Question

以下设置适用于我们，但我们可以看到更好的结果想保留特殊字符。可以有人建议什么更改以下保存特殊字符所需的设置？以下设置适用于我们，但我们可以看到更好的结果我想'保留特殊字符。可以有人建议什么更改以下保存特殊字符所需的设置？

      we would like to preserve following special characters...
      + - = && || > < ! ( ) { } [ ] ^ " ~ * ? : \ /

       settingsSimple() {
      curl -XPUT "$es_host:9200/$INDEX/" --data-binary @- <<EOF 
      {
       "settings": {
        "index": {
        "number_of_shards": $(($(curl -s $es_hostname:9200/_cat/nodes | wc -  
         l)*2)),
         "number_of_replicas": 0,
         "refresh_interval": "-1"
     },
      "analysis": {
       "char_filter": {
          "chr_decoder": {
              "type": "mapping",
             "mappings": [
        "2=>tu",
        "@=>a",
        "$=>s",
        ".=>-",
        "’=> ",
        ":=> ",
        "!=> "
      ],
      "preserve_original": true
     },
     "chr_decoder2": {
      "type": "mapping",
      "mappings": [
        "2=>tu",
        "@=>a",
        "$=>s"
      ],
      "preserve_original": true
    },
    "dash_remover": {
      "type": "pattern_replace",
      "pattern": "-",
      "replacement": ""
    }
   },
  "analyzer": {
    "all_analyzer": {
      "char_filter": [
        "chr_decoder",
        "dash_remover"
      ],
      "tokenizer": "standard",
      "filter": [
        "lowercase",
        "ascii_folding",
        "stop_filter"
      ]
    },
    "name_analyzer": {
      "char_filter": [
        "chr_decoder2"
      ],
      "tokenizer": "ngram_tokenizer",
      "filter": [
        "lowercase",
        "asciifolding"
      ]
    },
    "keep_analyzer": {
      "char_filter": [
        "chr_decoder2"
      ],
      "tokenizer": "whitespace",
      "filter": [
        "lowercase",
        "asciifolding"
      ]
    }
  },
  "filter": {
    "ascii_folding": {
      "type": "asciifolding",
      "preserve_original": false
    },
    "stop_filter": {
      "type": "stop",
      "stopwords": [
        "and",
        "the"
      ]
    },
    "shingle_filter": {
      "type": "shingle",
      "min_shingle_size": 2,
      "max_shingle_size": 3,
      "output_unigrams": true,
      "token_separator": " ",
      "filler_token": " "
    }
  },
  "tokenizer": {
    "ngram_tokenizer": {
      "type": "edgeNGram",
      "min_gram": "2",
      "max_gram": "20",
      "token_chars": [
        "letter",
        "digit"
      ],
      "preserve_original": true
    }
    }
    }
    }
    }
   EOF
   }   

  Query I use follows here:
  {
    "from" : 0,
    "size" : 10,
    "query" : {
    "function_score" : {
    "query" : {
    "bool" : {
      "should" : [ {
        "query_string" : {
          "query" : "!Mayday!",
          "fields" : [ "enm^8", "pnm^12", "upnm^31", "_all^10" ],
          "default_operator" : "and",
          "analyzer" : "all_analyzer"
        }
      }, {
        "query_string" : {
          "query" : "!Mayday!",
          "fields" : [ "_all^8", "enm^8", "pnm^12", "upnm^31" ],
          "default_operator" : "and",
          "analyzer" : "keep_analyzer"
        }
      } ]
    }
    },
    "filter" : {
    "terms" : {
      "sml" : [ "0" ]
     }
    },
     "functions" : [ {
      "field_value_factor" : {
      "field" : "pop",
      "factor" : 6.0,
      "missing" : 0.0,
      "modifier" : "none"
      }
      } ],
   "boost_mode" : "sum"
      }
      },
      "fields" : [ "uid", "enm", "pid", "upid", "pnm", "rd", "upnm" ]
       }

Answer 1

我有同样的问题。因为我正在使用＆＃34;空白＆＃34; tokenizer它保留所有特殊字符：

我已经通过以下方式创建了索引模板。然后，所有输入，聚合和查询都正确显示我的变量。

PUT _template/tracking_all
{
  "template": "tracking*",
  "version": 1,
  "settings": {
    "number_of_shards": 1,
    "analysis": {
      "analyzer": {
        "default": {
           "type": "custom",
           "filter": [ "lowercase" ],
           "tokenizer": "whitespace"
           }
        }
      }
    }
  }
}

在标记化期间保留特殊字符

1 个答案: