Elasticsearch拼音分词elasticsearch-analysis-pinyin

安装elasticsearch-analysis-pinyin插件

根据Elasticsearch版本选择对应的插件版本安装，下面是以6.8.0为例
拼音分词插件：https://github.com/medcl/elasticsearch-analysis-pinyin/releases
进入Elasticsearch安装目录下的bin目录，执行下面命令安装

./elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-pinyin/releases/download/v6.8.0/elasticsearch-analysis-pinyin-6.8.0.zip

查看已安装插件

./elasticsearch-plugin list

卸载插件

./elasticsearch-plugin remove 插件名称

安装完成后重启Elasticsearch

分词分析查看

GET /_analyze
{
  "text":"科技创新",
  "analyzer":"pinyin"
}

结果如下

{
  "tokens" : [
    {
      "token" : "ke",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "kjcx",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "ji",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 1
    },
    {
      "token" : "chuang",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 2
    },
    {
      "token" : "xin",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 3
    }
  ]
}

使用自定义分词

创建拼音索引分词

PUT /medcl/ 
{
    "index" : {
        "analysis" : {
            "analyzer" : {
                "pinyin_analyzer" : {
                    "tokenizer" : "my_pinyin"
                    }
            },
            "tokenizer" : {
                "my_pinyin" : {
                    "type" : "pinyin",
                    "keep_separate_first_letter" : false,
                    "keep_full_pinyin" : true,
                    "keep_original" : true,
                    "limit_first_letter_length" : 16,
                    "lowercase" : true,
                    "remove_duplicated_term" : true
                }
            }
        }
    }
}

测试分词器，分析一个中文名称，如：刘德华

GET /medcl/_analyze
{
  "text": ["刘德华"],
  "analyzer": "pinyin_analyzer"
}

结果如下

{
  "tokens" : [
    {
      "token" : "liu",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "刘德华",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "ldh",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "de",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 1
    },
    {
      "token" : "hua",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 2
    }
  ]
}

创建映射

POST /medcl/folks/_mapping 
{
    "folks": {
        "properties": {
            "name": {
                "type": "keyword",
                "fields": {
                    "pinyin": {
                        "type": "text",
                        "store": false,
                        "term_vector": "with_offsets",
                        "analyzer": "pinyin_analyzer",
                        "boost": 10
                    }
                }
            }
        }
    }
}

添加文档

POST /medcl/folks/andy 
{
	"name":"刘德华"
}

搜索测试

GET /medcl/folks/_search
{
	"query": {
    	"match": {
      		"name.pinyin": "liu"
    	}
  	}
}

搜索结果如下

{
	"took": 23,
	"timed_out": false,
	"_shards": {
		"total": 5,
		"successful": 5,
		"skipped": 0,
		"failed": 0
	},
	"hits": {
		"total": 1,
		"max_score": 3.439677,
		"hits": [{
			"_index": "medcl",
			"_type": "folks",
			"_id": "andy",
			"_score": 3.439677,
			"_source": {
				"name": "刘德华"
			}
		}]
	}
}

自定义拼音首字母分词

PUT /medcl1/ 
{
    "index" : {
        "analysis" : {
            "analyzer" : {
                "user_name_analyzer" : {
                    "tokenizer" : "whitespace",
                    "filter" : "pinyin_first_letter_and_full_pinyin_filter"
                }
            },
            "filter" : {
                "pinyin_first_letter_and_full_pinyin_filter" : {
                    "type" : "pinyin",
                    "keep_first_letter" : true,
                    "keep_full_pinyin" : false,
                    "keep_none_chinese" : true,
                    "keep_original" : false,
                    "limit_first_letter_length" : 16,
                    "lowercase" : true,
                    "trim_whitespace" : true,
                    "keep_none_chinese_in_first_letter" : true
                }
            }
        }
    }
}

测试分词器

GET /medcl1/_analyze
{
  "text": ["刘德华 张学友 郭富城 黎明 四大天王"],
  "analyzer": "user_name_analyzer"
}

结果

{
	"tokens": [{
			"token": "ldh",
			"start_offset": 0,
			"end_offset": 3,
			"type": "word",
			"position": 0
		},
		{
			"token": "zxy",
			"start_offset": 4,
			"end_offset": 7,
			"type": "word",
			"position": 1
		},
		{
			"token": "gfc",
			"start_offset": 8,
			"end_offset": 11,
			"type": "word",
			"position": 2
		},
		{
			"token": "lm",
			"start_offset": 12,
			"end_offset": 14,
			"type": "word",
			"position": 3
		},
		{
			"token": "sdtw",
			"start_offset": 15,
			"end_offset": 19,
			"type": "word",
			"position": 4
		}
	]
}

设置映射

POST /medcl1/folks/_mapping 
{
    "folks": {
        "properties": {
            "name": {
                "type": "keyword",
                "fields": {
                    "pinyin": {
                        "type": "text",
                        "store": false,
                        "term_vector": "with_offsets",
                        "analyzer": "user_name_analyzer",
                        "boost": 10
                    }
                }
            }
        }
    }
}

添加数据

POST /medcl1/folks/_bulk
{"index": {}}
{"name": "张学友"}
{"index": {}}
{"name": "刘德华"}
{"index": {}}
{"name": "黎明"}
{"index": {}}
{"name": "郭富城"}
{"index": {}}
{"name": "刘德华 张学友 郭富城 黎明 四大天王"}

搜索测试

GET /medcl1/folks/_search
{
	"query": {
		"match": {
			"name.pinyin": "ldh zxy"
		}
	}
}

搜索结果

{
	"took": 85,
	"timed_out": false,
	"_shards": {
		"total": 5,
		"successful": 5,
		"skipped": 0,
		"failed": 0
	},
	"hits": {
		"total": 3,
		"max_score": 0.6931472,
		"hits": [{
				"_index": "medcl1",
				"_type": "folks",
				"_id": "Z2EUYHIBkE_Scf7WBrTD",
				"_score": 0.6931472,
				"_source": {
					"name": "张学友"
				}
			},
			{
				"_index": "medcl1",
				"_type": "folks",
				"_id": "aGEUYHIBkE_Scf7WBrTD",
				"_score": 0.6931472,
				"_source": {
					"name": "刘德华"
				}
			},
			{
				"_index": "medcl1",
				"_type": "folks",
				"_id": "2WEcYHIBkE_Scf7WarSe",
				"_score": 0.5753642,
				"_source": {
					"name": "刘德华 张学友 郭富城 黎明 四大天王"
				}
			}
		]
	}
}