kibana.txt

# list of all filters / ...
# https://github.com/jprante/elasticsearch-plugin-bundle/blob/93ed7cb33b9c8095c279405467d4301422324655/src/main/java/org/xbib/elasticsearch/plugin/bundle/BundlePlugin.java#L91

# elasticsearch-analysis-autophrase
# @TODO
# https://github.com/jprante/elasticsearch-plugin-bundle/blob/68dc19c34c40364e04400f92500b973a6cbae170/src/main/java/org/xbib/elasticsearch/index/analysis/autophrase/AutoPhrasingTokenFilterFactory.java
GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "auto_phrase",
      "phrases": [
      ],
      "ignoreCase": false,
      "includeTokens": false,
      "replaceWhitespaceWith": "-"
    }
  ],
  "text": "Mein Text ist gut"
}

# baseform
# https://github.com/jprante/elasticsearch-analysis-baseform

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "baseform",
      "language": "de"
    }
  ],
  "text": "Ich gehe gerne mit meinen neuen Schuhen"
}

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "baseform",
      "language": "en"
    }
  ],
  "text": "Thing's are going to be awful"
}

# lemmatize
# @todo source https://github.com/jprante/elasticsearch-plugin-bundle/blob/86236c385f7937ad147c49002485940547377a67/src/main/java/org/xbib/elasticsearch/index/analysis/lemmatize/LemmatizeTokenFilterFactory.java#L28
GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "lemmatize",
      "language": "de"
    }
  ],
  "text": "Ich gehe gerne mit meinen neuen Schuhen"
}

# pair
# @todo
# https://github.com/jprante/elasticsearch-plugin-bundle/blob/68dc19c34c40364e04400f92500b973a6cbae170/src/main/java/org/xbib/elasticsearch/index/analysis/concat/PairTokenFilterFactory.java


# elasticsearch-analysis-concat
# @TODO
GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "concat"
    }
  ],
  "text": "eins 1, zwei 2"
}

# elasticsearch-analysis-decompound
# https://github.com/jprante/elasticsearch-analysis-decompound

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "decompound"
    }
  ],
  "text": "PowerShot Donaudampfschiff ich-gehe-gerne das_ist_nicht"
}

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

# elasticsearch-analysis-german
# https://github.com/jprante/elasticsearch-analysis-german

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "german_normalize"
    }
  ],
  "text": "Jörg Prante läuft zum Strauß"
}

# elasticsearch-analysis-hyphen
# https://jprante.github.io/elasticsearch-analysis-hyphen/

GET _analyze
{
  "tokenizer": "hyphen",
  "filter": [
    "hyphen"
  ],
  "text": "Do-not-break"
}

# elasticsearch-analysis-icu
# https://github.com/jprante/elasticsearch-icu
# https://jprante.github.io/elasticsearch-analysis-icu/
# https://www.elastic.co/guide/en/elasticsearch/plugins/current/analysis-icu-collation.html
https://www.elastic.co/guide/en/elasticsearch/plugins/current/analysis-icu-folding.html
# https://www.elastic.co/guide/en/elasticsearch/plugins/current/analysis-icu-transform.html

## icu_collation
# Could not finish it with _analyze API...
# https://www.elastic.co/guide/en/elasticsearch/reference/current/indices-analyze.html

## icu_tokenizer

GET _analyze
{
  "tokenizer": {
    "type": "icu_tokenizer"
  },
  "filter": [
    "icu_folding"
  ],
  "text": "Jörg Prante"
}

## icu_tokenizer

GET _analyze
{
  "tokenizer": {
    "type": "icu_tokenizer",
    "rulefiles": "Latn:icu/Latin-dont-break-on-hyphens.rbbi"
  },
  "text": "we do-not-break on hyphens"
}

## icu_numberformat

GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "icu_numberformat",
      "locale": "de",
      "format": "spellout"
    }
  ],
  "text": "Das sind 1000 Bücher"
}


# elasticsearch-analysis-naturalsort
# https://jprante.github.io/elasticsearch-analysis-naturalsort/
DELETE test
PUT test
{
  "settings": {
    "index": {
      "analysis": {
        "analyzer": {
          "natural": {
            "type": "naturalsort",
            "locale": "en",
            "digit": 5,
            "maxTokens": 5
          }
        }
      }
    }
  },
  "mappings": {
    "doc": {
      "properties": {
        "points": {
          "type": "text",
          "store": true,
          "fields": {
            "encoded": {
              "type": "text",
              "fielddata": true,
              "analyzer": "natural"
            }
          }
        }
      }
    }
  }
}

PUT test/doc/1
{
  "points": "Bob: 2 points"
}
PUT test/doc/2
{
  "points": "Bob: 3 points"
}
PUT test/doc/3
{
  "points": "Bob: 10 points"
}

# like expected: 2, 3 and 10 points in this order
POST test/_search
{
  "query": {
    "match_all": {}
  },
  "stored_fields": "points",
  "sort": {
    "points.encoded": {
      "order": "asc"
    }
  }
}

# elasticsearch-analysis-reference
# https://github.com/jprante/elasticsearch-analysis-reference

# elasticsearch-analysis-sortform
# @TODO

# standardnumber
# https://github.com/jprante/elasticsearch-analysis-standardnumber

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

# elasticsearch-analysis-symbolname
# @TODO
GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "symbolname"
    }
  ],
  "text": "eins 1, zwei 2"
}

# elasticsearch-analysis-worddelimiter
# https://github.com/jprante/elasticsearch-analysis-worddelimiter2

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

## old
GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "worddelimiter"
    }
  ],
  "text": "PowerShot Wi-Fi SD500. It is as-is!"
}

# elasticsearch-analysis-year
# @TODO
# https://github.com/jprante/elasticsearch-plugin-bundle/blob/68dc19c34c40364e04400f92500b973a6cbae170/src/main/java/org/xbib/elasticsearch/index/analysis/year/GregorianYearTokenFilterFactory.java#L16
GET _analyze
{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "year",
      "default_year": "2019"
    }
  ],
  "text": "2017 wird das Jahr!"
}

# elasticsearch-mapper-crypt
# https://github.com/jprante/elasticsearch-mapper-crypt
DELETE test
PUT test
{
  "mappings": {
    "docs": {
      "properties": {
        "sha_hash": {
          "type": "crypt",
          "algo": "SHA-512"
        }
      }
    }
  }
}
PUT test/docs/1
{
  "sha_hash": "test"
}
POST test/_search
{
  "query": {
    "match": {
      "sha_hash": "EE26B0DD4AF7E749AA1A8EE3C10AE9923F618980772E473F8819A5D4940E0DB27AC185F8A0E1D5F84F88BC887FD67B143732C304CC5FA9AD8E6F57F50028A8FF"
    }
  }
}

# elasticsearch-mapper-langdetect
# https://github.com/jprante/elasticsearch-langdetect
DELETE test
PUT test
{
  "mappings": {
    "docs": {
      "properties": {
        "text": {
          "type": "langdetect",
          "languages": [
            "en",
            "de",
            "fr"
          ]
        }
      }
    }
  }
}
PUT test/docs/1
{
  "text": "Oh, say can you see by the dawn`s early light, What so proudly we hailed at the twilight`s last gleaming?"
}
POST test/_search
{
  "query": {
    "term": {
      "text": "en"
    }
  }
}