Token过滤器参考

GET /_analyze
{
  "tokenizer" : "standard",
  "filter" : ["apostrophe"],
  "text" : "Istanbul'a veya Istanbul'dan"
}

PUT /apostrophe_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_apostrophe": {
          "tokenizer": "standard",
          "filter": [ "apostrophe" ]
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer" : "standard",
  "filter" : ["asciifolding"],
  "text" : "açaí à la carte"
}

PUT /asciifold_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_asciifolding": {
          "tokenizer": "standard",
          "filter": [ "asciifolding" ]
        }
      }
    }
  }
}

PUT /asciifold_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_asciifolding": {
          "tokenizer": "standard",
          "filter": [ "my_ascii_folding" ]
        }
      },
      "filter": {
        "my_ascii_folding": {
          "type": "asciifolding",
          "preserve_original": true
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer" : "standard",
  "filter" : ["cjk_bigram"],
  "text" : "東京都は、日本の首都であり"
}

PUT /cjk_bigram_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_cjk_bigram": {
          "tokenizer": "standard",
          "filter": [ "cjk_bigram" ]
        }
      }
    }
  }
}

PUT /cjk_bigram_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "han_bigrams": {
          "tokenizer": "standard",
          "filter": [ "han_bigrams_filter" ]
        }
      },
      "filter": {
        "han_bigrams_filter": {
          "type": "cjk_bigram",
          "ignored_scripts": [
            "hangul",
            "hiragana",
            "katakana"
          ],
          "output_unigrams": true
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer" : "standard",
  "filter" : ["cjk_width"],
  "text" : "ｼｰｻｲﾄﾞﾗｲﾅｰ"
}

PUT /cjk_width_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_cjk_width": {
          "tokenizer": "standard",
          "filter": [ "cjk_width" ]
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer" : "classic",
  "filter" : ["classic"],
  "text" : "The 2 Q.U.I.C.K. Brown-Foxes jumped over the lazy dog's bone."
}

PUT /classic_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "classic_analyzer": {
          "tokenizer": "classic",
          "filter": [ "classic" ]
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer" : "whitespace",
  "filter" : [
    {
      "type": "common_grams",
      "common_words": ["is", "the"]
    }
  ],
  "text" : "the quick fox is brown"
}

PUT /common_grams_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "index_grams": {
          "tokenizer": "whitespace",
          "filter": [ "common_grams" ]
        }
      },
      "filter": {
        "common_grams": {
          "type": "common_grams",
          "common_words": [ "a", "is", "the" ]
        }
      }
    }
  }
}

PUT /common_grams_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "index_grams": {
          "tokenizer": "whitespace",
          "filter": [ "common_grams_query" ]
        }
      },
      "filter": {
        "common_grams_query": {
          "type": "common_grams",
          "common_words": [ "a", "is", "the" ],
          "ignore_case": true,
          "query_mode": true
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "condition",
      "filter": [ "lowercase" ],
      "script": {
        "source": "token.getTerm().length() < 5"
      }
    }
  ],
  "text": "THE QUICK BROWN FOX"
}

PUT /palindrome_list
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_reverse_first_token": {
          "tokenizer": "whitespace",
          "filter": [ "reverse_first_token" ]
        }
      },
      "filter": {
        "reverse_first_token": {
          "type": "condition",
          "filter": [ "reverse" ],
          "script": {
            "source": "token.getPosition() === 0"
          }
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer" : "whitespace",
  "filter" : ["decimal_digit"],
  "text" : "१-one two-२ ३"
}

PUT /decimal_digit_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_decimal_digit": {
          "tokenizer": "whitespace",
          "filter": [ "decimal_digit" ]
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "whitespace",
  "filter": ["delimited_payload"],
  "text": "the|0 brown|10 fox|5 is|0 quick|10"
}

PUT delimited_payload
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_delimited_payload": {
          "tokenizer": "whitespace",
          "filter": [ "delimited_payload" ]
        }
      }
    }
  }
}

PUT delimited_payload_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_plus_delimited": {
          "tokenizer": "whitespace",
          "filter": [ "plus_delimited" ]
        }
      },
      "filter": {
        "plus_delimited": {
          "type": "delimited_payload",
          "delimiter": "+",
          "encoding": "int"
        }
      }
    }
  }
}

