Compound words demo with ngram tokenizer elasticsearch

elasticsearch ngram tokenizer

#!/bin/bash

export ELASTICSEARCH_ENDPOINT="http://localhost:9200"

# Create indexes

curl -XPUT "$ELASTICSEARCH_ENDPOINT/play" -d '{
    "settings": {
        "analysis": {
            "analyzer": {
                "myAnalyzer": {
                    "type": "custom",
                    "tokenizer": "my_toknizer"
                }
            },
            "tokenizer": {
                "my_toknizer": {
                    "type": "ngram",
                    "min_gram": 2,
                    "max_gram": 3
                }
            }
        }
    },
    "mappings": {
        "type": {
            "properties": {
                "foo": {
                    "type": "string",
                    "analyzer": "myAnalyzer"
                }
            }
        }
    }
}'

# Index documents
curl -XPOST "$ELASTICSEARCH_ENDPOINT/_bulk?refresh=true" -d '
{"index":{"_index":"play","_type":"type"}}
{"foo":"arbeid"}
{"index":{"_index":"play","_type":"type"}}
{"foo":"arbeidsmiljø"}
{"index":{"_index":"play","_type":"type"}}
{"foo":"arbeidsmiljølovgivning"}
'

# Do searches

curl -XPOST "$ELASTICSEARCH_ENDPOINT/_search?pretty" -d '
{
    "query": {
        "match": {
            "foo": "miljø"
        }
    }
}
'