Stop analyzer

The stop analyzer is the same as the simple analyzer but adds support for removing stop words. It defaults to using the _english_ stop words.

Example output

edit

resp = client.indices.analyze(
    analyzer="stop",
    text="The 2 QUICK Brown-Foxes jumped over the lazy dog's bone.",
)
print(resp)

response = client.indices.analyze(
  body: {
    analyzer: 'stop',
    text: "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
  }
)
puts response

const response = await client.indices.analyze({
  analyzer: "stop",
  text: "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone.",
});
console.log(response);

POST _analyze
{
  "analyzer": "stop",
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}

The above sentence would produce the following terms:

[ quick, brown, foxes, jumped, over, lazy, dog, s, bone ]

Configuration

edit

The stop analyzer accepts the following parameters:

`stopwords`	A pre-defined stop words list like `_english_` or an array containing a list of stop words. Defaults to `_english_`.
`stopwords_path`	The path to a file containing stop words. This path is relative to the Elasticsearch `config` directory.

See the Stop Token Filter for more information about stop word configuration.

Example configuration

edit

In this example, we configure the stop analyzer to use a specified list of words as stop words:

resp = client.indices.create(
    index="my-index-000001",
    settings={
        "analysis": {
            "analyzer": {
                "my_stop_analyzer": {
                    "type": "stop",
                    "stopwords": [
                        "the",
                        "over"
                    ]
                }
            }
        }
    },
)
print(resp)

resp1 = client.indices.analyze(
    index="my-index-000001",
    analyzer="my_stop_analyzer",
    text="The 2 QUICK Brown-Foxes jumped over the lazy dog's bone.",
)
print(resp1)

response = client.indices.create(
  index: 'my-index-000001',
  body: {
    settings: {
      analysis: {
        analyzer: {
          my_stop_analyzer: {
            type: 'stop',
            stopwords: [
              'the',
              'over'
            ]
          }
        }
      }
    }
  }
)
puts response

response = client.indices.analyze(
  index: 'my-index-000001',
  body: {
    analyzer: 'my_stop_analyzer',
    text: "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
  }
)
puts response

const response = await client.indices.create({
  index: "my-index-000001",
  settings: {
    analysis: {
      analyzer: {
        my_stop_analyzer: {
          type: "stop",
          stopwords: ["the", "over"],
        },
      },
    },
  },
});
console.log(response);

const response1 = await client.indices.analyze({
  index: "my-index-000001",
  analyzer: "my_stop_analyzer",
  text: "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone.",
});
console.log(response1);

PUT my-index-000001
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_stop_analyzer": {
          "type": "stop",
          "stopwords": ["the", "over"]
        }
      }
    }
  }
}

POST my-index-000001/_analyze
{
  "analyzer": "my_stop_analyzer",
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}

The above example produces the following terms:

[ quick, brown, foxes, jumped, lazy, dog, s, bone ]

Definition

edit

It consists of:

Tokenizer

Lower Case Tokenizer

Token filters

Stop Token Filter

If you need to customize the stop analyzer beyond the configuration parameters then you need to recreate it as a custom analyzer and modify it, usually by adding token filters. This would recreate the built-in stop analyzer and you can use it as a starting point for further customization:

resp = client.indices.create(
    index="stop_example",
    settings={
        "analysis": {
            "filter": {
                "english_stop": {
                    "type": "stop",
                    "stopwords": "_english_"
                }
            },
            "analyzer": {
                "rebuilt_stop": {
                    "tokenizer": "lowercase",
                    "filter": [
                        "english_stop"
                    ]
                }
            }
        }
    },
)
print(resp)

response = client.indices.create(
  index: 'stop_example',
  body: {
    settings: {
      analysis: {
        filter: {
          english_stop: {
            type: 'stop',
            stopwords: '_english_'
          }
        },
        analyzer: {
          rebuilt_stop: {
            tokenizer: 'lowercase',
            filter: [
              'english_stop'
            ]
          }
        }
      }
    }
  }
)
puts response

const response = await client.indices.create({
  index: "stop_example",
  settings: {
    analysis: {
      filter: {
        english_stop: {
          type: "stop",
          stopwords: "_english_",
        },
      },
      analyzer: {
        rebuilt_stop: {
          tokenizer: "lowercase",
          filter: ["english_stop"],
        },
      },
    },
  },
});
console.log(response);

PUT /stop_example
{
  "settings": {
    "analysis": {
      "filter": {
        "english_stop": {
          "type":       "stop",
          "stopwords":  "_english_" 
        }
      },
      "analyzer": {
        "rebuilt_stop": {
          "tokenizer": "lowercase",
          "filter": [
            "english_stop"          
          ]
        }
      }
    }
  }
}

	The default stopwords can be overridden with the `stopwords` or `stopwords_path` parameters.
	You’d add any token filters after `english_stop`.

« Standard analyzer Whitespace analyzer »