标签：prope 中华 tps tokenizer spring nes col temp div
elasticsearch 自定义分词器
安装拼音分词器、ik分词器
拼音分词器： https://github.com/medcl/elasticsearch-analysis-pinyin/releases
ik分词器：https://github.com/medcl/elasticsearch-analysis-ik/releases
下载源码需要使用maven打包
下载构建好的压缩包解压后放直接在elasticsearch安装目录下 plugins文件夹下，可以重命名
1.在es中设置分词
创建索引，添加setting属性
PUT myindex { "settings": { "index":{ "analysis":{ "analyzer":{ "ik_pinyin_analyzer":{ "type":"custom", "tokenizer":"ik_smart", "filter":"pinyin_filter" } }, "filter":{ "pinyin_filter":{ "type":"pinyin", "keep_separate_first_letter" : false,
"keep_full_pinyin" : true,
"keep_original" : false,
"limit_first_letter_length" : 10,
"lowercase" : true,
"remove_duplicated_term" : true } } } } } }
添加属性 设置mapping属性
PUT myindex/_mapping/users { "properties": { "uname":{ "type": "text", "analyzer": "ik_smart", "search_analyzer": "ik_smart", "fields": { "my_pinyin":{ "type": "text" , "analyzer": "ik_pinyin_analyzer", "search_analyzer": "ik_pinyin_analyzer" } } }, "age":{ "type": "integer" } } }
2.spring data elasticsearch设置分词
创建实体类
@Mapping(mappingPath = "elasticsearch_mapping.json")//设置mapping
@Setting(settingPath = "elasticsearch_setting.json")//设置setting
@Document(indexName = "myindex",type = "users")
public class User {
@Id
private Integer id;
//
// @Field(type =FieldType.keyword ,analyzer = "pinyin_analyzer",searchAnalyzer = "pinyin_analyzer")//没有作用
private String name1;
@Field(type = FieldType.keyword)
private String userName;
@Field(type = FieldType.Nested)
private List<Product> products;
}
在resources下创建elasticsearch_mapping.json 文件
{ "properties": { "uname": { "type": "text", "analyzer": "ik_smart", "search_analyzer": "ik_smart", "fields": { "my_pinyin": { "type": "text", "analyzer": "ik_pinyin_analyzer", "search_analyzer": "ik_pinyin_analyzer" } } }, "age": { "type": "integer" } } }
在resources下创建elasticsearch_setting.json 文件
{
"index": {
"analysis": {
"analyzer": {
"ik_pinyin_analyzer": {
"type": "custom",
"tokenizer": "ik_smart",
"filter": "pinyin_filter"
}
},
"filter": {
"pinyin_filter": {
"type": "pinyin",
//true：支持首字母
"keep_first_letter":true,
//false：不支持首字母分隔
"keep_separate_first_letter": false,
//true：支持全拼
"keep_full_pinyin": true,
"keep_original": false,
//设置最大长度
"limit_first_letter_length": 10,
//小写非中文字母
"lowercase": true,
//重复的项将被删除
"remove_duplicated_term": true
}
}
}
}
}
程序启动后分词并没有设置分词
实体创建后需要加上，创建的索引才可以分词
elasticsearchTemplate.putMapping(User.class);
elasticsearch 拼音+ik分词，spring data elasticsearch 拼音分词
标签：prope 中华 tps tokenizer spring nes col temp div
原文地址：https://www.cnblogs.com/double-yuan/p/9742567.html
