You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@spark.apache.org by Tridib Samanta <tr...@live.com> on 2014/11/06 18:25:07 UTC
RE: spark sql: join sql fails after sqlCtx.cacheTable()
I am getting exception at sparksheel at the following line:
val sqlContext = new org.apache.spark.sql.hive.HiveContext(sc)
error: bad symbolic reference. A signature in HiveContext.class refers to term hive
in package org.apache.hadoop which is not available.
It may be completely missing from the current classpath, or the version on
the classpath might be incompatible with the version used when compiling HiveContext.class.
error:
while compiling: <console>
during phase: erasure
library version: version 2.10.4
compiler version: version 2.10.4
reconstructed args:
last tree to typer: Apply(value $outer)
symbol: value $outer (flags: <method> <synthetic> <stable> <expandedname> <triedcooking>)
symbol definition: val $outer(): $iwC.$iwC.type
tpe: $iwC.$iwC.type
symbol owners: value $outer -> class $iwC -> class $iwC -> class $iwC -> class $read -> package $line5
context owners: class $iwC -> class $iwC -> class $iwC -> class $iwC -> class $read -> package $line5
== Enclosing template or block ==
ClassDef( // class $iwC extends Serializable
0
"$iwC"
[]
Template( // val <local $iwC>: <notype>, tree.tpe=$iwC
"java.lang.Object", "scala.Serializable" // parents
ValDef(
private
"_"
<tpt>
<empty>
)
// 5 statements
DefDef( // def <init>(arg$outer: $iwC.$iwC.$iwC.type): $iwC
<method> <triedcooking>
"<init>"
[]
// 1 parameter list
ValDef( // $outer: $iwC.$iwC.$iwC.type
<param>
"$outer"
<tpt> // tree.tpe=$iwC.$iwC.$iwC.type
<empty>
)
<tpt> // tree.tpe=$iwC
Block( // tree.tpe=Unit
Apply( // def <init>(): Object in class Object, tree.tpe=Object
$iwC.super."<init>" // def <init>(): Object in class Object, tree.tpe=()Object
Nil
)
()
)
)
ValDef( // private[this] val sqlContext: org.apache.spark.sql.hive.HiveContext
private <local> <triedcooking>
"sqlContext "
<tpt> // tree.tpe=org.apache.spark.sql.hive.HiveContext
Apply( // def <init>(sc: org.apache.spark.SparkContext): org.apache.spark.sql.hive.HiveContext in class HiveContext, tree.tpe=org.apache.spark.sql.hive.HiveContext
new org.apache.spark.sql.hive.HiveContext."<init>" // def <init>(sc: org.apache.spark.SparkContext): org.apache.spark.sql.hive.HiveContext in class HiveContext, tree.tpe=(sc: org.apache.spark.SparkContext)org.apache.spark.sql.hive.HiveContext
Apply( // val sc(): org.apache.spark.SparkContext, tree.tpe=org.apache.spark.SparkContext
$iwC.this.$line5$$read$$iwC$$iwC$$iwC$$iwC$$$outer().$line5$$read$$iwC$$iwC$$iwC$$$outer().$line5$$read$$iwC$$iwC$$$outer().$VAL1().$iw().$iw()."sc" // val sc(): org.apache.spark.SparkContext, tree.tpe=()org.apache.spark.SparkContext
Nil
)
)
)
DefDef( // val sqlContext(): org.apache.spark.sql.hive.HiveContext
<method> <stable> <accessor>
"sqlContext"
[]
List(Nil)
<tpt> // tree.tpe=org.apache.spark.sql.hive.HiveContext
$iwC.this."sqlContext " // private[this] val sqlContext: org.apache.spark.sql.hive.HiveContext, tree.tpe=org.apache.spark.sql.hive.HiveContext
)
ValDef( // protected val $outer: $iwC.$iwC.$iwC.type
protected <synthetic> <paramaccessor> <triedcooking>
"$outer "
<tpt> // tree.tpe=$iwC.$iwC.$iwC.type
<empty>
)
DefDef( // val $outer(): $iwC.$iwC.$iwC.type
<method> <synthetic> <stable> <expandedname> <triedcooking>
"$line5$$read$$iwC$$iwC$$iwC$$iwC$$$outer"
[]
List(Nil)
<tpt> // tree.tpe=Any
$iwC.this."$outer " // protected val $outer: $iwC.$iwC.$iwC.type, tree.tpe=$iwC.$iwC.$iwC.type
)
)
)
== Expanded type of tree ==
ThisType(class $iwC)
uncaught exception during compilation: scala.reflect.internal.Types$TypeError
scala.reflect.internal.Types$TypeError: bad symbolic reference. A signature in HiveContext.class refers to term conf
in value org.apache.hadoop.hive which is not available.
It may be completely missing from the current classpath, or the version on
the classpath might be incompatible with the version used when compiling HiveContext.class.
That entry seems to have slain the compiler. Shall I replay
your session? I can re-run each line except the last one.
Thanks
Tridib
Date: Tue, 21 Oct 2014 09:39:49 -0700
Subject: Re: spark sql: join sql fails after sqlCtx.cacheTable()
From: rishi@infoobjects.com
To: tridib.samanta@live.com
CC: user@spark.incubator.apache.org
Hi Tridib,
I changed SQLContext to HiveContext and it started working. These are steps I used.
val sqlContext = new org.apache.spark.sql.hive.HiveContext(sc)val person = sqlContext.jsonFile("json/person.json")person.printSchema()person.registerTempTable("person")val address = sqlContext.jsonFile("json/address.json")address.printSchema()address.registerTempTable("address")sqlContext.cacheTable("person")sqlContext.cacheTable("address")val rs2 = sqlContext.sql("select p.id,p.name,a.city from person p join address a on (p.id = a.id)").collect.foreach(println)
Rishi@InfoObjects
Pure-play Big Data Consulting
On Tue, Oct 21, 2014 at 5:47 AM, tridib <tr...@live.com> wrote:
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
val personPath = "/hdd/spark/person.json"
val person = sqlContext.jsonFile(personPath)
person.printSchema()
person.registerTempTable("person")
val addressPath = "/hdd/spark/address.json"
val address = sqlContext.jsonFile(addressPath)
address.printSchema()
address.registerTempTable("address")
sqlContext.cacheTable("person")
sqlContext.cacheTable("address")
val rs2 = sqlContext.sql("SELECT p.id, p.name, a.city FROM person p, address
a where p.id = a.id limit 10").collect.foreach(println)
person.json
{"id:"1","name":"Mr. X"}
address.json
{"city:"Earth","id":"1"}
--
View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/spark-sql-join-sql-fails-after-sqlCtx-cacheTable-tp16893p16914.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
---------------------------------------------------------------------
To unsubscribe, e-mail: user-unsubscribe@spark.apache.org
For additional commands, e-mail: user-help@spark.apache.org
RE: spark sql: join sql fails after sqlCtx.cacheTable()
Posted by tridib <tr...@live.com>.
Using Hivecontext solved it.
--
View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/spark-sql-join-sql-fails-after-sqlCtx-cacheTable-tp16893p21807.html
Sent from the Apache Spark User List mailing list archive at Nabble.com.
---------------------------------------------------------------------
To unsubscribe, e-mail: user-unsubscribe@spark.apache.org
For additional commands, e-mail: user-help@spark.apache.org