[
https://issues.apache.org/jira/browse/SPARK-9344?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14938918#comment-14938918
]
Simeon Simeonov commented on SPARK-9344:
----------------------------------------
[~joshrosen] Here is the reproducible test case you can try in {{spark-shell}}:
{code}
import org.apache.spark.sql.hive.HiveContext
val ctx = sqlContext.asInstanceOf[HiveContext]
import ctx.implicits._
(1 to 5).map(Tuple1.apply).toDF("w_int").write.save("test_data1")
(6 to 9).map(Tuple1.apply).toDF("w_int").write.save("test_data2")
ctx.sql("insert into table test_data1 select * from test_data2")
{code}
This fails with:
{code}
scala> ctx.sql("insert into table test_data1 select * from test_data2")
15/09/30 17:32:34 INFO ParseDriver: Parsing command: insert into table
test_data1 select * from test_data2
15/09/30 17:32:34 INFO ParseDriver: Parse Completed
15/09/30 17:32:34 INFO HiveMetaStore: 0: get_table : db=default tbl=test_data1
15/09/30 17:32:34 INFO audit: ugi=sim ip=unknown-ip-addr cmd=get_table :
db=default tbl=test_data1
org.apache.spark.sql.AnalysisException: no such table test_data1; line 1 pos 18
at
org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.getTable(Analyzer.scala:225)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$7.applyOrElse(Analyzer.scala:231)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$7.applyOrElse(Analyzer.scala:229)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$3.apply(TreeNode.scala:222)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:221)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:212)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:229)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:219)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:61)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:59)
at
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:59)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:51)
at scala.collection.immutable.List.foreach(List.scala:318)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:51)
at
org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:933)
at
org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:933)
at
org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:931)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:131)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:755)
at
$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
at
$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44)
at
$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:46)
at
$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
at
$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
at
$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
at
$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:54)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:56)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:58)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:60)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:62)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:64)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:66)
at $iwC$$iwC$$iwC.<init>(<console>:68)
at $iwC$$iwC.<init>(<console>:70)
at $iwC.<init>(<console>:72)
at <init>(<console>:74)
at .<init>(<console>:78)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at
org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1338)
at
org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at
org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at
org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at
scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at
org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:665)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:170)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:193)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:112)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
{code}
> Spark SQL documentation does not clarify INSERT INTO behavior
> -------------------------------------------------------------
>
> Key: SPARK-9344
> URL: https://issues.apache.org/jira/browse/SPARK-9344
> Project: Spark
> Issue Type: Documentation
> Components: Documentation, SQL
> Affects Versions: 1.4.1
> Reporter: Simeon Simeonov
> Priority: Minor
> Labels: documentation, sql
>
> The Spark SQL documentation does not address {{INSERT INTO}} behavior. The
> section on Hive compatibility is misleading as it claims support for "the
> vast majority of Hive features". The user mailing list has conflicting
> information, including posts that claim {{INSERT INTO}} support targeting 1.0.
> In 1.4.1, using Hive {{INSERT INTO}} syntax generates parse errors.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
