def test_overlapped_linestring_join_correctness(self):
window_rdd = PolygonRDD(
self.sc.parallelize(self.test_polygon_window_set),
StorageLevel.MEMORY_ONLY)
object_rdd = LineStringRDD(
self.sc.parallelize(self.test_overlapped_linestring_set),
StorageLevel.MEMORY_ONLY)
self.prepare_rdd(object_rdd, window_rdd, GridType.QUADTREE)
result = JoinQuery.SpatialJoinQuery(object_rdd, window_rdd, True,
True).collect()
self.verify_join_result(result)
result_no_index = JoinQuery.SpatialJoinQuery(object_rdd, window_rdd,
False, True).collect()
self.verify_join_result(result_no_index)
def test_outside_point_join_correctness(self):
self.once_before_all()
window_rdd = PolygonRDD(
self.sc.parallelize(self.test_polygon_window_set),
StorageLevel.MEMORY_ONLY)
object_rdd = PointRDD(self.sc.parallelize(self.test_outside_point_set),
StorageLevel.MEMORY_ONLY)
self.prepare_rdd(object_rdd, window_rdd, GridType.QUADTREE)
result = JoinQuery.SpatialJoinQuery(object_rdd, window_rdd, True,
False).collect()
assert 0 == result.__len__()
result_no_index = JoinQuery.SpatialJoinQuery(object_rdd, window_rdd,
False, False).collect()
assert 0 == result_no_index.__len__()
def test_inside_point_join_correctness(self):
self.once_before_all()
window_rdd = PolygonRDD(
self.sc.parallelize(self.test_polygon_window_set))
object_rdd = PointRDD(self.sc.parallelize(self.test_inside_point_set))
self.prepare_rdd(object_rdd, window_rdd, GridType.QUADTREE)
result = JoinQuery.SpatialJoinQuery(object_rdd, window_rdd, True,
False).collect()
self.verify_join_result(result)
result_no_index = JoinQuery.SpatialJoinQuery(object_rdd, window_rdd,
False, False).collect()
self.verify_join_result(result_no_index)
def test_nested_loop(self, num_partitions, use_legacy_apis, grid_type, intersects):
query_rdd = self.create_polygon_rdd(query_polygon_set, splitter, num_partitions)
spatial_rdd = self.create_polygon_rdd(input_location, splitter, num_partitions)
self.partition_rdds(query_rdd, spatial_rdd, grid_type, use_legacy_apis)
result = JoinQuery.SpatialJoinQuery(
spatial_rdd, query_rdd, False, intersects).collect()
self.sanity_check_join_results(result)
assert self.get_expected_count(intersects) == self.count_join_results(result)
def nested_loop(self, query_rdd, num_partitions, grid_type,
use_legacy_apis, expected_count):
spatial_rdd = self.create_point_rdd(input_location, splitter,
num_partitions)
self.partition_rdds(query_rdd, spatial_rdd, grid_type, use_legacy_apis)
result = JoinQuery.SpatialJoinQuery(spatial_rdd, query_rdd, False,
True).collect()
self.sanity_check_join_results(result)
assert expected_count == self.count_join_results(result)
def test_spatial_join_query(self):
point_rdd = PointRDD(self.sc, point_path, 4, FileDataSplitter.WKT,
True)
polygon_rdd = PolygonRDD(self.sc, counties_path, 2, 3,
FileDataSplitter.WKT, True)
point_rdd.analyze()
point_rdd.spatialPartitioning(GridType.KDBTREE)
polygon_rdd.spatialPartitioning(point_rdd.getPartitioner())
result = JoinQuery.SpatialJoinQuery(point_rdd, polygon_rdd, True,
False)
print(result.count())
def test_index_int(self, num_partitions, use_legacy_apis, grid_type,
index_type):
query_rdd = self.create_rectangle_rdd(input_location, splitter,
num_partitions)
spatial_rdd = self.create_rectangle_rdd(input_location, splitter,
num_partitions)
self.partition_rdds(query_rdd, spatial_rdd, grid_type, use_legacy_apis)
spatial_rdd.buildIndex(index_type, True)
result = JoinQuery.SpatialJoinQuery(spatial_rdd, query_rdd, False,
True).collect()
self.sanity_check_join_results(result)
assert match_count == self.count_join_results(result)
def test_nested_loop(self, num_partitions, use_legacy_apis, grid_type):
query_rdd = self.create_rectangle_rdd(input_location, splitter,
num_partitions)
spatial_rdd = self.create_rectangle_rdd(input_location, splitter,
num_partitions)
self.partition_rdds(query_rdd, spatial_rdd, grid_type, use_legacy_apis)
result = JoinQuery.SpatialJoinQuery(spatial_rdd, query_rdd, False,
True).collect()
count = 0
for el in result:
count += el[1].__len__()
self.sanity_check_join_results(result)
assert match_count == self.count_join_results(result)
def test_spatial_join_query_and_build_index_on_points_on_the_fly(self):
query_window = PolygonRDD(self.sc, polygon_rdd_input_location,
polygon_rdd_start_offset,
polygon_rdd_end_offset, polygon_rdd_splitter,
True)
object_rdd = PointRDD(sparkContext=self.sc,
InputLocation=point_rdd_input_location,
Offset=point_rdd_offset,
splitter=point_rdd_splitter,
carryInputData=False)
object_rdd.analyze()
object_rdd.spatialPartitioning(join_query_partitionin_type)
query_window.spatialPartitioning(object_rdd.getPartitioner())
for i in range(each_query_loop_times):
result_size = JoinQuery.SpatialJoinQuery(object_rdd, query_window,
True, False).count()
def test_spatial_join_query_with_polygon_rdd(self):
query_rdd = PolygonRDD(self.sc, input_location_query_polygon, splitter,
True, num_partitions, StorageLevel.MEMORY_ONLY,
"epsg:4326", "epsg:3005")
spatial_rdd = PointRDD(self.sc, input_location, offset, splitter, True,
num_partitions, StorageLevel.MEMORY_ONLY,
"epsg:4326", "epsg:3005")
spatial_rdd.spatialPartitioning(grid_type)
query_rdd.spatialPartitioning(spatial_rdd.grids)
result = JoinQuery.SpatialJoinQuery(spatial_rdd, query_rdd, False,
True).collect()
assert result[1][0].getUserData() is not None
for data in result:
if data[1].__len__() != 0:
for right_data in data[1]:
assert right_data.getUserData() is not None