elasticsearch之拼音搜索

拼音搜索在中文搜索环境中是经常使用的一种功能，用户只需要输入关键词的拼音全拼或者拼音首字母，搜索引擎就可以搜索出相关结果。在国内，中文输入法基本上都是基于汉语拼音的，这种在符合用户输入习惯的条件下缩短用户输入时间的功能是非常受欢迎的；

一、安装拼音搜索插件

下载对应版本的elasticsearch-analysis-pinyin插件；

https://github.com/medcl/elasticsearch-analysis-pinyin/releases/download/v7.9.2/elasticsearch-analysis-pinyin-7.9.2.zip

在elasticsearch安装目录下的的plugin目录新建analysis-pinyin目录，并解压下载的安装包；

重启elasticsearch，可以看到已经正常加载拼音插件

[2022-01-13T20:37:25,368][INFO ][o.e.p.PluginsService     ] [mango] loaded plugin [analysis-pinyin]

二、使用拼音插件

试一下分词效果，可以看到除了每个词的全频，还有每个字的首字母缩写；

POST _analyze

{

  "analyzer": "pinyin",

  "text": "我爱你,中国"

}

{

  "tokens" : [

    {

      "token" : "wo",

      "start_offset" : 0,

      "end_offset" : 0,

      "type" : "word",

      "position" : 0

    },

    {

      "token" : "wanzg",

      "start_offset" : 0,

      "end_offset" : 0,

      "type" : "word",

      "position" : 0

    },

    {

      "token" : "ai",

      "start_offset" : 0,

      "end_offset" : 0,

      "type" : "word",

      "position" : 1

    },

    {

      "token" : "ni",

      "start_offset" : 0,

      "end_offset" : 0,

      "type" : "word",

      "position" : 2

    },

    {

      "token" : "zhong",

      "start_offset" : 0,

      "end_offset" : 0,

      "type" : "word",

      "position" : 3

    },

    {

      "token" : "guo",

      "start_offset" : 0,

      "end_offset" : 0,

      "type" : "word",

      "position" : 4

    }

  ]

}

自定义pinyin filter，并创建mapping；

PUT /milk

{

  "settings": {

    "analysis": {

      "filter": {

        "pinyin_filter":{

          "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

}

      },

      "analyzer": {

        "ik_pinyin_analyzer":{

          "tokenizer":"ik_max_word",

           "filter":["pinyin_filter"]

        }

      }

    }

  },

  "mappings": {

    "properties": {

      "brand":{

        "type": "text",

        "analyzer": "ik_pinyin_analyzer"

      },

      "series":{

        "type": "text",

        "analyzer": "ik_pinyin_analyzer"

      },

      "price":{

        "type": "float"

      }

    }

  }

}

批量索引文档；

POST _bulk

{"index":{"_index":"milk", "_id":1}}}

{"brand":"蒙牛", "series":"特仑苏", "price":60}

{"index":{"_index":"milk", "_id":2}}}

{"brand":"蒙牛", "series":"真果粒", "price":40}

{"index":{"_index":"milk", "_id":3}}}

{"brand":"华山牧", "series":"华山牧", "price":49.90}

{"index":{"_index":"milk", "_id":4}}}

{"brand":"伊利", "series":"安慕希", "price":49.90}

{"index":{"_index":"milk", "_id":5}}}

{"brand":"伊利", "series":"金典", "price":49.90}

搜索tls，可以看到已经匹配到对应的记录；

POST milk/_search

{

  "query": {

    "match_phrase_prefix": {

      "series": "tl"

    }

  }

}

{

  "took" : 1,

  "timed_out" : false,

  "_shards" : {

    "total" : 1,

    "successful" : 1,

    "skipped" : 0,

    "failed" : 0

  },

  "hits" : {

    "total" : {

      "value" : 1,

      "relation" : "eq"

    },

    "max_score" : 6.691126,

    "hits" : [

      {

        "_index" : "milk",

        "_type" : "_doc",

        "_id" : "1",

        "_score" : 6.691126,

        "_source" : {

          "brand" : "蒙牛",

          "series" : "特仑苏",

          "price" : 60

        }

      }

    ]

  }

}

可以看到查询直接使用MultiPhraseQuery来实现对两个位置字符的定位；

POST milk/_search

{

  "query": {

    "match_phrase_prefix": {

      "series": "tl"

    }

  },

  "highlight": {

    "fields": {

      "series": {}

    }

  }

}

{

  "profile" : {

    "shards" : [

      {

        "id" : "[OoNXoregTmKQAFotUgOeaA][milk][0]",

        "searches" : [

          {

            "query" : [

              {

                "type" : "MultiPhraseQuery",

                "description" : "series:\"(t tl) (li l lun)\"",

                "time_in_nanos" : 177400,

                "breakdown" : {

                  "set_min_competitive_score_count" : 0,

                  "match_count" : 1,

                  "shallow_advance_count" : 0,

                  "set_min_competitive_score" : 0,

                  "next_doc" : 5400,

                  "match" : 12800,

                  "next_doc_count" : 1,

                  "score_count" : 1,

                  "compute_max_score_count" : 0,

                  "compute_max_score" : 0,

                  "advance" : 9200,

                  "advance_count" : 1,

                  "score" : 3900,

                  "build_scorer_count" : 2,

                  "create_weight" : 40800,

                  "shallow_advance" : 0,

                  "create_weight_count" : 1,

                  "build_scorer" : 105300

                }

              }

            ],

            "rewrite_time" : 45700,

            "collector" : [

              {

                "name" : "SimpleTopScoreDocCollector",

                "reason" : "search_top_hits",

                "time_in_nanos" : 14500

              }

            ]

          }

        ],

        "aggregations" : [ ]

      }

    ]

  }

}

查询也可以返回高亮信息

POST milk/_search

{

  "query": {

    "match_phrase_prefix": {

      "series": "tl"

    }

  },

  "highlight": {

    "fields": {

      "series": {}

    }

  }

}

{

  "took" : 2,

  "timed_out" : false,

  "_shards" : {

    "total" : 1,

    "successful" : 1,

    "skipped" : 0,

    "failed" : 0

  },

  "hits" : {

    "total" : {

      "value" : 1,

      "relation" : "eq"

    },

    "max_score" : 6.691126,

    "hits" : [

      {

        "_index" : "milk",

        "_type" : "_doc",

        "_id" : "1",

        "_score" : 6.691126,

        "_source" : {

          "brand" : "蒙牛",

          "series" : "特仑苏",

          "price" : 60

        },

        "highlight" : {

          "series" : [

            "<em>特</em><em>仑</em>苏"

          ]

        }

      }

    ]

  }

}

巴特西

elasticsearch之拼音搜索

最新文章

热门文章