ElasticSearch High Level REST API（2）搜索查询

基本搜索

在search搜索中大部分的搜索条件添加都可通过设置SearchSourceBuilder来实现。如下为一段带有分页的简单搜索查询示例

@GetMapping("/search/base")
public String searchBase() {
    SearchRequest searchRequest = new SearchRequest();
    SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
    sourceBuilder.query(QueryBuilders.termQuery("name.keyword", "Joe.Ye"));
    sourceBuilder.from(0);
    sourceBuilder.size(5);
    sourceBuilder.timeout(new TimeValue(60, TimeUnit.SECONDS)); //设置一个可选的超时，控制允许搜索的时间
    searchRequest.source(sourceBuilder);

    try {
        SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
        Long total = searchResponse.getHits().getTotalHits().value; //获取匹配的总数量
        System.out.println("总记录数: " + total);
        for (SearchHit hit : searchResponse.getHits().getHits()) {
            float score = hit.getScore(); //获得分数，即匹配度
            String source = hit.getSourceAsString();
            log.info("score: {}, source: {}", score, source);
        }
        //client.close();
        return JSON.toJSONString(searchResponse);
    } catch (IOException e) {
        e.printStackTrace();
    }
    return "";
}

Status: 200
总记录数: 4
score: 0.6931472, source: {"age":28,"height":175.2,"name":"Joe.Ye"}
score: 0.5389965, source: {"name":"Joe.Ye","email":"yezhou@yezhou.org","homepage":"http://www.appblog.cn"}
score: 0.5389965, source: {"name":"Joe.Ye","age":28,"homepage":"http://www.appblog.cn"}
score: 0.5389965, source: {"name":"Joe.Ye","email":"yezhou@yezhou.org","homepage":"http://www.appblog.cn"}

search查询的返回值为SearchResponse，调用SearchResponse的getHits()方法会获取SearchHits对象，然后再通过SearchHits的getHits()方法即返回一个SearchHit[]数组。

遍历SearchHit[]数组获取每一个对象，通过hit.getScore()可获取分数，即搜索匹配度。通过hit.getSourceAsString()可得到对象的json字符串。

备注：在上述查询中用到了termQuery查询，ES还提供了matchQuery查询，不同的查询需求中需要选择不同的查询，在此需要了解这两个查询的区别：

termQuery: term为不使用分词器查找，类似精确查找。
matchQuery: mactch为使用分词器进行查找，会查询到一些近似匹配的内容。

SearchHit使用汇总

要获取返回的内容，需要获得SearchHit，下面总结下SearchHit的一些使用：

SearchHits hits = searchResponse.getHits();
long totalHits = hits.getTotalHits().value; //查询命中总数
float maxScore = hits.getMaxScore(); //查询命中的最高分数
//SearchHits遍历
SearchHit[] searchHits = hits.getHits();
for (SearchHit hit : searchHits) {

}
//通过SearchHit还可以获取返回数据的索引、类型、docId和得分等基本信息
String index = hit.getIndex(); 
String type = hit.getType();
String id = hit.getId();
float score = hit.getScore();
//hit还可以以Json字符串或Map的形式返回数据
String sourceAsString = hit.getSourceAsString();
Map<String, Object> sourceAsMap = hit.getSourceAsMap();
String documentTitle = (String) sourceAsMap.get("title");
List<Object> users = (List<Object>) sourceAsMap.get("user");
Map<String, Object> innerObject = (Map<String, Object>) sourceAsMap.get("innerObject");

指定排序

排序有两种排序方式，第一通过ScoreSortBuilder实现按分数（即匹配度）排序；第二种方式通过指定字段来排序，如通过_uid字段排序

sourceBuilder.sort(new ScoreSortBuilder().order(SortOrder.DESC)); //按分数（即匹配度）排序
sourceBuilder.sort(new FieldSortBuilder("_uid").order(SortOrder.ASC)); //通过指定字段来排序

关闭检索

有时我们只想要知道到底匹配了多少条记录，但不关系具体每条记录的内容，这个时候我们可以选择关闭检索，不去查询每天数据的内容，可通过如下方式实现：

sourceBuilder.fetchSource(false);

