API: Single-value binary serialization for geometry and geography

api/src/main/java/org/apache/iceberg/types/Conversions.java

@@ -31,6 +31,7 @@
 import java.util.UUID;
 import org.apache.iceberg.exceptions.RuntimeIOException;
 import org.apache.iceberg.expressions.Literal;
+import org.apache.iceberg.geospatial.GeospatialBound;
 import org.apache.iceberg.util.UUIDUtil;
 import org.apache.iceberg.variants.Variant;
 import org.apache.iceberg.variants.VariantMetadata;
@@ -131,6 +132,12 @@ public static ByteBuffer toByteBuffer(Type.TypeID typeId, Object value) {
  variantMetadata.writeTo(variantBuffer, 0);
  variantValue.writeTo(variantBuffer, variantMetadata.sizeInBytes());
  return variantBuffer;
+ case GEOMETRY:
+ case GEOGRAPHY:
+ // Geometry and geography lower/upper bounds are single points encoded as an
+ // x:y:z:m concatenation of 8-byte little-endian IEEE 754 doubles. See the
+ // Bound Serialization section of the Iceberg spec.
+ return ((GeospatialBound) value).toByteBuffer();
  case UNKNOWN:
  // underlying type not known
  return null;
@@ -196,6 +203,9 @@ private static Object internalFromByteBuffer(Type type, ByteBuffer buffer) {
  return new BigDecimal(new BigInteger(unscaledBytes), decimal.scale());
  case VARIANT:
  return Variant.from(tmp);
+ case GEOMETRY:
+ case GEOGRAPHY:
+ return GeospatialBound.fromByteBuffer(tmp);
  case UNKNOWN:
  // underlying type not known
  return null;

api/src/test/java/org/apache/iceberg/types/TestConversions.java

@@ -26,13 +26,18 @@
 import java.nio.charset.StandardCharsets;
 import java.util.UUID;
 import org.apache.iceberg.expressions.Literal;
+import org.apache.iceberg.geospatial.GeospatialBound;
+import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList;
+import org.apache.iceberg.relocated.com.google.common.primitives.Bytes;
 import org.apache.iceberg.types.Types.BinaryType;
 import org.apache.iceberg.types.Types.BooleanType;
 import org.apache.iceberg.types.Types.DateType;
 import org.apache.iceberg.types.Types.DecimalType;
 import org.apache.iceberg.types.Types.DoubleType;
 import org.apache.iceberg.types.Types.FixedType;
 import org.apache.iceberg.types.Types.FloatType;
+import org.apache.iceberg.types.Types.GeographyType;
+import org.apache.iceberg.types.Types.GeometryType;
 import org.apache.iceberg.types.Types.IntegerType;
 import org.apache.iceberg.types.Types.LongType;
 import org.apache.iceberg.types.Types.StringType;
@@ -191,6 +196,52 @@ public void testByteBufferConversions() {
  .isEqualTo(new byte[] {11});
  }
 
+ @Test
+ public void testByteBufferConversionsForGeometry() {
+ // geometry/geography bounds are a single point encoded as 8-byte little-endian IEEE 754
+ // doubles in X, Y[, Z][, M] order:
+ // x:y (16B) when z and m are unset
+ // x:y:z (24B) when only m is unset
+ // x:y:NaN:m (32B) when only z is unset -- z slot is filled with NaN
+ // x:y:z:m (32B) when all are set
+ byte[] xBytes = {0, 0, 0, 0, 0, 0, 36, 64}; // 10.0
+ byte[] yBytes = {0, 0, 0, 0, 0, 0, 42, 64}; // 13.0
+ byte[] zBytes = {0, 0, 0, 0, 0, 0, 46, 64}; // 15.0
+ byte[] mBytes = {0, 0, 0, 0, 0, 0, 52, 64}; // 20.0
+ byte[] nanBytes = {0, 0, 0, 0, 0, 0, -8, 127};
+
+ for (Type type : ImmutableList.of(GeometryType.crs84(), GeographyType.crs84())) {
+ assertConversion(GeospatialBound.createXY(10.0, 13.0), type, Bytes.concat(xBytes, yBytes));
+ assertConversion(
+ GeospatialBound.createXYZ(10.0, 13.0, 15.0), type, Bytes.concat(xBytes, yBytes, zBytes));
+ assertConversion(
+ GeospatialBound.createXYM(10.0, 13.0, 20.0),
+ type,
+ Bytes.concat(xBytes, yBytes, nanBytes, mBytes));
+ assertConversion(
+ GeospatialBound.createXYZM(10.0, 13.0, 15.0, 20.0),
+ type,
+ Bytes.concat(xBytes, yBytes, zBytes, mBytes));
+ }
+
+ // a non-default CRS must not change the binary encoding
+ assertConversion(
+ GeospatialBound.createXY(10.0, 13.0),
+ GeometryType.of("EPSG:3857"),
+ Bytes.concat(xBytes, yBytes));
+ }
+
+ @Test
+ public void testNullByteBufferConversionsForGeometry() {
+ // Null is handled by the shared guards in toByteBuffer / fromByteBuffer before the type switch,
+ // so this pins the null contract for geo types rather than exercising the GEOMETRY / GEOGRAPHY
+ // arms (those are covered by testByteBufferConversionsForGeometry).
+ assertThat(Conversions.toByteBuffer(GeometryType.crs84(), null)).isNull();
+ assertThat(Conversions.toByteBuffer(GeographyType.crs84(), null)).isNull();
+ assertThat((Object) Conversions.fromByteBuffer(GeometryType.crs84(), null)).isNull();
+ assertThat((Object) Conversions.fromByteBuffer(GeographyType.crs84(), null)).isNull();
+ }
+
  private <T> void assertConversion(T value, Type type, byte[] expectedBinary) {
  ByteBuffer byteBuffer = Conversions.toByteBuffer(type, value);
  assertThat(byteBuffer.array()).isEqualTo(expectedBinary);