indexes.txt

GET _cat/indices?v

GET kyf

POST kyf/_search
{
    "query": {
        "match": {
            "fr": "salami"
        }
    }
}

PUT kyf
{
   "settings": {
      "analysis": {
         "analyzer": {
            "custom_analyzer": {
               "tokenizer": "standard",
               "filter": [
                    "lowercase",
                    "custom_word_delimiter",
                    "custom_ascii",
                    "custom_number_removal",
                    "custom_stop",
                    "custom_stemmer",
                    "custom_length",
                    "custom_bigram",
                    "custom_spacing_removal",
                    "trim"
                ]
            }
         },
         "filter": {
            "custom_word_delimiter": {
                "type": "word_delimiter",
                "generate_word_parts": false,
                "generate_number_parts": true,
                "catenate_words": true,
                "catenate_numbers": true,
                "catenate_all": false,
                "preserve_original": false,
                "split_on_case_change": false,
                "split_on_numerics": false,
                "stem_english_possessive": false
            },
            "custom_ascii": {
                "type" : "asciifolding",
                "preserve_original" : true
            },
            "custom_number_removal": {
                "type": "pattern_replace",
                "pattern": "([0-9]+)",
                "replacement": ""
            },
            "custom_spacing_removal": {
                "type": "pattern_replace",
                "pattern": "( +)",
                "replacement": " "
            },
            "custom_stop": {
                "type": "stop",
                "stopwords": "_french_",
                "ignore_case": true,
                "remove_trailing": true
            },
            "custom_stemmer" : {
                "type": "stemmer",
                "name": "light_french"
            },
            "custom_bigram" : {
                "type" : "shingle",
                "min_shingle_size": 2,
                "max_shingle_size": 4,
                "output_unigrams": true,
                "filler_token": ""
            },
            "custom_length": {
                "type": "length",
                "min": 2
            }
        }
      }
   },
   "mappings": {
        "default": {
            "properties": {
                "fr": {
                    "type": "string",
                    "term_vector": "yes",
                    "analyzer": "custom_analyzer"
                }
            }
        }
   }
}