（基于es5.4）先喵几眼github，按照步骤安装好分词器 link:https://github.com/medcl/elasticsearch-analysis-ik
复习一下常用的操作
.查看集群健康状况
GET /_cat/health?v&pretty .查看my_index的mapping和setting的相关信息
GET /my_index?pretty .查看所有的index
GET /_cat/indices?v&pretty .删除 my_index_new
DELETE /my_index_new?pretty&pretty
先测试ik分词器的基本功能
GET _analyze?pretty
{
"analyzer": "ik_smart",
"text": "*国歌"
}
结果：
{
"tokens": [
{
"token": "*",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "国歌",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
}
]
}
可以看出：通过ik_smart明显很智能的将 "*国歌"进行了正确的分词。
另外一个例子：
GET _analyze?pretty
{
"analyzer": "ik_smart",
"text": "王者荣耀是最好玩的游戏"
}
结果：
{
"tokens": [
{
"token": "王者荣耀",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "最",
"start_offset": ,
"end_offset": ,
"type": "CN_CHAR",
"position":
},
{
"token": "好玩",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "游戏",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
}
]
}
如果结果跟我的不一样，那就对了，中文ik分词词库里面将“王者荣耀”是分开的，但是我们又不愿意将其分开，根据github上面的指示可以配置
IKAnalyzer.cfg.xml 目录在：elasticsearch-5.4.0/plugins/ik/config
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
<properties>
<comment>IK Analyzer 扩展配置</comment>
<!--用户可以在这里配置自己的扩展字典 -->
<entry key="ext_dict">custom/mydict.dic;custom/single_word_low_freq.dic</entry>
<!--用户可以在这里配置自己的扩展停止词字典-->
<entry key="ext_stopwords">custom/ext_stopword.dic</entry>
<!--用户可以在这里配置远程扩展字典，下面是配置在nginx路径下面的 -->
<entry key="remote_ext_dict">http://tagtic-slave01:82/HotWords.php</entry>
<!--用户可以在这里配置远程扩展停止词字典-->
<!-- <entry key="remote_ext_stopwords">words_location</entry> -->
<entry key="remote_ext_stopwords">http://tagtic-slave01:82/StopWords.php</entry>
</properties>
可以看到HotWords.php
<?php
$s = <<<'EOF'
王者荣耀
阴阳师
EOF;
header("Content-type: text/html; charset=utf-8");
header('Last-Modified: '.gmdate('D, d M Y H:i:s', time()).' GMT', true, );
header('ETag: "5816f349-19"');
echo $s;
?>
配置完了之后就可以看到刚才的结果了
顺便测试一下ik_max_word
GET /index/_analyze?pretty
{
"analyzer": "ik_max_word",
"text": "*国歌"
}
结果看看就行了
{
"tokens": [
{
"token": "*",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "中华人民",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "中华",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "华人",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "人民*",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "人民",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "*",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "共和",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
},
{
"token": "国",
"start_offset": ,
"end_offset": ,
"type": "CN_CHAR",
"position":
},
{
"token": "国歌",
"start_offset": ,
"end_offset": ,
"type": "CN_WORD",
"position":
}
]
}
再看看github上面的一个例子
POST /index/fulltext/_mapping
{
"fulltext": {
"_all": {
"analyzer": "ik_smart"
},
"properties": {
"content": {
"type": "text"
}
}
}
}
存一些值
POST /index/fulltext/
{
"content": "美国留给伊拉克的是个烂摊子吗"
} POST /index/fulltext/
{
"content": "*部：各地校车将享最高路权"
} POST /index/fulltext/
{
"content": "中韩渔警冲突调查：韩警平均每天扣1艘中国渔船"
} POST /index/fulltext/
{
"content": "中国驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首"
}
取值
POST /index/fulltext/_search
{
"query": {
"match": {
"content": "中国"
}
}
}
结果
{
"took": ,
"timed_out": false,
"_shards": {
"total": ,
"successful": ,
"failed":
},
"hits": {
"total": ,
"max_score": 1.0869478,
"hits": [
{
"_index": "index",
"_type": "fulltext",
"_id": "",
"_score": 1.0869478,
