elasticsearch 精确,模糊查询实例

实例
http://www.bubuko.com/infodetail-648214.html

GET _search
{
  "query": {
    "match_all": {}
  }
}

PUT /useraudit

POST /useraudit/t_unparticiple_test/_mapping
{
  "t_unparticiple_test": {
    "properties": {
      "uid": {
        "type": "long"
      },
      "country": {
        "type": "string"
      },
      "city": {
        "type": "string"
      },
      "area": {
        "type": "string"
      },
      "address": {
        "type": "string"
      },
      "time": {
        "type": "long"
      }
    }
  }
}

POST /useraudit/t_participle_test/_mapping
{
  "t_participle_test": {
    "properties": {
      "uid": {
        "type": "long"
      },
      "country": {
        "type": "string"
      },
      "city": {
        "type": "string"
      },
      "area": {
        "type": "string"
      },
      "address": {
        "type": "string",
        "include_in_all": true,
        "analyzer": "ik",
        "term_vector": "with_positions_offsets"
      },
      "time": {
        "type": "long"
      }
    }
  }
}

POST /useraudit/t_participle_index_test/_mapping
{
  "t_participle_index_test": {
    "properties": {
      "uid": {
        "type": "long",
        "index":  "not_analyzed"
      },
      "country": {
        "type": "string",
        "index":  "not_analyzed" 
      },
      "city": {
        "type": "string",
        "index":  "not_analyzed"
      },
      "area": {
        "type": "string",
        "index":  "not_analyzed"
      },
      "address": {
        "type": "string",
        "include_in_all": true,
        "analyzer": "ik",
        "term_vector": "with_positions_offsets"
      },
      "time": {
        "type": "long",
        "index":  "not_analyzed"
      }
    }
  }
}

PUT /useraudit/t_unparticiple_test/1
{
  "uid": 200111,
  "country": "四川省",
  "city":"眉山市",
  "area":"东坡区",
  "time": 1441293300,
  "address": "红星东路二段139号"
}

PUT /useraudit/t_unparticiple_test/6
{
  "uid": 200111,
  "country": "四川省",
  "city":"眉山市",
  "area":"东坡区",
  "time": 1441293300,
  "address": "东坡胡公园"
}


PUT /useraudit/t_unparticiple_test/2
{
  "uid": 200115,
  "country": "四川省",
  "city":"眉山市",
  "area":"东坡区",
  "time": 1441293300,
  "address": "红星东路西三段123号冒菜店"
}

PUT /useraudit/t_unparticiple_test/3
{
  "uid": 362201,
  "country": "浙江省",
  "city":"杭州市",
  "area":"萧山区",
  "time": 1441293300,
  "address": "宁围镇二桥村顺发康庄4栋1单元902"
}

PUT /useraudit/t_unparticiple_test/4
{
  "uid": 362203,
  "country": "浙江省",
  "city":"衢州市",
  "area":"常山县",
  "time": 1441293300,
  "address": "新都工业区文东路852号天幕家纺"
}

PUT /useraudit/t_unparticiple_test/5
{
  "uid": 662203,
  "country": "浙江省",
  "city":"衢州市",
  "area":"常山县",
  "time": 1441293300,
  "address": "低塘街道新堰西路45号"
}

PUT /useraudit/t_participle_test/1
{
  "uid": 200111,
  "country": "四川省",
  "city":"眉山市",
  "area":"东坡区",
  "time": 1441293300,
  "address": "红星东路二段139号"
}

PUT /useraudit/t_participle_test/2
{
  "uid": 200115,
  "country": "四川省",
  "city":"眉山市",
  "area":"东坡区",
  "time": 1441293300,
  "address": "红星东路西三段123号冒菜店"
}

PUT /useraudit/t_participle_test/3
{
  "uid": 362201,
  "country": "浙江省",
  "city":"杭州市",
  "area":"萧山区",
  "time": 1441293300,
  "address": "宁围镇二桥村顺发康庄4栋1单元902"
}

PUT /useraudit/t_participle_test/4
{
  "uid": 362203,
  "country": "浙江省",
  "city":"衢州市",
  "area":"常山县",
  "time": 1441293300,
  "address": "新都工业区文东路852号天幕家纺"
}

PUT /useraudit/t_participle_test/5
{
  "uid": 662203,
  "country": "浙江省",
  "city":"衢州市",
  "area":"常山县",
  "time": 1441293300,
  "address": "低塘街道新堰西路45号"
}



PUT /useraudit/t_participle_index_test/1
{
  "uid": 200111,
  "country": "四川省",
  "city":"眉山市",
  "area":"东坡区",
  "time": 1441293300,
  "address": "红星东路二段139号"
}

PUT /useraudit/t_participle_index_test/2
{
  "uid": 200115,
  "country": "四川省",
  "city":"眉山市",
  "area":"东坡区",
  "time": 1441293300,
  "address": "红星东路西三段123号冒菜店"
}

