0
点赞
收藏
分享

微信扫一扫

Elasticsearch(二)

插入数据:

POST /forum/article/_bulk
{ "index": { "_id": 1 }}
{ "articleID" : "XHDK-A-1293-#fJ3", "userID" : 1, "hidden": false, "postDate": "2017-01-01" }
{ "index": { "_id": 2 }}
{ "articleID" : "KDKE-B-9947-#kL5", "userID" : 1, "hidden": false, "postDate": "2017-01-02" }
{ "index": { "_id": 3 }}
{ "articleID" : "JODL-X-1937-#pV7", "userID" : 2, "hidden": false, "postDate": "2017-01-01" }
{ "index": { "_id": 4 }}
{ "articleID" : "QQPX-R-3956-#aD8", "userID" : 2, "hidden": true, "postDate": "2017-01-02" }

  (2)根据用户ID搜索帖子

GET /forum/article/_search
{
"query" : {
"constant_score" : {
"filter" : {
"term" : {
"userID" : 1
}
}
}
}
}

 term filter/query:对搜索文本不分词,直接拿去倒排索引中匹配,你输入的是什么,就去匹配什么

(3)搜索没有隐藏的帖子

GET /forum/article/_search
{
"query": {
"constant_score": {
"filter": {
"term": {
"hidden": "false"
}
}
}
}
}

  (4)根据发帖日期搜索帖子

GET /forum/article/_search
{
"query" : {
"constant_score" : {
"filter" : {
"term" : {
"postDate" : "2017-01-01"
}
}
}
}
}

(5)根据帖子ID搜索帖子

GET /forum/article/_search
{
"query" : {
"constant_score" : {
"filter" : {
"term" : {
"articleID" : "XHDK-A-1293-#fJ3"
}
}
}
}
}

  结果:

{
"took": 1,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 0,
"max_score": null,
"hits": []
}
}

  正确写法:

GET /forum/article/_search
{
"query" : {
"constant_score" : {
"filter" : {
"term" : {
"articleID.keyword" : "XHDK-A-1293-#fJ3"
}
}
}
}
}

  (6)查看分词:

GET /forum/_analyze
{
"field": "articleID",
"text": "XHDK-A-1293-#fJ3"
}

  articleID.keyword,是es最新版本内置建立的field,就是不分词的。所以一个articleID过来的时候,会建立两次索引,

一次是自己本身,是要分词的,分词后放入倒排索引;另外一次是基于articleID.keyword,不分词,
保留256个字符最多,直接一个字符串放入倒排索引中。

所以term filter,对text过滤,可以考虑使用内置的field.keyword来进行匹配。
但是有个问题,默认就保留256个字符。所以尽可能还是自己去手动建立索引,指定not_analyzed吧。
在最新版本的es中,不需要指定not_analyzed也可以,将type=keyword即可。

(7)重建索引

DELETE /forum

PUT /forum
{
"mappings": {
"article": {
"properties": {
"articleID": {
"type": "keyword"
}
}
}
}
}

POST /forum/article/_bulk
{ "index": { "_id": 1 }}
{ "articleID" : "XHDK-A-1293-#fJ3", "userID" : 1, "hidden": false, "postDate": "2017-01-01" }
{ "index": { "_id": 2 }}
{ "articleID" : "KDKE-B-9947-#kL5", "userID" : 1, "hidden": false, "postDate": "2017-01-02" }
{ "index": { "_id": 3 }}
{ "articleID" : "JODL-X-1937-#pV7", "userID" : 2, "hidden": false, "postDate": "2017-01-01" }
{ "index": { "_id": 4 }}
{ "articleID" : "QQPX-R-3956-#aD8", "userID" : 2, "hidden": true, "postDate": "2017-01-02" }

  (8)重新根据帖子ID和发帖日期进行搜索

GET /forum/article/_search
{
"query" : {
"constant_score" : {
"filter" : {
"term" : {
"articleID" : "XHDK-A-1293-#fJ3"
}
}
}
}
}

  

