Demonstration of Beider-Morse phonetic filter with Elasticsearch

beidermorse.sh

curl -XDELETE 'localhost:9200/test'

# grasp available rules with: jar tvf plugins/analysis-phonetic/commons-codec-*.jar | grep bm

curl -XPUT 'localhost:9200/test' -d '
{
    "settings" : {
       "index" : {
          "analysis" : {
             "filter" : {
                "beider_morse": {
                    "type" : "phonetic",
                    "encoder" : "beider_morse",
                    "languageset" : [ "french", "english", "german" ]
                }
             },
             "analyzer" : {
                "phoneticAnalyzer" : {
                    "type" : "custom",
                    "tokenizer" : "standard",
                    "filter" : ["standard", "lowercase", "stemmer", "beider_morse"]
                }
             }
          }
       }        
    },
    "mappings" : {
       "_default_": {
           "properties" : {
               "nom" : {
                   "type" : "string",
                   "analyzer" : "phoneticAnalyzer"
               },
               "prenom" : {
                   "type" : "string",
                   "analyzer" : "phoneticAnalyzer"
               }
           }
       }
   }        
}
'

curl -XPUT 'localhost:9200/test/data/1' -d '
{
   "prenom" : "Yann",
   "nom" : " Rimbault"
}
'
 

curl -XGET 'localhost:9200/test/_refresh'

curl -XGET 'localhost:9200/test/_analyze?analyzer=phoneticAnalyzer&text=yann'

echo
echo "Query 1"
echo

curl -XGET 'localhost:9200/test/data/_search?pretty' -d '
{
    "query" : {
        "text": {
             "prenom": {
                 "query": "yann"
             }
        }
    }
}'

curl -XGET 'localhost:9200/test/_analyze?analyzer=phoneticAnalyzer&text=yan'

echo
echo "Query 2"
echo

curl -XGET 'localhost:9200/test/data/_search?pretty' -d '
{
    "query" : {
        "text": {
             "prenom": {
                 "query": "yan"
             }
        }
    }
}'