ES拼音分词自动补全实现

news2025/4/1 20:54:21

#测试拼音分词
POST /_analyze
{
"text":"如家酒店真不错",
"analyzer": "pinyin"
}
#这里把拼音的首字母放到这里，也说明了这句话没有被分词，而是作为一个整体出现的
#还把每一个字都形成了一个拼音，这也没什么用大多数情况下我们想用中文搜索

#自定义分词器创建test索引库的时候指定字段使用自定义的分词
PUT /test
{
"settings": {
"analysis": {
"analyzer": {
"my_analyzer":{
"tokenizer":"ik_max_word",
"filter":"py"
}
},
"filter":{
"py":{
"type":"pinyin",
"keep_full_pinyin":false,
"keep_joined_full_pinyin":true,
"keep_original":true,
"limit_first_letter_length":16,
"remove_duplicated_term":true,
"none_chinese_pinyin_tokenize":false
}
}
}
},
"mappings": {
"properties": {
"name":{
"type": "text",
"analyzer": "my_analyzer"
}
}
}
}

#删除索引库
DELETE /test

#查询索引库
GET /test

#在分词分词的汉字拼音都有，而且还有分词的首字母拼音
POST /test/_analyze
{
"text":["如家酒店真不错"],
"analyzer": "my_analyzer"
}

#在索引库test中插入一些文档
POST /test/_doc/1
{
"id":1,
"name":"狮子"
}

POST /test/_doc/2
{
"id":2,
"name":"虱子"
}

#搜索：有点问题搜索拼音，把同音字也搜到了
GET /test/_search
{
"query": {
"match": {
"name": "shizi"
}
}
}

#在创建的时候可以用拼音选择器，在搜索的时候不应该用拼音选择器，搜索用search_analyzer，在搜索是用户输入的是中文，用户用中文去搜，输入的是拼音，才拿拼音去搜

#自定义分词器创建test索引库的时候指定字段使用自定义的分词
PUT /test
{
"settings": {
"analysis": {
"analyzer": {
"my_analyzer":{
"tokenizer":"ik_max_word",
"filter":"py"
}
},
"filter":{
"py":{
"type":"pinyin",
"keep_full_pinyin":false,
"keep_joined_full_pinyin":true,
"keep_original":true,
"limit_first_letter_length":16,
"remove_duplicated_term":true,
"none_chinese_pinyin_tokenize":false
}
}
}
},
"mappings": {
"properties": {
"name":{
"type": "text",
"analyzer": "my_analyzer",
"search_analyzer": "ik_smart"
}
}
}
}
#现在搜索是用户输入的是中文，用户用中文去搜，输入的是拼音，才拿拼音去搜
GET /test/_search
{
"query": {
"match": {
"name": "虱子"
}
}
}

#自动补全参与自动补全的的字段必须是completion类型，字段的内容一般是用来补全的多个词条形成的数组
#创建索引库
PUT /test2
{
"mappings": {
"properties": {
"title":{
"type": "completion"
}
}
}
}

#查询索引库
GET /test2

#删除索引库
DELETE /test2

#插入数据
POST test2/_doc
{
"title":["Sorry","WH-1000XM3"]
}

POST test2/_doc
{
"title":["SK-IT","PITERA"]
}

POST test2/_doc
{
"title":["Nintendo","switch"]
}

#自动补全查询
GET /test2/_search
{
"suggest":{
"titleSuggest":{
"text":"s",
"completion":{
"field":"title",
"skip_duplicates":true,
"size":10
}
}
}
}

GET /test2/_search
{
"suggest":{
"titleSuggest":{
"text":"so",
"completion":{
"field":"title",
"skip_duplicates":true,
"size":10
}
}
}
}

#查看索引库的结构
GET /hotel/_mapping

#删除索引库
DELETE /hotel

#酒店数据索引库
#定义了两个分词器，全文检索用text_anlyzer，自动补全用completion_analyzer
PUT /hotel
{
"settings": {
"analysis": {
"analyzer": {
"text_anlyzer": {
"tokenizer": "ik_max_word",
"filter": "py"
},
"completion_analyzer": {
"tokenizer": "keyword",
"filter": "py"
}
},
"filter": {
"py": {
"type": "pinyin",
"keep_full_pinyin": false,
"keep_joined_full_pinyin": true,
"keep_original": true,
"limit_first_letter_length": 16,
"remove_duplicated_term": true,
"none_chinese_pinyin_tokenize": false
}
}
}
},
"mappings": {
"properties": {
"id":{
"type": "keyword"
},
"name":{
"type": "text",
"analyzer": "text_anlyzer",
"search_analyzer": "ik_smart",
"copy_to": "all"
},
"address":{
"type": "keyword",
"index": false
},
"price":{
"type": "integer"
},
"score":{
"type": "integer"
},
"brand":{
"type": "keyword",
"copy_to": "all"
},
"city":{
"type": "keyword"
},
"starName":{
"type": "keyword"
},
"business":{
"type": "keyword",
"copy_to": "all"
},
"location":{
"type": "geo_point"
},
"pic":{
"type": "keyword",
"index": false
},
"all":{
"type": "text",
"analyzer": "text_anlyzer",
"search_analyzer": "ik_smart"
},
"suggestion":{
"type": "completion",
"analyzer": "completion_analyzer"
}
}
}
}

#查询所有
GET /hotel/_search
{
"query":{
"match_all": {}
}
}

#自动补全查询
GET /hotel/_search
{
"suggest":{
"suggestions":{
"text":"h",
"completion":{
"field":"suggestion",
"skip_duplicates":true,
"size":10
}
}
}
}

 //自动补全查询：
    @Test
    void testSuggest() throws IOException {
        //准备requuest
        SearchRequest request=new SearchRequest("hotel");
        //准备DSL
        request.source().suggest(new SuggestBuilder().addSuggestion(
                "suggestions",
                SuggestBuilders.completionSuggestion("suggestion")
                        .prefix("hz")
                        .skipDuplicates(true)
                        .size(10)
        ));
        //发起请求
        SearchResponse response = client.search(request, RequestOptions.DEFAULT);
        //解析结果
        System.out.println(response);

        Suggest suggest = response.getSuggest();
        //根据补全查询名称，获取补全结果
        CompletionSuggestion suggestions= suggest.getSuggestion("suggestions");
        //获取options
        List<CompletionSuggestion.Entry.Option> options = suggestions.getOptions();
        //遍历
        for (CompletionSuggestion.Entry.Option option:options){
            String text = option.getText().toString();
            System.out.println(text);
        }
    }

@Override
    public List<String> getSuggestions(String prefix) {
        //准备requuest
        SearchRequest request=new SearchRequest("hotel");
        //准备DSL
        request.source().suggest(new SuggestBuilder().addSuggestion(
                "suggestions",
                SuggestBuilders.completionSuggestion("suggestion")
                        .prefix(prefix)
                        .skipDuplicates(true)
                        .size(10)
        ));

        try {
            //发起请求
            SearchResponse response = restHighLevelClient.search(request, RequestOptions.DEFAULT);
            //解析结果
            System.out.println(response);

            Suggest suggest = response.getSuggest();
            //根据补全查询名称，获取补全结果
            CompletionSuggestion suggestions= suggest.getSuggestion("suggestions");
            //获取options
            List<CompletionSuggestion.Entry.Option> options = suggestions.getOptions();
            //遍历
            List<String> list=new ArrayList<>(options.size());
            for (CompletionSuggestion.Entry.Option option:options){
                String text = option.getText().toString();
                System.out.println(text);
                list.add(text);
            }
            return list;
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }