[
https://issues.apache.org/jira/browse/SPARK-2883?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14393141#comment-14393141
]
Zhan Zhang edited comment on SPARK-2883 at 4/2/15 7:54 PM:
-----------------------------------------------------------
Following code demonstrate the usage of the orc support.
import org.apache.spark.sql.hive.orc._
import org.apache.spark.sql._
//schema
case class AllDataTypes(
stringField: String,
intField: Int,
longField: Long,
floatField: Float,
doubleField: Double,
shortField: Short,
byteField: Byte,
booleanField: Boolean)
//saveAsOrcFile
val range = (0 to 255)
val data = sc.parallelize(range).map(x => AllDataTypes(s"$x", x, x.toLong,
x.toFloat, x.toDouble, x.toShort, x.toByte, x % 2 == 0))
data.toDF().saveAsOrcFile("orcTest")
//read orcFile
val hiveContext = new org.apache.spark.sql.hive.HiveContext(sc)
//orcFile
val orcTest = hiveContext.orcFile("orcTest")
orcTest.registerTempTable("orcTest")
hiveContext.sql("SELECT * from orcTest where
intfield>185").collect.foreach(println)
//new data source API, read
hiveContext.sql("create temporary table orc using
org.apache.spark.sql.hive.orc OPTIONS (path \"orcTest\")")
hiveContext.sql("select * from orc").collect.foreach(println)
val table = hiveContext.sql("select * from orc")
// new data source API write
table.saveAsTable("table", "org.apache.spark.sql.hive.orc")
val hiveOrc = hiveContext.orcFile("/user/hive/warehouse/table")
hiveOrc.registerTempTable("hiveOrc")
hiveContext.sql("select * from hiveOrc").collect.foreach(println)
table.saveAsOrcFile("/user/ambari-qa/table")
hiveContext.sql("create temporary table normal_orc_as_source USING
org.apache.spark.sql.hive.orc OPTIONS (path 'saveTable') as select * from
table")
was (Author: zzhan):
Following code demonstrate the usage of the orc support.
@climberus following examples demonstrate how to use it:
import org.apache.spark.sql.hive.orc._
import org.apache.spark.sql._
//schema
case class AllDataTypes(
stringField: String,
intField: Int,
longField: Long,
floatField: Float,
doubleField: Double,
shortField: Short,
byteField: Byte,
booleanField: Boolean)
//saveAsOrcFile
val range = (0 to 255)
val data = sc.parallelize(range).map(x => AllDataTypes(s"$x", x, x.toLong,
x.toFloat, x.toDouble, x.toShort, x.toByte, x % 2 == 0))
data.toDF().saveAsOrcFile("orcTest")
//read orcFile
val hiveContext = new org.apache.spark.sql.hive.HiveContext(sc)
//orcFile
val orcTest = hiveContext.orcFile("orcTest")
orcTest.registerTempTable("orcTest")
hiveContext.sql("SELECT * from orcTest where
intfield>185").collect.foreach(println)
//new data source API, read
hiveContext.sql("create temporary table orc using
org.apache.spark.sql.hive.orc OPTIONS (path \"orcTest\")")
hiveContext.sql("select * from orc").collect.foreach(println)
val table = hiveContext.sql("select * from orc")
// new data source API write
table.saveAsTable("table", "org.apache.spark.sql.hive.orc")
val hiveOrc = hiveContext.orcFile("/user/hive/warehouse/table")
hiveOrc.registerTempTable("hiveOrc")
hiveContext.sql("select * from hiveOrc").collect.foreach(println)
table.saveAsOrcFile("/user/ambari-qa/table")
hiveContext.sql("create temporary table normal_orc_as_source USING
org.apache.spark.sql.hive.orc OPTIONS (path 'saveTable') as select * from
table")
> Spark Support for ORCFile format
> --------------------------------
>
> Key: SPARK-2883
> URL: https://issues.apache.org/jira/browse/SPARK-2883
> Project: Spark
> Issue Type: Bug
> Components: Input/Output, SQL
> Reporter: Zhan Zhang
> Priority: Blocker
> Attachments: 2014-09-12 07.05.24 pm Spark UI.png, 2014-09-12 07.07.19
> pm jobtracker.png, orc.diff
>
>
> Verify the support of OrcInputFormat in spark, fix issues if exists and add
> documentation of its usage.
--
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
