elasticsearch中文分词插件IK使用

安装

# git clone https://github.com/medcl/elasticsearch-analysis-ik.git --depth 1
# cd elasticsearch-analysis-ik/
# mvn package
# unzip ./target/releases/elasticsearch-analysis-ik-1.2.9.zip

# git clone https://github.com/medcl/elasticsearch-analysis-ik
# cd elasticsearch-analysis-ik
# mvn compile
# mvn package
# plugin --install analysis-ik --url file:///#{project_path}/elasticsearch-analysis-ik/target/releases/elasticsearch-analysis-ik-1.3.0.zip

[]- elasticsearch-analysis-ik-1.2.9.jar[/][]- httpclient-4.3.5.jar[/][]- httpcore-4.3.2.jar[/][]- commons-logging-1.1.3.jar[/][]- commons-codec-1.6.jar[/]

index:
  analysis:
    analyzer:
      ik:
          alias: [news_analyzer_ik,ik_analyzer]
          type: org.elasticsearch.index.analysis.IkAnalyzerProvider

index.analysis.analyzer.default.type : "ik"

[b]index.analysis.analyzer.ik.type : "ik"[/b]

Example

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

# curl -XPUT http://localhost:9200/index
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
            }
        }
    }
}'

# 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艘中国渔船"}
' 

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

# curl -XPOST http://localhost:9200/index/fulltext/_search  -d'
{
    "query" : { "term" : { "content" : "中国" }},
    "highlight" : {
        "pre_tags" : ["", ""],
        "post_tags" : ["", ""],
        "fields" : {
            "content" : {}
        }
    }
}
'

{
    "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": [
                        "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": "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艘中国渔船 "
                    ]
                }
            }
        ]
    }
}