.hasNext()) {
Histogram.Bucket groupByJoinDateBucket = groupByJoinDateIterator.next();
System.out.println(groupByJoinDateBucket.getKey() + ":" + groupByJoinDateBucket.getDocCount());
Avg avg = (Avg) groupByJoinDateBucket.getAggregations().asMap().get("avg_salary");
System.out.println(avg.getValue());
}
}
}
public void close() {
transportClient.close();
}}
在主程序中调用如下(一般我们可以先不执行搜索操作,先注入数据,因为elasticsearch本身有一个秒级写读的问题,如果数据写入,得需要1秒的时间才能读取出来)
@SpringBootApplication
public class EsApplication {
public static void main(String[] args) {
ApplicationContext applicationContext = SpringApplication.run(EsApplication.class, args);
DataEs dataEs = (DataEs) applicationContext.getBean(DataEs.class);
dataEs.executeSearch();
dataEs.executeAggregation();
dataEs.close();}
}
