elasticsearch - 查询被索引词有空格的Elastic Search

Question

我最近尝试使用 flex 搜索。但是，我正在努力查询以下情况:
我为此设置了索引:

"analysis": {
    "index_analyzer": {
        "my_index_analyzer": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": ["standard", "lowercase", "nGram"],
            "char-filter": ["my_pattern"]
        }
    },
    "search_analyzer": {
        "my_search_analyzer": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": ["standard", "lowercase", "nGram"],
            "char-filter": ["my_pattern"]
        }
    },
    "filter": {
        "nGram": {
            "type": "nGram",
            "min_gram": 3,
            "max_gram": 40
        }
    },
    "char_filter" : {
        "my_pattern":{
            "type":"pattern_replace",
            "pattern":"\u0020",
            "replacement":""
        }
    }

被索引的文档是:

{
   name:'My self'
},
{
   name:'Hell o'
}

如果我搜索“我自己”，则期望它返回第一个JSON对象，但是这没有发生。

我正在使用此搜索(其中术语只是被搜索的字符串):

var query = {
            match: {
                location: term

            }
        };
client.search({
            index: 'requests',
            analyzer:'my_search_analyzer',
            body: {
                query:query
            }
         })

我真的很感谢一些指导!

亲切的问候
JB

Answer 1

您快到了，您的索引定义只有一些小问题和错别字，我们将解决:

您不需要index_analyzer和search_analyzer，只需直接在my_index_analyzer元素下定义my_search_analyzer和analyzer即可。

char-filter应该读取char_filter(带下划线)

您的空间模式需要额外的反斜线

这是我使用的更正的设置/映射:

{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_index_analyzer": {         <--- 1. directly under analyzer
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "standard",
            "lowercase",
            "nGram"
          ],
          "char_filter": [             <--- 2. underscore
            "my_pattern"
          ]
        },
        "my_search_analyzer": {        <--- 1. directly under analyzer
          "type": "custom",
          "tokenizer": "standard",
          "filter": [
            "standard",
            "lowercase",
            "nGram"
          ],
          "char_filter": [             <--- 2. underscore
            "my_pattern"
          ]
        }
      },
      "filter": {
        "nGram": {
          "type": "nGram",
          "min_gram": 3,
          "max_gram": 40
        }
      },
      "char_filter": {
        "my_pattern": {
          "type": "pattern_replace",
          "pattern": "\\u0020",        <--- 3. additional backslash
          "replacement": ""
        }
      }
    }
  },
  "mappings": {
    "request": {
      "properties": {
        "location": {
          "type": "string",
          "index_analyzer": "my_index_analyzer"
        }
      }
    }
  }
}

然后，您可以为两个样本文档建立索引:

curl -XPUT localhost:9200/requests/request/1 -d '{"location":"My self"}'
curl -XPUT localhost:9200/requests/request/2 -d '{"location":"Hell o"}'

您将得到您所期望的:

curl -XPOST localhost:9200/requests/request/_search -d '{
  "query": {
    "match": {
      "location": "Myself"
    }
  }
}'

将返回带有 My self的文档