ElasticSearch学习笔记二

前缀搜索

prefix query不计算relevance score，与prefix filter唯一的区别就是，filter会cache bitset

性能比较差

<code># 创建mapping

PUT my_index
{
  "mappings": {
    "properties": {
      "title": {
        "type":"keyword"
      }
    }
  }
}

# 添加数据
POST /my_index/_doc/1
{
 "title":"C3D0-KD345" 
}
POST /my_index/_doc/2
{
 "title":"C3K5-DFG65" 
}

POST /my_index/_doc/3
{
 "title":"C4I8-UI365" 
}

# 查询
GET /my_index/_search
{
  "query": {
    "prefix": {
      "title": {
        "value": "C3"
      }
    }
  }
}

/<code>

通配符搜索 & 正则匹配

与prefix类似性能比较差

<code># 通配符搜索
GET /my_index/_search
{
  "query": {
    "wildcard": {
      "title": {
        "value": "C?K*5"
      }
    }
  }
}

# 正则匹配
GET /my_index/_search
{
  "query": {
    "regexp": {
      "title": "C[0-9].+"
    }
  }
}

/<code>

搜索推荐

<code># 更新数据

DELETE /my_index

PUT /my_index/_doc/1
{
  "title":"hello world"
}
PUT /my_index/_doc/2
{
  "title":"hello dog"
}
PUT /my_index/_doc/3
{
  "title":"hello we"
}
PUT /my_index/_doc/4
{
  "title":"hello wind"
}

# 查询
GET /my_index/_search
{
  "query": {
    "match_phrase_prefix": {
      "title": "hello"
    }
  }
}

/<code>

ngram分词

<code># 更新数据

DELETE /my_index


PUT /my_index
{
    "settings": {
        "analysis": {
            "filter": {
                "autocomplete_filter": { 
                    "type":     "edge_ngram",
                    "min_gram": 1,
                    "max_gram": 20
                }
            },
            "analyzer": {
                "autocomplete": {
                    "type":      "custom",
                    "tokenizer": "standard",
                    "filter": [
                        "lowercase",
                        "autocomplete_filter" 
                    ]
                }
            }
        }
    }
}

GET /my_index/_analyze
{
  "analyzer": "autocomplete",
  "text": "quick brown"
}


PUT /my_index/_mapping
{
  "properties": {
      "title": {
          "type":     "text",
          "analyzer": "autocomplete",
          "search_analyzer": "standard"
      }
  }
}


PUT /my_index/_doc/1
{
  "title":"hello world"
}
PUT /my_index/_doc/2
{
  "title":"hello dog"
}
PUT /my_index/_doc/3
{
  "title":"hello we"
}
PUT /my_index/_doc/4
{
  "title":"hello wind"
}

GET /my_index/_search 
{
  "query": {
    "match_phrase": {
      "title": "hello w"
    }
  }
}

/<code>

nagative boost

<code>
GET /forum/_search
{
  "query": {
    "boosting": {
      "positive": {  # 正序
        "match": {
          "content": "java"
        }
      },
      "negative": { # 反序
        "match": {
          "content": "spark"
        }
      },
      "negative_boost": 0.2
    }
  }
}

/<code>

function_score

<code>
POST /forum/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"follower_num" : 5} }
{ "update": { "_id": "2"} }
{ "doc" : {"follower_num" : 10} }
{ "update": { "_id": "3"} }
{ "doc" : {"follower_num" : 25} }
{ "update": { "_id": "4"} }
{ "doc" : {"follower_num" : 3} }
{ "update": { "_id": "5"} }
{ "doc" : {"follower_num" : 60} }


GET /forum/_search
{
  "query": {
    "function_score": {
      "query": {
        "multi_match": {
          "query": "java spark",
          "fields": ["title","content"]
        }
      },
      "field_value_factor": {
        "field": "follower_num",
        "modifier": "log1p",
        "factor": 0.5
      },
      "boost_mode": "sum",
      "max_boost": 2
    }
  }
}

# boost_mode，可以决定分数与指定字段的值如何计算，multiply，sum，min，max，replace
# max_boost，限制计算出来的分数不要超过max_boost指定的值

/<code>

fuzzy搜索

<code>POST /my_index/_bulk
{ "index": { "_id": 1 }}
{ "text": "Surprise me!"}
{ "index": { "_id": 2 }}
{ "text": "That was surprising."}
{ "index": { "_id": 3 }}
{ "text": "I wasn't surprised."}

GET /my_index/_search
{
  "query": {
    "fuzzy": {
      "text": {
        "value": "surprize",
        "fuzziness": 2
      }
    }
  }
}

# 一般使用语法如下

GET /my_index/_search
{
  "query": {
    "match": {
      "text": {
        "query": "SURPIZE ME",
        "fuzziness": "AUTO",
        "operator": "and"
      }
    }
  }
}
/<code>

閱讀更多 碼代碼 的文章

關鍵字: ElasticSearch