Skip to main content

ElasticSearch (Analyze Scripts)

Analyze Text Based on A Field​

In this case, there is a sub-field called text.metaphone. This command will analyze "My Text" by using the analyzer for text.metaphone.

GET /tms-009/_analyze 
{
  "field": "text.metaphone",
  "text": "My Text"
}

metaphone​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "metaphone"
    }],
  "text": "${searchTerm}"
}

double_metaphone​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "double_metaphone",
      "max_code_len": 100
    }],
  "text": "${searchTerm}"
}

soundex​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "soundex"
    }],
  "text": "${searchTerm}"
}

refined_soundex​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "refined_soundex"
    }],
  "text": "${searchTerm}"
}

caverphone1​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "caverphone1"
    }],
  "text": "${searchTerm}"
}

caverphone2​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "caverphone2"
    }],
  "text": "${searchTerm}"
}

cologne​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "cologne"
    }],
  "text": "${searchTerm}"
}

nysiis​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "nysiis"
    }],
  "text": "${searchTerm}"
}

koelnerphonetik​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "koelnerphonetik"
    }],
  "text": "${searchTerm}"
}

haasephonetik​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "haasephonetik"
    }],
  "text": "${searchTerm}"
}

beider_morse​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "beider_morse",
      "languageset": "english"
    }],
  "text": "${searchTerm}"
}

daitch_mokotoff​

POST _analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase", "asciifolding",
    {
      "type": "phonetic",
      "encoder": "daitch_mokotoff"
    }],
  "text": "${searchTerm}"
}