./bin/elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v6.0.0/elasticsearch-analysis-ik-6.0.0.zip
./bin/sh elastic search –d
GET _analyze
{
"analyzer":"ik_max_word",
"text":"中华人民共和国国歌"
}
{
"tokens": [
{
"token": "中华人民共和国",
"start_offset": 0,
"end_offset": 7,
"type": "CN_WORD",
"position": 0
},
{
"token": "中华人民",
"start_offset": 0,
"end_offset": 4,
"type": "CN_WORD",
"position": 1
},
{
"token": "中华",
"start_offset": 0,
"end_offset": 2,
"type": "CN_WORD",
"position": 2
},
{
"token": "华人",
"start_offset": 1,
"end_offset": 3,
"type": "CN_WORD",
"position": 3
},
{
"token": "人民共和国",
"start_offset": 2,
"end_offset": 7,
"type": "CN_WORD",
"position": 4
},
{
"token": "人民",
"start_offset": 2,
"end_offset": 4,
"type": "CN_WORD",
"position": 5
},
{
"token": "共和国",
"start_offset": 4,
"end_offset": 7,
"type": "CN_WORD",
"position": 6
},
{
"token": "共和",
"start_offset": 4,
"end_offset": 6,
"type": "CN_WORD",
"position": 7
},
{
"token": "国",
"start_offset": 6,
"end_offset": 7,
"type": "CN_CHAR",
"position": 8
},
{
"token": "国歌",
"start_offset": 7,
"end_offset": 9,
"type": "CN_WORD",
"position": 9
}
]
}
GET _analyze
{
"analyzer":"ik_smart",
"text":"中华人民共和国国歌"
}
{
"tokens": [
{
"token": "中华人民共和国",
"start_offset": 0,
"end_offset": 7,
"type": "CN_WORD",
"position": 0
},
{
"token": "国歌",
"start_offset": 7,
"end_offset": 9,
"type": "CN_WORD",
"position": 1
}
]
}
@Test
public void analyzer_ik_max_word() throws Exception {
java.lang.String text = "提前祝大家春节快乐!";
TransportClient client = EsClient.get();
AnalyzeRequest request = (new AnalyzeRequest()).analyzer("ik_max_word").text(text);
List<AnalyzeResponse.AnalyzeToken> tokens = client.admin().indices().analyze(request).actionGet().getTokens();
System.out.println(tokens.size());//6
for (AnalyzeResponse.AnalyzeToken token : tokens) {
System.out.println(token.getTerm() + " ");
}
}
@Test
public void analyzer_ik_smart() throws Exception {
java.lang.String text = "提前祝大家春节快乐!";
TransportClient client = EsClient.get();
AnalyzeRequest request = (new AnalyzeRequest()).analyzer("ik_smart").text(text);
List<AnalyzeResponse.AnalyzeToken> tokens = client.admin().indices().analyze(request).actionGet().getTokens();
System.out.println(tokens.size());
for (AnalyzeResponse.AnalyzeToken token : tokens) {
System.out.println(token.getTerm() + " ");
}
}