PUT text_payloads
{
  "mappings": {
    "properties": {
      "text": {
        "type": "text",
        "term_vector": "with_positions_payloads",
        "analyzer": "payload_delimiter"
      }
    }
  },
  "settings": {
    "analysis": {
      "analyzer": {
        "payload_delimiter": {
          "tokenizer": "whitespace",
          "filter": [ "delimited_payload" ]
        }
      }
    }
  }
}

POST text_payloads/_doc/1
{
  "text": "the|0 brown|3 fox|4 is|0 quick|10"
}

GET text_payloads/_termvectors/1
{
  "fields": [ "text" ],
  "payloads": true
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "dictionary_decompounder",
      "word_list": ["Donau", "dampf", "meer", "schiff"]
    }
  ],
  "text": "Donaudampfschiff"
}

PUT dictionary_decompound_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_dictionary_decompound": {
          "tokenizer": "standard",
          "filter": [ "22_char_dictionary_decompound" ]
        }
      },
      "filter": {
        "22_char_dictionary_decompound": {
          "type": "dictionary_decompounder",
          "word_list_path": "analysis/example_word_list.txt",
          "max_subword_size": 22
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    { "type": "edge_ngram",
      "min_gram": 1,
      "max_gram": 2
    }
  ],
  "text": "the quick brown fox jumps"
}

PUT edge_ngram_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_edge_ngram": {
          "tokenizer": "standard",
          "filter": [ "edge_ngram" ]
        }
      }
    }
  }
}

PUT edge_ngram_custom_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "default": {
          "tokenizer": "whitespace",
          "filter": [ "3_5_edgegrams" ]
        }
      },
      "filter": {
        "3_5_edgegrams": {
          "type": "edge_ngram",
          "min_gram": 3,
          "max_gram": 5
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer" : "standard",
  "filter" : ["elision"],
  "text" : "j’examine près du wharf"
}

PUT /elision_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_elision": {
          "tokenizer": "whitespace",
          "filter": [ "elision" ]
        }
      }
    }
  }
}

PUT /elision_case_insensitive_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "default": {
          "tokenizer": "whitespace",
          "filter": [ "elision_case_insensitive" ]
        }
      },
      "filter": {
        "elision_case_insensitive": {
          "type": "elision",
          "articles": [ "l", "m", "t", "qu", "n", "s", "j" ],
          "articles_case": true
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer" : "whitespace",
  "filter" : ["fingerprint"],
  "text" : "zebra jumps over resting resting dog"
}

PUT fingerprint_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_fingerprint": {
          "tokenizer": "whitespace",
          "filter": [ "fingerprint" ]
        }
      }
    }
  }
}

PUT custom_fingerprint_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_": {
          "tokenizer": "whitespace",
          "filter": [ "fingerprint_plus_concat" ]
        }
      },
      "filter": {
        "fingerprint_plus_concat": {
          "type": "fingerprint",
          "max_output_size": 100,
          "separator": "+"
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "synonym_graph",
      "synonyms": [ "dns, domain name system" ]
    }
  ],
  "text": "domain name system is fragile"
}

GET /_analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "synonym_graph",
      "synonyms": [ "dns, domain name system" ]
    },
    "flatten_graph"
  ],
  "text": "domain name system is fragile"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_custom_index_analyzer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "my_custom_word_delimiter_graph_filter",
            "flatten_graph"
          ]
        }
      },
      "filter": {
        "my_custom_word_delimiter_graph_filter": {
          "type": "word_delimiter_graph",
          "catenate_all": true
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "hunspell",
      "locale": "en_US"
    }
  ],
  "text": "the foxes jumping quickly"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "en": {
          "tokenizer": "standard",
          "filter": [ "my_en_US_dict_stemmer" ]
        }
      },
      "filter": {
        "my_en_US_dict_stemmer": {
          "type": "hunspell",
          "locale": "en_US",
          "dedup": false
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "hyphenation_decompounder",
      "hyphenation_patterns_path": "analysis/hyphenation_patterns.xml",
      "word_list": ["Kaffee", "zucker", "tasse"]
    }
  ],
  "text": "Kaffeetasse"
}

