2

我有两张桌子t1t2t1有 1/10 的大小t2)。每个表都有两列<Lat, Long>,其中包含一些点的纬度和经度。对于中的每一行,t1我想找到t2最接近它的行。这样做最有效的查询是什么?Hive 是否有任何类型的地理空间搜索库?

4

1 回答 1

2

你需要做一些触发。

请参考这篇关于数据库日志的文章

我相信最后一个例程是您正在寻找的(您需要对其进行修改以供使用):

CREATE DEFINER=`root`@`localhost` PROCEDURE closest_restaurants_optimized`
(IN units varchar(5), IN lat Decimal(9,6), IN lon Decimal(9,6), 
IN max_distance SMALLINT, IN limit_rows MEDIUMINT)
BEGIN
    DECLARE ONE_DEGREE_CONSTANT TINYINT;
    DECLARE EARTH_RADIUS_CONSTANT SMALLINT;
    DECLARE lon1, lon2, lat1, lat2 float;  
    IF units = 'miles' THEN
        SET ONE_DEGREE_CONSTANT   = 69;
        SET EARTH_RADIUS_CONSTANT = 3959;
    ELSE -- default to kilometers
        SET ONE_DEGREE_CONSTANT   = 111;
        SET EARTH_RADIUS_CONSTANT = 6371;
    END IF;  
    SET lon1 = lon-max_distance/abs(cos(radians(lat))*ONE_DEGREE_CONSTANT);
    SET lon2 = lon+max_distance/abs(cos(radians(lat))*ONE_DEGREE_CONSTANT);
    SET lat1 = lat-(max_distance/ONE_DEGREE_CONSTANT);
    SET lat2 = lat+(max_distance/ONE_DEGREE_CONSTANT);
    SELECT pm1.post_id, p.post_title,
        ROUND((EARTH_RADIUS_CONSTANT * acos( cos( radians(lat) ) 
            * cos( radians(pm1.meta_value) ) 
            * cos( radians(pm2.meta_value) - radians(lon)) + sin(radians(lat)) 
            * sin( radians(pm1.meta_value)))
        ), 3) AS distance
    FROM goodfood_wp_md20m_postmeta AS pm1, 
        goodfood_wp_md20m_postmeta AS pm2,
        goodfood_wp_md20m_posts    AS p 
    WHERE pm1.meta_key = 'latitude' AND pm2.meta_key = 'longitude'
    AND pm1.post_id = pm2.post_id
    AND pm1.post_id = p.id
    AND p.post_status = 'publish'
    AND pm2.meta_value between lon1 and lon2 
    AND pm1.meta_value between lat1 and lat2
    ORDER BY distance ASC
    LIMIT limit_rows;
END
于 2015-08-31T06:20:43.120 回答