[
https://issues.apache.org/jira/browse/SPARK-23230?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
dzcxzl updated SPARK-23230:
---------------------------
Description:
When hive.default.fileformat is other kinds of file types, create textfile
table cause a serde error.
We should take the default type of textfile and sequencefile both as
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.
{code:java}
set hive.default.fileformat=orc;
create table tbl( i string ) stored as textfile;
desc formatted tbl;
Serde Library org.apache.hadoop.hive.ql.io.orc.OrcSerde
InputFormat org.apache.hadoop.mapred.TextInputFormat
OutputFormat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat{code}
{code:java}
set hive.default.fileformat=orc;
create table tbl stored as textfile
as
select 1
{code}
{{It failed because it used the wrong SERDE}}{{}}
{code:java}
Caused by: java.lang.ClassCastException:
org.apache.hadoop.hive.ql.io.orc.OrcSerde$OrcSerdeRow cannot be cast to
org.apache.hadoop.io.BytesWritable
at
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat$1.write(HiveIgnoreKeyTextOutputFormat.java:91)
at
org.apache.spark.sql.hive.execution.HiveOutputWriter.write(HiveFileFormat.scala:149)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:327)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:258)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:256)
at
org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1375)
at
org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:261)
... 16 more
{code}
was:
When hive.default.fileformat is other kinds of file types, create textfile
table cause a serde error.
We should take the default type of textfile and sequencefile both as
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.
{code:java}
set hive.default.fileformat=orc;
create table tbl( i string ) stored as textfile;
desc formatted tbl;
Serde Library org.apache.hadoop.hive.ql.io.orc.OrcSerde
InputFormat org.apache.hadoop.mapred.TextInputFormat
OutputFormat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat{code}
> When hive.default.fileformat is other kinds of file types, create textfile
> table cause a serde error
> ----------------------------------------------------------------------------------------------------
>
> Key: SPARK-23230
> URL: https://issues.apache.org/jira/browse/SPARK-23230
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.0.0, 2.0.1, 2.0.2, 2.1.0, 2.1.1, 2.1.2, 2.2.0, 2.2.1
> Reporter: dzcxzl
> Priority: Minor
>
> When hive.default.fileformat is other kinds of file types, create textfile
> table cause a serde error.
> We should take the default type of textfile and sequencefile both as
> org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.
> {code:java}
> set hive.default.fileformat=orc;
> create table tbl( i string ) stored as textfile;
> desc formatted tbl;
> Serde Library org.apache.hadoop.hive.ql.io.orc.OrcSerde
> InputFormat org.apache.hadoop.mapred.TextInputFormat
> OutputFormat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat{code}
>
> {code:java}
> set hive.default.fileformat=orc;
> create table tbl stored as textfile
> as
> select 1
> {code}
> {{It failed because it used the wrong SERDE}}{{}}
> {code:java}
> Caused by: java.lang.ClassCastException:
> org.apache.hadoop.hive.ql.io.orc.OrcSerde$OrcSerdeRow cannot be cast to
> org.apache.hadoop.io.BytesWritable
> at
> org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat$1.write(HiveIgnoreKeyTextOutputFormat.java:91)
> at
> org.apache.spark.sql.hive.execution.HiveOutputWriter.write(HiveFileFormat.scala:149)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:327)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:258)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:256)
> at
> org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1375)
> at
> org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:261)
> ... 16 more
> {code}
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
