› › ›

Stemmer override token filter

Overrides stemming algorithms, by applying a custom mapping, then protecting these terms from being modified by stemmers. Must be placed before any stemming filters.

Rules are mappings in the form of token1[, ..., tokenN] => override.

Setting	Description
`rules`	A list of mapping rules to use.
`rules_path`	A path (either relative to `config` location, or absolute) to a list of mappings.

Here is an example:

resp = client.indices.create(
    index="my-index-000001",
    settings={
        "analysis": {
            "analyzer": {
                "my_analyzer": {
                    "tokenizer": "standard",
                    "filter": [
                        "lowercase",
                        "custom_stems",
                        "porter_stem"
                    ]
                }
            },
            "filter": {
                "custom_stems": {
                    "type": "stemmer_override",
                    "rules_path": "analysis/stemmer_override.txt"
                }
            }
        }
    },
)
print(resp)

response = client.indices.create(
  index: 'my-index-000001',
  body: {
    settings: {
      analysis: {
        analyzer: {
          my_analyzer: {
            tokenizer: 'standard',
            filter: [
              'lowercase',
              'custom_stems',
              'porter_stem'
            ]
          }
        },
        filter: {
          custom_stems: {
            type: 'stemmer_override',
            rules_path: 'analysis/stemmer_override.txt'
          }
        }
      }
    }
  }
)
puts response

const response = await client.indices.create({
  index: "my-index-000001",
  settings: {
    analysis: {
      analyzer: {
        my_analyzer: {
          tokenizer: "standard",
          filter: ["lowercase", "custom_stems", "porter_stem"],
        },
      },
      filter: {
        custom_stems: {
          type: "stemmer_override",
          rules_path: "analysis/stemmer_override.txt",
        },
      },
    },
  },
});
console.log(response);

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "standard",
          "filter": [ "lowercase", "custom_stems", "porter_stem" ]
        }
      },
      "filter": {
        "custom_stems": {
          "type": "stemmer_override",
          "rules_path": "analysis/stemmer_override.txt"
        }
      }
    }
  }
}

Where the file looks like:

running, runs => run

stemmer => stemmer

You can also define the overrides rules inline:

resp = client.indices.create(
    index="my-index-000001",
    settings={
        "analysis": {
            "analyzer": {
                "my_analyzer": {
                    "tokenizer": "standard",
                    "filter": [
                        "lowercase",
                        "custom_stems",
                        "porter_stem"
                    ]
                }
            },
            "filter": {
                "custom_stems": {
                    "type": "stemmer_override",
                    "rules": [
                        "running, runs => run",
                        "stemmer => stemmer"
                    ]
                }
            }
        }
    },
)
print(resp)

response = client.indices.create(
  index: 'my-index-000001',
  body: {
    settings: {
      analysis: {
        analyzer: {
          my_analyzer: {
            tokenizer: 'standard',
            filter: [
              'lowercase',
              'custom_stems',
              'porter_stem'
            ]
          }
        },
        filter: {
          custom_stems: {
            type: 'stemmer_override',
            rules: [
              'running, runs => run',
              'stemmer => stemmer'
            ]
          }
        }
      }
    }
  }
)
puts response

const response = await client.indices.create({
  index: "my-index-000001",
  settings: {
    analysis: {
      analyzer: {
        my_analyzer: {
          tokenizer: "standard",
          filter: ["lowercase", "custom_stems", "porter_stem"],
        },
      },
      filter: {
        custom_stems: {
          type: "stemmer_override",
          rules: ["running, runs => run", "stemmer => stemmer"],
        },
      },
    },
  },
});
console.log(response);

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "standard",
          "filter": [ "lowercase", "custom_stems", "porter_stem" ]
        }
      },
      "filter": {
        "custom_stems": {
          "type": "stemmer_override",
          "rules": [
            "running, runs => run",
            "stemmer => stemmer"
          ]
        }
      }
    }
  }
}

© 2023-2025 Elasticsearch
As of September 2024, Elasticsearch is available under a choice of three licenses: the Server Side Public License (SSPL), the Elastic License, or the AGPLv3 (OSI approved).
Elasticsearch and the Elasticsearch logo are trademarks of Elasticsearch B.V., registered in the U.S. and in other countries.
https://www.elastic.co/guide/en/elasticsearch/reference/8.17/analysis-stemmer-override-tokenfilter.html