[ https://issues.apache.org/jira/browse/HIVE-16480?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16440247#comment-16440247 ]
Jaehwa Jung commented on HIVE-16480: ------------------------------------ [~owen.omalley] ORC-285 already included in ORC 1.4.3 version. Could you start to review this patch? > ORC file with empty array<double> and array<float> fails to read > ---------------------------------------------------------------- > > Key: HIVE-16480 > URL: https://issues.apache.org/jira/browse/HIVE-16480 > Project: Hive > Issue Type: Bug > Affects Versions: 2.1.1, 2.2.0 > Reporter: David Capwell > Assignee: Owen O'Malley > Priority: Major > Labels: pull-request-available > > We have a schema that has a array<double> in it. We were unable to read this > file and digging into ORC it seems that the issue is when the array is empty. > Here is the stack trace > {code:title=EmptyList.log|borderStyle=solid} > ERROR 2017-04-19 09:29:17,075 [main] [EmptyList] [line 56] Failed to work > with type float > java.io.IOException: Error reading file: > /var/folders/t8/t5x1031d7mn17f6xpwnkkv_40000gn/T/1492619355819-0/file-float.orc > at > org.apache.orc.impl.RecordReaderImpl.nextBatch(RecordReaderImpl.java:1052) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.nextBatch(RecordReaderImpl.java:135) > ~[hive-exec-2.1.1.jar:2.1.1] > at EmptyList.emptyList(EmptyList.java:49) ~[test-classes/:na] > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > ~[na:1.8.0_121] > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > ~[na:1.8.0_121] > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > ~[na:1.8.0_121] > at java.lang.reflect.Method.invoke(Method.java:498) ~[na:1.8.0_121] > at > org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50) > [junit-4.12.jar:4.12] > at > org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12) > [junit-4.12.jar:4.12] > at > org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47) > [junit-4.12.jar:4.12] > at > org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325) > [junit-4.12.jar:4.12] > at > org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78) > [junit-4.12.jar:4.12] > at > org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner.run(ParentRunner.java:363) > [junit-4.12.jar:4.12] > at org.junit.runner.JUnitCore.run(JUnitCore.java:137) [junit-4.12.jar:4.12] > at > com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:68) > [junit-rt.jar:na] > at > com.intellij.rt.execution.junit.IdeaTestRunner$Repeater.startRunnerWithArgs(IdeaTestRunner.java:51) > [junit-rt.jar:na] > at > com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:237) > [junit-rt.jar:na] > at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:70) > [junit-rt.jar:na] > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > ~[na:1.8.0_121] > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > ~[na:1.8.0_121] > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > ~[na:1.8.0_121] > at java.lang.reflect.Method.invoke(Method.java:498) ~[na:1.8.0_121] > at com.intellij.rt.execution.application.AppMain.main(AppMain.java:147) > [idea_rt.jar:na] > Caused by: java.io.EOFException: Read past EOF for compressed stream Stream > for column 1 kind DATA position: 0 length: 0 range: 0 offset: 0 limit: 0 > at > org.apache.orc.impl.SerializationUtils.readFully(SerializationUtils.java:118) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.SerializationUtils.readFloat(SerializationUtils.java:78) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.TreeReaderFactory$FloatTreeReader.nextVector(TreeReaderFactory.java:619) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.TreeReaderFactory$ListTreeReader.nextVector(TreeReaderFactory.java:1902) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.TreeReaderFactory$TreeReader.nextBatch(TreeReaderFactory.java:154) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.RecordReaderImpl.nextBatch(RecordReaderImpl.java:1045) > ~[hive-orc-2.1.1.jar:2.1.1] > ... 