spring data es拼音插件

1. 下载安装

   • 下载和es对应版本的拼音插件，现用的es版本是2.4.5，对应下载1.8.5版本插件
     https://github.com/medcl/elasticsearch-analysis-pinyin/releases/download/v1.8.5/elasticsearch-analysis-pinyin-1.8.5.zip
   • 在{ES_HOME}/plugins下新建pinyin目录
   • 解压插件zip文件到{ES_HOME}/plugins/pinyin/下
   • 重启es

2. 添加index

 http://localhost:9200/phr/-d
'{
    "index" : {
        "analysis" : {
            "analyzer" : {
                "pinyin_analyzer" : {
                    "tokenizer" : "my_pinyin"
                    }
            },
            "tokenizer" : {
                "my_pinyin" : {
                    "type" : "pinyin",
                    //true：支持首字母  eg: 刘德华 -> [ldh]
                    "keep_first_letter": true,
                    //false：不支持首字母分隔 eg: 刘德华 -> [l,d,h]
                    "keep_separate_first_letter" : false,   
                    //true：支持全拼  eg: 刘德华 -> [liu,de,hua]
                    "keep_full_pinyin" : true,
                    //true：支持全拼  eg: 刘德华 -> [liudehua]
                    "keep_joined_full_pinyin": true,
                    //设置最大长度
                    "limit_first_letter_length" : 16,
                    //小写非中文字母
                    "lowercase" : true,
                    //重复的项将被删除,eg: 德的 -> de
                    "remove_duplicated_term" : true
                }
            }
        }
    }
}'

3.测试分词

http://localhost:9200/phr/_analyze?text=刘德华&analyzer=pinyin_analyzer

    {
        "tokens": [
            {
                "token": "liu",
                "start_offset": 0,
                "end_offset": 1,
                "type": "word",
                "position": 0
            },
            {
                "token": "de",
                "start_offset": 1,
                "end_offset": 2,
                "type": "word",
                "position": 1
            },
            {
                "token": "hua",
                "start_offset": 2,
                "end_offset": 3,
                "type": "word",
                "position": 2
            },
            {
                "token": "刘德华",
                "start_offset": 0,
                "end_offset": 3,
                "type": "word",
                "position": 3
            },
            {
                "token": "liudehua",
                "start_offset": 0,
                "end_offset": 8,
                "type": "word",
                "position": 4
            },
            {
                "token": "ldh",
                "start_offset": 0,
                "end_offset": 3,
                "type": "word",
                "position": 5
            }
        ]
    }

4.es bean

public class TestEsBean {
        @Id
        public Long id;

        @Field(type = FieldType.String, searchAnalyzer = "pinyin_analyzer", analyzer = "pinyin_analyzer")
        private String name;

        public Long getId() {
            return id;
        }

        public void setId(Long id) {
            this.id = id;
        }

        public String getName() {
            return name;
        }

        public void setName(String name) {
            this.name = name;
        }
    }

type：默认auto，这里要显示指定字段类型
analyzer：建立索引时指定的分词器
searchAnalyzer：搜索时使用的分词器