Ukázka ICU Collation pro češtinu. Předpokládá Elasticsearch 0.90.0 a nainstalovaný ICU plugin 1.9.0

gistfile1.sh

#!/bin/sh

curl -X DELETE 'localhost:9200/i/'

curl -X POST 'localhost:9200/i/' -d '{
  "settings" : {
    "number_of_shards" : 1,
    "number_of_replicas" : 0,
    "analysis" : {
      "analyzer" : {
        "cs_icu_analyzer" : {
          "type" : "custom",
          "tokenizer" : "standard",
          "filter" : ["cs_icu_collation"]
        }
      },
      "filter" : {
        "cs_icu_collation" : {
          "type" : "icu_collation",
          "language" : "cs"
        }
      }
    }
  },
  "mappings" : {
    "t" : {
      "properties" : {
        "text_icu" : { "type" : "string", "analyzer" : "cs_icu_analyzer" },
        "text"     : { "type" : "string" }
      }
    }
  }
}'

curl -X POST 'localhost:9200/i/t/' -d '{ "text_icu" : "Celer", "text" : "Celer" }'
curl -X POST 'localhost:9200/i/t/' -d '{ "text_icu" : "Cypřiš", "text" : "Cypřiš" }'
curl -X POST 'localhost:9200/i/t/' -d '{ "text_icu" : "Cizrna", "text" : "Cizrna" }'
curl -X POST 'localhost:9200/i/t/' -d '{ "text_icu" : "Chřest", "text" : "Chřest" }'

curl -X POST 'localhost:9200/i/_refresh'
echo

echo; echo "Non ICU"
curl -X GET 'localhost:9200/i/t/_search?pretty=true' -d '{
  "query" : { "match_all" : {} },
  "sort" : [ "text" ]
}'

echo; echo "ICU"
curl -X GET 'localhost:9200/i/t/_search?pretty=true' -d '{
  "query" : { "match_all" : {} },
  "sort" : [ "text_icu" ]
}'