Skip to content

Instantly share code, notes, and snippets.

@kcleong
Created February 2, 2018 14:41
Show Gist options
  • Save kcleong/b6b0758de740ca6a5acde93a15518e70 to your computer and use it in GitHub Desktop.
Save kcleong/b6b0758de740ca6a5acde93a15518e70 to your computer and use it in GitHub Desktop.
Dutch language analyzer in Elasticsearch
PUT ham
{
"mappings": {
"doc": {
"properties": {
"created": {
"type": "date"
},
"title": {
"type": "text",
"fields": {
"dutch": {
"type": "text",
"analyzer": "dutchy"
}
}
},
"description": {
"type": "text",
"analyzer": "dutchy"
}
}
}
},
"settings": {
"analysis": {
"filter": {
"dutch_stop": {
"type": "stop",
"stopwords": "_dutch_"
},
"dutch_kp_stemmer": {
"type": "stemmer",
"language": "dutch_kp"
},
"dutch_override": {
"type": "stemmer_override",
"rules": [
"calamiteiten=>calamiteit",
"calamiteit=>calamiteit",
"konijn=>lindelaan"
]
}
},
"analyzer": {
"dutchy": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"lowercase",
"dutch_stop",
"dutch_override",
"dutch_kp_stemmer"
]
}
}
}
}
}
GET ham/_settings
PUT ham/doc/bla
{
"title": "de artikeltje met vele calamiteiten, en grote zaken. scholen",
"created": "2018-02-02T12:00:00"
}
PUT ham/doc/vla
{
"title": "leentje leerde lotje lopen langs de lange lindelaan",
"created": "2018-02-02T12:00:00"
}
GET ham/doc/bla/
GET ham/doc/bla/_explain
{
"query": {
"query_string": {
"query": "lotje",
"analyzer": "dutchy"
}
}
}
}
GET ham/_search?pretty
{
"query": {
"query_string": {
"query": "konijn",
"analyzer": "dutchy"
}
}
}
}
GET ham/_analyze
{
"analyzer" : "dutchy",
"text" : "leentje leerde lotje lopen langs de lange lindelaan"
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment