ES查询
matchAll
脚本方式
该方式可以通过kabana、curl、elasticsearch-head（纯前端）去操作
# 默认情况下，es一次展示10条数据,通过from和size来控制分页
# 查询结果详解
GET goods/_search
{
"query": {
"match_all": {}
},
"from": 0,
"size": 100
}
# 默认为10条
GET goodsJava API方式
/**
* 查询所有
* 1. matchAll
* 2. 将查询结果封装为Goods对象，装载到List中
* 3. 分页。默认显示10条
*/
@Test
public void testMatchAll() throws IOException {
//2. 构建查询请求对象，指定查询的索引名称
SearchRequest searchRequest = new SearchRequest("goods");
//4. 创建查询条件构建器SearchSourceBuilder
SearchSourceBuilder sourceBuilder = new SearchSourceBuilder();
//6. 查询条件
QueryBuilder query = QueryBuilders.matchAllQuery();//查询所有文档
//5. 指定查询条件
sourceBuilder.query(query);
//3. 添加查询条件构建器 SearchSourceBuilder
searchRequest.source(sourceBuilder);
// 8 . 添加分页信息
sourceBuilder.from(0);
sourceBuilder.size(100);
//1. 查询,获取查询结果
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
//7. 获取命中对象 SearchHits
SearchHits searchHits = searchResponse.getHits();
//7.1 获取总记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
//7.2 获取Hits数据 数组
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
//获取json字符串格式的数据
String sourceAsString = hit.getSourceAsString();
//转为java对象
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}termQuery
term查询和字段类型有关系，首先回顾一下ElasticSearch两个数据类型
ElasticSearch两个数据类型
1、text：会分词，不支持聚合
2、keyword：不会分词，将全部内容作为一个词条，支持聚合
脚本方式
term查询：不会对查询条件进行分词。
GET goods/_search
{
"query": {
"term": {
"title": {
"value": "华为"
}
}
}
}term查询，查询text类型字段时，只有其中的单词相匹配都会查到，text字段会对数据进行分词
例如：查询title 为“华为”的，title type 为text
"title": {
"type": "text",
"analyzer": "ik_smart"
}
查询categoryName 字段时，categoryName字段为keyword ,keyword：不会分词，将全部内容作为一个词条,即完全匹配，才能查询出结果.
GET goods/_search
{
"query": {
"term": {
"categoryName": {
"value": "华为手机"
}
}
}
}
Java API
/**
* termQuery:词条查询
*/
@Test
public void testTermQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
QueryBuilder query = QueryBuilders.termQuery("title","华为");//term词条查询
sourceBulider.query(query);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}matchQuery
match查询：
•会对查询条件进行分词。
•然后将分词后的查询条件和词条进行等值匹配
•默认取并集（OR）
# match查询
GET goods/_search
{
"query": {
"match": {
"title": "华为手机"
}
},
"size": 500
}match 的默认搜索（or 并集）
例如：华为手机，会分词为 “华为”，“手机” 只要出现其中一个词条都会搜索到
match的 and（交集） 搜索
例如：例如：华为手机，会分词为 “华为”，“手机” 但要求“华为”，和“手机”同时出现在词条中
总结：
term query会去倒排索引中寻找确切的term，它并不知道分词器的存在。这种查询适合keyword
、numeric、date
match query知道分词器的存在。并且理解是如何被分词的
java api
/**
* matchQuery:词条分词查询
*/
@Test
public void testMatchQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
MatchQueryBuilder query = QueryBuilders.matchQuery("title", "华为手机");
query.operator(Operator.AND);//求并集
sourceBulider.query(query);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}模糊查询-脚本
wildcard查询
wildcard查询：会对查询条件进行分词。还可以使用通配符 ?（任意单个字符） 和 * （0个或多个字符）
*华*" 包含华字的
"华*" 华字后边多个字符
"华?" 华字后边多个字符
"*华"或"?华" 会引发全表（全索引）扫描 注意效率问题
# wildcard 查询。查询条件分词，模糊查询
GET goods/_search
{
"query": {
"wildcard": {
"title": {
"value": "华*"
}
}
}
}正则查询
\W：匹配包括下划线的任何单词字符，等价于 [A-Z a-z 0-9_] 开头的反斜杠是转义符
+号多次出现
(.)*为任意字符
正则查询取决于正则表达式的效率
GET goods/_search
{
"query": {
"regexp": {
"title": "\\w+(.)*"
}
}
}前缀查询
#前缀查询 对keyword类型支持比较好
GET goods/_search
{
"query": {
"prefix": {
"brandName": {
"value": "三"
}
}
}
}模糊查询- Java Api
/**
* 模糊查询:WildcardQuery
*/
@Test
public void testWildcardQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
WildcardQueryBuilder query = QueryBuilders.wildcardQuery("title", "华*");
sourceBulider.query(query);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}
/**
* 模糊查询:regexpQuery
*/
@Test
public void testRegexpQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
RegexpQueryBuilder query = QueryBuilders.regexpQuery("title", "\\w+(.)*");
