elasticsearch自定义分析器

elasticsearch分析器三功能自定义

• 字符过滤器(char_filter)

  首先，字符串按顺序通过每个字符过滤器，他们的任务是在分词前整理字符串
  一个字符过滤器可以用来去掉HTML，或者将&转化成and
  

• 分词器(tokenizer)

  其次，字符串被分词器分爲单个的词条，一个简单的分词器遇到空格和标点的时候，可能会将文本拆分成词条
  Hello how are you?会被ES预设的分词器standard分成hello、how、are、you
  

• Token 过滤器 (filter)

  最后，词条按顺序通过每个 token 过滤器，这个过程可能会改变词条(Quick -> quick)、
  删除词条(a、an、and、the...)、增加词条(jump和leap这种同义词)
  

• 过滤器(filter)解析

  edge_ngram_filter：将每个词都进行进一步的切分，用于即时搜索(instant search)。
  `min_gram`表示只要用户搜索了一个字符我们就去进行匹配。
  `max_gram`表示匹配的最大长度，最大长度越长越占用空间
  pinyin_simple_filter：拼音首字母的过滤器
  pinyin_full_filter：拼音全拼的过滤器
  

自定义分析器

• 自定义setting格式

  PUT 127.0.0.1:9200/mytest
  {
      "setting": {
          "analysis": {
              "char_filter": { 自定义的字符过滤器 },
              "tokenizer": { 自定义的分词器 },
              "filter": { 自定义的token过滤器 },
              "analyzer": { 自定义的分析器，可以将上面的char_filter、tokenizer、filter用不同的组合拼起来，形成不同的分析器 }
          }
      }
  }
  

实例

#设置setting
PUT /enterpriseextend
{
  "settings": {
    "analysis": {
      "filter": {
        "edge_ngram_filter": {
          "type": "edge_ngram",
          "min_gram": 1,
          "max_gram": 50
        },
        "pinyin_simple_filter": {
          "type": "pinyin",
          "keep_first_letter": true,
          "keep_separate_first_letter": false,
          "keep_full_pinyin": false,
          "keep_original": false,
          "limit_first_letter_length": 50,
          "lowercase": true
        },
        "pinyin_full_filter": {
          "type": "pinyin",
          "keep_first_letter": false,
          "keep_separate_first_letter": false,
          "keep_full_pinyin": true,
          "none_chinese_pinyin_tokenize": true,
          "keep_original": false,
          "limit_first_letter_length": 50,
          "lowercase": true
        }
      },
      "tokenizer": {
        "ik_max_word": {
          "type": "ik_max_word",
          "use_smart": true
        }
      },
      "analyzer": {
        "ngramIndexAnalyzer": {
          "type": "custom",
          "tokenizer": "keyword",
          "filter": [
            "edge_ngram_filter",
            "lowercase"
          ]
        },
        "ikIndexAnalyzer": {
          "type": "custom",
          "tokenizer": "ik_max_word"
        },
        "pinyiSimpleIndexAnalyzer": {
          "tokenizer": "keyword",
          "filter": [
            "pinyin_simple_filter",
            "edge_ngram_filter",
            "lowercase"
          ]
        },
        "pinyiFullIndexAnalyzer": {
          "tokenizer": "keyword",
          "filter": [
            "pinyin_full_filter",
            "lowercase"
          ]
        }
      }
    }
  }
}
#设置mapping
PUT enterpriseextend/_mapping/enterpriseextend
{
  "properties": {
    "id": {
      "type": "long"
    },
    "entName": {
      "type": "text", 
      "analyzer": "ikIndexAnalyzer",
      "fields": {
        "ngram": {
          "type": "text", 
          "analyzer": "ngramIndexAnalyzer"
        },
        "SPY": {
          "type": "text", 
          "analyzer": "pinyiSimpleIndexAnalyzer"
        },
        "FPY": {
          "type": "text", 
          "analyzer": "pinyiFullIndexAnalyzer"
        }
      }
    }
  }
}
#插入语句
PUT enterpriseextend/_doc/1
{
  "entName":"确实不是啥好东西"
}
#三种查询
GET enterpriseextend/_search
{
  "query": {
    "match": {
      "entName.ngram": "确实不是啥好东西"
    }
  }
}
GET enterpriseextend/_search
{
  "query": {
    "match": {
      "entName.SPY": "qsbsshdx"
    }
  }
}
GET enterpriseextend/_search
{
  "query": {
    "match": {
      "entName.FPY": "queshibushishahaodongxi"
    }
  }
}

综合查询

GET enterpriseextend/_search
{
  "query": {
    "bool": {
      "should": [
        {
          "match": {
            "entName.ngram": {
              "query": "确实不是啥好东西",
              "boost": 5 
            }
          }
        },
        {
          "match": { 
            "entName.SPY": {
              "query": "qsbsshdx",
              "boost": 1 
            }
          }
        },
        {
          "match": { 
            "entName.FPY": {
              "query": "queshibushishahaodongxi",
              "boost": 0.8
            }
          }
        }
      ]
    }
  }
}