[SPARK-55262][GEO][SQL] Block Geo types in all file based data sources except Parquet

### What changes were proposed in this pull request?
Disable geospatial types (Geometry and Geography) in all file based data sources except Parquet: CSV, JSON, ORC, Avro, XML.

### Why are the changes needed?
Explicitly disallow geospatial data types in the unsupported formats.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
Added tests to verify that GEOMETRY and GEOGRAPHY are disallowed in CSV, JSON, ORC, Avro, and XML.

### Was this patch authored or co-authored using generative AI tooling?
No.

Closes apache#54038 from uros-db/geo-data-sources.

Authored-by: Uros Bojanic <uros.bojanic@databricks.com>
Signed-off-by: Wenchen Fan <wenchen@databricks.com>

Author: uros-db

connector/avro/src/test/scala/org/apache/spark/sql/avro/AvroSuite.scala

@@ -3482,4 +3482,29 @@ class AvroV2Suite extends AvroSuite with ExplainSuiteHelper {
       checkAnswer(readDf, df)
     }
   }
+
+  test("Geospatial types are not supported in Avro") {
+    withTempDir { dir =>
+      // Temporary directory for writing the test data.
+      val tempDir = new File(dir, "files").getCanonicalPath
+      // Test data: WKB representation of POINT(1 2).
+      val wkb = "0101000000000000000000F03F0000000000000040"
+      // Test GEOMETRY and GEOGRAPHY data types.
+      val geoTestCases = Seq(
+        (s"ST_GeomFromWKB(X'$wkb')", "\"GEOMETRY(0)\""),
+        (s"ST_GeogFromWKB(X'$wkb')", "\"GEOGRAPHY(4326)\"")
+      )
+      geoTestCases.foreach { case (expr, expectedType) =>
+        checkError(
+          exception = intercept[AnalysisException] {
+            sql(s"select $expr as g").write.format("avro").mode("overwrite").save(tempDir)
+          },
+          condition = "UNSUPPORTED_DATA_TYPE_FOR_DATASOURCE",
+          parameters = Map(
+            "columnName" -> "`g`",
+            "columnType" -> expectedType,
+            "format" -> "Avro"))
+      }
+    }
+  }
 }

sql/core/src/main/scala/org/apache/spark/sql/avro/AvroUtils.scala

@@ -83,6 +83,8 @@ private[sql] object AvroUtils extends Logging {
   def supportsDataType(dataType: DataType): Boolean = dataType match {
     case _: VariantType => false
 
+    case _: GeometryType | _: GeographyType => false
+
     case _: AtomicType => true
 
     case st: StructType => st.forall { f => supportsDataType(f.dataType) }

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala

@@ -155,6 +155,8 @@ case class CSVFileFormat() extends TextBasedFileFormat with DataSourceRegister {
   private def supportDataType(dataType: DataType, allowVariant: Boolean): Boolean = dataType match {
     case _: VariantType => allowVariant
 
+    case _: GeometryType | _: GeographyType => false
+
     case _: AtomicType => true
 
     case udt: UserDefinedType[_] => supportDataType(udt.sqlType)

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonFileFormat.scala

@@ -115,6 +115,8 @@ case class JsonFileFormat() extends TextBasedFileFormat with DataSourceRegister
   override def supportDataType(dataType: DataType): Boolean = dataType match {
     case _: VariantType => true
 
+    case _: GeometryType | _: GeographyType => false
+
     case _: AtomicType => true
 
     case st: StructType => st.forall { f => supportDataType(f.dataType) }

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala

@@ -249,6 +249,8 @@ class OrcFileFormat
   override def supportDataType(dataType: DataType): Boolean = dataType match {
     case _: VariantType => false
 
