Heltman commented on issue #1359:
URL: https://github.com/apache/iceberg/issues/1359#issuecomment-676060270
But a new problem:
> scala> df.writeTo("local.iceberg_test1").create()
20/08/19 17:50:28 WARN BaseMetastoreTableOperations: Could not find the
table during refresh, setting current metadata to null
org.apache.iceberg.exceptions.NoSuchIcebergTableException: Not an iceberg
table: spark_catalog.default.big_table (type=null)
...
> scala> spark.sql("select * from local.iceberg_test1").show()
java.lang.NoClassDefFoundError: org/apache/commons/compress/utils/Lists
at
org.apache.iceberg.hadoop.HadoopInputFile.getBlockLocations(HadoopInputFile.java:182)
at org.apache.iceberg.hadoop.Util.blockLocations(Util.java:75)
at
org.apache.iceberg.spark.source.SparkBatchScan$ReadTask.<init>(SparkBatchScan.java:322)
at
org.apache.iceberg.spark.source.SparkBatchScan.planInputPartitions(SparkBatchScan.java:142)
at
org.apache.spark.sql.execution.datasources.v2.BatchScanExec.partitions$lzycompute(BatchScanExec.scala:43)
at
org.apache.spark.sql.execution.datasources.v2.BatchScanExec.partitions(BatchScanExec.scala:43)
at
org.apache.spark.sql.execution.datasources.v2.DataSourceV2ScanExecBase.supportsColumnar(DataSourceV2ScanExecBase.scala:61)
at
org.apache.spark.sql.execution.datasources.v2.DataSourceV2ScanExecBase.supportsColumnar$(DataSourceV2ScanExecBase.scala:60)
at
org.apache.spark.sql.execution.datasources.v2.BatchScanExec.supportsColumnar(BatchScanExec.scala:29)
at
org.apache.spark.sql.execution.datasources.v2.DataSourceV2Strategy.apply(DataSourceV2Strategy.scala:84)
at
org.apache.spark.sql.catalyst.planning.QueryPlanner.$anonfun$plan$1(QueryPlanner.scala:63)
at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:484)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:490)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:489)
at
org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:93)
at
org.apache.spark.sql.execution.SparkStrategies.plan(SparkStrategies.scala:68)
at
org.apache.spark.sql.catalyst.planning.QueryPlanner.$anonfun$plan$3(QueryPlanner.scala:78)
at
scala.collection.TraversableOnce.$anonfun$foldLeft$1(TraversableOnce.scala:162)
at
scala.collection.TraversableOnce.$anonfun$foldLeft$1$adapted(TraversableOnce.scala:162)
at scala.collection.Iterator.foreach(Iterator.scala:941)
at scala.collection.Iterator.foreach$(Iterator.scala:941)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1429)
at scala.collection.TraversableOnce.foldLeft(TraversableOnce.scala:162)
at scala.collection.TraversableOnce.foldLeft$(TraversableOnce.scala:160)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1429)
at
org.apache.spark.sql.catalyst.planning.QueryPlanner.$anonfun$plan$2(QueryPlanner.scala:75)
at scala.collection.Iterator$$anon$11.nextCur(Iterator.scala:484)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:490)
at
org.apache.spark.sql.catalyst.planning.QueryPlanner.plan(QueryPlanner.scala:93)
at
org.apache.spark.sql.execution.SparkStrategies.plan(SparkStrategies.scala:68)
at
org.apache.spark.sql.execution.QueryExecution$.createSparkPlan(QueryExecution.scala:330)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$sparkPlan$1(QueryExecution.scala:94)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:133)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:763)
at
org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:133)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:94)
at
org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:87)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$executedPlan$1(QueryExecution.scala:107)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:133)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:763)
at
org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:133)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:107)
at
org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:100)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$writePlans$5(QueryExecution.scala:199)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$.append(QueryPlan.scala:381)
at
org.apache.spark.sql.execution.QueryExecution.org$apache$spark$sql$execution$QueryExecution$$writePlans(QueryExecution.scala:199)
at
org.apache.spark.sql.execution.QueryExecution.toString(QueryExecution.scala:207)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:95)
at
org.apache.spark.sql.execution.SQLExecution$.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)
... 47 elided
Caused by: java.lang.ClassNotFoundException:
org.apache.commons.compress.utils.Lists
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
Maybe I need more test!
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
