1. 数据构造
索引2个文档到 hotel 索引中：
PUT /hotel/_doc/1
{
"title": "文雅酒店",
"city": "青岛",
"price": 556,
"create_time": "20200418120000",
"amenities": "浴池,普通停车场/充电停车场",
"full_room": false,
"location": {
"lat": 36.083078,
"lon": 120.37566
},
"praise": 10
}
PUT /hotel/_doc/2
{
"title": "金都嘉怡假日酒店",
"city": "北京",
"price": 337,
"create_time": "20210315200000",
"amenities": "wifi,充电停车场/可升降停车场",
"full_room": false,
"location": {
"lat": 39.915153,
"lon": 116.403
},
"praise": 60
}
PUT /hotel/_doc/1
{
"title": "文雅酒店",
"city": "青岛",
"price": 556,
"create_time": "20200418120000",
"amenities": "浴池,普通停车场/充电停车场",
"full_room": false,
"location": {
"lat": 36.083078,
"lon": 120.37566
},
"praise": 10
}
PUT /hotel/_doc/2
{
"title": "金都嘉怡假日酒店",
"city": "北京",
"price": 337,
"create_time": "20210315200000",
"amenities": "wifi,充电停车场/可升降停车场",
"full_room": false,
"location": {
"lat": 39.915153,
"lon": 116.403
},
"praise": 60
}2. ElasticSearch 查询集群中所有索引中的所有文档
GET /hotel/_search
{
"took" : 499,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 2,
"relation" : "eq"
},
"max_score" : 1.0,
"hits" : [
{
"_index" : "hotel",
"_type" : "_doc",
"_id" : "2",
"_score" : 1.0,
"_source" : {
"title" : "金都嘉怡假日酒店",
"city" : "北京",
"price" : 337,
"create_time" : "20210315200000",
"amenities" : "wifi,充电停车场/可升降停车场",
"full_room" : false,
"location" : {
"lat" : 39.915153,
"lon" : 116.403
},
"praise" : 60
}
},
{
"_index" : "hotel",
"_type" : "_doc",
"_id" : "1",
"_score" : 1.0,
"_source" : {
"title" : "文雅酒店",
"city" : "青岛",
"price" : 556,
"create_time" : "20200418120000",
"amenities" : "浴池,普通停车场/充电停车场",
"full_room" : false,
"location" : {
"lat" : 36.083078,
"lon" : 120.37566
},
"praise" : 10
}
}
]
}
}3. ElasticSearch 搜索结果字段解析
1. took 搜索请求耗费了多少毫秒
took 值告诉我们执行整个搜索请求耗费了多少毫秒。
2. shards 查询中参与分片的总数
_shards 部分告诉我们在查询中参与分片的总数，以及这些分片成功了多少个失败了多少个。正常情况下我们不希望分片失败，但是分片失败是可能发生的。如果我们遭遇到一种灾难级别的故障，在这个故障中丢失了相同分片的原始数据和副本，那么对这个分片将没有可用副本来对搜索请求作出响应。假若这样，Elasticsearch 将报告这个分片是失败的，但是会继续返回剩余分片的结果。
3. timed_out 查询是否超时
timed_out 值告诉我们查询是否超时。默认情况下，搜索请求不会超时。
4. hits 表示搜索结果
返回结果中最重要的部分是 hits ，它包含 total 字段来表示匹配到的文档总数，并且一个 hits 数组包含所查询结果的前十个文档。在解析搜索结果时，我们通常需要关注以下几个字段：
hits.total.value：匹配的文档总数。hits.max_score：与查询所匹配文档的_score的最大值。hits.hits：匹配的文档列表。hits.hits._source：匹配的文档的原始数据。hits.hits._score：匹配的文档的分数。它衡量了文档与查询的匹配程度,默认情况下，首先返回最相关的文档结果，就是说，返回的文档是按照score 降序排列的。hits.hits.highlight：匹配的文档的高亮显示信息。
4. SpringBoot 整合ElasticSearch获取搜索结果
@Slf4j
@Service
public class ElasticSearchImpl {
@Autowired
private RestHighLevelClient restHighLevelClient;
public void searchUser() throws IOException {
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
SearchRequest searchRequest = new SearchRequest(new String[]{"hotel"},searchSourceBuilder);
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
TimeValue took = searchResponse.getTook();
System.out.println("took = " + took);
// 搜索结果
SearchHits searchHits = searchResponse.getHits();
// hits.total.value:匹配的文档总数
TotalHits totalHits = searchHits.getTotalHits();
long value = totalHits.value;
System.out.println("value = " + value);
// hits.max_score:与查询所匹配文档的_score的最大值
float maxScore = searchHits.getMaxScore();
System.out.println("maxScore = " + maxScore);
// hits.hits:匹配的文档列表
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
// hits.hits._source：匹配的文档的原始数据
String sourceAsString = hit.getSourceAsString();
System.out.println("sourceAsString = " + sourceAsString);
// hits.hits._id：匹配的文档的id
String id = hit.getId();
System.out.println("id = " + id);
Map<String, DocumentField> fields = hit.getFields();