+    case _: GeometryType | _: GeographyType => false
+
     case _: AtomicType => true
 
     case st: StructType => st.forall { f => supportDataType(f.dataType) }

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVTable.scala

@@ -26,7 +26,7 @@ import org.apache.spark.sql.connector.write.{LogicalWriteInfo, Write, WriteBuild
 import org.apache.spark.sql.execution.datasources.FileFormat
 import org.apache.spark.sql.execution.datasources.csv.CSVDataSource
 import org.apache.spark.sql.execution.datasources.v2.FileTable
-import org.apache.spark.sql.types.{AtomicType, DataType, StructType, UserDefinedType}
+import org.apache.spark.sql.types.{AtomicType, DataType, GeographyType, GeometryType, StructType, UserDefinedType}
 import org.apache.spark.sql.util.CaseInsensitiveStringMap
 
 case class CSVTable(
@@ -57,6 +57,8 @@ case class CSVTable(
   }
 
   override def supportsDataType(dataType: DataType): Boolean = dataType match {
+    case _: GeometryType | _: GeographyType => false
+
     case _: AtomicType => true
 
     case udt: UserDefinedType[_] => supportsDataType(udt.sqlType)

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/json/JsonTable.scala

@@ -57,6 +57,8 @@ case class JsonTable(
   }
 
   override def supportsDataType(dataType: DataType): Boolean = dataType match {
+    case _: GeometryType | _: GeographyType => false
+
     case _: AtomicType => true
 
     case st: StructType => st.forall { f => supportsDataType(f.dataType) }

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/orc/OrcTable.scala

@@ -51,6 +51,8 @@ case class OrcTable(
   }
 
   override def supportsDataType(dataType: DataType): Boolean = dataType match {
+    case _: GeometryType | _: GeographyType => false
+
     case _: AtomicType => true
 
     case st: StructType => st.forall { f => supportsDataType(f.dataType) }

sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/xml/XmlFileFormat.scala

@@ -131,6 +131,9 @@ case class XmlFileFormat() extends TextBasedFileFormat with DataSourceRegister {
 
   override def supportDataType(dataType: DataType): Boolean = dataType match {
     case _: VariantType => true
+
+    case _: GeometryType | _: GeographyType => false
+
     case _: AtomicType => true
 
     case st: StructType => st.forall { f => supportDataType(f.dataType) }

sql/core/src/test/scala/org/apache/spark/sql/FileBasedDataSourceSuite.scala

@@ -1273,6 +1273,45 @@ class FileBasedDataSourceSuite extends QueryTest
       }
     }
   }
+
+  test("Geospatial types are not supported in file data sources other than Parquet") {
+    // All of these file formats do NOT support geospatial types (GEOMETRY and GEOGRAPHY).
+    val unsupportedDataSources = Seq("csv", "json", "orc", "text", "xml")
+    // Test both v1 and v2 data sources.
+    Seq(true, false).foreach { useV1 =>
+      val useV1List = if (useV1) {
+        unsupportedDataSources.mkString(",")
+      } else {
+        ""
+      }
+      withSQLConf(SQLConf.USE_V1_SOURCE_LIST.key -> useV1List) {
+        withTempDir { dir =>
+          // Temporary directory for writing the test data.
+          val tempDir = new File(dir, "files").getCanonicalPath
+          // Test data: WKB representation of POINT(1 2).
+          val wkb = "0101000000000000000000F03F0000000000000040"
+          // Test GEOMETRY and GEOGRAPHY data types.
+          val geoTestCases = Seq(
+            (s"ST_GeomFromWKB(X'$wkb')", "\"GEOMETRY(0)\""),
+            (s"ST_GeogFromWKB(X'$wkb')", "\"GEOGRAPHY(4326)\"")
+          )
+          unsupportedDataSources.foreach { format =>
+            geoTestCases.foreach { case (expr, expectedType) =>
+              checkError(
+                exception = intercept[AnalysisException] {
+                  sql(s"select $expr as g").write.format(format).mode("overwrite").save(tempDir)
+                },
+                condition = "UNSUPPORTED_DATA_TYPE_FOR_DATASOURCE",
+                parameters = Map(
+                  "columnName" -> "`g`",
+                  "columnType" -> expectedType,
+                  "format" -> formatMapping(format)))
+            }
+          }
+        }
+      }
+    }
+  }
 }
 
 object TestingUDT {