[
https://issues.apache.org/jira/browse/SPARK-13173?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Davies Liu updated SPARK-13173:
-------------------------------
Description:
{code}
id|end_date|start_date|location
1|2015-10-14 00:00:00|2015-09-14 00:00:00|CA-SF
2|2015-10-15 01:00:20|2015-08-14 00:00:00|CA-SD
3|2015-10-16 02:30:00|2015-01-14 00:00:00|NY-NY
4|2015-10-17 03:00:20|2015-02-14 00:00:00|NY-NY
5|2015-10-18 04:30:00|2014-04-14 00:00:00|CA-SD
{code}
{code}
adult_df = sqlContext.read.\
format("org.apache.spark.sql.execution.datasources.csv").\
option("header", "true").option("delimiter", "|").\
option("inferSchema", "true").load("/tmp/dataframe_sample.csv")
{code}
{code}
Py4JJavaError: An error occurred while calling o239.load.
: java.lang.NullPointerException
at
scala.collection.mutable.ArrayOps$ofRef$.length$extension(ArrayOps.scala:114)
at scala.collection.mutable.ArrayOps$ofRef.length(ArrayOps.scala:114)
at
scala.collection.IndexedSeqOptimized$class.zipWithIndex(IndexedSeqOptimized.scala:93)
at
scala.collection.mutable.ArrayOps$ofRef.zipWithIndex(ArrayOps.scala:108)
at
org.apache.spark.sql.execution.datasources.csv.CSVRelation.inferSchema(CSVRelation.scala:137)
at
org.apache.spark.sql.execution.datasources.csv.CSVRelation.dataSchema$lzycompute(CSVRelation.scala:50)
at
org.apache.spark.sql.execution.datasources.csv.CSVRelation.dataSchema(CSVRelation.scala:48)
at
org.apache.spark.sql.sources.HadoopFsRelation.schema$lzycompute(interfaces.scala:666)
at
org.apache.spark.sql.sources.HadoopFsRelation.schema(interfaces.scala:665)
at
org.apache.spark.sql.execution.datasources.LogicalRelation.<init>(LogicalRelation.scala:39)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:115)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:136)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:290)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)
{code}
was:
{code}
id|end_date|start_date|location
1|2015-10-14 00:00:00|2015-09-14 00:00:00|CA-SF
2|2015-10-15 01:00:20|2015-08-14 00:00:00|CA-SD
3|2015-10-16 02:30:00|2015-01-14 00:00:00|NY-NY
4|2015-10-17 03:00:20|2015-02-14 00:00:00|NY-NY
5|2015-10-18 04:30:00|2014-04-14 00:00:00|CA-SD
{code}
{code}
adult_df = sqlContext.read.\
format("org.apache.spark.sql.execution.datasources.csv").\
option("header", "false").option("delimiter", "|").\
option("inferSchema", "true").load("/tmp/dataframe_sample.csv")
{code}
{code}
Py4JJavaError: An error occurred while calling o239.load.
: java.lang.NullPointerException
at
scala.collection.mutable.ArrayOps$ofRef$.length$extension(ArrayOps.scala:114)
at scala.collection.mutable.ArrayOps$ofRef.length(ArrayOps.scala:114)
at
scala.collection.IndexedSeqOptimized$class.zipWithIndex(IndexedSeqOptimized.scala:93)
at
scala.collection.mutable.ArrayOps$ofRef.zipWithIndex(ArrayOps.scala:108)
at
org.apache.spark.sql.execution.datasources.csv.CSVRelation.inferSchema(CSVRelation.scala:137)
at
org.apache.spark.sql.execution.datasources.csv.CSVRelation.dataSchema$lzycompute(CSVRelation.scala:50)
at
org.apache.spark.sql.execution.datasources.csv.CSVRelation.dataSchema(CSVRelation.scala:48)
at
org.apache.spark.sql.sources.HadoopFsRelation.schema$lzycompute(interfaces.scala:666)
at
org.apache.spark.sql.sources.HadoopFsRelation.schema(interfaces.scala:665)
at
org.apache.spark.sql.execution.datasources.LogicalRelation.<init>(LogicalRelation.scala:39)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:115)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:136)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:290)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)
{code}
> Fail to load CSV file with NPE
> ------------------------------
>
> Key: SPARK-13173
> URL: https://issues.apache.org/jira/browse/SPARK-13173
> Project: Spark
> Issue Type: Bug
> Components: Input/Output, SQL
> Reporter: Davies Liu
>
> {code}
> id|end_date|start_date|location
> 1|2015-10-14 00:00:00|2015-09-14 00:00:00|CA-SF
> 2|2015-10-15 01:00:20|2015-08-14 00:00:00|CA-SD
> 3|2015-10-16 02:30:00|2015-01-14 00:00:00|NY-NY
> 4|2015-10-17 03:00:20|2015-02-14 00:00:00|NY-NY
> 5|2015-10-18 04:30:00|2014-04-14 00:00:00|CA-SD
> {code}
> {code}
> adult_df = sqlContext.read.\
> format("org.apache.spark.sql.execution.datasources.csv").\
> option("header", "true").option("delimiter", "|").\
> option("inferSchema", "true").load("/tmp/dataframe_sample.csv")
> {code}
> {code}
> Py4JJavaError: An error occurred while calling o239.load.
> : java.lang.NullPointerException
> at
> scala.collection.mutable.ArrayOps$ofRef$.length$extension(ArrayOps.scala:114)
> at scala.collection.mutable.ArrayOps$ofRef.length(ArrayOps.scala:114)
> at
> scala.collection.IndexedSeqOptimized$class.zipWithIndex(IndexedSeqOptimized.scala:93)
> at
> scala.collection.mutable.ArrayOps$ofRef.zipWithIndex(ArrayOps.scala:108)
> at
> org.apache.spark.sql.execution.datasources.csv.CSVRelation.inferSchema(CSVRelation.scala:137)
> at
> org.apache.spark.sql.execution.datasources.csv.CSVRelation.dataSchema$lzycompute(CSVRelation.scala:50)
> at
> org.apache.spark.sql.execution.datasources.csv.CSVRelation.dataSchema(CSVRelation.scala:48)
> at
> org.apache.spark.sql.sources.HadoopFsRelation.schema$lzycompute(interfaces.scala:666)
> at
> org.apache.spark.sql.sources.HadoopFsRelation.schema(interfaces.scala:665)
> at
> org.apache.spark.sql.execution.datasources.LogicalRelation.<init>(LogicalRelation.scala:39)
> at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:115)
> at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:136)
> 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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
> at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
> at py4j.Gateway.invoke(Gateway.java:290)
> at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
> at py4j.commands.CallCommand.execute(CallCommand.java:79)
> at py4j.GatewayConnection.run(GatewayConnection.java:209)
> at java.lang.Thread.run(Thread.java:745)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
