elasticsearch - 在 Elasticsearch 的一个映射中使用带有 ngram Analyzer 的不同语言分析器

Question

我想将英语和德语自定义分析器与其他分析器（例如 ngram）一起使用。以下映射是否正确？我收到德国分析仪的错误。[未知设置 [index.filter.german_stop.type]。我进行了搜索，但没有找到有关在自定义类型中使用多种语言分析器的任何信息。是否可以使用特定于语言的 ngram-filter？

PUT test  {
    "settings": {
        "analysis": {
            "analyzer": {
                "english_analyzer": {
                    "type": "custom",
                    "filter": [
                        "lowercase",
                        "english_stop",
                        "ngram_filter_en"
                    ],
                    "tokenizer": "whitespace"
                }
            },
            "filter": {
                "english_stop": {
                    "type": "stop"
                },
                "ngram_filter_en": {
                    "type": "edge_ngram",
                    "min_gram": 1,
                    "max_gram": 25
                }
              },
                  "german_analyzer" : {
                    "type" : "custom",
                    "filter" : [
                         "lowercase",
                         "german_stop",
                        "ngram_filter_de"
                          ],
                    "tokenizer" : "whitespace"
              }
            },
            "filter" : {
                "german_stop" : {
                    "type" : "stop"
              },
                "ngram_filter_de" : {
                    "type" : "edge_ngram",
                    "min_ngram" : "1",
                    "max_gram" : 25
              }
        }
    },
    "mappings" : {
      "dynamic" : true,
      "properties": {
        "content" : {
          "tye" : "text",
          "properties" : {
            "en" : {
              "type" : "text",
              "analyzer" : "english_analyzer"
            },
            "de" : {
              "type" : "text",
              "analyzer" : "german_analyzer"
            }
        }
      }
    } 

Answer 1

有小的语法错误。

1. 您的最后一个过滤器对象位于分析上下文之外。
2. 您不能在 JSON 中多次使用相同的键。

因此，以下设置会有所帮助

{
  "analysis": {
    "analyzer": {
      "english_analyzer": {
        "type": "custom",
        "filter": [
          "lowercase",
          "english_stop",
          "ngram_filter_en"
        ],
        "tokenizer": "whitespace"
      }
    },
    "filter": {
      "english_stop": {
        "type": "stop"
      },
      "ngram_filter_en": {
        "type": "edge_ngram",
        "min_gram": 1,
        "max_gram": 25
      },
      "german_stop": {
        "type": "stop"
      },
      "ngram_filter_de": {
        "type": "edge_ngram",
        "min_ngram": "1",
        "max_gram": 25
      }
    },
    "german_analyzer": {
      "type": "custom",
      "filter": [
        "lowercase",
        "german_stop",
        "ngram_filter_de"
      ],
      "tokenizer": "whitespace"
    }
  }
}

---

了解映射中的错误

{
        "analysis": {
            "analyzer": {
            "filter": {
                "english_stop": {
                    "type": "stop"
                },
                "ngram_filter_en": {
                    "type": "edge_ngram",
                    "min_gram": 1,
                    "max_gram": 25
                }
              },
                  "german_analyzer" : {
                    "type" : "custom",
                    "filter" : [
                         "lowercase",
                         "german_stop",
                        "ngram_filter_de"
                          ],
                    "tokenizer" : "whitespace"
              }
            }, 
            "filter" : {//**This is outside analysis, you cannot simply add another filter key inside analysis, so you can merge both as above**
                "german_stop" : {
                    "type" : "stop"
              },
                "ngram_filter_de" : {
                    "type" : "edge_ngram",
                    "min_ngram" : "1",
                    "max_gram" : 25
              }
        }