dreamfrog / elasticsearch-analysis-ik Goto Github PK

IK Analysis for ElasticSearch
==========

The IK Analysis plugin integrates Lucene IK analyzer into elasticsearch, support customized dictionary.

Version
-—————
master | 0.90.0 → master
1.2.0 | 0.90.0
1.1.3 | 0.20.2
1.1.2 | 0.19.x
1.0.0 | 0.16.2 → 0.19.0

Install
-—————
you can download this plugin from RTF project(https://github.com/medcl/elasticsearch-rtf)
https://github.com/medcl/elasticsearch-rtf/tree/master/elasticsearch/plugins/analysis-ik
https://github.com/medcl/elasticsearch-rtf/tree/master/elasticsearch/config/ik

also remember to download the dict files,unzip these dict file into your elasticsearch’s config folder,such as: your-es-root/config/ik

you need a service restart after that!

Dict Configuration (es-root/config/ik/IKAnalyzer.cfg.xml)
-—————

https://github.com/medcl/elasticsearch-analysis-ik/blob/master/config/ik/IKAnalyzer.cfg.xml

<?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/sougou.dict</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> 	
</properties>

Analysis Configuration (elasticsearch.yml)
-—————

index:

  analysis:                   

    analyzer:      

      ik:

          alias: [ik_analyzer]

          type: org.elasticsearch.index.analysis.IkAnalyzerProvider

      ik_max_word:

          type: ik

          use_smart: false

      ik_smart:

          type: ik

          use_smart: true

index.analysis.analyzer.ik.type : “ik”

you can set your prefer segment mode,default `use_smart` is false.

Mapping Configuration
-—————

Here is a quick example:
1.create a index

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

2.create a mapping

curl -XPOST http://localhost:9200/index/fulltext/_mapping -d'
{
    "fulltext": {
             "_all": {
            "indexAnalyzer": "ik",
            "searchAnalyzer": "ik",
            "term_vector": "no",
            "store": "false"
        },
        "properties": {
            "content": {
                "type": "string",
                "store": "no",
                "term_vector": "with_positions_offsets",
                "indexAnalyzer": "ik",
                "searchAnalyzer": "ik",
                "include_in_all": "true",
                "boost": 8
            }
        }
    }
}'

3.index some docs

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

curl -XPOST http://localhost:9200/index/fulltext/2 -d'
{content:"公安部：各地校车将享最高路权"}
'

curl -XPOST http://localhost:9200/index/fulltext/3 -d'
{content:"中韩渔警冲突调查：韩警平均每天扣1艘**渔船"}
'

curl -XPOST http://localhost:9200/index/fulltext/4 -d'
{content:"**驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首"}
'

4.query with highlighting

curl -XPOST http://localhost:9200/index/fulltext/_search  -d'
{
    "query" : { "term" : { "content" : "**" }},
    "highlight" : {
        "pre_tags" : ["<tag1>", "<tag2>"],
        "post_tags" : ["</tag1>", "</tag2>"],
        "fields" : {
            "content" : {}
        }
    }
}
'

here is the query result

{
    "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": "**驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首"
                },
                "highlight": {
                    "content": [
                        "<tag1>**</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**渔船"
                },
                "highlight": {
                    "content": [
                        "均每天扣1艘<tag1>**</tag1>渔船 "
                    ]
                }
            }
        ]
    }
}

have fun.