Test an analyzer

edit

The analyze API is an invaluable tool for viewing the terms produced by an analyzer. A built-in analyzer can be specified inline in the request:

resp = client.indices.analyze(
    analyzer="whitespace",
    text="The quick brown fox.",
)
print(resp)
response = client.indices.analyze(
  body: {
    analyzer: 'whitespace',
    text: 'The quick brown fox.'
  }
)
puts response
const response = await client.indices.analyze({
  analyzer: "whitespace",
  text: "The quick brown fox.",
});
console.log(response);
POST _analyze
{
  "analyzer": "whitespace",
  "text":     "The quick brown fox."
}

The API returns the following response:

{
  "tokens": [
    {
      "token": "The",
      "start_offset": 0,
      "end_offset": 3,
      "type": "word",
      "position": 0
    },
    {
      "token": "quick",
      "start_offset": 4,
      "end_offset": 9,
      "type": "word",
      "position": 1
    },
    {
      "token": "brown",
      "start_offset": 10,
      "end_offset": 15,
      "type": "word",
      "position": 2
    },
    {
      "token": "fox.",
      "start_offset": 16,
      "end_offset": 20,
      "type": "word",
      "position": 3
    }
  ]
}

You can also test combinations of:

  • A tokenizer
  • Zero or more token filters
  • Zero or more character filters
resp = client.indices.analyze(
    tokenizer="standard",
    filter=[
        "lowercase",
        "asciifolding"
    ],
    text="Is this déja vu?",
)
print(resp)
response = client.indices.analyze(
  body: {
    tokenizer: 'standard',
    filter: [
      'lowercase',
      'asciifolding'
    ],
    text: 'Is this déja vu?'
  }
)
puts response
const response = await client.indices.analyze({
  tokenizer: "standard",
  filter: ["lowercase", "asciifolding"],
  text: "Is this déja vu?",
});
console.log(response);
POST _analyze
{
  "tokenizer": "standard",
  "filter":  [ "lowercase", "asciifolding" ],
  "text":      "Is this déja vu?"
}

The API returns the following response:

{
  "tokens": [
    {
      "token": "is",
      "start_offset": 0,
      "end_offset": 2,
      "type": "<ALPHANUM>",
      "position": 0
    },
    {
      "token": "this",
      "start_offset": 3,
      "end_offset": 7,
      "type": "<ALPHANUM>",
      "position": 1
    },
    {
      "token": "deja",
      "start_offset": 8,
      "end_offset": 12,
      "type": "<ALPHANUM>",
      "position": 2
    },
    {
      "token": "vu",
      "start_offset": 13,
      "end_offset": 15,
      "type": "<ALPHANUM>",
      "position": 3
    }
  ]
}

Alternatively, a custom analyzer can be referred to when running the analyze API on a specific index:

resp = client.indices.create(
    index="my-index-000001",
    settings={
        "analysis": {
            "analyzer": {
                "std_folded": {
                    "type": "custom",
                    "tokenizer": "standard",
                    "filter": [
                        "lowercase",
                        "asciifolding"
                    ]
                }
            }
        }
    },
    mappings={
        "properties": {
            "my_text": {
                "type": "text",
                "analyzer": "std_folded"
            }
        }
    },
)
print(resp)

resp1 = client.indices.analyze(
    index="my-index-000001",
    analyzer="std_folded",
    text="Is this déjà vu?",
)
print(resp1)

resp2 = client.indices.analyze(
    index="my-index-000001",
    field="my_text",
    text="Is this déjà vu?",
)
print(resp2)
response = client.indices.create(
  index: 'my-index-000001',
  body: {
    settings: {
      analysis: {
        analyzer: {
          std_folded: {
            type: 'custom',
            tokenizer: 'standard',
            filter: [
              'lowercase',
              'asciifolding'
            ]
          }
        }
      }
    },
    mappings: {
      properties: {
        my_text: {
          type: 'text',
          analyzer: 'std_folded'
        }
      }
    }
  }
)
puts response

response = client.indices.analyze(
  index: 'my-index-000001',
  body: {
    analyzer: 'std_folded',
    text: 'Is this déjà vu?'
  }
)
puts response

response = client.indices.analyze(
  index: 'my-index-000001',
  body: {
    field: 'my_text',
    text: 'Is this déjà vu?'
  }
)
puts response
const response = await client.indices.create({
  index: "my-index-000001",
  settings: {
    analysis: {
      analyzer: {
        std_folded: {
          type: "custom",
          tokenizer: "standard",
          filter: ["lowercase", "asciifolding"],
        },
      },
    },
  },
  mappings: {
    properties: {
      my_text: {
        type: "text",
        analyzer: "std_folded",
      },
    },
  },
});
console.log(response);

const response1 = await client.indices.analyze({
  index: "my-index-000001",
  analyzer: "std_folded",
  text: "Is this déjà vu?",
});
console.log(response1);

const response2 = await client.indices.analyze({
  index: "my-index-000001",
  field: "my_text",
  text: "Is this déjà vu?",
});
console.log(response2);
PUT my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "std_folded": { 
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "lowercase",
            "asciifolding"
          ]
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "my_text": {
        "type": "text",
        "analyzer": "std_folded" 
      }
    }
  }
}

GET my-index-000001/_analyze 
{
  "analyzer": "std_folded", 
  "text":     "Is this déjà vu?"
}

GET my-index-000001/_analyze 
{
  "field": "my_text", 
  "text":  "Is this déjà vu?"
}

The API returns the following response:

{
  "tokens": [
    {
      "token": "is",
      "start_offset": 0,
      "end_offset": 2,
      "type": "<ALPHANUM>",
      "position": 0
    },
    {
      "token": "this",
      "start_offset": 3,
      "end_offset": 7,
      "type": "<ALPHANUM>",
      "position": 1
    },
    {
      "token": "deja",
      "start_offset": 8,
      "end_offset": 12,
      "type": "<ALPHANUM>",
      "position": 2
    },
    {
      "token": "vu",
      "start_offset": 13,
      "end_offset": 15,
      "type": "<ALPHANUM>",
      "position": 3
    }
  ]
}

Define a custom analyzer called std_folded.

The field my_text uses the std_folded analyzer.

To refer to this analyzer, the analyze API must specify the index name.

Refer to the analyzer by name.

Refer to the analyzer used by field my_text.