PUT hyphenation_decompound_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_hyphenation_decompound": {
          "tokenizer": "standard",
          "filter": [ "22_char_hyphenation_decompound" ]
        }
      },
      "filter": {
        "22_char_hyphenation_decompound": {
          "type": "hyphenation_decompounder",
          "word_list_path": "analysis/example_word_list.txt",
          "hyphenation_patterns_path": "analysis/hyphenation_patterns.xml",
          "max_subword_size": 22
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "keep_types",
      "types": [ "<NUM>" ]
    }
  ],
  "text": "1 quick fox 2 lazy dogs"
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "keep_types",
      "types": [ "<NUM>" ],
      "mode": "exclude"
    }
  ],
  "text": "1 quick fox 2 lazy dogs"
}

PUT keep_types_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "standard",
          "filter": [ "extract_alpha" ]
        }
      },
      "filter": {
        "extract_alpha": {
          "type": "keep_types",
          "types": [ "<ALPHANUM>" ]
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "whitespace",
  "filter": [
    {
      "type": "keep",
      "keep_words": [ "dog", "elephant", "fox" ]
    }
  ],
  "text": "the quick fox jumps over the lazy dog"
}

PUT keep_words_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_keep_word_array": {
          "tokenizer": "standard",
          "filter": [ "keep_word_array" ]
        },
        "standard_keep_word_file": {
          "tokenizer": "standard",
          "filter": [ "keep_word_file" ]
        }
      },
      "filter": {
        "keep_word_array": {
          "type": "keep",
          "keep_words": [ "one", "two", "three" ]
        },
        "keep_word_file": {
          "type": "keep",
          "keep_words_path": "analysis/example_word_list.txt"
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [ "stemmer" ],
  "text": "fox running and jumping"
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    {
      "type": "keyword_marker",
      "keywords": [ "jumping" ]
    },
    "stemmer"
  ],
  "text": "fox running and jumping"
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    {
      "type": "keyword_marker",
      "keywords": [ "jumping" ]
    },
    "stemmer"
  ],
  "text": "fox running and jumping",
  "explain": true,
  "attributes": "keyword"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_custom_analyzer": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "my_custom_keyword_marker_filter",
            "porter_stem"
          ]
        }
      },
      "filter": {
        "my_custom_keyword_marker_filter": {
          "type": "keyword_marker",
          "keywords_path": "analysis/example_word_list.txt"
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    "keyword_repeat"
  ],
  "text": "fox running and jumping",
  "explain": true,
  "attributes": "keyword"
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    "keyword_repeat",
    "stemmer"
  ],
  "text": "fox running and jumping",
  "explain": true,
  "attributes": "keyword"
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    "keyword_repeat",
    "stemmer",
    "remove_duplicates"
  ],
  "text": "fox running and jumping",
  "explain": true,
  "attributes": "keyword"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_custom_analyzer": {
          "tokenizer": "standard",
          "filter": [
            "keyword_repeat",
            "porter_stem",
            "remove_duplicates"
          ]
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "standard",
  "filter": [ "kstem" ],
  "text": "the foxes jumping quickly"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "whitespace",
          "filter": [
            "lowercase",
            "kstem"
          ]
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "whitespace",
  "filter": [
    {
      "type": "length",
      "min": 0,
      "max": 4
    }
  ],
  "text": "the quick brown fox jumps over the lazy dog"
}

PUT length_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_length": {
          "tokenizer": "standard",
          "filter": [ "length" ]
        }
      }
    }
  }
}

PUT length_custom_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_length_2_to_10_char": {
          "tokenizer": "whitespace",
          "filter": [ "length_2_to_10_char" ]
        }
      },
      "filter": {
        "length_2_to_10_char": {
          "type": "length",
          "min": 2,
          "max": 10
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "standard",
    "filter": [
    {
      "type": "limit",
      "max_token_count": 2
    }
  ],
  "text": "quick fox jumps over lazy dog"
}

PUT limit_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_one_token_limit": {
          "tokenizer": "standard",
          "filter": [ "limit" ]
        }
      }
    }
  }
}

PUT custom_limit_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_five_token_limit": {
          "tokenizer": "whitespace",
          "filter": [ "five_token_limit" ]
        }
      },
      "filter": {
        "five_token_limit": {
          "type": "limit",
          "max_token_count": 5
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer" : "standard",
  "filter" : ["lowercase"],
  "text" : "THE Quick FoX JUMPs"
}

