or

Do not forget to restart the node after installing.

or

Do not forget to restart the node after installing.

Do not forget to restart the node after installing.

PUT /test
{
   "settings": {
      "index": {
         "analysis": {
            "filter": {
               "umlaut": {
                  "type": "german_normalize"
               }
            },
            "analyzer": {
               "umlaut": {
                  "type": "custom",
                  "tokenizer": "standard",
                  "filter": [
                     "umlaut",
                     "lowercase"
                  ]
               }
            }
         }
      }
   },
   "mappings": {
      "docs": {
         "properties": {
            "text": {
               "type": "text",
               "analyzer": "umlaut"
            }
         }
      }
   }
}

GET /test/docs/_mapping

PUT /test/docs/1
{
    "text" : "Jörg Prante"
}

POST /test/docs/_search?explain
{
    "query": {
        "match": {
           "text": "Jörg"
        }
    }
}

POST /test/docs/_search?explain
{
    "query": {
        "match": {
           "text": "joerg"
        }
    }
}

POST /test/docs/_search?explain
{
    "query": {
        "match": {
           "text": "jorg"
        }
    }
}

The icu_collation analyzer can apply rbbi ICU rule files on a field.

The icu_folding character filter folds characters in strings according to Unicode folding rules. UTR#30 is retracted, but still used here.

The icu_tokenizer can use rules from file. Here, we set up rules to prevent tokenization of words with hyphen.

With the icu_numberformat filter, you can index numbers as they are spelled out in a language.

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "baseform",
      "language": "de"
    }
  ],
  "text": "Ich gehe dahin"
}

{
 "index":{
    "analysis":{
        "filter":{
            "baseform":{
                "type" : "baseform",
                "language" : "de"
            }
        },
        "tokenizer" : {
            "baseform" : {
               "type" : "standard",
               "filter" : [ "baseform", "unique" ]
            }
        }
    }
 }
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "worddelimiter2"
    }
  ],
  "text": "PowerShot Wi-Fi SD500"
}

{
    "index":{
        "analysis":{
            "filter" : {
                "wd" : {
                   "type" : "worddelimiter2",
                   "generate_word_parts" : true,
                   "generate_number_parts" : true,
                   "catenate_all" : true,
                   "split_on_case_change" : true,
                   "split_on_numerics" : true,
                   "stem_english_possessive" : true
                }
            }
        }
    }
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "decompound"
    }
  ],
  "text": "PowerShot Donaudampfschiff"
}

{
   "index" : {
      "analysis" : {
          "filter" : {
              "decomp" : {
                  "type" : "decompound",
                  "subwords_only" : true
              }
          },
          "tokenizer" : {
              "decomp" : {
                 "type" : "standard",
                 "filter" : [ "decomp" ]
              }
          }
      }
   }
}

