|
| 1 | +// Licensed to the Apache Software Foundation (ASF) under one |
| 2 | +// or more contributor license agreements. See the NOTICE file |
| 3 | +// distributed with this work for additional information |
| 4 | +// regarding copyright ownership. The ASF licenses this file |
| 5 | +// to you under the Apache License, Version 2.0 (the |
| 6 | +// "License"); you may not use this file except in compliance |
| 7 | +// with the License. You may obtain a copy of the License at |
| 8 | +// |
| 9 | +// http://www.apache.org/licenses/LICENSE-2.0 |
| 10 | +// |
| 11 | +// Unless required by applicable law or agreed to in writing, |
| 12 | +// software distributed under the License is distributed on an |
| 13 | +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 14 | +// KIND, either express or implied. See the License for the |
| 15 | +// specific language governing permissions and limitations |
| 16 | +// under the License. |
| 17 | + |
| 18 | +use std::sync::Arc; |
| 19 | + |
| 20 | +use arrow_array::builder::BinaryBuilder; |
| 21 | +use datafusion_common::{DataFusionError, Result}; |
| 22 | +use datafusion_expr::ColumnarValue; |
| 23 | +use geos::Geom; |
| 24 | +use sedona_expr::scalar_udf::{ScalarKernelRef, SedonaScalarKernel}; |
| 25 | +use sedona_geometry::wkb_factory::WKB_MIN_PROBABLE_BYTES; |
| 26 | +use sedona_schema::datatypes::SedonaType; |
| 27 | +use sedona_schema::{datatypes::WKB_GEOMETRY, matchers::ArgMatcher}; |
| 28 | + |
| 29 | +use crate::executor::GeosExecutor; |
| 30 | + |
| 31 | +/// ST_UnaryUnion() implementation using the geos crate |
| 32 | +pub fn st_unary_union_impl() -> ScalarKernelRef { |
| 33 | + Arc::new(STUnaryUnion {}) |
| 34 | +} |
| 35 | + |
| 36 | +#[derive(Debug)] |
| 37 | +struct STUnaryUnion {} |
| 38 | + |
| 39 | +impl SedonaScalarKernel for STUnaryUnion { |
| 40 | + fn return_type(&self, args: &[SedonaType]) -> Result<Option<SedonaType>> { |
| 41 | + let matcher = ArgMatcher::new(vec![ArgMatcher::is_geometry()], WKB_GEOMETRY); |
| 42 | + matcher.match_args(args) |
| 43 | + } |
| 44 | + |
| 45 | + fn invoke_batch( |
| 46 | + &self, |
| 47 | + arg_types: &[SedonaType], |
| 48 | + args: &[ColumnarValue], |
| 49 | + ) -> Result<ColumnarValue> { |
| 50 | + let executor = GeosExecutor::new(arg_types, args); |
| 51 | + let mut builder = BinaryBuilder::with_capacity( |
| 52 | + executor.num_iterations(), |
| 53 | + WKB_MIN_PROBABLE_BYTES * executor.num_iterations(), |
| 54 | + ); |
| 55 | + executor.execute_wkb_void(|maybe_wkb| { |
| 56 | + match maybe_wkb { |
| 57 | + Some(wkb) => { |
| 58 | + let result_wkb = invoke_scalar(&wkb)?; |
| 59 | + builder.append_value(&result_wkb); |
| 60 | + } |
| 61 | + _ => builder.append_null(), |
| 62 | + } |
| 63 | + |
| 64 | + Ok(()) |
| 65 | + })?; |
| 66 | + |
| 67 | + executor.finish(Arc::new(builder.finish())) |
| 68 | + } |
| 69 | +} |
| 70 | + |
| 71 | +fn invoke_scalar(geos_geom: &geos::Geometry) -> Result<Vec<u8>> { |
| 72 | + let geometry = geos_geom |
| 73 | + .unary_union() |
| 74 | + .map_err(|e| DataFusionError::Execution(format!("Failed to perform unary union: {e}")))?; |
| 75 | + |
| 76 | + let wkb = geometry |
| 77 | + .to_wkb() |
| 78 | + .map_err(|e| DataFusionError::Execution(format!("Failed to convert to wkb: {e}")))?; |
| 79 | + |
| 80 | + Ok(wkb.into()) |
| 81 | +} |
| 82 | + |
| 83 | +#[cfg(test)] |
| 84 | +mod tests { |
| 85 | + use datafusion_common::ScalarValue; |
| 86 | + use rstest::rstest; |
| 87 | + use sedona_expr::scalar_udf::SedonaScalarUDF; |
| 88 | + use sedona_schema::datatypes::{WKB_GEOMETRY, WKB_VIEW_GEOMETRY}; |
| 89 | + use sedona_testing::compare::assert_array_equal; |
| 90 | + use sedona_testing::create::create_array; |
| 91 | + use sedona_testing::testers::ScalarUdfTester; |
| 92 | + |
| 93 | + use super::*; |
| 94 | + |
| 95 | + #[rstest] |
| 96 | + fn udf(#[values(WKB_GEOMETRY, WKB_VIEW_GEOMETRY)] sedona_type: SedonaType) { |
| 97 | + let udf = SedonaScalarUDF::from_kernel("st_unary_union", st_unary_union_impl()); |
| 98 | + let tester = ScalarUdfTester::new(udf.into(), vec![sedona_type]); |
| 99 | + tester.assert_return_type(WKB_GEOMETRY); |
| 100 | + |
| 101 | + let result = tester |
| 102 | + .invoke_scalar( |
| 103 | + "MULTIPOLYGON (((0 0, 1 0, 1 1, 0 1, 0 0)), ((1 0, 2 0, 2 1, 1 1, 1 0)))", |
| 104 | + ) |
| 105 | + .unwrap(); |
| 106 | + tester.assert_scalar_result_equals(result, "POLYGON ((0 0, 0 1, 1 1, 2 1, 2 0, 1 0, 0 0))"); |
| 107 | + |
| 108 | + let result = tester |
| 109 | + .invoke_scalar("MULTIPOINT ((0 0), (1 1), (2 2))") |
| 110 | + .unwrap(); |
| 111 | + tester.assert_scalar_result_equals(result, "MULTIPOINT ((0 0), (1 1), (2 2))"); |
| 112 | + |
| 113 | + let result = tester.invoke_scalar(ScalarValue::Null).unwrap(); |
| 114 | + assert!(result.is_null()); |
| 115 | + |
| 116 | + let input_wkt = vec![ |
| 117 | + Some("MULTIPOLYGON (((0 0, 1 0, 1 1, 0 1, 0 0)), ((1 0, 2 0, 2 1, 1 1, 1 0)))"), |
| 118 | + Some("LINESTRING (0 0, 1 1, 2 2)"), |
| 119 | + Some("POINT EMPTY"), |
| 120 | + None, |
| 121 | + ]; |
| 122 | + |
| 123 | + let expected = create_array( |
| 124 | + &[ |
| 125 | + Some("POLYGON ((0 0, 0 1, 1 1, 2 1, 2 0, 1 0, 0 0))"), |
| 126 | + Some("LINESTRING (0 0, 1 1, 2 2)"), |
| 127 | + Some("POINT EMPTY"), |
| 128 | + None, |
| 129 | + ], |
| 130 | + &WKB_GEOMETRY, |
| 131 | + ); |
| 132 | + assert_array_equal(&tester.invoke_wkb_array(input_wkt).unwrap(), &expected); |
| 133 | + } |
| 134 | +} |
0 commit comments