elasticsearch 深入 —— normalizer

keyword字段的normalizer属性类似于分析器，只是它保证分析链生成单个token。

在索引关键字之前，以及在通过诸如match查询之类的查询解析器或者通过诸如term查询之类的术语级查询搜索keyword字段时的搜索，应用规范化器——normalizer。

PUT index
{
  "settings": {
    "analysis": {
      "normalizer": {
        "my_normalizer": {
          "type": "custom",
          "char_filter": [],
          "filter": ["lowercase", "asciifolding"]
        }
      }
    }
  },
  "mappings": {
    "_doc": {
      "properties": {
        "foo": {
          "type": "keyword",
          "normalizer": "my_normalizer"
        }
      }
    }
  }
}

PUT index/_doc/1
{
  "foo": "BÀR"
}

PUT index/_doc/2
{
  "foo": "bar"
}

PUT index/_doc/3
{
  "foo": "baz"
}

POST index/_refresh

GET index/_search
{
  "query": {
    "term": {
      "foo": "BAR"
    }
  }
}

GET index/_search
{
  "query": {
    "match": {
      "foo": "BAR"
    }
  }
}

上述查询与文档1和2匹配，因为在索引和查询时都将BÀR转换为bar 。

{
  "took": $body.took,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "skipped" : 0,
    "failed": 0
  },
  "hits": {
    "total": 2,
    "max_score": 0.2876821,
    "hits": [
      {
        "_index": "index",
        "_type": "_doc",
        "_id": "2",
        "_score": 0.2876821,
        "_source": {
          "foo": "bar"
        }
      },
      {
        "_index": "index",
        "_type": "_doc",
        "_id": "1",
        "_score": 0.2876821,
        "_source": {
          "foo": "BÀR"
        }
      }
    ]
  }
}

此外，关键字在索引之前被转换的事实也意味着聚合返回归一化值：

GET index/_search
{
  "size": 0,
  "aggs": {
    "foo_terms": {
      "terms": {
        "field": "foo"
      }
    }
  }
}

返回：

{
  "took": 43,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "skipped" : 0,
    "failed": 0
  },
  "hits": {
    "total": 3,
    "max_score": 0.0,
    "hits": []
  },
  "aggregations": {
    "foo_terms": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "key": "bar",
          "doc_count": 2
        },
        {
          "key": "baz",
          "doc_count": 1
        }
      ]
    }
  }
}