chore: remove dead validateObjectStoreConfig path

CometScanRule.validateObjectStoreConfig had no production caller; only
NativeConfigSuite invoked it. Drop the Scala wrapper, its configValidity
cache, the Native.java JNI declaration (which leaves the file empty),
the backing Rust JNI impl, and the tests that exercised the wrapper.
Keep the extractObjectStoreOptions tests since that utility is still
used by the native scan paths.

Author: andygrove

native/core/src/parquet/mod.rs

@@ -129,31 +129,6 @@ pub fn get_object_store_options(
     Ok(collected_map)
 }
 
-/// # Safety
-/// This function is inherently unsafe since it deals with raw pointers passed from JNI.
-#[no_mangle]
-pub unsafe extern "system" fn Java_org_apache_comet_parquet_Native_validateObjectStoreConfig(
-    e: EnvUnowned,
-    _jclass: JClass,
-    file_path: JString,
-    object_store_options: JObject,
-) {
-    try_unwrap_or_throw(&e, |env| {
-        let session_config = SessionConfig::new();
-        let planner =
-            PhysicalPlanner::new(Arc::new(SessionContext::new_with_config(session_config)), 0);
-        let session_ctx = planner.session_ctx();
-        let path: String = file_path.try_to_string(env).unwrap();
-        let object_store_config = get_object_store_options(env, object_store_options)?;
-        let (_, _) = prepare_object_store_with_configs(
-            session_ctx.runtime_env(),
-            path.clone(),
-            &object_store_config,
-        )?;
-        Ok(())
-    })
-}
-
 /// # Safety
 /// This function is inherently unsafe since it deals with raw pointers passed from JNI.
 #[no_mangle]

spark/src/main/java/org/apache/comet/parquet/Native.java

@@ -40,14 +40,13 @@ import org.apache.spark.sql.execution.datasources.v2.csv.CSVScan
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.types._
 
-import org.apache.comet.{CometConf, CometNativeException, DataTypeSupport}
+import org.apache.comet.{CometConf, DataTypeSupport}
 import org.apache.comet.CometConf._
 import org.apache.comet.CometSparkSessionExtensions.{isCometLoaded, isSpark35Plus, withInfo, withInfos}
 import org.apache.comet.DataTypeSupport.isComplexType
 import org.apache.comet.iceberg.{CometIcebergNativeScanMetadata, IcebergReflection}
 import org.apache.comet.objectstore.NativeConfig
 import org.apache.comet.parquet.CometParquetUtils.{encryptionEnabled, isEncryptionConfigSupported}
-import org.apache.comet.parquet.Native
 import org.apache.comet.serde.operator.{CometIcebergNativeScan, CometNativeScan}
 import org.apache.comet.shims.{CometTypeShim, ShimCometStreaming, ShimFileFormat, ShimSubqueryBroadcast}
 
@@ -735,61 +734,6 @@ object CometScanRule extends Logging {
   val SKIP_COMET_SCAN_TAG: org.apache.spark.sql.catalyst.trees.TreeNodeTag[Unit] =
     org.apache.spark.sql.catalyst.trees.TreeNodeTag[Unit]("comet.skipCometScan")
 
-  /**
-   * Validating object store configs can cause requests to be made to S3 APIs (such as when
-   * resolving the region for a bucket). We use a cache to reduce the number of S3 calls.
-   *
-   * The key is the config map converted to a string. The value is the reason that the config is
-   * not valid, or None if the config is valid.
-   */
-  val configValidityMap = new mutable.HashMap[String, Option[String]]()
-
-  /**
-   * We do not expect to see a large number of unique configs within the lifetime of a Spark
-   * session, but we reset the cache once it reaches a fixed size to prevent it growing
-   * indefinitely.
-   */
-  val configValidityMapMaxSize = 1024
-
-  def validateObjectStoreConfig(
-      filePath: String,
-      hadoopConf: Configuration,
-      fallbackReasons: mutable.ListBuffer[String]): Unit = {
-    val objectStoreConfigMap =
-      NativeConfig.extractObjectStoreOptions(hadoopConf, URI.create(filePath))
-
-    val cacheKey = objectStoreConfigMap
-      .map { case (k, v) =>
-        s"$k=$v"
-      }
-      .toList
-      .sorted
-      .mkString("\n")
-
-    if (configValidityMap.size >= configValidityMapMaxSize) {
-      logWarning("Resetting S3 object store validity cache")
-      configValidityMap.clear()
-    }
-
-    configValidityMap.get(cacheKey) match {
-      case Some(Some(reason)) =>
-        fallbackReasons += reason
-      case Some(None) =>
-      // previously validated
-      case _ =>
-        try {
-          val objectStoreOptions = objectStoreConfigMap.asJava
-          Native.validateObjectStoreConfig(filePath, objectStoreOptions)
-        } catch {
-          case e: CometNativeException =>
-            val reason = s"Object store config not supported: ${e.getMessage}"
-            fallbackReasons += reason
-            configValidityMap.put(cacheKey, Some(reason))
-        }
-    }
-
-  }
-
   /**
    * Single-pass validation of Iceberg FileScanTasks.
    *

