Demo: Generated Columns¶

val dataPath = "/tmp/delta/values"

import io.delta.tables.DeltaTable
import org.apache.spark.sql.types.DataTypes

DeltaTable.create
  .addColumn("id", DataTypes.LongType, nullable = false)
  .addColumn(
    DeltaTable.columnBuilder("value")
      .dataType(DataTypes.BooleanType)
      .generatedAlwaysAs("true")
      .build)
  .location(dataPath)
  .execute

import org.apache.spark.sql.delta.DeltaLog
val deltaLog = DeltaLog.forTable(spark, dataPath)

println(deltaLog.snapshot.metadata.dataSchema("value").metadata.json)

{"delta.generationExpression":"true"}

import io.delta.implicits._
import org.apache.spark.sql.SaveMode

spark.range(5)
  .write
  .mode(SaveMode.Append)
  .delta(dataPath)

DeltaTable.forPath(dataPath).toDF.orderBy('id).show

+---+-----+
| id|value|
+---+-----+
|  0| true|
|  1| true|
|  2| true|
|  3| true|
|  4| true|
+---+-----+

spark.range(5, 6)
  .withColumn("value", lit(false))
  .write
  .mode(SaveMode.Append)
  .delta(dataPath)

org.apache.spark.sql.delta.schema.InvariantViolationException: CHECK constraint Generated Column (`value` <=> true) violated by row with values:
 - value : false
  at org.apache.spark.sql.delta.schema.InvariantViolationException$.apply(InvariantViolationException.scala:50)
  at org.apache.spark.sql.delta.schema.InvariantViolationException$.apply(InvariantViolationException.scala:60)
  at org.apache.spark.sql.delta.schema.InvariantViolationException.apply(InvariantViolationException.scala)
  at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown Source)
  at org.apache.spark.sql.delta.constraints.DeltaInvariantCheckerExec.$anonfun$doExecute$3(DeltaInvariantCheckerExec.scala:86)
  at scala.collection.Iterator$$anon$10.next(Iterator.scala:459)
  at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$executeTask$1(FileFormatWriter.scala:278)
  at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1473)
  at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:286)
  at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$write$15(FileFormatWriter.scala:210)
  at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
  at org.apache.spark.scheduler.Task.run(Task.scala:131)
  at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
  at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
  at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
  at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
  at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
  at java.base/java.lang.Thread.run(Thread.java:829)