[HUDI-3254] Introduce HoodieCatalog to manage tables for Spark Datasource V2 (#4611)

hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/HoodieSparkUtils.scala

@@ -53,8 +53,18 @@ object HoodieSparkUtils extends SparkAdapterSupport {
 
   def isSpark3_0: Boolean = SPARK_VERSION.startsWith("3.0")
 
+  def isSpark3_1: Boolean = SPARK_VERSION.startsWith("3.1")
+
   def isSpark3_2: Boolean = SPARK_VERSION.startsWith("3.2")
 
+  def beforeSpark3_2(): Boolean = {
+    if (isSpark2 || isSpark3_0 || isSpark3_1) {
+      true
+    } else {
+      false
+    }
+  }
+
   def getMetaSchema: StructType = {
     StructType(HoodieRecord.HOODIE_META_COLUMNS.asScala.map(col => {
       StructField(col, StringType, nullable = true)

hudi-client/hudi-spark-client/src/main/scala/org/apache/spark/sql/hudi/SparkAdapter.scala

@@ -18,19 +18,22 @@
 
 package org.apache.spark.sql.hudi
 
+import org.apache.hudi.HoodieSparkUtils.sparkAdapter
 import org.apache.hudi.client.utils.SparkRowSerDe
-
 import org.apache.spark.sql.catalyst.analysis.UnresolvedRelation
+import org.apache.spark.sql.catalyst.catalog.CatalogTable
 import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
 import org.apache.spark.sql.catalyst.expressions.Expression
 import org.apache.spark.sql.catalyst.parser.ParserInterface
 import org.apache.spark.sql.catalyst.plans.JoinType
-import org.apache.spark.sql.catalyst.plans.logical.{Join, LogicalPlan}
+import org.apache.spark.sql.catalyst.plans.logical.{Join, LogicalPlan, SubqueryAlias}
 import org.apache.spark.sql.catalyst.{AliasIdentifier, TableIdentifier}
-import org.apache.spark.sql.execution.datasources.{FilePartition, PartitionedFile, SparkParsePartitionUtil}
+import org.apache.spark.sql.execution.datasources.{FilePartition, LogicalRelation, PartitionedFile, SparkParsePartitionUtil}
 import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.{Row, SparkSession}
 
+import java.util.Locale
+
 /**
  * An interface to adapter the difference between spark2 and spark3
  * in some spark related class.
@@ -99,4 +102,35 @@ trait SparkAdapter extends Serializable {
    */
   def getFilePartitions(sparkSession: SparkSession, partitionedFiles: Seq[PartitionedFile],
       maxSplitBytes: Long): Seq[FilePartition]
+
+  def isHoodieTable(table: LogicalPlan, spark: SparkSession): Boolean = {
+    tripAlias(table) match {
+      case LogicalRelation(_, _, Some(tbl), _) => isHoodieTable(tbl)
+      case relation: UnresolvedRelation =>
+        isHoodieTable(toTableIdentifier(relation), spark)
+      case _=> false
+    }
+  }
+
+  def isHoodieTable(map: java.util.Map[String, String]): Boolean = {
+    map.getOrDefault("provider", "").equals("hudi")
+  }
+
+  def isHoodieTable(table: CatalogTable): Boolean = {
+    table.provider.map(_.toLowerCase(Locale.ROOT)).orNull == "hudi"
+  }
+
+  def isHoodieTable(tableId: TableIdentifier, spark: SparkSession): Boolean = {
+    val table = spark.sessionState.catalog.getTableMetadata(tableId)
+    isHoodieTable(table)
+  }
+
+  def tripAlias(plan: LogicalPlan): LogicalPlan = {
+    plan match {
+      case SubqueryAlias(_, relation: LogicalPlan) =>
+        tripAlias(relation)
+      case other =>
+        other
+    }
+  }
 }