validation

Author: AnishMahto

common/utils/src/main/resources/error/error-conditions.json

@@ -203,6 +203,12 @@
     ],
     "sqlState" : "42703"
   },
+  "AUTOCDC_RESERVED_COLUMN_NAME_CONFLICT" : {
+    "message" : [
+      "Using <caseSensitivity> column name comparison, the column `<columnName>` in the <schemaName> schema conflicts with the reserved AutoCDC column name `<reservedColumnName>`. Rename or remove the column."
+    ],
+    "sqlState" : "42710"
+  },
   "AVRO_CANNOT_WRITE_NULL_FIELD" : {
     "message" : [
       "Cannot write null value for field <name> defined as non-null Avro data type <dataType>.",

sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/Scd1BatchProcessor.scala

@@ -17,16 +17,26 @@
 
 package org.apache.spark.sql.pipelines.autocdc
 
-import org.apache.spark.sql.{functions => F}
+import org.apache.spark.SparkException
+import org.apache.spark.sql.{functions => F, AnalysisException}
+import org.apache.spark.sql.Column
 import org.apache.spark.sql.catalyst.util.QuotingUtils
 import org.apache.spark.sql.classic.DataFrame
+import org.apache.spark.sql.types.{DataType, StructField, StructType}
 import org.apache.spark.util.ArrayImplicits._
 
 /**
  * Per-microbatch processor for SCD Type 1 AutoCDC flows, complying to the specified [[changeArgs]]
  * configuration.
+ *
+ * @param changeArgs The CDC flow configuration.
+ * @param resolvedSequencingType The post-analysis [[DataType]] of the sequencing column, derived
+ *                               from the flow's resolved DataFrame at flow setup time.
  */
-case class Scd1BatchProcessor(changeArgs: ChangeArgs) {
+case class Scd1BatchProcessor(
+    changeArgs: ChangeArgs,
+    resolvedSequencingType: DataType) {
+
   /**
    * Deduplicate the incoming CDC microbatch by key, keeping the most recent event per key
    * as ordered by [[ChangeArgs.sequencing]].
@@ -59,9 +69,102 @@ case class Scd1BatchProcessor(changeArgs: ChangeArgs) {
       )
       .select(F.col(s"$winningRowCol.*"))
   }
+
+  /**
+   * Project the CDC metadata column onto the microbatch.
+   */
+  def extendMicrobatchRowsWithCdcMetadata(microbatchDf: DataFrame): DataFrame = {
+    // Proactively validate the reserved CDC metadata column does not exist in the microbatch.
+    validateCdcMetadataColumnNotPresent(microbatchDf)
+
+    val rowDeleteSequence: Column = changeArgs.deleteCondition match {
+      case Some(deleteCondition) =>
+        F.when(deleteCondition, changeArgs.sequencing).otherwise(F.lit(null))
+      case None =>
+        F.lit(null)
+    }
+
+    val rowUpsertSequence: Column =
+      // A row that is not a delete must be an upsert, these are mutually exclusive and a complete
+      // set of CDC event types.
+      F.when(rowDeleteSequence.isNull, changeArgs.sequencing).otherwise(F.lit(null))
+
+    microbatchDf.withColumn(
+      Scd1BatchProcessor.cdcMetadataColName,
+      Scd1BatchProcessor.constructCdcMetadataCol(
+        deleteSequence = rowDeleteSequence,
+        upsertSequence = rowUpsertSequence,
+        sequencingType = resolvedSequencingType
+      )
+    )
+  }
+
+  private def validateCdcMetadataColumnNotPresent(microbatchDf: DataFrame): Unit = {
+    val ignoreColumnNameCase =
+      !microbatchDf.sparkSession.sessionState.conf.caseSensitiveAnalysis
+
+    microbatchDf.schema.fieldNames
+      .find { fieldName =>
+        if (ignoreColumnNameCase) {
+          fieldName.equalsIgnoreCase(Scd1BatchProcessor.cdcMetadataColName)
+        } else {
+          fieldName.equals(Scd1BatchProcessor.cdcMetadataColName)
+        }
+      }
+      .foreach { conflictingColumnName =>
+        throw new AnalysisException(
+          errorClass = "AUTOCDC_RESERVED_COLUMN_NAME_CONFLICT",
+          messageParameters = Map(
+            "caseSensitivity" -> CaseSensitivityLabels.of(!ignoreColumnNameCase),
+            "columnName" -> conflictingColumnName,
+            "schemaName" -> "microbatch",
+            "reservedColumnName" -> Scd1BatchProcessor.cdcMetadataColName
+          )
+        )
+      }
+  }
 }
 
 object Scd1BatchProcessor {
   // Columns prefixed with `__spark_autocdc_` are reserved for internal SDP AutoCDC processing.
-  private val winningRowColName = "__spark_autocdc_winning_row"
+  private[autocdc] val winningRowColName: String = "__spark_autocdc_winning_row"
+  private[autocdc] val cdcMetadataColName: String = "__spark_autocdc_metadata"
+
+  private[autocdc] val cdcDeleteSequenceFieldName: String = "deleteSequence"
+  private[autocdc] val cdcUpsertSequenceFieldName: String = "upsertSequence"
+
+  /**
+   * Schema of the CDC metadata struct column for SCD1.
+   */
+  private def cdcMetadataColSchema(sequencingType: DataType): StructType =
+    StructType(
+      Seq(
+        // The sequencing of the event if it represents a delete, null otherwise.
+        StructField(cdcDeleteSequenceFieldName, sequencingType, nullable = true),
+        // The sequencing of the event if it represents an upsert, null otherwise.
+        StructField(cdcUpsertSequenceFieldName, sequencingType, nullable = true)
+      )
+    )
+
+  /**
+   * Construct the CDC metadata struct column for SCD1, following the exact schema and field
+   * ordering defined by [[cdcMetadataColSchema]].
+   */
+  private[autocdc] def constructCdcMetadataCol(
+      deleteSequence: Column,
+      upsertSequence: Column,
+      sequencingType: DataType): Column = {
+    val cdcMetadataFieldsInOrder = cdcMetadataColSchema(sequencingType).fields.map { field =>
+      val value = field.name match {
+        case `cdcDeleteSequenceFieldName` => deleteSequence
+        case `cdcUpsertSequenceFieldName` => upsertSequence
+        case other =>
+          throw SparkException.internalError(
+            s"Unable to construct SCD1 CDC metadata column due to unknown `${other}` field."
+          )
+      }
+      value.cast(field.dataType).as(field.name)
+    }
+    F.struct(cdcMetadataFieldsInOrder.toImmutableArraySeq: _*)
+  }
 }