29 common frames omitted > INFO 2017-04-19 09:29:17,091 [main] [WriterImpl] [line 205] ORC writer > created for path: > /var/folders/t8/t5x1031d7mn17f6xpwnkkv_40000gn/T/1492619355819-0/file-double.orc > with stripeSize: 67108864 blockSize: 268435456 compression: ZLIB bufferSize: > 262144 > INFO 2017-04-19 09:29:17,100 [main] [ReaderImpl] [line 357] Reading ORC rows > from > /var/folders/t8/t5x1031d7mn17f6xpwnkkv_40000gn/T/1492619355819-0/file-double.orc > with {include: null, offset: 0, length: 9223372036854775807} > INFO 2017-04-19 09:29:17,101 [main] [RecordReaderImpl] [line 142] Schema on > read not provided -- using file schema array<double> > ERROR 2017-04-19 09:29:17,104 [main] [EmptyList] [line 56] Failed to work > with type double > java.io.IOException: Error reading file: > /var/folders/t8/t5x1031d7mn17f6xpwnkkv_40000gn/T/1492619355819-0/file-double.orc > at > org.apache.orc.impl.RecordReaderImpl.nextBatch(RecordReaderImpl.java:1052) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.hadoop.hive.ql.io.orc.RecordReaderImpl.nextBatch(RecordReaderImpl.java:135) > ~[hive-exec-2.1.1.jar:2.1.1] > at EmptyList.emptyList(EmptyList.java:49) ~[test-classes/:na] > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > ~[na:1.8.0_121] > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > ~[na:1.8.0_121] > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > ~[na:1.8.0_121] > at java.lang.reflect.Method.invoke(Method.java:498) ~[na:1.8.0_121] > at > org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50) > [junit-4.12.jar:4.12] > at > org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12) > [junit-4.12.jar:4.12] > at > org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47) > [junit-4.12.jar:4.12] > at > org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325) > [junit-4.12.jar:4.12] > at > org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78) > [junit-4.12.jar:4.12] > at > org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268) > [junit-4.12.jar:4.12] > at org.junit.runners.ParentRunner.run(ParentRunner.java:363) > [junit-4.12.jar:4.12] > at org.junit.runner.JUnitCore.run(JUnitCore.java:137) [junit-4.12.jar:4.12] > at > com.intellij.junit4.JUnit4IdeaTestRunner.startRunnerWithArgs(JUnit4IdeaTestRunner.java:68) > [junit-rt.jar:na] > at > com.intellij.rt.execution.junit.IdeaTestRunner$Repeater.startRunnerWithArgs(IdeaTestRunner.java:51) > [junit-rt.jar:na] > at > com.intellij.rt.execution.junit.JUnitStarter.prepareStreamsAndStart(JUnitStarter.java:237) > [junit-rt.jar:na] > at com.intellij.rt.execution.junit.JUnitStarter.main(JUnitStarter.java:70) > [junit-rt.jar:na] > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > ~[na:1.8.0_121] > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > ~[na:1.8.0_121] > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > ~[na:1.8.0_121] > at java.lang.reflect.Method.invoke(Method.java:498) ~[na:1.8.0_121] > at com.intellij.rt.execution.application.AppMain.main(AppMain.java:147) > [idea_rt.jar:na] > Caused by: java.io.EOFException: Read past EOF for compressed stream Stream > for column 1 kind DATA position: 0 length: 0 range: 0 offset: 0 limit: 0 > at > org.apache.orc.impl.SerializationUtils.readFully(SerializationUtils.java:118) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.SerializationUtils.readLongLE(SerializationUtils.java:101) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.SerializationUtils.readDouble(SerializationUtils.java:97) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.TreeReaderFactory$DoubleTreeReader.nextVector(TreeReaderFactory.java:713) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.TreeReaderFactory$ListTreeReader.nextVector(TreeReaderFactory.java:1902) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.TreeReaderFactory$TreeReader.nextBatch(TreeReaderFactory.java:154) > ~[hive-orc-2.1.1.jar:2.1.1] > at > org.apache.orc.impl.RecordReaderImpl.nextBatch(RecordReaderImpl.java:1045) > ~[hive-orc-2.1.1.jar:2.1.1] > ... 29 common frames omitted > {code} > If you create a ORC file with one row as the following > {code} > orc.addRow(Lists.newArrayList()); > {code} > then try to read it > {code} > VectorizedRowBatch batch = reader.getSchema().createRowBatch(); > while (rows.nextBatch(batch)) { } > {code} > You will produce the above stack trace. -- This message was sent by Atlassian JIRA (v7.6.3#76005)