IMPORTANT: No additional bug fixes or documentation updates
will be released for this version. For the latest information, see the
current release documentation.
Stemmer override token filter
editStemmer override token filter
editOverrides 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 |
---|---|
|
A list of mapping rules to use. |
|
A path (either relative to |
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" ] } } } } }