如何在大量经纬度数据中搜索附近的点

空间数据库

例如在postgresql中新建一个可以保存空间数据的表：
CREATE TABLE "public"."roadpoint" (
"lat" float8 DEFAULT 0,
"lng" float8 DEFAULT 0,
"gisp" point,
"id" int4 DEFAULT nextval('roadpoint_id_seq'::regclass) NOT NULL,
"geohashcode" varchar(20) DEFAULT NULL::character varying,
CONSTRAINT "roadpoint_idpkey" PRIMARY KEY ("id")
)
WITH (OIDS=FALSE)
;

ALTER TABLE "public"."roadpoint" OWNER TO "bmkpdev";

COMMENT ON COLUMN "public"."roadpoint"."lat" IS '纬度';

COMMENT ON COLUMN "public"."roadpoint"."lng" IS '经度';

CREATE INDEX "geohash_index" ON "public"."roadpoint" USING hash ("geohashcode");

CREATE INDEX "georoadpointgis_idx" ON "public"."roadpoint" USING gist ("gisp") WITH (fillfactor = 85);

CREATE INDEX "lat_index" ON "public"."roadpoint" USING btree ("lat");

CREATE INDEX "lng_index" ON "public"."roadpoint" USING btree ("lng");

建立之后打开表如下：

其中 lng 和 lat为经纬度数据：
gisp为空间数据列：
生成gisp数据列的sql语句如下：
update roadpoint set gisp = point(lng,lat) where gisp is null

生成geohashcode

python代码如下：
from math import log10
base32 = '0123456789bcdefghjkmnpqrstuvwxyz'
decodemap = { }
for i in range(len(base32)):
decodemap[__base32[i]] = i
del i

def decode_exactly(geohash):
lat_interval, lon_interval = (-90.0, 90.0), (-180.0, 180.0)
lat_err, lon_err = 90.0, 180.0
is_even = True
for c in geohash:
cd = __decodemap[c]
for mask in [16, 8, 4, 2, 1]:
if is_even: # adds longitude info
lon_err /= 2
if cd & mask:
lon_interval = ((lon_interval[0]+lon_interval[1])/2, lon_interval[1])
else:
lon_interval = (lon_interval[0], (lon_interval[0]+lon_interval[1])/2)
else: # adds latitude info
lat_err /= 2
if cd & mask:
lat_interval = ((lat_interval[0]+lat_interval[1])/2, lat_interval[1])
else:
lat_interval = (lat_interval[0], (lat_interval[0]+lat_interval[1])/2)
is_even = not is_even
lat = (lat_interval[0] + lat_interval[1]) / 2
lon = (lon_interval[0] + lon_interval[1]) / 2
return lat, lon, lat_err, lon_err

def decode(geohash):
"""
Decode geohash, returning two strings with latitude and longitude
containing only relevant digits and with trailing zeroes removed.
"""
lat, lon, lat_err, lon_err = decode_exactly(geohash)

Format to the number of decimals that are known

lats = "%.*f" % (max(1, int(round(-log10(lat_err)))) - 1, lat)
lons = "%.*f" % (max(1, int(round(-log10(lon_err)))) - 1, lon)
if '.' in lats: lats = lats.rstrip('0')
if '.' in lons: lons = lons.rstrip('0')
return lats, lons

def encode(latitude, longitude, precision=12):
"""
Encode a position given in float arguments latitude, longitude to
a geohash which will have the character count precision.
"""
lat_interval, lon_interval = (-90.0, 90.0), (-180.0, 180.0)
geohash = []
bits = [ 16, 8, 4, 2, 1 ]
bit = 0
ch = 0
even = True
while len(geohash) < precision:
if even:
mid = (lon_interval[0] + lon_interval[1]) / 2
if longitude > mid:
ch |= bits[bit]
lon_interval = (mid, lon_interval[1])
else:
lon_interval = (lon_interval[0], mid)
else:
mid = (lat_interval[0] + lat_interval[1]) / 2
if latitude > mid:
ch |= bits[bit]
lat_interval = (mid, lat_interval[1])
else:
lat_interval = (lat_interval[0], mid)
even = not even
if bit < 4:
bit += 1
else:
geohash += __base32[ch]
bit = 0
ch = 0
return ''.join(geohash)

调用示例

geohashtext = geohash.encode(float(lat),float(lng),7)
其中lat为纬度 lng为经度 7为定位精度

再 将数据导入到上面的postgresql 表中
在geohashcode列添加上索引，执行如下语句：
select lng,lat from roadpoint where geohashcode = '' and geo_distance(gisp,point(114.404498,30.511795)) = (select MIN(geo_distance(gisp,point(114.404498,30.511795))) from roadpoint)

就可以很快的找到最近的定位数据。