Khurram Faraaz created DRILL-5591:
-------------------------------------
Summary: non-ASCII characters in text file result in
MalformedInputException
Key: DRILL-5591
URL: https://issues.apache.org/jira/browse/DRILL-5591
Project: Apache Drill
Issue Type: Bug
Components: Storage - Text & CSV
Affects Versions: 1.11.0
Reporter: Khurram Faraaz
I am on Drill 1.11.0 commit id: 874bf62
To repro the issue:
wget http://cfdisat.blob.core.windows.net/lco/l_RFC_2017_05_11_2.txt.gz
gunzip l_RFC_2017_05_11_2.txt.gz
hadoop fs -put l_RFC_2017_05_11_2.txt /tmp
There are some non-ASCII characters at the beginning and end of the file used
in the test.
{noformat}
[root@centos-01 drill_5590]# head l_RFC_2017_05_11_2.txt
����0���1��
��� ��RFC|SNCF|SUBCONTRATACION
CUBB910321AC1|0|0
CUBB9104187K9|0|0
CUBB910709KD0|0|0
CUBB910817CE8|0|0
CUBB9111286YA|0|0
CUBB920408J69|0|0
{noformat}
Failing query
{noformat}
0: jdbc:drill:schema=dfs.tmp> select count(1) from `l_RFC_2017_05_11_2.txt` t
where columns[0] like 'CUBA7706%';
Error: SYSTEM ERROR: MalformedInputException: Input length = 1
Fragment 0:0
[Error Id: cdfa704c-0bc8-4791-95ae-d05b4c63beab on centos-01.qa.lab:31010]
(state=,code=0)
{noformat}
Stack trace from drillbit.log
{noformat}
Caused by: java.lang.RuntimeException:
java.nio.charset.MalformedInputException: Input length = 1
at
org.apache.drill.exec.expr.fn.impl.CharSequenceWrapper.decodeUT8(CharSequenceWrapper.java:185)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.expr.fn.impl.CharSequenceWrapper.setBuffer(CharSequenceWrapper.java:119)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.test.generated.FiltererGen15.doEval(FilterTemplate2.java:50)
~[na:na]
at
org.apache.drill.exec.test.generated.FiltererGen15.filterBatchNoSV(FilterTemplate2.java:100)
~[na:na]
at
org.apache.drill.exec.test.generated.FiltererGen15.filterBatch(FilterTemplate2.java:73)
~[na:na]
at
org.apache.drill.exec.physical.impl.filter.FilterRecordBatch.doWork(FilterRecordBatch.java:81)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:93)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:162)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:225)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:119)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:109)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.svremover.RemovingRecordBatch.innerNext(RemovingRecordBatch.java:93)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:162)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:225)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:119)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:109)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.innerNext(ProjectRecordBatch.java:133)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:162)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:225)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:119)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:109)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.aggregate.StreamingAggBatch.buildSchema(StreamingAggBatch.java:102)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:142)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:225)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:119)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:109)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.aggregate.StreamingAggBatch.buildSchema(StreamingAggBatch.java:102)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:142)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:225)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:119)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:109)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.innerNext(ProjectRecordBatch.java:133)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:162)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:225)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:105)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.ScreenCreator$ScreenRoot.innerNext(ScreenCreator.java:81)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:95)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:234)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at
org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:227)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
at java.security.AccessController.doPrivileged(Native Method)
~[na:1.8.0_91]
at javax.security.auth.Subject.doAs(Subject.java:422) ~[na:1.8.0_91]
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1595)
~[hadoop-common-2.7.0-mapr-1607.jar:na]
at
org.apache.drill.exec.work.fragment.FragmentExecutor.run(FragmentExecutor.java:227)
[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
... 4 common frames omitted
Caused by: java.nio.charset.MalformedInputException: Input length = 1
at java.nio.charset.CoderResult.throwException(CoderResult.java:281)
~[na:1.8.0_91]
at
org.apache.drill.exec.expr.fn.impl.CharSequenceWrapper.decodeUT8(CharSequenceWrapper.java:183)
~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT]
... 49 common frames omitted
{noformat}
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)