[
https://issues.apache.org/jira/browse/SPARK-12764?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15093836#comment-15093836
]
Ewan Leith edited comment on SPARK-12764 at 1/12/16 12:57 PM:
--------------------------------------------------------------
What are you expecting it to do, output the XML as a string, or something else?
I doubt this will work, but you might try adding this code before the initial
references to JDBC:
{noformat}
import org.apache.spark.sql.jdbc.JdbcDialects
import org.apache.spark.sql.jdbc.JdbcDialect
import org.apache.spark.sql.types._
case object PostgresDialect extends JdbcDialect {
override def canHandle(url: String): Boolean =
url.startsWith("jdbc:postgresql")
override def getCatalystType(
sqlType: Int, typeName: String, size: Int, md: MetadataBuilder):
Option[DataType] = {
if (typeName.contains("xml")) {
Some(StringType)
} else None
}
}
JdbcDialects.registerDialect(PostgresDialect)
{noformat}
was (Author: ewanleith):
What are you expecting it to do, output the XML as a string, or something else?
I doubt this will work, but you might try adding this code before the initial
references to JDBC:
case object PostgresDialect extends JdbcDialect {
override def canHandle(url: String): Boolean =
url.startsWith("jdbc:postgresql")
override def getCatalystType(
sqlType: Int, typeName: String, size: Int, md: MetadataBuilder):
Option[DataType] = {
if (typeName.contains("xml")) {
Some(StringType)
} else None
}
}
JdbcDialects.registerDialect(PostgresDialect)
> XML Column type is not supported
> --------------------------------
>
> Key: SPARK-12764
> URL: https://issues.apache.org/jira/browse/SPARK-12764
> Project: Spark
> Issue Type: Bug
> Components: Spark Shell
> Affects Versions: 1.6.0
> Environment: Mac Os X El Capitan
> Reporter: Rajeshwar Gaini
>
> Hi All,
> I am using PostgreSQL database. I am using the following jdbc call to access
> a customer table (customer_id int, event text, country text, content xml) in
> my database.
> {code}
> val dataframe1 = sqlContext.load("jdbc", Map("url" ->
> "jdbc:postgresql://localhost/customerlogs?user=postgres&password=postgres",
> "dbtable" -> "customer"))
> {code}
> When i run above command in spark-shell i receive the following error.
> {code}
> java.sql.SQLException: Unsupported type 1111
> at
> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.org$apache$spark$sql$execution$datasources$jdbc$JDBCRDD$$getCatalystType(JDBCRDD.scala:103)
> at
> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anonfun$1.apply(JDBCRDD.scala:140)
> at
> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anonfun$1.apply(JDBCRDD.scala:140)
> at scala.Option.getOrElse(Option.scala:120)
> at
> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:139)
> at
> org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation.<init>(JDBCRelation.scala:91)
> at
> org.apache.spark.sql.execution.datasources.jdbc.DefaultSource.createRelation(DefaultSource.scala:60)
> at
> org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:158)
> at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:119)
> at org.apache.spark.sql.SQLContext.load(SQLContext.scala:1153)
> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:25)
> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:30)
> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32)
> at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:34)
> at $iwC$$iwC$$iwC$$iwC.<init>(<console>:36)
> at $iwC$$iwC$$iwC.<init>(<console>:38)
> at $iwC$$iwC.<init>(<console>:40)
> at $iwC.<init>(<console>:42)
> at <init>(<console>:44)
> at .<init>(<console>:48)
> at .<clinit>(<console>)
> at .<init>(<console>:7)
> at .<clinit>(<console>)
> at $print(<console>)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:497)
> at
> org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
> at
> org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
> at
> org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
> at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
> at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
> at
> org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
> at
> org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
> at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
> at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
> at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
> at
> org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$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$$process(SparkILoop.scala:945)
> at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
> at org.apache.spark.repl.Main$.main(Main.scala:31)
> at org.apache.spark.repl.Main.main(Main.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:497)
> at
> org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
> at
> org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> {code}
--
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
