ES Scroll 遍历查询

业务场景中遇到需要取一段时间范围内的数据,一开始选择深度检索,每次查询10000条,发现查询越来越慢,显然From+ size 不适用于此场景这是需要用到search_after或者Scroll

因为需要取一段时间内的全量或数据量很大时遍历结果数据所以选择了Scroll

  1. 创建ES连接

import lombok.Data;

import org.apache.http.HttpHost;

import org.apache.http.client.config.RequestConfig;

import org.elasticsearch.client.RestClient;

import org.elasticsearch.client.RestClientBuilder;

import org.elasticsearch.client.RestHighLevelClient;

import org.springframework.boot.context.properties.ConfigurationProperties;

import org.springframework.context.annotation.Bean;

import org.springframework.context.annotation.Configuration;

import java.net.InetAddress;

import java.net.UnknownHostException;

@Configuration

@ConfigurationProperties(prefix = "test.config.es")

@Data

public class ElasticlLikwsConfig {

private String ip;

private String port;

private String indexName = "cdr";

private int timeOut = 5 * 60 * 1000;

private int scrollTime = 180000;

@Bean

public RestHighLevelClient restHighLevelClient() throws UnknownHostException {

String[] ips = ip.split(",");

HttpHost[] hosts = new HttpHost[ips.length];

for (int i = 0; i < ips.length; i++) {

hosts[i] = new HttpHost(InetAddress.getByName(ips[i]), Integer.parseInt(port));

}

RestClientBuilder.RequestConfigCallback requestConfigCallback = new RestClientBuilder.RequestConfigCallback() {

@Override

public RequestConfig.Builder customizeRequestConfig(RequestConfig.Builder builder) {

return builder.setConnectTimeout(timeOut).setSocketTimeout(timeOut).setConnectionRequestTimeout(timeOut);

}

};

RestClient restTargetClient = RestClient.builder(hosts).setMaxRetryTimeoutMillis(timeOut).setRequestConfigCallback(requestConfigCallback).build();

RestHighLevelClient restHighLevelClient = new RestHighLevelClient(restTargetClient);

return restHighLevelClient;

}

}

  1. 应用

@Autowired

private RestHighLevelClient restHighLevelClient;

@Value("${es.pageSize:10000}")

private Integer pageSize;

public void esSearch() {

//转换json

BoolQueryBuilder boolQueryBuilder = new BoolQueryBuilder();

SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();

searchSourceBuilder.size(pageSize);

FetchSourceContext fetchSourceContext = new FetchSourceContext(true, EsQueryConsts.getLikwsCloums(), Strings.EMPTY_ARRAY);

searchSourceBuilder.fetchSource(fetchSourceContext);

Date beginDate = new Date();

Date endDate = new Date();

//时间

boolQueryBuilder.must(QueryBuilders.rangeQuery("begin_time").gte(beginDate.getTime()).lte(endDate.getTime()));

//语种

List<String> langs = searchParameter.getBaseParamter().getLangs();

BoolQueryBuilder builder = new BoolQueryBuilder();

for (String lang : langs) {

builder.should(QueryBuilders.termQuery(EsQueryConsts.LANG, lang));

}

boolQueryBuilder.must(builder);

//设置返回条数和排序方式

searchSourceBuilder.sort(new FieldSortBuilder("begin_time").order(SortOrder.DESC));

//索引信息

SearchRequest request = new SearchRequest(elasticlLikwsConfig.getIndexName() + "/" + TYPE);

searchSourceBuilder.timeout(new TimeValue(elasticlLikwsConfig.getTimeOut(), TimeUnit.SECONDS));

//滚动查询的Scroll

Scroll scroll = new Scroll(TimeValue.timeValueMillis(elasticlLikwsConfig.getScrollTime()));

request.source(searchSourceBuilder.query(boolQueryBuilder));

request.scroll(scroll);

logger.debug("ES查询条件:" + searchSourceBuilder.toString());

//存储scroll的list

List<String> scrollIdList = new ArrayList<>();

SearchResponse searchResponse = null;

try {

searchResponse = restLikwsHighLevelClient.search(request);

if (searchResponse.status() == RestStatus.OK) {

//第一个ScrollId(游标)

String scrollId = searchResponse.getScrollId();

//hits结果

SearchHits hits = searchResponse.getHits();

if (hits.getHits() == null || hits.getHits().length == 0) {

//TODO 业务处理

} else {

//TODO 业务处理

}

scrollIdList.add(scrollId);

try {

//滚动查询将SearchHit封装到result中

while (ArrayUtils.isNotEmpty(hits.getHits())) {

//说明滚动完了,返回结果即可

if (hits.getHits().length < pageSize) {

break;

}

//继续滚动,根据上一个游标,得到这次开始查询位置

SearchScrollRequest searchScrollRequest = new SearchScrollRequest(scrollId);

searchScrollRequest.scroll(scroll);

//结果

SearchResponse searchScrollResponse = restHighLevelClient.searchScroll(searchScrollRequest);

//定位游标

scrollId = searchScrollResponse.getScrollId();

hits = searchScrollResponse.getHits();

//TODO 业务处理

scrollIdList.add(scrollId);

}

} finally {

//清理scroll,释放资源

ClearScrollRequest clearScrollRequest = new ClearScrollRequest();

clearScrollRequest.setScrollIds(scrollIdList);

restLikwsHighLevelClient.clearScroll(clearScrollRequest);

}

}

} catch (Exception e) {

logger.error("es查询出错:{}", e);

}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

郑在努力中

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值