(1)term filter:根据exact value进行搜索,数字、boolean、date天然支持
(2)text需要建索引时指定为not_analyzed,才能用term query
(3)相当于SQL中的单个where条件

filter比query的好处就在于会caching,但是之前不知道caching的是什么东西,
实际上并不是一个filter返回的完整的doc list数据结果。而是filter bitset缓存起来。

filter大部分情况下来说,在query之前执行,先尽量过滤掉尽可能多的数据

query:是会计算doc对搜索条件的relevance score,还会根据这个score去排序
filter:只是简单过滤出想要的数据,不计算relevance score,也不排序

 

 基于bool组合多个filter条件来搜索数据

1、搜索发帖日期为2017-01-01,或者帖子ID为XHDK-A-1293-#fJ3的帖子,同时要求帖子的发帖日期绝对不为2017-01-02

select *
from forum.article
where (post_date='2017-01-01' or article_id='XHDK-A-1293-#fJ3')
and post_date!='2017-01-02'

  

GET /forum/article/_search
{
"query": {
"constant_score": {
"filter": {
"bool": {
"should": [
{
"term": {
"postDate": "2017-01-01"
}
},
{
"term": {
"articleID": "XHDK-A-1293-#fJ3"
}
}
],
"must_not": {
"term": {
"postDate": "2017-01-02"
}
}
}
}
}
}
}

  must,should,must_not,filter:必须匹配,可以匹配其中任意一个即可,必须不匹配

2、搜索帖子ID为XHDK-A-1293-#fJ3,或者是帖子ID为JODL-X-1937-#pV7而且发帖日期为2017-01-01的帖子

 

select *
from forum.article
where article_id='XHDK-A-1293-#fJ3'
or (article_id='JODL-X-1937-#pV7' and post_date='2017-01-01')

  

GET /forum/article/_search 
{
"query": {
"constant_score": {
"filter": {
"bool": {
"should": [
{
"term": {
"articleID.keyword": "XHDK-A-1293-#fJ3"
}
},
{
"bool": {
"must": [
{
"term":{
"articleID.keyword": "JODL-X-1937-#pV7"
}
},
{
"term": {
"postDate": "2017-01-01"
}
}
]
}
}
]
}
}
}
}
}

  terms搜索多个值以及多值搜索结果

 1、为帖子数据增加tag字段

POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"tag" : ["java", "hadoop"]} }
{ "update": { "_id": "2"} }
{ "doc" : {"tag" : ["java"]} }
{ "update": { "_id": "3"} }
{ "doc" : {"tag" : ["hadoop"]} }
{ "update": { "_id": "4"} }
{ "doc" : {"tag" : ["java", "elasticsearch"]} }

  2、搜索articleID为KDKE-B-9947-#kL5或QQPX-R-3956-#aD8的帖子,搜索tag中包含java的帖子

GET /forum/article/_search 
{
"query": {
"constant_score": {
"filter": {
"terms": {
"articleID.keyword": [
"KDKE-B-9947-#kL5",
"QQPX-R-3956-#aD8"
]
}
}
}
}
}

  

GET /forum/article/_search
{
"query" : {
"constant_score" : {
"filter" : {
"terms" : {
"tag" : ["java"]
}
}
}
}
}

  terms搜索多个值以及多值搜索结果优化

添加字段:

POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"tag_cnt" : 2} }
{ "update": { "_id": "2"} }
{ "doc" : {"tag_cnt" : 1} }
{ "update": { "_id": "3"} }
{ "doc" : {"tag_cnt" : 1} }
{ "update": { "_id": "4"} }
{ "doc" : {"tag_cnt" : 2} }

  

GET /forum/article/_search
{
"query": {
"constant_score": {
"filter": {
"bool": {
"must": [
{
"term": {
"tag_cnt": 1
}
},
{
"terms": {
"tag": ["java"]
}
}
]
}
}
}
}
}

  range filter来进行范围过滤

1、为帖子数据增加浏览量的字段

POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"view_cnt" : 30} }
{ "update": { "_id": "2"} }
{ "doc" : {"view_cnt" : 50} }
{ "update": { "_id": "3"} }
{ "doc" : {"view_cnt" : 100} }
{ "update": { "_id": "4"} }
{ "doc" : {"view_cnt" : 80} }