"_source": {
"content": "中国驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首"
}
},
{
"_index": "index",
"_type": "fulltext",
"_id": "",
"_score": 0.61094594,
"_source": {
"content": "中韩渔警冲突调查：韩警平均每天扣1艘中国渔船"
}
},
{
"_index": "index",
"_type": "fulltext",
"_id": "",
"_score": 0.27179778,
"_source": {
"content": "美国留给伊拉克的是个烂摊子吗"
}
}
]
}
}
es会按照分词进行索引，然后根据你的查询条件按照分数的高低给出结果
官网有一个例子，可以学习学习：https://github.com/medcl/elasticsearch-analysis-ik
看另一个有趣的例子
PUT /index1
{
"settings": {
"refresh_interval": "5s",
"number_of_shards" : ,
"number_of_replicas" :
},
"mappings": {
"_default_":{
"_all": { "enabled": false }
},
"resource": {
"dynamic": false,
"properties": {
"title": {
"type": "text",
"fields": {
"cn": {
"type": "text",
"analyzer": "ik_smart"
},
"en": {
"type": "text",
"analyzer": "english"
}
}
}
}
}
}
}
field的作用有二：
.比如一个string类型可以映射成text类型来进行全文检索，keyword类型作为排序和聚合;
相当于起了个别名，使用不同的分类器
批量插入值
POST /_bulk
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "周星驰最新电影" }
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "周星驰最好看的新电影" }
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "周星驰最新电影，最好，新电影" }
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "最最最最好的新新新新电影" }
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "I'm not happy about the foxes" }
取值
POST /index1/resource/_search
{
"query": {
"multi_match": {
"type": "most_fields",
"query": "fox",
"fields": "title"
}
}
}
结果
{
"took": ,
"timed_out": false,
"_shards": {
"total": ,
"successful": ,
"failed":
},
"hits": {
"total": ,
"max_score": null,
"hits": []
}
}
原因，使用title里面查询fox,而title使用的是Standard标准分词器，被索引的是foxes，所以不会有结果，下面这种情况就会有结果了
POST /index1/resource/_search
{
"query": {
"multi_match": {
"type": "most_fields",
"query": "fox",
"fields": "title.en"
}
}
}
结果就不列出来了，因为title.en使用的是english分词器
对比一下下面的输出，体会一下field的使用
GET /index1/resource/_search
{
"query": {
"match": {
"title.cn": "the最好游戏"
}
}
} POST /index1/resource/_search
{
"query": {
"multi_match": {
"type": "most_fields",
"query": "the最新游戏",
"fields": [ "title", "title.cn", "title.en" ]
}
}
} POST /index1/resource/_search
{
"query": {
"multi_match": {
"type": "most_fields",
"query": "the最新",
"fields": "title.cn"
}
}
}
根据结果体会体会用法
下面使用“王者荣耀做测试”，这里可以看到前面配置的HotWords.php是一把双刃剑，将“王者荣耀”放在里面之后，“王者荣耀”这个词就是一个整体，不会被切分成“王者”和“荣耀”，但是就是要搜索王者怎么办呢，这里就体现出fields的强大了，具体看下面
先存入数据
POST /_bulk
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "王者荣耀最好玩的游戏" }
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "王者荣耀最好玩的新游戏" }
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "王者荣耀最新游戏，最好玩，新游戏" }
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "最最最最好的新新新新游戏" }
{ "create": { "_index": "index1", "_type": "resource", "_id": } }
{ "title": "I'm not happy about the foxes" }
查询
POST /index1/resource/_search
{
"query": {
"multi_match": {
"type": "most_fields",
"query": "王者荣耀",
"fields": "title.cn"
}
}
} #下面会没有结果返回
POST /index1/resource/_search
{
"query": {
"multi_match": {
"type": "most_fields",
"query": "王者",
"fields": "title.cn"
}
}
} POST /index1/resource/_search
{
"query": {
"multi_match": {
"type": "most_fields",
"query": "王者",
"fields": "title"
}
}
}
对比结果就可以一目了然了，结果略！
所以一开始业务的需求要相当了解，才能有好的映射（mapping）被设计，搜索的时候也会省事不少
参考：
https://github.com/medcl/elasticsearch-analysis-ik
http://keenwon.com/1404.html
https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-standard-analyzer.html#_example_output