增量表插入無法正常工作，讀取錯誤 - org.apache.spark.sql.AnalysisException：表不支持讀取

Question

我在 Apache Zeppelin Notebook 上使用 Spark 版本 3.0.0，delta 版本：io.delta:delta-core_2.12:0.7.0。

在下面的場景中，我嘗試將數據插入 delta 表，PFB Apache Zeppeline Screenshot

STEP 1:

spark.sql("drop table if exists delta_dummy3")
spark.sql("create table delta_dummy3 (number integer,fname string) using DELTA options(path='/tmp/dummy_delta3')")

STEP 2:
%spark3
spark.sql("insert into delta_dummy3 values ( 1,'sid','1')")

STEP 3:
%spark3
val a = spark.sql("select * from delta_dummy3")
a.printSchema()
Result:
root
 |-- number: integer (nullable = true)
 |-- fname: string (nullable = true)
 |-- col1: integer (nullable = true)
 |-- col2: string (nullable = true)
 |-- col3: string (nullable = true)

%spark3
val events_delta = spark.read.format("delta").load("/tmp/dummy_delta3/")
events_delta.show()
+------+-----+----+----+----+
|number|fname|col1|col2|col3|
+------+-----+----+----+----+
|  null| null|   1| sid|   1|
|  null| null|   1| sid|null|
|  null| null|   1| sid|null|
+------+-----+----+----+----+

正如您所看到的，一個不正確的插入場景正在工作，預計會引發一個錯誤（當我使用 PARQUET 表時確實會發生這種情況）

此外，當我嘗試通過 Spark-SQL 選項讀取數據時，也會出現錯誤：

spark.sql("select * from delta_dummy3").show()

org.apache.spark.sql.AnalysisException: Table does not support reads: datahub.delta_dummy3;
  at org.apache.spark.sql.execution.datasources.v2.DataSourceV2Implicits$TableHelper.asReadable(DataSourceV2Implicits.scala:33)
  at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$$anonfun$apply$1.applyOrElse(V2ScanRelationPushDown.scala:34)
  at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$$anonfun$apply$1.applyOrElse(V2ScanRelationPushDown.scala:32)
  at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$1(TreeNode.scala:309)
  at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:72)
  at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:309)
  at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29)
  at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown(AnalysisHelper.scala:149)
  at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown$(AnalysisHelper.scala:147)
  at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29)
  at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29)
  at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$3(TreeNode.scala:314)
  at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:399)
  at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:237)
  at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:397)
  at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:350)
  at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:314)
  at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29)
  at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown(AnalysisHelper.scala:149)
  at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown$(AnalysisHelper.scala:147)
  at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29)
  at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29)
  at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDown$3(TreeNode.scala:314)
  at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:399)
  at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:237)
  at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:397)
  at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:350)
  at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:314)
  at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDown(LogicalPlan.scala:29)
  at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown(AnalysisHelper.scala:149)
  at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDown$(AnalysisHelper.scala:147)
  at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDown(LogicalPlan.scala:29)
  at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$.apply(V2ScanRelationPushDown.scala:32)
  at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$.apply(V2ScanRelationPushDown.scala:29)
  at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:149)
  at scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
  at scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
  at scala.collection.immutable.List.foldLeft(List.scala:89)
  at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:146)
  at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:138)
  at scala.collection.immutable.List.foreach(List.scala:392)
  at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:138)
  at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:116)
  at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:88)
  at org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:116)
  at org.apache.spark.sql.execution.QueryExecution.$anonfun$optimizedPlan$1(QueryExecution.scala:82)
  at org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
  at org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:133)
  at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:763)
  at org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:133)
  at org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:82)
  at org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:79)
  at org.apache.spark.sql.execution.QueryExecution.assertOptimized(QueryExecution.scala:85)
  at org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:103)
  at org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:100)
  at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:98)
  at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
  at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:87)
  at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:763)
  at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
  at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3614)
  at org.apache.spark.sql.Dataset.head(Dataset.scala:2695)
  at org.apache.spark.sql.Dataset.take(Dataset.scala:2902)
  at org.apache.spark.sql.Dataset.getRows(Dataset.scala:300)
  at org.apache.spark.sql.Dataset.showString(Dataset.scala:337)
  at org.apache.spark.sql.Dataset.show(Dataset.scala:824)
  at org.apache.spark.sql.Dataset.show(Dataset.scala:783)
  at org.apache.spark.sql.Dataset.show(Dataset.scala:792)
  ... 53 elided

我無法在這里找出問題的根本原因。

Answer 1

我建議您按順序執行以下操作。

%sql DROP TABLE delta_dummy3
%scala dbutils.fs.rm('/tmp/dummy_delta3', true)

執行這兩個命令后，您將執行您的步驟...

spark.sql("create table delta_dummy3 (number integer,fname string) using DELTA options(path='/tmp/dummy_delta3')")

STEP 2:
%spark3
spark.sql("insert into delta_dummy3 values ( 1,'sid','1')")

STEP 3:
%spark3
val a = spark.sql("select * from delta_dummy3")
a.printSchema()