System.out.println("fields = " + fields);
String index = hit.getIndex();
System.out.println("index = " + index);
float score = hit.getScore();
System.out.println("score = " + score);
}
System.out.println(searchResponse);
}
}
@Slf4j
@Service
public class ElasticSearchImpl {
@Autowired
private RestHighLevelClient restHighLevelClient;
public void searchUser() throws IOException {
SearchSourceBuilder searchSourceBuilder = new SearchSourceBuilder();
SearchRequest searchRequest = new SearchRequest(new String[]{"hotel"},searchSourceBuilder);
SearchResponse searchResponse = restHighLevelClient.search(searchRequest, RequestOptions.DEFAULT);
TimeValue took = searchResponse.getTook();
System.out.println("took = " + took);
// 搜索结果
SearchHits searchHits = searchResponse.getHits();
// hits.total.value:匹配的文档总数
TotalHits totalHits = searchHits.getTotalHits();
long value = totalHits.value;
System.out.println("value = " + value);
// hits.max_score:与查询所匹配文档的_score的最大值
float maxScore = searchHits.getMaxScore();
System.out.println("maxScore = " + maxScore);
// hits.hits:匹配的文档列表
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
// hits.hits._source：匹配的文档的原始数据
String sourceAsString = hit.getSourceAsString();
System.out.println("sourceAsString = " + sourceAsString);
// hits.hits._id：匹配的文档的id
String id = hit.getId();
System.out.println("id = " + id);
Map<String, DocumentField> fields = hit.getFields();
System.out.println("fields = " + fields);
String index = hit.getIndex();
System.out.println("index = " + index);
float score = hit.getScore();
System.out.println("score = " + score);
}
System.out.println(searchResponse);
}
}took=2ms
value = 2
maxScore = 1.0
sourceAsString = {"title":"金都嘉怡假日酒店","city":"北京","price":337,"create_time":"20210315200000","amenities":"wifi,充电停车场/可升降停车场","full_room":false,"location":{"lat":39.915153,"lon":116.403},"praise":60}
id = 2
fields = {}
index = hotel
score = 1.0
sourceAsString = {"title":"文雅酒店","city":"青岛","price":556,"create_time":"20200418120000","amenities":"浴池,普通停车场/充电停车场","full_room":false,"location":{"lat":36.083078,"lon":120.37566},"praise":10}
id = 1
fields = {}
index = hotel
score = 1.0{
"took": 2,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 2,
"relation": "eq"
},
"max_score": 1.0,
"hits": [
{
"_index": "hotel",
"_type": "_doc",
"_id": "2",
"_score": 1.0,
"_source": {
"title": "金都嘉怡假日酒店",
"city": "北京",
"price": 337,
"create_time": "20210315200000",
"amenities": "wifi,充电停车场/可升降停车场",
"full_room": false,
"location": {
"lat": 39.915153,
"lon": 116.403
},
"praise": 60
}
},
{
"_index": "hotel",
"_type": "_doc",
"_id": "1",
"_score": 1.0,
"_source": {
"title": "文雅酒店",
"city": "青岛",
"price": 556,
"create_time": "20200418120000",
"amenities": "浴池,普通停车场/充电停车场",
"full_room": false,
"location": {
"lat": 36.083078,
"lon": 120.37566
},
"praise": 10
}
}
]
}
}5 .ElasticSearch 搜索结果的面试题
1. ElasticSearch 搜索结果中的 _score 字段是什么意思？
答：_score 字段表示匹配文档的相关度得分，分数越高表示匹配度越高。
2. ElasticSearch 搜索结果中的 highlight 字段是什么意思？
答：highlight 字段表示匹配文档中被高亮显示的字段及其高亮显示的内容。
3. 如何获取 ElasticSearch 搜索结果中的总文档数？
答：可以通过 hits.total.value 字段获取匹配的文档总数。
4. 如何获取 ElasticSearch 搜索结果中的匹配文档列表？
答：可以通过 hits.hits 字段获取匹配的文档列表。
5. 如何获取 ElasticSearch 搜索结果中匹配文档的原始数据？
答：可以通过 hits.hits._source 字段获取匹配文档的原始数据。
6. 如何获取 ElasticSearch 搜索结果中匹配文档的高亮显示信息？
答：可以通过 hits.hits.highlight 字段获取匹配文档的高亮显示信息。
7. ElasticSearch 搜索结果中的 _shards 字段是什么意思？
答：_shards 字段表示搜索涉及的分片信息，包括总分片数、成功的分片数、跳过的分片数和失败的分片数。
8. ElasticSearch 搜索结果中的 took 字段是什么意思？
答：took 字段表示搜索耗时，单位为毫秒。
