opensearch安装ik分词器

你的猪脑我另做他用

于 2024-09-29 10:38:35 发布

阅读量221

点赞数 2

文章标签：大数据

本文链接：https://blog.csdn.net/q704013673/article/details/142629839

版权

opensearca安装ik分词器

ik分词器源码地址

https://github.com/infinilabs/analysis-ik/

您可以从这里下载打包的插件：https://release.infinilabs.com/，

或者你可以使用opensearch-plugin 来安装插件，如下所示：
找到安装目录中的bin/opensearch-plugin

bin/opensearch-plugin install https://get.infini.cloud/opensearch/analysis-ik/2.12.0

提示：请替换与您的 opensearch 相关的版本号

1.创建索引

curl -XPUT http://localhost:9200/index

2.创建映射

curl -XPOST http://localhost:9200/index/_mapping -H 'Content-Type:application/json' -d'
{
        "properties": {
            "content": {
                "type": "text",
                "analyzer": "ik_max_word",
                "search_analyzer": "ik_smart"
            }
        }

}

3.索引一些文档

curl -XPOST http://localhost:9200/index/_create/1 -H 'Content-Type:application/json' -d'
{"content":"美国留给伊拉克的是个烂摊子吗"}
'

curl -XPOST http://localhost:9200/index/_create/2 -H 'Content-Type:application/json' -d'
{"content":"公安部：各地校车将享最高路权"}
'

curl -XPOST http://localhost:9200/index/_create/3 -H 'Content-Type:application/json' -d'
{"content":"中韩渔警冲突调查：韩警平均每天扣1艘中国渔船"}
'

curl -XPOST http://localhost:9200/index/_create/4 -H 'Content-Type:application/json' -d'
{"content":"中国驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首"}
'

4. 查询高亮

curl -XPOST http://localhost:9200/index/_search  -H 'Content-Type:application/json' -d'
{
    "query" : { "match" : { "content" : "中国" }},
    "highlight" : {
        "pre_tags" : ["<tag1>", "<tag2>"],
        "post_tags" : ["</tag1>", "</tag2>"],
        "fields" : {
            "content" : {}
        }
    }
}
'

结果

{
    "took": 14,
    "timed_out": false,
    "_shards": {
        "total": 5,
        "successful": 5,
        "failed": 0
    },
    "hits": {
        "total": 2,
        "max_score": 2,
        "hits": [
            {
                "_index": "index",
                "_type": "fulltext",
                "_id": "4",
                "_score": 2,
                "_source": {
                    "content": "中国驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首"
                },
                "highlight": {
                    "content": [
                        "<tag1>中国</tag1>驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首 "
                    ]
                }
            },
            {
                "_index": "index",
                "_type": "fulltext",
                "_id": "3",
                "_score": 2,
                "_source": {
                    "content": "中韩渔警冲突调查：韩警平均每天扣1艘中国渔船"
                },
                "highlight": {
                    "content": [
                        "均每天扣1艘<tag1>中国</tag1>渔船 "
                    ]
                }
            }
        ]
    }
}

字典配置

配置文件IKAnalyzer.cfg.xml可以位于{conf}/analysis-ik/config/IKAnalyzer.cfg.xml 或{plugins}/elasticsearch-analysis-ik-*/config/IKAnalyzer.cfg.xml

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
<properties>
	<entry key="ext_dict">custom/mydict.dic;custom/single_word_low_freq.dic</entry>
	<entry key="ext_stopwords">custom/ext_stopword.dic</entry>
	<entry key="remote_ext_dict">location</entry>
	<entry key="remote_ext_stopwords">http://xxx.com/xxx.dic</entry>
</properties>