  2、搜索浏览量在30~60之间的帖子

GET /forum/article/_search
{
"query": {
"constant_score": {
"filter": {
"range": {
"view_cnt": {
"gt": 30,
"lt": 60
}
}
}
}
}
}

  3、搜索发帖日期在最近1个月的帖子

POST /forum/article/_bulk
{"index":{"_id":5}}
{"articleID":"DHJK-B-1395-#Ky5","userID":3,"hidden":false,"postDate":"2017-03-01","tag":["elasticsearch"],"tag_cnt":1,"view_cnt":10}


GET /forum/article/_search
{
"query": {
"constant_score": {
"filter": {
"range": {
"postDate": {
"gt": "2017-03-10||-30d"
}
}
}
}
}
}

GET /forum/article/_search
{
"query": {
"constant_score": {
"filter": {
"range": {
"postDate": {
"gt": "now-30d"
}
}
}
}
}
}

  手动控制全文检索结果的精准度

1、为帖子数据增加标题字段

POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"title" : "this is java and elasticsearch blog"} }
{ "update": { "_id": "2"} }
{ "doc" : {"title" : "this is java blog"} }
{ "update": { "_id": "3"} }
{ "doc" : {"title" : "this is elasticsearch blog"} }
{ "update": { "_id": "4"} }
{ "doc" : {"title" : "this is java, elasticsearch, hadoop blog"} }
{ "update": { "_id": "5"} }
{ "doc" : {"title" : "this is spark blog"} }

  2、搜索标题中包含java或elasticsearch的blog

GET /forum/article/_search
{
"query": {
"match": {
"title": "java elasticsearch"
}
}
}

  3、搜索标题中包含java和elasticsearch的blog

搜索结果精准控制的第一步:灵活使用and关键字,希望所有的搜索关键字都要匹配的,那么就用and,
可以实现单纯match query无法实现的效果

GET /forum/article/_search
{
"query": {
"match": {
"title": {
"query": "java elasticsearch",
"operator": "and"
}
}
}
}

  4、搜索包含java,elasticsearch,spark,hadoop,4个关键字中,至少3个的blog

控制搜索结果的精准度的第二步:指定一些关键字中,必须至少匹配其中的多少个关键字,才能作为结果返回

GET /forum/article/_search
{
"query": {
"match": {
"title": {
"query": "java elasticsearch spark hadoop",
"minimum_should_match": "75%"
}
}
}
}

  5、用bool组合多个搜索条件,来搜索title

GET /forum/article/_search
{
"query": {
"bool": {
"must": {
"match": {
"title": "java"
}
},
"must_not": {
"match": {
"title": "spark"
}
},
"should": [
{
"match": {
"title": "hadoop"
}
},
{
"match": {
"title": "elasticsearch"
}
}
]
}
}
}

  6、bool组合多个搜索条件,如何计算relevance score

must和should搜索对应的分数,加起来,除以must和should的总数

排名第一:java,同时包含should中所有的关键字,hadoop,elasticsearch
排名第二:java,同时包含should中的elasticsearch
排名第三:java,不包含should中的任何关键字

should是可以影响相关度分数的

must是确保说,谁必须有这个关键字,同时会根据这个must的条件去计算出document对这个搜索条件的relevance score
在满足must的基础之上,should中的条件,不匹配也可以,但是如果匹配的更多,那么document的relevance score就会更高

  7、搜索java,hadoop,spark,elasticsearch,至少包含其中3个关键字

默认情况下,should是可以不匹配任何一个的,比如上面的搜索中,this is java blog,就不匹配任何一个should条件
但是有个例外的情况,如果没有must的话,那么should中必须至少匹配一个才可以
比如下面的搜索,should中有4个条件,默认情况下,只要满足其中一个条件,就可以匹配作为结果返回

