› › ›

测试分析器

analyze API 是一个非常有用的工具，用于查看分析器生成的词项。可以在请求中内联指定内置分析器。

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."
}

API 返回以下响应

{
  "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
    }
  ]
}

您还可以测试以下组合：

一个分词器
零个或多个词项过滤器
零个或多个字符过滤器

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?"
}

API 返回以下响应

{
  "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
    }
  ]
}

或者，在特定索引上运行 analyze API 时，可以引用自定义分析器。

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?"
}

API 返回以下响应

{
  "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
    }
  ]
}

	定义一个名为 `std_folded` 的 `custom` 分析器。
	字段 `my_text` 使用 `std_folded` 分析器。
	要引用此分析器，`analyze` API 必须指定索引名称。
	按名称引用分析器。
	引用字段 `my_text` 使用的分析器。

« 配置文本分析配置内置分析器 »