Snowball token filter
editSnowball token filter
editA filter that stems words using a Snowball-generated stemmer. The
language parameter controls the stemmer with the following available
values: Arabic, Armenian, Basque, Catalan, Danish, Dutch, English,
Estonian, Finnish, French, German, German2, Hungarian, Italian, Irish, Kp,
Lithuanian, Lovins, Norwegian, Porter, Portuguese, Romanian,
Russian, Serbian, Spanish, Swedish, Turkish.
For example:
resp = client.indices.create(
index="my-index-000001",
settings={
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "standard",
"filter": [
"lowercase",
"my_snow"
]
}
},
"filter": {
"my_snow": {
"type": "snowball",
"language": "Lovins"
}
}
}
},
)
print(resp)
response = client.indices.create(
index: 'my-index-000001',
body: {
settings: {
analysis: {
analyzer: {
my_analyzer: {
tokenizer: 'standard',
filter: [
'lowercase',
'my_snow'
]
}
},
filter: {
my_snow: {
type: 'snowball',
language: 'Lovins'
}
}
}
}
}
)
puts response
const response = await client.indices.create({
index: "my-index-000001",
settings: {
analysis: {
analyzer: {
my_analyzer: {
tokenizer: "standard",
filter: ["lowercase", "my_snow"],
},
},
filter: {
my_snow: {
type: "snowball",
language: "Lovins",
},
},
},
},
});
console.log(response);
PUT /my-index-000001
{
"settings": {
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "standard",
"filter": [ "lowercase", "my_snow" ]
}
},
"filter": {
"my_snow": {
"type": "snowball",
"language": "Lovins"
}
}
}
}
}