Elasticsearchのstring fieldに対する各filterの挙動

個人的メモ

準備

$ curl -XPUT localhost:9200/test_idx/test_type/1 -d '{"test_str": "foo"}'
{"_index":"test_idx","_type":"test_type","_id":"1","_version":1,"created":true}
$ curl -XPUT localhost:9200/test_idx/test_type/2 -d '{"test_str": ""}'
{"_index":"test_idx","_type":"test_type","_id":"2","_version":1,"created":true}
$ curl -XPUT localhost:9200/test_idx/test_type/3 -d '{"test_str": null}'
{"_index":"test_idx","_type":"test_type","_id":"3","_version":1,"created":true}

filtering

exitis filter

GET test_idx/test_type/_search
{
  "filter": {
    "exists": {
      "field": "test_str"
    }
  }
}

{
   "took": 3,
   "timed_out": false,
   "_shards": {
      "total": 5,
      "successful": 5,
      "failed": 0
   },
   "hits": {
      "total": 2,
      "max_score": 1,
      "hits": [
         {
            "_index": "test_idx",
            "_type": "test_type",
            "_id": "1",
            "_score": 1,
            "_source": {
               "test_str": "foo"
            }
         },
         {
            "_index": "test_idx",
            "_type": "test_type",
            "_id": "2",
            "_score": 1,
            "_source": {
               "test_str": ""
            }
         }
      ]
   }
}

missing filter

GET test_idx/test_type/_search
{
  "filter": {
    "missing": {
      "field": "test_str"
    }
  }
}

{
   "took": 1,
   "timed_out": false,
   "_shards": {
      "total": 5,
      "successful": 5,
      "failed": 0
   },
   "hits": {
      "total": 1,
      "max_score": 1,
      "hits": [
         {
            "_index": "test_idx",
            "_type": "test_type",
            "_id": "3",
            "_score": 1,
            "_source": {
               "test_str": null
            }
         }
      ]
   }
}

term filter (by empty string)

GET test_idx/test_type/_search
{
  "filter": {
    "term": {
      "test_str": ""
    }
  }
}

{
   "took": 5,
   "timed_out": false,
   "_shards": {
      "total": 5,
      "successful": 5,
      "failed": 0
   },
   "hits": {
      "total": 0,
      "max_score": null,
      "hits": []
   }
}