[
https://issues.apache.org/jira/browse/SPARK-5741?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14717053#comment-14717053
]
koert kuipers commented on SPARK-5741:
--------------------------------------
i realize i am late to the party but...
by doing this you are losing a very important functionality: passing in
multiple input paths comma separated. globs only cover a very limited subset of
what you can do with multiple paths. for example selecting partitions (by day)
for the last 30 days cannot be expressed with a glob.
so you are giving up major functionality just to be able to pass in a character
that people would generally advice should not be part of a filename anyhow?
doesnt sound like a good idea to me.
> Support the path contains comma in HiveContext
> ----------------------------------------------
>
> Key: SPARK-5741
> URL: https://issues.apache.org/jira/browse/SPARK-5741
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.2.0
> Reporter: Yadong Qi
> Assignee: Yadong Qi
> Fix For: 1.3.0
>
>
> When run ```select * from nzhang_part where hr = 'file,';```, it throws
> exception ```java.lang.IllegalArgumentException: Can not create a Path from
> an empty string```. Because the path of hdfs contains comma, and
> FileInputFormat.setInputPaths will split path by comma.
> ###############################
> SQL
> ###############################
> set hive.merge.mapfiles=true;
> set hive.merge.mapredfiles=true;
> set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
> set hive.exec.dynamic.partition=true;
> set hive.exec.dynamic.partition.mode=nonstrict;
> create table nzhang_part like srcpart;
> insert overwrite table nzhang_part partition (ds='2010-08-15', hr) select
> key, value, hr from srcpart where ds='2008-04-08';
> insert overwrite table nzhang_part partition (ds='2010-08-15', hr=11) select
> key, value from srcpart where ds='2008-04-08';
> insert overwrite table nzhang_part partition (ds='2010-08-15', hr)
> select * from (
> select key, value, hr from srcpart where ds='2008-04-08'
> union all
> select '1' as key, '1' as value, 'file,' as hr from src limit 1) s;
> select * from nzhang_part where hr = 'file,';
> ###############################
> Error log
> ###############################
> 15/02/10 14:33:16 ERROR SparkSQLDriver: Failed in [select * from nzhang_part
> where hr = 'file,']
> java.lang.IllegalArgumentException: Can not create a Path from an empty string
> at org.apache.hadoop.fs.Path.checkPathArg(Path.java:127)
> at org.apache.hadoop.fs.Path.<init>(Path.java:135)
> at
> org.apache.hadoop.util.StringUtils.stringToPath(StringUtils.java:241)
> at
> org.apache.hadoop.mapred.FileInputFormat.setInputPaths(FileInputFormat.java:400)
> at
> org.apache.spark.sql.hive.HadoopTableReader$.initializeLocalJobConfFunc(TableReader.scala:251)
> at
> org.apache.spark.sql.hive.HadoopTableReader$$anonfun$11.apply(TableReader.scala:229)
> at
> org.apache.spark.sql.hive.HadoopTableReader$$anonfun$11.apply(TableReader.scala:229)
> at
> org.apache.spark.rdd.HadoopRDD$$anonfun$getJobConf$6.apply(HadoopRDD.scala:172)
> at
> org.apache.spark.rdd.HadoopRDD$$anonfun$getJobConf$6.apply(HadoopRDD.scala:172)
> at scala.Option.map(Option.scala:145)
> at org.apache.spark.rdd.HadoopRDD.getJobConf(HadoopRDD.scala:172)
> at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:196)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:223)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:221)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:221)
> at
> org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:223)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:221)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:221)
> at
> org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:223)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:221)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:221)
> at org.apache.spark.rdd.UnionRDD$$anonfun$1.apply(UnionRDD.scala:66)
> at org.apache.spark.rdd.UnionRDD$$anonfun$1.apply(UnionRDD.scala:66)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at
> scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at org.apache.spark.rdd.UnionRDD.getPartitions(UnionRDD.scala:66)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:223)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:221)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:221)
> at
> org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:223)
> at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:221)
> at scala.Option.getOrElse(Option.scala:120)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:221)
> at org.apache.spark.SparkContext.runJob(SparkContext.scala:1391)
> at org.apache.spark.rdd.RDD.collect(RDD.scala:811)
> at
> org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:81)
> at
> org.apache.spark.sql.hive.HiveContext$QueryExecution.stringResult(HiveContext.scala:446)
> at
> org.apache.spark.sql.hive.thriftserver.AbstractSparkSQLDriver.run(AbstractSparkSQLDriver.scala:58)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:275)
> at
> org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:423)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:211)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:403)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:77)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
