Indus

Once you are certain of your script parametrization, it is quite comfortable to store it in Elasticsearch.

Parametrization store exemple

Mapping

{
  "settings": {
    "index.number_of_shards": 1,
    "index.number_of_replicas": 0
  },
  "mappings": {
    "entity-configuration": {
      "properties": {
        "name": {
          "type": "string",
          "index": "not_analyzed"
        },
        "comparator": {
          "type": "string",
          "index": "not_analyzed"
        },
        "low": {
          "type": "double"
        },
        "high": {
          "type": "double"
        },
        "cleaners": {
            "type": "string",
            "index" : "not_analyzed"
        }
      }
    }
  }
}

Parameters

{
  "entity" : {
    "fields" : [ {
      "field" : "city",
      "cleaners" : [ {
        "name" : "no.priv.garshol.duke.cleaners.TrimCleaner"
      }, {
        "name" : "no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner"
      } ],
      "high" : 0.95,
      "comparator" : {
        "name" : "no.priv.garshol.duke.comparators.JaroWinkler"
      },
      "low" : 0.1
    }, {
      "field" : "state",
      "cleaners" : [ {
        "name" : "no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner"
      } ],
      "high" : 0.95,
      "comparator" : {
        "name" : "no.priv.garshol.duke.comparators.JaroWinkler"
      },
      "low" : 0.1
    }, {
      "field" : "population",
      "cleaners" : [ {
        "name" : "no.priv.garshol.duke.cleaners.DigitsOnlyCleaner"
      } ],
      "high" : 0.95,
      "comparator" : {
        "name" : "no.priv.garshol.duke.comparators.NumericComparator"
      },
      "low" : 0.1
    }, {
      "field" : "position",
      "cleaners" : [ {
        "name" : "no.priv.garshol.duke.cleaners.LowerCaseNormalizeCleaner"
      } ],
      "high" : 0.95,
      "comparator" : {
        "name" : "no.priv.garshol.duke.comparators.GeopositionComparator",
        "params" : {
          "max-distance" : "100"
        }
      },
      "low" : 0.1
    } ]
  }
}

Request

{
  "size": 4,
  "query": {
    "custom_score": {
      "query": {
        "match_all": {
        }
      },
      "script": "entity-resolution",
      "lang": "native",
      "params": {
        "entity": {
          "configuration": {
            "index": "entity",
            "type": "entity-configuration",
            "name": "test"
          },
          "fields": [
            {
              "field": "city",
              "value": "South"
            },
            {
              "field": "state",
              "value": "ME"
            },
            {
              "field": "population",
              "value": "26000"
            },
            {
              "field": "position",
              "value": "43,70"
            }
          ]
        }
      }
    }
  }
}