用ES实现拼音搜索策略

最新推荐文章于 2024-01-11 11:30:50 发布

百木森森

最新推荐文章于 2024-01-11 11:30:50 发布

阅读量1.6k

点赞数

文章标签： elasticsearch 搜索引擎

本文链接：https://blog.csdn.net/baimusensen/article/details/127002320

版权

构建拼音索引

Step 1 在ES中安装pinyin分词器

安装步骤详见网上的众多介绍，这里不赘述，ES-pinyin分词器安装。pinyin的开源见：GitHub - medcl/elasticsearch-analysis-pinyin: This Pinyin Analysis plugin is used to do conversionb

Step 2 新建索引并初始化测试数据

PUT idx_test_user
{
  "mappings": {
    "dynamic": false,
    "properties": {
      "name": {
       "analyzer": "standard",
       "type": "text",
       "fields": {
         "pinyin": {
           "type": "text",
           "analyzer": "index_pinyin_analyzer"
         }
       }
      }
    }
  },
  "settings": {
    "analysis": {
      "analyzer": {
        "index_pinyin_analyzer": {                         // MARK 1
          "tokenizer": "index_pinyin_tokenizer"
        },
        "search_pinyin_analyzer": {                        // MARK 2
          "tokenizer": "search_pinyin_tokenzier"
        }
      },
      "tokenizer": {
        "index_pinyin_tokenizer": {
          "keep_joined_full_pinyin" : "true",
          "lowercase" : "true",
          "none_chinese_pinyin_tokenize" : "false",
          "keep_none_chinese_in_joined_full_pinyin" : "true",
          "keep_original" : "true",
          "keep_none_chinese_together" : "true",
          "remove_duplicated_term" : "false",
          "keep_separate_first_letter" : "false",
          "type" : "pinyin",
          "limit_first_letter_length" : "16",
          "keep_full_pinyin" : "true"
        },
        "search_pinyin_tokenzier": {
          "keep_joined_full_pinyin" : "true",
          "lowercase" : "true",
          "keep_original" : "true",
          "remove_duplicated_term" : "false",