Rahul Challapalli created DRILL-4032:
----------------------------------------
Summary: Drill unable to parse json files with schema changes
Key: DRILL-4032
URL: https://issues.apache.org/jira/browse/DRILL-4032
Project: Apache Drill
Issue Type: Bug
Components: Execution - Data Types, Storage - JSON
Affects Versions: 1.3.0
Reporter: Rahul Challapalli
Priority: Blocker
git.commit.id.abbrev=bb69f22
{code}
select d.col2.col3 from reg1 d;
Error: DATA_READ ERROR: Error parsing JSON - index: 0, length: 4 (expected:
range(0, 0))
File /drill/testdata/reg1/a.json
Record 2
Fragment 0:0
{code}
The folder reg1 contains 2 files
File 1 : a.json
{code}
{"col1": "val1","col2": null}
{"col1": "val1","col2": {"col3":"abc", "col4":"xyz"}}
{code}
File 2 : b.json
{code}
{"col1": "val1","col2": null}
{"col1": "val1","col2": null}
{code}
Exception from the log file :
{code}
[Error Id: a7e3c716-838d-4f8f-9361-3727b98f04cd ]
at
org.apache.drill.common.exceptions.UserException$Builder.build(UserException.java:534)
~[drill-common-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.store.easy.json.JSONRecordReader.handleAndRaise(JSONRecordReader.java:165)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.store.easy.json.JSONRecordReader.next(JSONRecordReader.java:205)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.ScanBatch.next(ScanBatch.java:183)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:119)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:113)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:103)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:51)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.innerNext(ProjectRecordBatch.java:130)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:156)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.validate.IteratorValidatorBatchIterator.next(IteratorValidatorBatchIterator.java:119)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:104)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.ScreenCreator$ScreenRoot.innerNext(ScreenCreator.java:80)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:94)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:256)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.work.fragment.FragmentExecutor$1.run(FragmentExecutor.java:250)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at java.security.AccessController.doPrivileged(Native Method)
[na:1.7.0_71]
at javax.security.auth.Subject.doAs(Subject.java:415) [na:1.7.0_71]
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1595)
[hadoop-common-2.7.0-mapr-1506.jar:na]
at
org.apache.drill.exec.work.fragment.FragmentExecutor.run(FragmentExecutor.java:250)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.common.SelfCleaningRunnable.run(SelfCleaningRunnable.java:38)
[drill-common-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
[na:1.7.0_71]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
[na:1.7.0_71]
at java.lang.Thread.run(Thread.java:745) [na:1.7.0_71]
Caused by: java.lang.IndexOutOfBoundsException: index: 0, length: 4 (expected:
range(0, 0))
at io.netty.buffer.DrillBuf.checkIndexD(DrillBuf.java:189)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:4.0.27.Final]
at io.netty.buffer.DrillBuf.chk(DrillBuf.java:211)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:4.0.27.Final]
at io.netty.buffer.DrillBuf.getInt(DrillBuf.java:491)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:4.0.27.Final]
at
org.apache.drill.exec.vector.UInt4Vector$Accessor.get(UInt4Vector.java:364)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.VarCharVector$Mutator.setSafe(VarCharVector.java:525)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.NullableVarCharVector$Mutator.fillEmpties(NullableVarCharVector.java:465)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.NullableVarCharVector$Mutator.setSafe(NullableVarCharVector.java:545)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.impl.NullableVarCharWriterImpl.writeVarChar(NullableVarCharWriterImpl.java:151)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.fn.JsonReader.handleString(JsonReader.java:461)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.fn.JsonReader.writeData(JsonReader.java:342)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.fn.JsonReader.writeData(JsonReader.java:310)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.fn.JsonReader.writeDataSwitch(JsonReader.java:241)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.fn.JsonReader.writeToVector(JsonReader.java:179)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.vector.complex.fn.JsonReader.write(JsonReader.java:145)
~[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
at
org.apache.drill.exec.store.easy.json.JSONRecordReader.next(JSONRecordReader.java:183)
[drill-java-exec-1.3.0-SNAPSHOT.jar:1.3.0-SNAPSHOT]
{code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)