# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
from pyspark import RDD, SparkContext
from sedona.spark.core.enums import FileDataSplitter
from sedona.spark.core.enums.file_data_splitter import FileSplitterJvm
from sedona.spark.core.jvm.translate import PythonRddToJavaRDDAdapter
from sedona.spark.core.SpatialRDD.spatial_rdd import JvmSpatialRDD, SpatialRDD
from sedona.spark.core.SpatialRDD.spatial_rdd_factory import SpatialRDDFactory
from sedona.spark.utils.meta import MultipleMeta
[docs]
class LineStringRDD(SpatialRDD, metaclass=MultipleMeta):
def __init__(self, rdd: RDD):
super().__init__(rdd.ctx)
spatial_rdd = PythonRddToJavaRDDAdapter(
self._jvm
).deserialize_to_linestring_raw_rdd(rdd._jrdd)
srdd = self._jvm_spatial_rdd(spatial_rdd)
self._srdd = srdd
def __init__(self):
self._do_init()
self._srdd = self._jvm_spatial_rdd()
def __init__(self, rawSpatialRDD: JvmSpatialRDD):
"""
:param rawSpatialRDD: RDD
"""
super().__init__(rawSpatialRDD.sc)
jsrdd = rawSpatialRDD.jsrdd
self._srdd = self._jvm_spatial_rdd(jsrdd)
def __init__(
self,
sparkContext: SparkContext,
InputLocation: str,
startOffset: int,
endOffset: int,
splitter: FileDataSplitter,
carryInputData: bool,
partitions: int,
):
"""
:param sparkContext: SparkContext instance
:param InputLocation: str, location for loaded file
:param startOffset: int, starting offset
:param endOffset: int, ending offset
:param splitter: FileDataSplitter, data file splitter
:param carryInputData: bool, if spatial rdd should keep non geometry attributes
:param partitions: int, number of partitions
"""
super().__init__(sparkContext)
jvm_splitter = FileSplitterJvm(self._jvm, splitter).jvm_instance
self._srdd = self._jvm_spatial_rdd(
self._jsc,
InputLocation,
startOffset,
endOffset,
jvm_splitter,
carryInputData,
partitions,
)
def __init__(
self,
sparkContext: SparkContext,
InputLocation: str,
startOffset: int,
endOffset: int,
splitter: FileDataSplitter,
carryInputData: bool,
):
"""
:param sparkContext: SparkContext instance
:param InputLocation: str, location for loaded file
:param startOffset: int, starting offset
:param endOffset: int, ending offset
:param splitter: FileDataSplitter, data file splitter
:param carryInputData: bool, if spatial rdd should keep non geometry attributes
"""
super().__init__(sparkContext)
jvm_splitter = FileSplitterJvm(self._jvm, splitter).jvm_instance
self._srdd = self._jvm_spatial_rdd(
self._jsc,
InputLocation,
startOffset,
endOffset,
jvm_splitter,
carryInputData,
)
def __init__(
self,
sparkContext: SparkContext,
InputLocation: str,
splitter: FileDataSplitter,
carryInputData: bool,
partitions: int,
):
"""
:param sparkContext: SparkContext instance
:param InputLocation: str, location for loaded file
:param splitter: FileDataSplitter, data file splitter
:param carryInputData: bool, if spatial rdd should keep non geometry attributes
:param partitions: int, number of partitions
"""
super().__init__(sparkContext)
jvm_splitter = FileSplitterJvm(self._jvm, splitter).jvm_instance
self._srdd = self._jvm_spatial_rdd(
self._jsc, InputLocation, jvm_splitter, carryInputData, partitions
)
def __init__(
self,
sparkContext: SparkContext,
InputLocation: str,
splitter: FileDataSplitter,
carryInputData: bool,
):
"""
:param sparkContext: SparkContext instance
:param InputLocation: str, location for loaded file
:param splitter: FileDataSplitter, data file splitter
:param carryInputData: bool, if spatial rdd should keep non geometry attributes
"""
super().__init__(sparkContext)
jvm_splitter = FileSplitterJvm(self._jvm, splitter).jvm_instance
self._srdd = self._jvm_spatial_rdd(
self._jsc, InputLocation, jvm_splitter, carryInputData
)
@property
def _jvm_spatial_rdd(self):
if self._sc is not None:
spatial_factory = SpatialRDDFactory(self._sc)
else:
raise TypeError("Please initialize spark Session first")
return spatial_factory.create_linestring_rdd()
[docs]
def MinimumBoundingRectangle(self):
from sedona.spark.core.SpatialRDD import RectangleRDD
rectangle_rdd = RectangleRDD()
srdd = self._srdd.MinimumBoundingRectangle()
rectangle_rdd.set_srdd(srdd)
return rectangle_rdd