sourceBulider.query(query);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}
/**
* 模糊查询:perfixQuery
*/
@Test
public void testPrefixQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
PrefixQueryBuilder query = QueryBuilders.prefixQuery("brandName", "三");
sourceBulider.query(query);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}
范围和排序
# 范围查询
GET goods/_search
{
"query": {
"range": {
"price": {
"gte": 2000,
"lte": 3000
}
}
},
"sort": [
{
"price": {
"order": "desc"
}
}
]
}/**
* 1. 范围查询：rangeQuery
* 2. 排序
*/
@Test
public void testRangeQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
//范围查询
RangeQueryBuilder query = QueryBuilders.rangeQuery("price");
//指定下限
query.gte(2000);
//指定上限
query.lte(3000);
sourceBulider.query(query);
//排序
sourceBulider.sort("price", SortOrder.DESC);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}queryString查询
queryString 多条件查询
•会对查询条件进行分词。
•然后将分词后的查询条件和词条进行等值匹配
•默认取并集（OR）
•可以指定多个查询字段
query_string：识别query中的连接符（or 、and）
# queryString
GET goods/_search
{
"query": {
"query_string": {
"fields": ["title","categoryName","brandName"],
"query": "华为 AND 手机"
}
}
}
#simple_query_string：不识别query中的连接符（or 、and），查询时会将 “华为”、"and"、“手机”分别进行查询
GET goods/_search
{
"query": {
"simple_query_string": {
"fields": ["title","categoryName","brandName"],
"query": "华为 AND 手机"
}
}
}
# simple_query_string：有default_operator连接符的脚本
GET goods/_search
{
"query": {
"simple_query_string": {
"fields": ["title","brandName","categoryName"],
"query": "华为手机 "
, "default_operator": "OR"
}
}
}
// 注意：query中的or and 是查询时 匹配条件是否同时出现----or 出现一个即可，and 两个条件同时出现default_operator的or and 是对结果进行 并集（or）、交集（and）
query_string：有default_operator连接符的脚本
GET goods/_search
{
"query": {
"query_string": {
"fields": ["title","brandName","categoryName"],
"query": "华为手机 ",
"default_operator": "AND"
}
}
}Java API
/**
* queryString
*/
@Test
public void testQueryStringQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
//queryString
QueryStringQueryBuilder query = QueryBuilders.queryStringQuery("华为手机").field("title").field("categoryName").field("brandName").defaultOperator(Operator.AND);
sourceBulider.query(query);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}布尔查询
boolQuery：对多个查询条件连接。连接方式：
•must（and）：条件必须成立
•must_not（not）：条件必须不成立
•should（or）：条件可以成立
•filter：条件必须成立，性能比must高。不会计算得分
得分:即条件匹配度,匹配度越高，得分越高
eg: 布尔查询：boolQuery
1. 查询品牌名称为:华为
2. 查询标题包含：手机
3. 查询价格在：2000-3000
#boolquery
#must和filter配合使用时，max_score（得分）是显示的
#must 默认数组形式
GET goods/_search
{
"query": {
"bool": {
"must": [
{
"term": {
"brandName": {
"value": "华为"
}
}
}
],
"filter":[
{
"term": {
"title": "手机"
}
},
{
"range":{
"price": {
"gte": 2000,
"lte": 3000
}
}
}
]
}
}
}
#filter 单独使用 filter可以是单个条件，也可多个条件（数组形式）
GET goods/_search
{
"query": {
"bool": {
"filter": [
{
"term": {
"brandName": {
"value": "华为"
}
}
}
]
}
}
}java api
/**
* 布尔查询：boolQuery
* 1. 查询品牌名称为:华为
* 2. 查询标题包含：手机
* 3. 查询价格在：2000-3000
*/
@Test
public void testBoolQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
//1.构建boolQuery
BoolQueryBuilder query = QueryBuilders.boolQuery();
//2.构建各个查询条件
//2.1 查询品牌名称为:华为
QueryBuilder termQuery = QueryBuilders.termQuery("brandName","华为");
query.must(termQuery);
//2.2. 查询标题包含：手机
QueryBuilder matchQuery = QueryBuilders.matchQuery("title","手机");
query.filter(matchQuery);
//2.3 查询价格在：2000-3000
QueryBuilder rangeQuery = QueryBuilders.rangeQuery("price");
((RangeQueryBuilder) rangeQuery).gte(2000);
((RangeQueryBuilder) rangeQuery).lte(3000);
query.filter(rangeQuery);
//3.使用boolQuery连接
sourceBulider.query(query);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
}聚合查询
指标聚合：相当于MySQL的聚合函数。max、min、avg、sum等
