ASCII 折叠词元过滤器

编辑

将不在基本拉丁 Unicode 区块(前 127 个 ASCII 字符)中的字母、数字和符号字符转换为其 ASCII 等效字符(如果存在)。例如,该过滤器将 à 更改为 a

此过滤器使用 Lucene 的 ASCIIFoldingFilter

示例

编辑

以下 analyze API 请求使用 asciifolding 过滤器删除 açaí à la carte 中的变音符号。

resp = client.indices.analyze(
    tokenizer="standard",
    filter=[
        "asciifolding"
    ],
    text="açaí à la carte",
)
print(resp)
response = client.indices.analyze(
  body: {
    tokenizer: 'standard',
    filter: [
      'asciifolding'
    ],
    text: 'açaí à la carte'
  }
)
puts response
const response = await client.indices.analyze({
  tokenizer: "standard",
  filter: ["asciifolding"],
  text: "açaí à la carte",
});
console.log(response);
GET /_analyze
{
  "tokenizer" : "standard",
  "filter" : ["asciifolding"],
  "text" : "açaí à la carte"
}

该过滤器生成以下词元:

[ acai, a, la, carte ]

添加到分析器

编辑

以下 创建索引 API 请求使用 asciifolding 过滤器来配置新的自定义分析器

resp = client.indices.create(
    index="asciifold_example",
    settings={
        "analysis": {
            "analyzer": {
                "standard_asciifolding": {
                    "tokenizer": "standard",
                    "filter": [
                        "asciifolding"
                    ]
                }
            }
        }
    },
)
print(resp)
response = client.indices.create(
  index: 'asciifold_example',
  body: {
    settings: {
      analysis: {
        analyzer: {
          standard_asciifolding: {
            tokenizer: 'standard',
            filter: [
              'asciifolding'
            ]
          }
        }
      }
    }
  }
)
puts response
const response = await client.indices.create({
  index: "asciifold_example",
  settings: {
    analysis: {
      analyzer: {
        standard_asciifolding: {
          tokenizer: "standard",
          filter: ["asciifolding"],
        },
      },
    },
  },
});
console.log(response);
PUT /asciifold_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_asciifolding": {
          "tokenizer": "standard",
          "filter": [ "asciifolding" ]
        }
      }
    }
  }
}

可配置参数

编辑
preserve_original
(可选,布尔值)如果为 true,则同时发出原始词元和折叠后的词元。默认为 false

自定义

编辑

要自定义 asciifolding 过滤器,请将其复制以创建新的自定义词元过滤器的基础。您可以使用其可配置参数修改过滤器。

例如,以下请求创建一个将 preserve_original 设置为 true 的自定义 asciifolding 过滤器:

resp = client.indices.create(
    index="asciifold_example",
    settings={
        "analysis": {
            "analyzer": {
                "standard_asciifolding": {
                    "tokenizer": "standard",
                    "filter": [
                        "my_ascii_folding"
                    ]
                }
            },
            "filter": {
                "my_ascii_folding": {
                    "type": "asciifolding",
                    "preserve_original": True
                }
            }
        }
    },
)
print(resp)
response = client.indices.create(
  index: 'asciifold_example',
  body: {
    settings: {
      analysis: {
        analyzer: {
          standard_asciifolding: {
            tokenizer: 'standard',
            filter: [
              'my_ascii_folding'
            ]
          }
        },
        filter: {
          my_ascii_folding: {
            type: 'asciifolding',
            preserve_original: true
          }
        }
      }
    }
  }
)
puts response
const response = await client.indices.create({
  index: "asciifold_example",
  settings: {
    analysis: {
      analyzer: {
        standard_asciifolding: {
          tokenizer: "standard",
          filter: ["my_ascii_folding"],
        },
      },
      filter: {
        my_ascii_folding: {
          type: "asciifolding",
          preserve_original: true,
        },
      },
    },
  },
});
console.log(response);
PUT /asciifold_example
{
  "settings": {
    "analysis": {
      "analyzer": {
        "standard_asciifolding": {
          "tokenizer": "standard",
          "filter": [ "my_ascii_folding" ]
        }
      },
      "filter": {
        "my_ascii_folding": {
          "type": "asciifolding",
          "preserve_original": true
        }
      }
    }
  }
}