PUT /useraudit/t_participle_index_test/3
{
  "uid": 362201,
  "country": "浙江省",
  "city":"杭州市",
  "area":"萧山区",
  "time": 1441293300,
  "address": "宁围镇二桥村顺发康庄4栋1单元902"
}

PUT /useraudit/t_participle_index_test/4
{
  "uid": 362203,
  "country": "浙江省",
  "city":"衢州市",
  "area":"常山县",
  "time": 1441293300,
  "address": "新都工业区文东路852号天幕家纺"
}

PUT /useraudit/t_participle_index_test/5
{
  "uid": 662203,
  "country": "浙江省",
  "city":"衢州市",
  "area":"常山县",
  "time": 1441293300,
  "address": "低塘街道新堰西路45号"
}


#精确查询
GET /useraudit/t_unparticiple_test/_search?q=uid:200111
GET /useraudit/t_unparticiple_test/_search
{
  "query": {
    "match": {
      "uid": "200111"
    }
  }
}

# 字段为strin类型,mappin中未定义取消分词,精确查询不到数据
GET /useraudit/t_unparticiple_test/_search
{
  "query": {
    "match": {
      "city": "衢州市"
    }
  }
}

GET /useraudit/t_participle_test/_search
{
  "query": {
    "match": {
      "country": "四川省"
    }
  }
}

# 字段为strin类型,mappin中定义取消分词,精确查询数据
GET /useraudit/t_participle_index_test/_search
{
  "query": {
    "match": {
      "country": "四川省"
    }
  }
}


#模糊查询
GET /useraudit/t_participle_test/_search
{
    "query" : { "term" : { "address" : "红星" }},
    "highlight" : {
        "pre_tags" : ["<tag1>", "<tag2>"],
        "post_tags" : ["</tag1>", "</tag2>"],
        "fields" : {
            "address" : {}
        }
    }
}
GET /useraudit/t_participle_index_test/_search
{
    "query" : { "term" : { "address" : "红星" }},
    "highlight" : {
        "pre_tags" : ["<tag1>", "<tag2>"],
        "post_tags" : ["</tag1>", "</tag2>"],
        "fields" : {
            "address" : {}
        }
    }
}

POST /index/fulltext/_search
{
    "query" : { "term" : { "content" : "中国" }},
    "highlight" : {
        "pre_tags" : ["<tag1>", "<tag2>"],
        "post_tags" : ["</tag1>", "</tag2>"],
        "fields" : {
            "content" : {}
        }
    }
}

二, java客户端调用Elasticsearch集群
1, 精准查询
2, 模糊查询(使用分词)

public class ESQueryClient {
    static Client CLIENT = null;
    static {
        // on startup
        Settings settings = ImmutableSettings.settingsBuilder().put("cluster.name", "elasticsearch_useraudit").put("client.transport.sniff", true)
                .build();
        CLIENT = new TransportClient(settings).addTransportAddress(new InetSocketTransportAddress("127.0.0.1", 9301))
                .addTransportAddress(new InetSocketTransportAddress("127.0.0.1", 9302))
                .addTransportAddress(new InetSocketTransportAddress("127.0.0.1", 9303));
    }

    public static void main(String[] args) throws ElasticsearchException, IOException {
        // 通过id查询
        qryById();
        // 通过某个字段查询,例如uid, country
        SearchRequestBuilder builder = CLIENT.prepareSearch("useraudit").setTypes("t_participle_test").setSearchType(SearchType.DEFAULT)
                .setFrom(0).setSize(100);
        BoolQueryBuilder qb = QueryBuilders.boolQuery().must(new QueryStringQueryBuilder("眉山市").field("city"));
        builder.setQuery(qb);
        SearchResponse response = builder.execute().actionGet();
        System.out.println("字段为strin类型, mappin中未定义取消分词,精确查询不到数据, 测试结果:");
        System.out.println("通过city字段查询:" + response);
        System.out.println("通过city字段查询信息数量:" + response.getHits().getTotalHits());

        // 通过某个字段查询,例如uid, country
        builder = CLIENT.prepareSearch("useraudit").setTypes("t_participle_index_test").setSearchType(SearchType.DEFAULT).setFrom(0).setSize(100);
        qb = QueryBuilders.boolQuery().must(new QueryStringQueryBuilder("眉山市").field("city"));
        builder.setQuery(qb);
        response = builder.execute().actionGet();
        System.out.println("字段为strin类型, mappin中定义取消分词,精确查询数据 , 测试结果:");
        System.out.println("通过city字段查询:" + response);
        System.out.println("通过city字段查询信息数量:" + response.getHits().getTotalHits());

        // .should(new QueryStringQueryBuilder("太多").field("city"))
        CLIENT.close();
    }

    private static void qryById() {
        GetResponse response = CLIENT.prepareGet("useraudit", "t_participle_test", "1").setOperationThreaded(false).execute().actionGet();
        System.out.println("通过id查询:" + response.getSourceAsString());
    }
}

三, 索引数据的维护
四, 批量插入数据
测试数据量5千万
五, 压力测试并发精准查询和模糊查询