•桶聚合：相当于MySQL的 group by 操作。不要对text类型的数据进行分组，会失败。
# 聚合查询
# 指标聚合 聚合函数
GET goods/_search
{
"query": {
"match": {
"title": "手机"
}
},
"aggs": {
"max_price": {
"max": {
"field": "price"
}
}
}
}
#桶聚合 分组
GET goods/_search
{
"query": {
"match": {
"title": "手机"
}
},
"aggs": {
"goods_brands": {
"terms": {
"field": "brandName",
"size": 100
}
}
}
}
java api
/**
* 聚合查询：桶聚合，分组查询
* 1. 查询title包含手机的数据
* 2. 查询品牌列表
*/
@Test
public void testAggQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
// 1. 查询title包含手机的数据
MatchQueryBuilder query = QueryBuilders.matchQuery("title", "手机");
sourceBulider.query(query);
// 2. 查询品牌列表
/*
参数：
1. 自定义的名称，将来用于获取数据
2. 分组的字段
*/
AggregationBuilder agg = AggregationBuilders.terms("goods_brands").field("brandName").size(100);
sourceBulider.aggregation(agg);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
// 获取聚合结果
Aggregations aggregations = searchResponse.getAggregations();
Map<String, Aggregation> aggregationMap = aggregations.asMap();
//System.out.println(aggregationMap);
Terms goods_brands = (Terms) aggregationMap.get("goods_brands");
List<? extends Terms.Bucket> buckets = goods_brands.getBuckets();
List brands = new ArrayList();
for (Terms.Bucket bucket : buckets) {
Object key = bucket.getKey();
brands.add(key);
}
for (Object brand : brands) {
System.out.println(brand);
}
}高亮查询
高亮三要素：
•高亮字段
•前缀
•后缀
默认前后缀 ：em
GET goods/_search
{
"query": {
"match": {
"title": "电视"
}
},
"highlight": {
"fields": {
"title": {
"pre_tags": "<font color='red'>",
"post_tags": "</font>"
}
}
}
}java api
/**
*
* 高亮查询：
* 1. 设置高亮
* * 高亮字段
* * 前缀
* * 后缀
* 2. 将高亮了的字段数据，替换原有数据
*/
@Test
public void testHighLightQuery() throws IOException {
SearchRequest searchRequest = new SearchRequest("goods");
SearchSourceBuilder sourceBulider = new SearchSourceBuilder();
// 1. 查询title包含手机的数据
MatchQueryBuilder query = QueryBuilders.matchQuery("title", "手机");
sourceBulider.query(query);
//设置高亮
HighlightBuilder highlighter = new HighlightBuilder();
//设置三要素
highlighter.field("title");
highlighter.preTags("<font color='red'>");
highlighter.postTags("</font>");
sourceBulider.highlighter(highlighter);
// 2. 查询品牌列表
/*
参数：
1. 自定义的名称，将来用于获取数据
2. 分组的字段
*/
AggregationBuilder agg = AggregationBuilders.terms("goods_brands").field("brandName").size(100);
sourceBulider.aggregation(agg);
searchRequest.source(sourceBulider);
SearchResponse searchResponse = client.search(searchRequest, RequestOptions.DEFAULT);
SearchHits searchHits = searchResponse.getHits();
//获取记录数
long value = searchHits.getTotalHits().value;
System.out.println("总记录数："+value);
List<Goods> goodsList = new ArrayList<>();
SearchHit[] hits = searchHits.getHits();
for (SearchHit hit : hits) {
String sourceAsString = hit.getSourceAsString();
//转为java
Goods goods = JSON.parseObject(sourceAsString, Goods.class);
// 获取高亮结果，替换goods中的title
Map<String, HighlightField> highlightFields = hit.getHighlightFields();
HighlightField HighlightField = highlightFields.get("title");
Text[] fragments = HighlightField.fragments();
//替换
goods.setTitle(fragments[0].toString());
goodsList.add(goods);
}
for (Goods goods : goodsList) {
System.out.println(goods);
}
// 获取聚合结果
Aggregations aggregations = searchResponse.getAggregations();
Map<String, Aggregation> aggregationMap = aggregations.asMap();
//System.out.println(aggregationMap);
Terms goods_brands = (Terms) aggregationMap.get("goods_brands");
List<? extends Terms.Bucket> buckets = goods_brands.getBuckets();
List brands = new ArrayList();
for (Terms.Bucket bucket : buckets) {
Object key = bucket.getKey();
brands.add(key);
}
for (Object brand : brands) {
System.out.println(brand);
}
}