{
  "settings": {
    "index": {
      "number_of_shards": 1,
      "number_of_replicas": 0,
      "analysis": {
        "filter": {
          "decomp":{
            "type" : "decompound",
            "use_payload": true,
            "use_cache": true
          }
        },
        "analyzer": {
          "decomp": {
            "type": "custom",
            "tokenizer" : "standard",
            "filter" : [
              "decomp",
              "lowercase"
            ]
          },
          "lowercase": {
            "type": "custom",
            "tokenizer" : "standard",
            "filter" : [
              "lowercase"
            ]
          }
        }
      }
    }
  },
  "mappings": {
    "_doc": {
      "properties": {
        "text": {
          "type": "text",
          "analyzer": "decomp",
          "search_analyzer": "lowercase"
        }
      }
    }
  }
}

 ```
{
  "query": {
    "exact_phrase": {
      "query": {
        "query_string": {
          "query": "\"deutsche bank\"",
          "fields": [
            "message"
          ]
        }
      }
    }
  }
}

# Langdetect

    curl -XDELETE 'localhost:9200/test'

    curl -XPUT 'localhost:9200/test'

    curl -XPOST 'localhost:9200/test/article/_mapping' -d '
    {
      "article" : {
        "properties" : {
           "content" : { "type" : "langdetect" }
        }
      }
    }
    '

    curl -XPUT 'localhost:9200/test/article/1' -d '
    {
      "title" : "Some title",
      "content" : "Oh, say can you see by the dawn`s early light, What so proudly we hailed at the twilight`s last gleaming?"
    }
    '

    curl -XPUT 'localhost:9200/test/article/2' -d '
    {
      "title" : "Ein Titel",
      "content" : "Einigkeit und Recht und Freiheit für das deutsche Vaterland!"
    }
    '

    curl -XPUT 'localhost:9200/test/article/3' -d '
    {
      "title" : "Un titre",
      "content" : "Allons enfants de la Patrie, Le jour de gloire est arrivé!"
    }
    '

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

    curl -XPOST 'localhost:9200/test/_search' -d '
    {
       "query" : {
           "term" : {
                "content" : "en"
           }
       }
    }
    '
    curl -XPOST 'localhost:9200/test/_search' -d '
    {
       "query" : {
           "term" : {
                "content" : "de"
           }
       }
    }
    '

    curl -XPOST 'localhost:9200/test/_search' -d '
    {
       "query" : {
           "term" : {
                "content" : "fr"
           }
       }
    }
    '

# Standardnumber

Try it out
----
GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "standardnumber"
    }
  ],
  "text": "Die ISBN von Elasticsearch in Action lautet 9781617291623"
}
----

    {
       "index" : {
          "analysis" : {
              "filter" : {
                  "standardnumber" : {
                      "type" : "standardnumber"
                  }
              },
              "analyzer" : {
                  "standardnumber" : {
                      "tokenizer" : "whitespace",
                      "filter" : [ "standardnumber", "unique" ]
                  }
              }
          }
       }
    }


- WordDelimiterFilter2: taken from Lucene

- baseform: index also base forms of words (german, english)

- decompound: decompose words if possible (german)

- langdetect: find language code of detected languages

- standardnumber: standard number entity recognition

- hyphen: token filter for shingling and combining hyphenated words (german: Bindestrichwörter), the opposite of the decompound token filter

- sortform: process string forms for bibliographical sorting, taking non-sort areas into account

- year: token filter for 4-digit sequences

- reference:


## Crypt mapper

    {
        "someType" : {
            "_source" : {
                "enabled": false
            },
            "properties" : {
                "someField":{ "type" : "crypt", "algo": "SHA-512" }
            }
        }
    }

## Issues

All feedback is welcome! If you find issues, please post them at [Github](https://github.com/jprante/elasticsearch-plugin-bundle/issues)

# References

The decompunder is a derived work of ASV toolbox http://asv.informatik.uni-leipzig.de/asv/methoden

Copyright (C) 2005 Abteilung Automatische Sprachverarbeitung, Institut für Informatik, Universität Leipzig

The Compact Patricia Trie data structure can be found in

*Morrison, D.: Patricia - practical algorithm to retrieve information coded in alphanumeric. Journal of ACM, 1968, 15(4):514–534*

The compound splitter used for generating features for document classification is described in

*Witschel, F., Biemann, C.: Rigorous dimensionality reduction through linguistically motivated feature selection for text categorization. Proceedings of NODALIDA 2005, Joensuu, Finland*

The base form reduction step (for Norwegian) is described in

*Eiken, U.C., Liseth, A.T., Richter, M., Witschel, F. and Biemann, C.: Ord i Dag: Mining Norwegian Daily Newswire. Proceedings of FinTAL, Turku, 2006, Finland*



# License

elasticsearch-plugin-bundle - a compilation of useful plugins for Elasticsearch

Copyright (C) 2014 Jörg Prante

This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU Affero General Public License for more details.

You should have received a copy of the GNU Affero General Public License
along with this program.  If not, see <http://www.gnu.org/licenses/>.