PUT lowercase_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_lowercase": {
          "tokenizer": "whitespace",
          "filter": [ "lowercase" ]
        }
      }
    }
  }
}

PUT custom_lowercase_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "greek_lowercase_example": {
          "type": "custom",
          "tokenizer": "standard",
          "filter": ["greek_lowercase"]
        }
      },
      "filter": {
        "greek_lowercase": {
          "type": "lowercase",
          "language": "greek"
        }
      }
    }
  }
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "filter": {
        "my_shingle_filter": {      
          "type": "shingle",
          "min_shingle_size": 5,
          "max_shingle_size": 5,
          "output_unigrams": false
        },
        "my_minhash_filter": {
          "type": "min_hash",
          "hash_count": 1,          
          "bucket_count": 512,      
          "hash_set_size": 1,       
          "with_rotation": true     
        }
      },
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "standard",
          "filter": [
            "my_shingle_filter",
            "my_minhash_filter"
          ]
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "fingerprint": {
        "type": "text",
        "analyzer": "my_analyzer"
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [ "ngram" ],
  "text": "Quick fox"
}

PUT ngram_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_ngram": {
          "tokenizer": "standard",
          "filter": [ "ngram" ]
        }
      }
    }
  }
}

PUT ngram_custom_example
{
  "settings": {
    "index": {
      "max_ngram_diff": 2
    },
    "analysis": {
      "analyzer": {
        "default": {
          "tokenizer": "whitespace",
          "filter": [ "3_5_grams" ]
        }
      },
      "filter": {
        "3_5_grams": {
          "type": "ngram",
          "min_gram": 3,
          "max_gram": 5
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    {
      "type": "pattern_replace",
      "pattern": "(dog)",
      "replacement": "watch$1"
    }
  ],
  "text": "foxes jump lazy dogs"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "keyword",
          "filter": [
            "my_pattern_replace_filter"
          ]
        }
      },
      "filter": {
        "my_pattern_replace_filter": {
          "type": "pattern_replace",
          "pattern": "[£|€]",
          "replacement": "",
          "all": false
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "standard",
  "filter": [ "porter_stem" ],
  "text": "the foxes jumping quickly"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "whitespace",
          "filter": [
            "lowercase",
            "porter_stem"
          ]
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    {
      "type": "predicate_token_filter",
      "script": {
        "source": """
          token.term.length() > 3
        """
      }
    }
  ],
  "text": "the fox jumps the lazy dog"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "standard",
          "filter": [
            "my_script_filter"
          ]
        }
      },
      "filter": {
        "my_script_filter": {
          "type": "predicate_token_filter",
          "script": {
            "source": """
              token.type.contains("ALPHANUM")
            """
          }
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer": "whitespace",
  "filter": [
    "keyword_repeat",
    "stemmer"
  ],
  "text": "jumping dog"
}

GET _analyze
{
  "tokenizer": "whitespace",
  "filter": [
    "keyword_repeat",
    "stemmer",
    "remove_duplicates"
  ],
  "text": "jumping dog"
}

PUT my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_custom_analyzer": {
          "tokenizer": "standard",
          "filter": [
            "keyword_repeat",
            "stemmer",
            "remove_duplicates"
          ]
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer" : "standard",
  "filter" : ["reverse"],
  "text" : "quick fox jumps"
}

PUT reverse_example
{
  "settings" : {
    "analysis" : {
      "analyzer" : {
        "whitespace_reverse" : {
          "tokenizer" : "whitespace",
          "filter" : ["reverse"]
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [ "shingle" ],
  "text": "quick brown fox jumps"
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    {
      "type": "shingle",
      "min_shingle_size": 2,
      "max_shingle_size": 3
    }
  ],
  "text": "quick brown fox jumps"
}

