[ https://issues.apache.org/jira/browse/SPARK-11102?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jeff Zhang updated SPARK-11102: ------------------------------- Issue Type: Improvement (was: Bug) > Not readable exception when specifing non-exist input for JSON data source > -------------------------------------------------------------------------- > > Key: SPARK-11102 > URL: https://issues.apache.org/jira/browse/SPARK-11102 > Project: Spark > Issue Type: Improvement > Components: SQL > Affects Versions: 1.5.1 > Reporter: Jeff Zhang > > If I specify a non-exist input path for json data source, the following > exception will be thrown, it is not readable. > {code} > 15/10/14 16:14:39 INFO MemoryStore: Block broadcast_0_piece0 stored as bytes > in memory (estimated size 19.9 KB, free 251.4 KB) > 15/10/14 16:14:39 INFO BlockManagerInfo: Added broadcast_0_piece0 in memory > on 192.168.3.3:54725 (size: 19.9 KB, free: 2.2 GB) > 15/10/14 16:14:39 INFO SparkContext: Created broadcast 0 from json at > <console>:19 > java.io.IOException: No input paths specified in job > at > org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:201) > at > org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:313) > at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:201) > at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) > at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) > at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35) > at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239) > at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237) > at scala.Option.getOrElse(Option.scala:120) > at org.apache.spark.rdd.RDD.partitions(RDD.scala:237) > at > org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1.apply(RDD.scala:1087) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111) > at org.apache.spark.rdd.RDD.withScope(RDD.scala:306) > at org.apache.spark.rdd.RDD.treeAggregate(RDD.scala:1085) > at > org.apache.spark.sql.execution.datasources.json.InferSchema$.apply(InferSchema.scala:58) > at > org.apache.spark.sql.execution.datasources.json.JSONRelation$$anonfun$6.apply(JSONRelation.scala:105) > at > org.apache.spark.sql.execution.datasources.json.JSONRelation$$anonfun$6.apply(JSONRelation.scala:100) > at scala.Option.getOrElse(Option.scala:120) > at > org.apache.spark.sql.execution.datasources.json.JSONRelation.dataSchema$lzycompute(JSONRelation.scala:100) > at > org.apache.spark.sql.execution.datasources.json.JSONRelation.dataSchema(JSONRelation.scala:99) > at > org.apache.spark.sql.sources.HadoopFsRelation.schema$lzycompute(interfaces.scala:561) > at > org.apache.spark.sql.sources.HadoopFsRelation.schema(interfaces.scala:560) > at > org.apache.spark.sql.execution.datasources.LogicalRelation.<init>(LogicalRelation.scala:37) > at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:122) > at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:106) > at org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:221) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:19) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:24) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:26) > at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:28) > at $iwC$$iwC$$iwC$$iwC.<init>(<console>:30) > at $iwC$$iwC$$iwC.<init>(<console>:32) > at $iwC$$iwC.<init>(<console>:34) > at $iwC.<init>(<console>:36) > {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