[elasticsearch笔记] mapping-data type1

demo

base

#
# 最开始，type被类比成数据库的table，但是lucene底层对于同一index下面相同的field（type不同）必须是要同种类型，即lucene底层会把index下所有相同的field一致对待。
# 多个type不利于数据压缩
# 全文检索中用于计分的词条统计会更精准
#
PUT my_index 
{
  "mappings": {
    "properties": { 
      "title":    { "type": "text"  }, 
      "name":     { "type": "text"  }, 
      "age":      { "type": "integer" },  
      "created":  {
        "type":   "date", 
        "format": "strict_date_optional_time||epoch_millis"
      }
    }
  }
}

PUT users
{
  "settings": {
    "index.mapping.single_type": true
  },
  "mappings": {
    "_doc": {
      "properties": {
        "name": {
          "type": "text"
        },
        "user_name": {
          "type": "keyword"
        },
        "email": {
          "type": "keyword"
        }
      }
    }
  }
}

PUT tweets
{
  "settings": {
    "index.mapping.single_type": true
  },
  "mappings": {
    "_doc": {
      "properties": {
        "content": {
          "type": "text"
        },
        "user_name": {
          "type": "keyword"
        },
        "tweeted_at": {
          "type": "date"
        }
      }
    }
  }
}

POST _reindex
{
  "source": {
    "index": "twitter",
    "type": "user"
  },
  "dest": {
    "index": "users"
  }
}

POST _reindex
{
  "source": {
    "index": "twitter",
    "type": "tweet"
  },
  "dest": {
    "index": "tweets"
  }
}

DELETE new_twitter
PUT new_twitter
{
  "mappings": {
    "_doc": {
      "properties": {
        "type": {
          "type": "keyword"
        },
        "name": {
          "type": "text"
        },
        "user_name": {
          "type": "keyword"
        },
        "email": {
          "type": "keyword"
        },
        "content": {
          "type": "text"
        },
        "tweeted_at": {
          "type": "date"
        }
      }
    }
  }
}

POST _reindex
{
  "source": {
    "index": "twitter"
  },
  "dest": {
    "index": "new_twitter"
  },
  "script": {
    "source": """
      ctx._source.type = ctx._type;
      ctx._id = ctx._type + '-' + ctx._id;
      ctx._type = '_doc';
    """
  }
}

PUT index?include_type_name=false
{
  "mappings": {
    "properties": { 
      "foo": {
        "type": "keyword"
      }
    }
  }
}

PUT index/_mappings?include_type_name=false
{
  "properties": { 
    "bar": {
      "type": "text"
    }
  }
}

GET index/_mappings?include_type_name=false

PUT index/_doc/1
{
  "foo": "baz"
}

GET index/_doc/1

POST index/_update/1
{
  "doc": {
    "foo": "qux"
  }
}

# can not format. if you do, you get errors when you execut
POST _bulk
{"index":{"_index":"index","_id":"3"}}
{"foo":"baz"}
{"index":{"_index":"index","_id":"4"}}
{"foo":"qux"}

field alias

• field alias 并不是真是存在于 document source 中。
• Currently only the search and field capabilities APIs will accept and resolve field aliases.

PUT trips
{
  "mappings": {
    "properties": {
      "distance": {
        "type": "long"
      },
      "route_length_miles": {
        "type": "alias",
        "path": "distance" 
      },
      "transit_mode": {
        "type": "keyword"
      }
    }
  }
}

GET _search
{
  "query": {
    "range" : {
      "route_length_miles" : {
        "gte" : 39
      }
    }
  }
}

PUT trips
{
  "mappings": {
    "properties": {
      "distance": {
        "type": "long"
      },
      "route_length_miles": {
        "type": "alias",
        "path": "distance" 
      },
      "transit_mode": {
        "type": "keyword"
      }
    }
  }
}

GET _search
{
  "query": {
    "range" : {
      "route_length_miles" : {
        "gte" : 39
      }
    }
  }
}

array

• array 必须是统一类型

PUT my_index/_doc/1
{
  "message": "some arrays in this document...",
  "tags":  [ "elasticsearch", "wow" ], 
  "lists": [ 
    {
      "name": "prog_list",
      "description": "programming list"
    },
    {
      "name": "cool_list",
      "description": "cool stuff list"
    }
  ]
}

PUT my_index/_doc/2 
{
  "message": "no arrays in this document...",
  "tags":  "elasticsearch",
  "lists": {
    "name": "prog_list",
    "description": "programming list"
  }
}

GET my_index/_search
{
  "query": {
    "match": {
      "tags": "elasticsearch" 
    }
  }
}

text/binary/ip/geo/boolean/date/date_nanos

• The binary type accepts a binary value as a Base64 encoded string.
• The binary type accepts a binary value as a Base64 encoded string.
• date
  • format : “2015-01-01” or “2015/01/01 12:10:30” or 1420070400001
  • date range query on long represention
  • date stored as a string depending on the date format that is associated with the field
  • date_nanos: Aggregations are still on millisecond resolution, even when using a date_nanos field.

