elasticsearch - 短语提示与ngrams

Question

因为我在搜索建议的“shingle_filter”过滤器中使用了选项“output_unigrams_if_no_shingles”:true”，因此在建议中仅显示带状疱疹，但是建议显示了ngram

        "shingle_filter": {
        "type": "shingle",
        "min_shingle_size": 2,
        "max_shingle_size": 3,
        "output_unigrams_if_no_shingles": true

按照下面我的 map

    {
  "settings": {
    "index": {
      "number_of_shards": "5",
      "number_of_replicas": "0",
   
      
      "analysis": {
        "filter": {
          "stemmer_plural_portugues": {
            "name": "minimal_portuguese",
            "stopwords" : ["http", "https", "ftp", "www"],
            "type": "stemmer"
          },
          
          
       
        "ngram_filter": {
          "type": "ngram",
          "min_gram": 3,
          "max_gram": 3,
          "token_chars": [
            "letter",
            "digit"
          ]
          
        },
            "synonym_filter": {
            "type": "synonym",
            "lenient": true,
            "synonyms_path": "analysis/synonym.txt",
            "updateable" : false

          },
          
       
          "shingle_filter": {
            "type": "shingle",
            "min_shingle_size": 2,
            "max_shingle_size": 3,
            "output_unigrams_if_no_shingles": true
          }

        },
        
        "analyzer": {
          "analyzer_customizado": {
            "filter": [
              "lowercase",
              "stemmer_plural_portugues",
              "asciifolding",
                "synonym_filter",
                 "ngram_filter",
                  "shingle_filter"
              
            ],
            "tokenizer": "lowercase"
          }
        }

      }
    }
  },
  "mappings": {
      "properties": {

        "id": {
         "type": "long"
        },
         "data": {
          "type": "date"
        },
         "quebrado": {
          "type": "byte"
          
        },
         "pgrk": {
           "type":  "integer" 
        },
         "url_length": {
           "type":  "integer" 
        },
        "title": {
          "analyzer": "analyzer_customizado",
          "type": "text",
          "fields": {
            "keyword": {
              "ignore_above": 256,
              "type": "keyword"
            }
          }
        },
        "description": {
        "analyzer": "analyzer_customizado",
          "type": "text",
          "fields": {
            "keyword": {
              "ignore_above": 256,
              "type": "keyword"
            }
          }
        },
        "url": {
          "analyzer": "analyzer_customizado",
          "type": "text",
          "fields": {
            "keyword": {
              "ignore_above": 256,
              "type": "keyword"
            }
          }
        }
      }
    }
  
}

我在下面插入文档

{
    "title": "shopping",
    "description": "sex video",
    "url": "www.ohcs.com"
}

在下面的建议查询中，我以错误的方式“vidio”输入“video”

    {
  "suggest": {
    "text": "vidio",
    "simple_phrase": {
      "phrase": {
        "field": "description",
        "size": 1,
        "max_errors": 100,
        "direct_generator": [
          {
          "field" :            "description",
          "suggest_mode" :     "always",
          "min_word_length" :  1
          }
        ],
        "collate": {
          "query": { 
            "source" : {
              "match": {
                "{{field_name}}": {
                  "query": "{{suggestion}}",
                  "operator": "and"
                }
              }
            }
          },
          "params": {"field_name" : "description"},
          "prune": true
        },
        "highlight": {
          "pre_tag": "<strong>",
          "post_tag": "</strong>"
        }
      }
    }
  }
}

在建议搜索下方的结果中，结果显示正确的建议“视频”，但显示和多个ngram标记而不是整个单词

    {
  "took": 1,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 0,
      "relation": "eq"
    },
    "max_score": null,
    "hits": [

    ]
  },
  "suggest": {
    "simple_phrase": [
      {
        "text": "vidio",
        "offset": 0,
        "length": 5,
        "options": [
          {
            "text": "vid ide deo",
            "highlighted": "vid <strong>ide deo</strong>",
            "score": 0.2648209,
            "collate_match": true
          }
        ]
      }
    ]
  }
}

如何获得建议的结果，以显示整个“视频”一词而不被分成几个ngram标记？

Answer 1

我按照您订购的顺序放置了映射

{
  "settings": {
    "index": {
      "number_of_shards": "5",
      "number_of_replicas": "0",
      "max_ngram_diff": 2,
   
      
      "analysis": {
        "filter": {
          "stemmer_plural_portugues": {
            "name": "minimal_portuguese",
            "stopwords" : ["http", "https", "ftp", "www"],
            "type": "stemmer"
          },
          
          
       
        "ngram_filter": {
          "type": "ngram",
          "min_gram": 1, 
          "max_gram": 3,
          "token_chars": [
            "letter",
            "digit"
          ]
          
        },
            "synonym_filter": {
            "type": "synonym",
            "lenient": true,
            "synonyms_path": "analysis/synonym.txt",
            "updateable" : false

          },
          
       
          "shingle_filter": {
            "type": "shingle",
            "min_shingle_size": 2,
            "max_shingle_size": 3,
            "output_unigrams" : false, 
            "output_unigrams_if_no_shingles" : true
            
          }

        },
        
        "analyzer": {
          "analyzer_customizado": {
            "filter": [
              "lowercase",
              "stemmer_plural_portugues",
              "asciifolding",
                "synonym_filter",
                 "ngram_filter",
                  "shingle_filter"
              
            ],
            "tokenizer": "lowercase"
          }
        }

      }
    }
  },
  "mappings": {
      "properties": {

        "id": {
         "type": "long"
        },
         "data": {
          "type": "date"
        },
         "quebrado": {
          "type": "byte"
          
        },
         "pgrk": {
           "type":  "integer" 
        },
         "url_length": {
           "type":  "integer" 
        },
        "title": {
          "analyzer": "analyzer_customizado",
          "type": "text",
          "fields": {
            "keyword": {
              "ignore_above": 256,
              "type": "keyword"
            }
          }
        },
        "description": {
        "analyzer": "analyzer_customizado",
          "type": "text",
          "fields": {
            "keyword": {
              "ignore_above": 256,
              "type": "keyword"
            }
          }
        },
        "url": {
          "analyzer": "analyzer_customizado",
          "type": "text",
          "fields": {
            "keyword": {
              "ignore_above": 256,
              "type": "keyword"
            }
          }
        }
      }
    }
  
}

，然后我执行了下面的查询和建议

 {
  "suggest": {
    "text": "vidio",
    "simple_phrase": {
      "phrase": {
        "field": "description",
        "size": 1,
        "max_errors": 100,
        "direct_generator": [
          {
          "field" :            "description",
          "suggest_mode" :     "always",
          "min_word_length" :  1
          }
        ],
        "collate": {
          "query": { 
            "source" : {
              "match": {
                "{{field_name}}": {
                  "query": "{{suggestion}}",
                  "operator": "and"
                }
              }
            }
          },
          "params": {"field_name" : "description"},
          "prune": true
        },
        "highlight": {
          "pre_tag": "<strong>",
          "post_tag": "</strong>"
        }
      }
    }
  }
}

，建议查询在下面显示错误消息

{
  "took": 6,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 4,
    "skipped": 0,
    "failed": 1,
    "failures": [
      {
        "shard": 4,
        "index": "teste",
        "node": "IW_SN_-fSkSIySZ4CO9rGA",
        "reason": {
          "type": "illegal_state_exception",
          "reason": "At least one unigram is required but all tokens were ngrams"
        }
      }
    ]
  },
  "hits": {
    "total": {
      "value": 0,
      "relation": "eq"
    },
    "max_score": null,
    "hits": [

    ]
  }
}