但是可以精准控制,should的4个条件中,至少匹配几个才能作为结果返回

GET /forum/article/_search
{
"query": {
"bool": {
"should": [
{
"match": {
"title": "java"
}
},
{
"match": {
"title": "elasticsearch"
}
},
{
"match": {
"title": "hadoop"
}
},
{
"match": {
"title": "spark"
}
}
],
"minimum_should_match": 3
}
}
}

  

1、全文检索的时候,进行多个值的检索,有两种做法,match query;should
2、控制搜索结果精准度:and operator,minimum_should_match

 

boost的细粒度搜索条件权重控制

GET /forum/article/_search 
{
"query": {
"bool": {
"must": [
{
"match": {
"title": "blog"
}
}
],
"should": [
{
"match": {
"title": {
"query": "java"
}
}
},
{
"match": {
"title": {
"query": "hadoop"
}
}
},
{
"match": {
"title": {
"query": "elasticsearch"
}
}
},
{
"match": {
"title": {
"query": "spark",
"boost": 5
}
}
}
]
}
}
}

  dis_max实现best fields策略进行多字段搜索

1、为帖子数据增加content字段

POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"content" : "i like to write best elasticsearch article"} }
{ "update": { "_id": "2"} }
{ "doc" : {"content" : "i think java is the best programming language"} }
{ "update": { "_id": "3"} }
{ "doc" : {"content" : "i am only an elasticsearch beginner"} }
{ "update": { "_id": "4"} }
{ "doc" : {"content" : "elasticsearch and hadoop are all very good solution, i am a beginner"} }
{ "update": { "_id": "5"} }
{ "doc" : {"content" : "spark is best big data solution based on scala ,an programming language similar to java"} }

  2、搜索title或content中包含java或solution的帖子

这个就是multi-field搜索,多字段搜索

GET /forum/article/_search
{
"query": {
"bool": {
"should": [
{ "match": { "title": "java solution" }},
{ "match": { "content": "java solution" }}
]
}
}
}

  

best fields策略,就是说,搜索到的结果,应该是某一个field中匹配到了尽可能多的关键词,被排在前面;
而不是尽可能多的field匹配到了少数的关键词,排在了前面

dis_max语法,直接取多个query中,分数最高的那一个query的分数即可

GET /forum/article/_search
{
"query": {
"dis_max": {
"queries": [
{ "match": { "title": "java solution" }},
{ "match": { "content": "java solution" }}
]
}
}
}

  tie_breaker参数优化dis_max搜索效果

1、搜索title或content中包含java beginner的帖子

GET /forum/article/_search
{
"query": {
"dis_max": {
"queries": [
{ "match": { "title": "java beginner" }},
{ "match": { "body": "java beginner" }}
]
}
}
}

  dis_max,只是取分数最高的那个query的分数而已

2、dis_max只取某一个query最大的分数,完全不考虑其他query的分数

3、使用tie_breaker将其他query的分数也考虑进去

GET /forum/article/_search
{
"query": {
"dis_max": {
"queries": [
{ "match": { "title": "java beginner" }},
{ "match": { "body": "java beginner" }}
],
"tie_breaker": 0.3
}
}
}

  基于multi_match语法实现dis_max+tie_breaker

GET /forum/article/_search
{
"query": {
"multi_match": {
"query": "java solution",
"type": "best_fields",
"fields": [ "title^2", "content" ],
"tie_breaker": 0.3,
"minimum_should_match": "50%"
}
}
}

  

GET /forum/article/_search
{
"query": {
"dis_max": {
"queries": [
{
"match": {
"title": {
"query": "java beginner",
"minimum_should_match": "50%",
"boost": 2
}
}
},
{
"match": {
"body": {
"query": "java beginner",
"minimum_should_match": "30%"
}
}
}
],
"tie_breaker": 0.3
}
}
}

  

minimum_should_match,的作用
去长尾,long tail
长尾,比如你搜索5个关键词,但是很多结果是只匹配1个关键词的,其实跟你想要的结果相差甚远,这些结果就是长尾
minimum_should_match,控制搜索结果的精准度,只有匹配一定数量的关键词的数据,才能返回



举报

相关推荐

0 条评论