GET /_analyze
{
  "tokenizer": "whitespace",
  "filter": [
    {
      "type": "shingle",
      "min_shingle_size": 2,
      "max_shingle_size": 3,
      "output_unigrams": false
    }
  ],
  "text": "quick brown fox jumps"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_shingle": {
          "tokenizer": "standard",
          "filter": [ "shingle" ]
        }
      }
    }
  }
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "en": {
          "tokenizer": "standard",
          "filter": [ "my_shingle_filter" ]
        }
      },
      "filter": {
        "my_shingle_filter": {
          "type": "shingle",
          "min_shingle_size": 2,
          "max_shingle_size": 5,
          "output_unigrams": false
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "standard",
  "filter": [ "stemmer" ],
  "text": "the foxes jumping quickly"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "whitespace",
          "filter": [ "stemmer" ]
        }
      }
    }
  }
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "standard",
          "filter": [
            "lowercase",
            "my_stemmer"
          ]
        }
      },
      "filter": {
        "my_stemmer": {
          "type": "stemmer",
          "language": "light_german"
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "standard",
  "filter": [ "stop" ],
  "text": "a quick fox jumps over the lazy dog"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "whitespace",
          "filter": [ "stop" ]
        }
      }
    }
  }
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "default": {
          "tokenizer": "whitespace",
          "filter": [ "my_custom_stop_words_filter" ]
        }
      },
      "filter": {
        "my_custom_stop_words_filter": {
          "type": "stop",
          "ignore_case": true
        }
      }
    }
  }
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "default": {
          "tokenizer": "whitespace",
          "filter": [ "my_custom_stop_words_filter" ]
        }
      },
      "filter": {
        "my_custom_stop_words_filter": {
          "type": "stop",
          "ignore_case": true,
          "stopwords": [ "and", "is", "the" ]
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer" : "keyword",
  "text" : " fox "
}

GET _analyze
{
  "tokenizer" : "keyword",
  "filter" : ["trim"],
  "text" : " fox "
}

PUT trim_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "keyword_trim": {
          "tokenizer": "keyword",
          "filter": [ "trim" ]
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer" : "whitespace",
  "filter" : ["truncate"],
  "text" : "the quinquennial extravaganza carried on"
}

PUT custom_truncate_example
{
  "settings" : {
    "analysis" : {
      "analyzer" : {
        "standard_truncate" : {
        "tokenizer" : "standard",
        "filter" : ["truncate"]
        }
      }
    }
  }
}

PUT 5_char_words_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "lowercase_5_char": {
          "tokenizer": "lowercase",
          "filter": [ "5_char_trunc" ]
        }
      },
      "filter": {
        "5_char_trunc": {
          "type": "truncate",
          "length": 5
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer" : "whitespace",
  "filter" : ["unique"],
  "text" : "the quick fox jumps the lazy fox"
}

PUT custom_unique_example
{
  "settings" : {
    "analysis" : {
      "analyzer" : {
        "standard_truncate" : {
        "tokenizer" : "standard",
        "filter" : ["unique"]
        }
      }
    }
  }
}

PUT letter_unique_pos_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "letter_unique_pos": {
          "tokenizer": "letter",
          "filter": [ "unique_pos" ]
        }
      },
      "filter": {
        "unique_pos": {
          "type": "unique",
          "only_on_same_position": true
        }
      }
    }
  }
}

GET _analyze
{
  "tokenizer" : "standard",
  "filter" : ["uppercase"],
  "text" : "the Quick FoX JUMPs"
}

PUT uppercase_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "whitespace_uppercase": {
          "tokenizer": "whitespace",
          "filter": [ "uppercase" ]
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "keyword",
  "filter": [ "word_delimiter" ],
  "text": "Neil's-Super-Duper-XL500--42+AutoCoder"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "keyword",
          "filter": [ "my_custom_word_delimiter_filter" ]
        }
      },
      "filter": {
        "my_custom_word_delimiter_filter": {
          "type": "word_delimiter",
          "type_table": [ "- => ALPHA" ],
          "split_on_case_change": false,
          "split_on_numerics": false,
          "stem_english_possessive": true
        }
      }
    }
  }
}

GET /_analyze
{
  "tokenizer": "keyword",
  "filter": [ "word_delimiter_graph" ],
  "text": "Neil's-Super-Duper-XL500--42+AutoCoder"
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "keyword",
          "filter": [ "word_delimiter_graph" ]
        }
      }
    }
  }
}

PUT /my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_analyzer": {
          "tokenizer": "keyword",
          "filter": [ "my_custom_word_delimiter_graph_filter" ]
        }
      },
      "filter": {
        "my_custom_word_delimiter_graph_filter": {
          "type": "word_delimiter_graph",
          "type_table": [ "- => ALPHA" ],
          "split_on_case_change": false,
          "split_on_numerics": false,
          "stem_english_possessive": true
        }
      }
    }
  }
}