[
https://issues.apache.org/jira/browse/SPARK-32226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17156287#comment-17156287
]
Chen Zhang commented on SPARK-32226:
------------------------------------
Hello [~thesuperzapper],
The dialect of Informix database is not implemented in spark source code.
You can run code similar to the following to register a dialect about the
Informix database, which may solve your program errors.
{code:scala}
import java.sql.Timestamp
import java.text.SimpleDateFormat
import java.util.Locale
import org.apache.spark.sql.jdbc.JdbcDialect
import org.apache.spark.sql.jdbc.JdbcDialects
case object InformixDialect extends JdbcDialect {
override def canHandle(url: String): Boolean =
url.toLowerCase(Locale.ROOT).startsWith("jdbc:informix")
override def compileValue(value: Any): Any = value match {
case timestampValue: Timestamp =>
val dateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss.SSS")
val timestampString = dateFormat.format(timestampValue)
"'" + timestampString + "'"
case v => super.compileValue(v)
}
}
JdbcDialects.registerDialect(InformixDialect)
{code}
> JDBC TimeStamp predicates always append `.0`
> --------------------------------------------
>
> Key: SPARK-32226
> URL: https://issues.apache.org/jira/browse/SPARK-32226
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 3.0.0
> Reporter: Mathew Wicks
> Priority: Major
>
> If you have an Informix column with type `DATETIME YEAR TO SECOND`, Informix
> will not let you pass a filter of the form `2020-01-01 00:00:00.0` (with the
> `.0` at the end).
>
> In Spark 3.0.0, our predicate pushdown will alway append this `.0` to the end
> of a TimeStamp column filter, even if you don't specify it:
> {code:java}
> df.where("col1 > '2020-01-01 00:00:00'")
> {code}
>
> I think we should only pass the `.XXX` suffix if the user passes it in the
> filter, for example:
> {code:java}
> df.where("col1 > '2020-01-01 00:00:00.123'")
> {code}
>
> The relevant Spark class is:
> {code:java}
> org.apache.spark.sql.catalyst.util.DateTimeUtils.timestampToString
> {code}
>
> To aid people searching for this error, here is the error emitted by spark:
> {code:java}
> Driver stacktrace:
> at
> org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2023)
> at
> org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:1972)
> at
> org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:1971)
> at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
> at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
> at
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1971)
> at
> org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:950)
> at
> org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:950)
> at scala.Option.foreach(Option.scala:407)
> at
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:950)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2203)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2152)
> at
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2141)
> at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
> at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:752)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:2093)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:2114)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:2133)
> at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:467)
> at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:420)
> at
> org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:47)
> at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3625)
> at org.apache.spark.sql.Dataset.$anonfun$head$1(Dataset.scala:2695)
> at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3616)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:100)
> at
> org.apache.spark.sql.execution.SQLExecution$.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.sql.SQLException: Extra characters at the end of a datetime
> or interval.
> at com.informix.util.IfxErrMsg.buildExceptionWithMessage(IfxErrMsg.java:416)
> at com.informix.util.IfxErrMsg.buildIsamException(IfxErrMsg.java:401)
> at com.informix.jdbc.IfxSqli.addException(IfxSqli.java:3096)
> at com.informix.jdbc.IfxSqli.receiveError(IfxSqli.java:3368)
> at com.informix.jdbc.IfxSqli.dispatchMsg(IfxSqli.java:2292)
> at com.informix.jdbc.IfxSqli.receiveMessage(IfxSqli.java:2217)
> at com.informix.jdbc.IfxSqli.executePrepare(IfxSqli.java:1213)
> at
> com.informix.jdbc.IfxPreparedStatement.setupExecutePrepare(IfxPreparedStatement.java:245)
> at
> com.informix.jdbc.IfxPreparedStatement.processSQL(IfxPreparedStatement.java:229)
> at
> com.informix.jdbc.IfxPreparedStatement.<init>(IfxPreparedStatement.java:119)
> at
> com.informix.jdbc.IfxSqliConnect.prepareStatement(IfxSqliConnect.java:5905)
> at
> com.informix.jdbc.IfxSqliConnect.prepareStatement(IfxSqliConnect.java:2474)
> at
> org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(JDBCRDD.scala:301)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
> at org.apache.spark.scheduler.Task.run(Task.scala:127)
> at
> org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:444)
> at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:447)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
> at java.lang.Thread.run(Thread.java:748)
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