关闭检索后，只返回总记录数，遍历输出每条数据均为 null

另外还可以通过SourceBuilder接受一个或多个数组，来控制需要返回哪些字段，排除哪些字段。具体实现如下，第一个数组参数为要接受的字段，第二个数组参数为要排除的内容：

String[] includeFields = new String[] {"title", "user", "innerObject.*"};
String[] excludeFields = new String[] {"_type"};
sourceBuilder.fetchSource(includeFields, excludeFields);

高亮显示

通过向SearchSourceBuilder添加HighlightBuilder示例可添加高亮显示功能

SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
HighlightBuilder highlightBuilder = new HighlightBuilder();
HighlightBuilder.Field highlightTitle = new HighlightBuilder.Field("title");
highlightTitle.highlighterType("unified"); //字段高亮显示类型，默认用标签包裹高亮字词
highlightBuilder.field(highlightTitle);
searchSourceBuilder.highlighter(highlightBuilder);

以上只是在查询中加入高亮显示的功能，那么我们如何在查询结果中获取呢，通过SearchHit的getHighlightFields()方法获取我们需要关键内容：

SearchHits hits = searchResponse.getHits();
for (SearchHit hit : hits.getHits()) {
    Map highlightFields = hit.getHighlightFields();
    HighlightField highlight = highlightFields.get("title");
    Text[] fragments = highlight.fragments();
    String fragmentString = fragments[0].string();
}

聚合操作

获取平均值聚合示例，最大值、最小值、求和类似

@GetMapping("search/aggregation")
public void aggregation() {
    RestHighLevelClient client = elasticClient.getRestHighLevelClient();
    SearchRequest searchRequest = new SearchRequest();
    SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
    TermsAggregationBuilder aggregation = AggregationBuilders.terms("by_sex")
            .field("sex.keyword");  //若不加keyword，在text类型上进行聚合操作时会报错
    aggregation.subAggregation(AggregationBuilders.avg("avg_age")
            .field("age"));  //avg_age 为子聚合名称，名称可随意
    searchSourceBuilder.aggregation(aggregation);
    searchRequest.source(searchSourceBuilder);
    SearchResponse searchResponse = null;
    try {
        searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
    } catch (IOException e) {
        e.printStackTrace();
    }
    Aggregations aggregations = searchResponse.getAggregations();
    Terms bySexAggregation = aggregations.get("by_sex");
    Terms.Bucket elasticBucket = bySexAggregation.getBucketByKey("女性");
    Avg averageAge = elasticBucket.getAggregations().get("avg_age");
    double avg = averageAge.getValue();
    System.out.println("女性平均年龄：" + avg);
}

Stats统计

@GetMapping("search/stats")
public void stats() {
    RestHighLevelClient client = elasticClient.getRestHighLevelClient();
    SearchRequest searchRequest = new SearchRequest();
    SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
    TermsAggregationBuilder aggregation = AggregationBuilders.terms("by_sex")
            .field("sex.keyword");  //by_sex为聚合名称，名称可随意
    aggregation.subAggregation(AggregationBuilders.stats("stat_age")
            .field("age"));  //avg_age 为子聚合名称，名称可随意
    searchSourceBuilder.aggregation(aggregation);
    searchRequest.source(searchSourceBuilder);
    SearchResponse searchResponse = null;
    try {
        searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
    } catch (IOException e) {
        e.printStackTrace();
    }
    Aggregations aggregations = searchResponse.getAggregations();
    Terms bySexAggregation = aggregations.get("by_sex");
    List<? extends Terms.Bucket> buckets = bySexAggregation.getBuckets();
    for (Terms.Bucket bucket : buckets) {
        Stats statAge = bucket.getAggregations().get("stat_age");
        System.out.println(bucket.getKey()); //获取分组名称
        System.out.println("平均值：" + statAge.getAvg());
        System.out.println("总数：" + statAge.getSum());
        System.out.println("最大值：" + statAge.getMaxAsString());
        System.out.println("最小值：" + statAge.getMin());
    }
}