DELETE mapping_index

PUT mapping_index
{
  "mappings": {
    "properties": {
      "name": {
        "type": "text",
        "fields": {
          "keyword":{
            "type":"keyword"
          }
        }
      },
      "ip_addr":{
        "type": "ip"
      },
      "location":{
        "type": "geo_point"
      },
      "is_published":{
        "type": "boolean"
      },
      "blob": {
        "type": "binary"
      },
      "created":{
        "type": "date"
      },
      "created_in_nanos":{
        "type": "date_nanos"
      }
    }
  }
}

# can not format. if you do, you get errors when you execut
POST _bulk
{"index":{"_index":"mapping_index","_id":"1"}}
{"name":"Some binary blob","ip_addr":"192.168.1.1","is_published":true,"location":{"lat":41.12,"lon":-71.34},"blob":"U29tZSBiaW5hcnkgYmxvYg==","created":"2019-07-21","created_in_nanos":"2019-07-21"}
{"index":{"_index":"mapping_index","_id":"2"}}
{"name":"zhengcj","ip_addr":"192.168.1.2","is_published":true,"location":"41.12,-71.34","blob":"U29tZSBiaW5hcnkgYmxvYg==","created":"2019-07-30T16:51:30Z","created_in_nanos":"2019-07-30T16:51:30Z"}
{"index":{"_index":"mapping_index","_id":"3"}}
{"name":"dongyc","ip_addr":"192.168.1.3","is_published":false,"location":"drm3btev3e86","blob":"U29tZSBiaW5hcnkgYmxvYg==","created":1420070400001,"created_in_nanos":1420070400}

# milliseconds-since-the-epoch
PUT mapping_index/_doc/4
{
  "name": "zhengjerry",
  "ip_addr":"192.168.1.4",
  "is_published":false,
  "location": [ -71.34, 41.12 ],
  "blob": "U29tZSBiaW5hcnkgYmxvYg==",
  "created":1420070400001,
  "created_in_nanos":1420070400
}

GET mapping_index/_search
{
  "query": {
    "term": {
      "ip_addr": {
        "value": "192.168.0.0/16"
      }
    }
  }
}

GET mapping_index/_search
{
  "size": 0, 
  "aggs": {
    "publish_state": {
      "terms": {
        "field": "is_published"
      }
    }
  },
  "script_fields": {
    "is_published": {
      "script": {
        "lang": "painless",
        "source": "doc['is_published'].value"
      }
    }
  }
}


GET mapping_index/_search
{
  "query": {
    "geo_bounding_box":{
      "location":{
        "top_left":{
          "lat":42,
          "lon":-72
        },
        "bottom_right":{
          "lat":40,
          "lon":-74
        }
      }
    }
  }
}

range/integer_range/date_range/ip_range

PUT range_index
{
  "settings": {
    "number_of_shards": 2
  },
  "mappings": {
    "properties": {
      "expected_attendees": {
        "type": "integer_range"
      },
      "time_frame": {
        "type": "date_range", 
        "format": "yyyy-MM-dd HH:mm:ss||yyyy-MM-dd||epoch_millis"
      }
    }
  }
}

PUT range_index/_doc/1?refresh
{
  "expected_attendees" : { 
    "gte" : 10,
    "lte" : 20
  },
  "time_frame" : { 
    "gte" : "2015-10-31 12:00:00", 
    "lte" : "2015-11-01"
  }
}

GET range_index/_search
{
  "query" : {
    "term" : {
      "expected_attendees" : {
        "value": 12
      }
    }
  }
}

GET range_index/_search
{
  "query" : {
    "range" : {
      "time_frame" : { 
        "gte" : "2015-10-31",
        "lte" : "2015-11-01",
        "relation" : "within" 
      }
    }
  }
}

PUT range_index/_mapping
{
  "properties": {
    "ip_whitelist": {
      "type": "ip_range"
    }
  }
}

PUT range_index/_doc/2
{
  "ip_whitelist" : "192.168.0.0/16"
}

GET range_index/_mapping

token_count

DELETE token_count_index
PUT token_count_index
{
  "mappings": {
    "properties": {
      "name": { 
        "type": "text",
        "fields": {
          "length": { 
            "type":     "token_count",
            "analyzer": "standard"
          }
        }
      }
    }
  }
}

PUT token_count_index/_doc/1
{ "name": "John Smith" }

PUT token_count_index/_doc/2
{ "name": "Rachel Alice Williams" }

GET token_count_index/_search
{
  "query": {
    "term": {
      "name.length": 3 
    }
  }
}