spark/src/main/scala/org/apache/comet/rules/CometScanRule.scala

@@ -21,21 +21,12 @@ package org.apache.comet.objectstore
 
 import java.net.URI
 
-import scala.collection.mutable
-
-import org.scalatest.BeforeAndAfterEach
 import org.scalatest.funsuite.AnyFunSuite
 import org.scalatest.matchers.should.Matchers
 
 import org.apache.hadoop.conf.Configuration
 
-import org.apache.comet.rules.CometScanRule
-
-class NativeConfigSuite extends AnyFunSuite with Matchers with BeforeAndAfterEach {
-
-  override protected def beforeEach(): Unit = {
-    CometScanRule.configValidityMap.clear()
-  }
+class NativeConfigSuite extends AnyFunSuite with Matchers {
 
   test("extractObjectStoreOptions - multiple cloud provider configurations") {
     val hadoopConf = new Configuration()
@@ -79,61 +70,4 @@ class NativeConfigSuite extends AnyFunSuite with Matchers with BeforeAndAfterEac
       new URI("unsupported://test-bucket/test-object"))
     assert(unsupportedOptions.isEmpty, "Unsupported scheme should return empty options")
   }
-
-  test("validate object store config - no provider") {
-    val hadoopConf = new Configuration()
-    validate(hadoopConf)
-  }
-
-  test("validate object store config - valid providers") {
-    val hadoopConf = new Configuration()
-    val provider1 = "com.amazonaws.auth.EnvironmentVariableCredentialsProvider"
-    val provider2 = "com.amazonaws.auth.WebIdentityTokenCredentialsProvider"
-    hadoopConf.set("fs.s3a.aws.credentials.provider", Seq(provider1, provider2).mkString(","))
-    validate(hadoopConf)
-  }
-
-  test("validate object store config - invalid provider") {
-    val hadoopConf = new Configuration()
-    hadoopConf.set("fs.s3a.aws.credentials.provider", "invalid")
-    val fallbackReasons = validate(hadoopConf)
-    val expectedError = "Unsupported credential provider: invalid"
-    assert(fallbackReasons.exists(_.contains(expectedError)))
-  }
-
-  test("validate object store config - mixed anonymous providers") {
-    val hadoopConf = new Configuration()
-    val provider1 = "com.amazonaws.auth.AnonymousAWSCredentials"
-    val provider2 = "software.amazon.awssdk.auth.credentials.AnonymousCredentialsProvider"
-    hadoopConf.set("fs.s3a.aws.credentials.provider", Seq(provider1, provider2).mkString(","))
-    val fallbackReasons = validate(hadoopConf)
-    val expectedError =
-      "Anonymous credential provider cannot be mixed with other credential providers"
-    assert(fallbackReasons.exists(_.contains(expectedError)))
-  }
-
-  test("validity cache") {
-    val hadoopConf = new Configuration()
-    val provider1 = "com.amazonaws.auth.AnonymousAWSCredentials"
-    val provider2 = "software.amazon.awssdk.auth.credentials.AnonymousCredentialsProvider"
-    hadoopConf.set("fs.s3a.aws.credentials.provider", Seq(provider1, provider2).mkString(","))
-
-    assert(CometScanRule.configValidityMap.isEmpty)
-    for (_ <- 0 until 5) {
-      assert(validate(hadoopConf).nonEmpty)
-      assert(CometScanRule.configValidityMap.size == 1)
-    }
-
-    // set the same providers but in a different order
-    hadoopConf.set("fs.s3a.aws.credentials.provider", Seq(provider2, provider1).mkString(","))
-    assert(validate(hadoopConf).nonEmpty)
-    assert(CometScanRule.configValidityMap.size == 2)
-  }
-
-  private def validate(hadoopConf: Configuration): Set[String] = {
-    val path = "s3a://path/to/file.parquet"
-    val fallbackReasons = mutable.ListBuffer[String]()
-    CometScanRule.validateObjectStoreConfig(path, hadoopConf, fallbackReasons)
-    fallbackReasons.toSet
-  }
 }