40_Compound_words.json

# Delete the `my_index` index
DELETE /my_index

# Map the `text` field to be create ngrams of length 3
PUT /my_index
{
  "settings": {
    "analysis": {
      "filter": {
        "trigrams_filter": {
          "type": "ngram",
          "min_gram": 3,
          "max_gram": 3
        }
      },
      "analyzer": {
        "trigrams": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "lowercase",
            "trigrams_filter"
          ]
        }
      }
    }
  },
  "mappings": {
    "my_type": {
      "properties": {
        "text": {
          "type": "string",
          "analyzer": "trigrams"
        }
      }
    }
  }
}

# Test the analyzer
GET /my_index/_analyze?analyzer=trigrams&text=Weißkopfseeadler

# Index some example docs
POST /my_index/my_type/_bulk
{"index":{"_id":1}}
{"text":"Aussprachewörterbuch"}
{"index":{"_id":2}}
{"text":"Militärgeschichte"}
{"index":{"_id":3}}
{"text":"Weißkopfseeadler"}
{"index":{"_id":4}}
{"text":"Weltgesundheitsorganisation"}
{"index":{"_id":5}}
{"text":"Rindfleischetikettierungsüberwachungsaufgabenübertragungsgesetz"}

# Simple search - matches correct doc
GET /my_index/_search
{
  "query": {
    "match": {
      "text": "Adler"
    }
  }
}

# Simple search - matches too many docs!
GET /my_index/_search
{
  "query": {
    "match": {
      "text": {
        "query": "Gesundheit"
      }
    }
  }
}

# Explanation of why the above query matches too many docs
GET /my_index/_validate/query?explain
{
  "query": {
    "match": {
      "text": {
        "query": "Gesundheit"
      }
    }
  }
}

# Trimming the long tail with minimum_should_match
GET /my_index/_search
{
  "query": {
    "match": {
      "text": {
        "query": "Gesundheit",
        "minimum_should_match": "80%"
      }
    }
  }
}