(sedona) branch master updated: [GH-2886] Recognize Box2D columns as GeoParquet bbox covering columns (#2921)

[ji...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

jiayuasu pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/sedona.git


The following commit(s) were added to refs/heads/master by this push:
     new 6116cb9210 [GH-2886] Recognize Box2D columns as GeoParquet bbox covering columns (#2921)
6116cb9210 is described below

commit 6116cb9210f27d73a0acef1f787ae9ab023d1625
Author: Jia Yu <ji...@apache.org>
AuthorDate: Thu May 7 22:37:47 2026 -0700

    [GH-2886] Recognize Box2D columns as GeoParquet bbox covering columns (#2921)
---
 .../geoparquet/GeoParquetMetaData.scala            | 13 ++++++
 .../org/apache/sedona/sql/geoparquetIOTests.scala  | 47 ++++++++++++++++++++++
 2 files changed, 60 insertions(+)

diff --git a/spark/common/src/main/scala/org/apache/spark/sql/execution/datasources/geoparquet/GeoParquetMetaData.scala b/spark/common/src/main/scala/org/apache/spark/sql/execution/datasources/geoparquet/GeoParquetMetaData.scala
index 7517b8e5fc..4068b3f69a 100644
--- a/spark/common/src/main/scala/org/apache/spark/sql/execution/datasources/geoparquet/GeoParquetMetaData.scala
+++ b/spark/common/src/main/scala/org/apache/spark/sql/execution/datasources/geoparquet/GeoParquetMetaData.scala
@@ -20,6 +20,7 @@ package org.apache.spark.sql.execution.datasources.geoparquet
 
 import scala.util.control.NonFatal
 
+import org.apache.spark.sql.sedona_sql.UDT.Box2DUDT
 import org.apache.spark.sql.types.{DoubleType, FloatType, StructType}
 import org.datasyslab.proj4sedona.core.Proj
 import org.datasyslab.proj4sedona.parser.CRSSerializer
@@ -236,6 +237,18 @@ object GeoParquetMetaData {
     schema(coveringColumnIndex).dataType match {
       case coveringColumnType: StructType =>
         coveringColumnTypeToCovering(coveringColumnName, coveringColumnType)
+      case udt: Box2DUDT =>
+        // Box2DUDT exposes a struct<xmin, ymin, xmax, ymax: double> sqlType, which is the exact
+        // shape required by GeoParquet 1.1 bbox covering columns. Treat the underlying struct as
+        // the covering struct so users can write a Box2D column and have it referenced as a
+        // covering column in GeoParquet metadata without any manual struct construction.
+        udt.sqlType match {
+          case structType: StructType =>
+            coveringColumnTypeToCovering(coveringColumnName, structType)
+          case other =>
+            throw new IllegalStateException(
+              s"Box2DUDT.sqlType is expected to be a StructType, got $other")
+        }
       case _ =>
         throw new IllegalArgumentException(
           s"Covering column $coveringColumnName is not a struct type")
diff --git a/spark/common/src/test/scala/org/apache/sedona/sql/geoparquetIOTests.scala b/spark/common/src/test/scala/org/apache/sedona/sql/geoparquetIOTests.scala
index 5d2a13f486..2924292cd5 100644
--- a/spark/common/src/test/scala/org/apache/sedona/sql/geoparquetIOTests.scala
+++ b/spark/common/src/test/scala/org/apache/sedona/sql/geoparquetIOTests.scala
@@ -1021,6 +1021,53 @@ class geoparquetIOTests extends TestBaseScala with BeforeAndAfterAll {
       }
     }
 
+    it("GeoParquet supports writing covering metadata from a Box2D column") {
+      // User-provided Box2D column referenced via the geoparquet.covering option.
+      val df = sparkSession
+        .range(0, 100)
+        .toDF("id")
+        .withColumn("id", expr("CAST(id AS DOUBLE)"))
+        .withColumn("geometry", expr("ST_Point(id, id + 1)"))
+        .withColumn("test_cov", expr("ST_Box2D(geometry)"))
+      val geoParquetSavePath = geoparquetoutputlocation + "/gp_with_box2d_covering.parquet"
+      df.write
+        .format("geoparquet")
+        .option("geoparquet.covering.geometry", "test_cov")
+        .mode("overwrite")
+        .save(geoParquetSavePath)
+      validateGeoParquetMetadata(geoParquetSavePath) { geo =>
+        implicit val formats: org.json4s.Formats = org.json4s.DefaultFormats
+        val coveringJsValue = geo \ "columns" \ "geometry" \ "covering"
+        val covering = coveringJsValue.extract[Covering]
+        assert(covering.bbox.xmin == Seq("test_cov", "xmin"))
+        assert(covering.bbox.ymin == Seq("test_cov", "ymin"))
+        assert(covering.bbox.xmax == Seq("test_cov", "xmax"))
+        assert(covering.bbox.ymax == Seq("test_cov", "ymax"))
+      }
+    }
+
+    it("GeoParquet auto populates covering metadata for a Box2D <geom>_bbox column") {
+      // Auto-detect path: when a column named <geom>_bbox is a Box2D, reuse it as the
+      // covering column instead of synthesizing a separate float64 struct.
+      val df = sparkSession
+        .range(0, 100)
+        .toDF("id")
+        .withColumn("id", expr("CAST(id AS DOUBLE)"))
+        .withColumn("geometry", expr("ST_Point(id, id + 1)"))
+        .withColumn("geometry_bbox", expr("ST_Box2D(geometry)"))
+      val geoParquetSavePath = geoparquetoutputlocation + "/gp_box2d_auto_covering.parquet"
+      df.write.format("geoparquet").mode("overwrite").save(geoParquetSavePath)
+      validateGeoParquetMetadata(geoParquetSavePath) { geo =>
+        implicit val formats: org.json4s.Formats = org.json4s.DefaultFormats
+        val coveringJsValue = geo \ "columns" \ "geometry" \ "covering"
+        val covering = coveringJsValue.extract[Covering]
+        assert(covering.bbox.xmin == Seq("geometry_bbox", "xmin"))
+        assert(covering.bbox.ymin == Seq("geometry_bbox", "ymin"))
+        assert(covering.bbox.xmax == Seq("geometry_bbox", "xmax"))
+        assert(covering.bbox.ymax == Seq("geometry_bbox", "ymax"))
+      }
+    }
+
     it("GeoParquet auto populates covering metadata for single geometry column") {
       val df = sparkSession
         .range(0, 100)