Khurram Faraaz created DRILL-5458: ------------------------------------- Summary: REPEATED_COUNT over varchar data results in SchemaChangeException Key: DRILL-5458 URL: https://issues.apache.org/jira/browse/DRILL-5458 Project: Apache Drill Issue Type: Bug Affects Versions: 1.11.0 Reporter: Khurram Faraaz
REPEATED_COUNT over varchar type data results in SchemaChangeException Apache Drill 1.11.0 commit id: 3e8b01d5 {noformat} // CTAS over JSON file. 0: jdbc:drill:schema=dfs.tmp> create table tblwarr01 as select convert_to(t.arr,'JSON') arr, id from `rptd_count.json` t; +-----------+----------------------------+ | Fragment | Number of records written | +-----------+----------------------------+ | 0_0 | 10 | +-----------+----------------------------+ 1 row selected (0.221 seconds) 0: jdbc:drill:schema=dfs.tmp> select * from tblwarr01; +--------------+-----+ | arr | id | +--------------+-----+ | [B@67cf1438 | 1 | | [B@4c389dc6 | 2 | | [B@18fe5942 | 3 | | [B@629608df | 4 | | [B@68209b09 | 5 | | [B@34a2a147 | 6 | | [B@210a5750 | 7 | | [B@2dea5622 | 8 | | [B@73bce9ba | 9 | | [B@7794edb2 | 10 | +--------------+-----+ 10 rows selected (0.209 seconds) {noformat} {noformat} 0: jdbc:drill:schema=dfs.tmp> select convert_from(t.arr,'UTF8') from tblwarr01 t; +---------------------------------------+ | EXPR$0 | +---------------------------------------+ | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | | [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] | +---------------------------------------+ 10 rows selected (0.195 seconds) // Performing a REPEATED_COUNT on the array results in SchemaChangeException 0: jdbc:drill:schema=dfs.tmp> select REPEATED_COUNT(convert_from(t.arr,'UTF8')) from tblwarr01 t; Error: SYSTEM ERROR: SchemaChangeException: Failure while trying to materialize incoming schema. Errors: Error in expression at index -1. Error: Missing function implementation: [repeated_count(VARCHAR-REQUIRED)]. Full expression: --UNKNOWN EXPRESSION--.. Fragment 0:0 [Error Id: 1a891918-79f6-49d1-a594-f9ec5f28a99a on centos-01.qa.lab:31010] (state=,code=0) {noformat} Data used in CTAS. {noformat} [root@centos-01 ~]# cat rptd_count.json {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":1} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":2} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":3} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":4} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":5} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":6} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":7} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":8} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":9} {"arr":[0,1,2,3,4,5,6,7,8,9,10],"id":10} [root@centos-01 ~]# {noformat} Stack trace from drillbit.log {noformat} 2017-05-02 05:17:03,651 [26f7e9b0-5f11-e764-6fa8-92c27ca2c6cf:frag:0:0] ERROR o.a.d.e.w.fragment.FragmentExecutor - SYSTEM ERROR: SchemaChangeException: Failure while trying to materialize incoming schema. Errors: Error in expression at index -1. Error: Missing function implementation: [repeated_count(VARCHAR-REQUIRED)]. Full expression: --UNKNOWN EXPRESSION--.. Fragment 0:0 [Error Id: 1a891918-79f6-49d1-a594-f9ec5f28a99a on centos-01.qa.lab:31010] org.apache.drill.common.exceptions.UserException: SYSTEM ERROR: SchemaChangeException: Failure while trying to materialize incoming schema. Errors: Error in expression at index -1. Error: Missing function implementation: [repeated_count(VARCHAR-REQUIRED)]. Full expression: --UNKNOWN EXPRESSION--.. Fragment 0:0 [Error Id: 1a891918-79f6-49d1-a594-f9ec5f28a99a on centos-01.qa.lab:31010] at org.apache.drill.common.exceptions.UserException$Builder.build(UserException.java:544) ~[drill-common-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.exec.work.fragment.FragmentExecutor.sendFinalState(FragmentExecutor.java:295) [drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.exec.work.fragment.FragmentExecutor.cleanup(FragmentExecutor.java:160) [drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.exec.work.fragment.FragmentExecutor.run(FragmentExecutor.java:264) [drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.common.SelfCleaningRunnable.run(SelfCleaningRunnable.java:38) [drill-common-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) [na:1.8.0_91] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) [na:1.8.0_91] at java.lang.Thread.run(Thread.java:745) [na:1.8.0_91] Caused by: org.apache.drill.exec.exception.SchemaChangeException: Failure while trying to materialize incoming schema. Errors: Error in expression at index -1. Error: Missing function implementation: [repeated_count(VARCHAR-REQUIRED)]. Full expression: --UNKNOWN EXPRESSION--.. at org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.setupNewSchema(ProjectRecordBatch.java:427) ~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.exec.record.AbstractSingleRecordBatch.innerNext(AbstractSingleRecordBatch.java:78) ~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.exec.physical.impl.project.ProjectRecordBatch.innerNext(ProjectRecordBatch.java:135) ~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.exec.record.AbstractRecordBatch.next(AbstractRecordBatch.java:162) ~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.exec.physical.impl.BaseRootExec.next(BaseRootExec.java:104) ~[drill-java-exec-1.11.0-SNAPSHOT.jar:1.11.0-SNAPSHOT] at org.apache.drill.exec.physical.impl.ScreenCreator$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:94) ~[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 {noformat} -- This message was sent by Atlassian JIRA (v6.3.15#6346)