[jira] [Commented] (CARBONDATA-864) After adding column using alter query, when we put any column in "Dictionary Exclude" then perform select query on that column then it will throws an exception.

[Akash R Nilugal (Jira)]

    [ https://issues.apache.org/jira/browse/CARBONDATA-864?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15960416#comment-15960416 ]

SWATI RAO commented on CARBONDATA-864:
--------------------------------------

When we put string datatype in dictionary_exclude it will display "NULL" values when perform select query.

CREATE TABLE uniqdata (CUST_ID int,CUST_NAME String,ACTIVE_EMUI_VERSION string, DOB timestamp, DOJ timestamp, BIGINT_COLUMN1 bigint,BIGINT_COLUMN2 bigint,DECIMAL_COLUMN1 decimal(30,10), DECIMAL_COLUMN2 decimal(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1 int) STORED BY 'org.apache.carbondata.format' TBLPROPERTIES ("TABLE_BLOCKSIZE"= "256 MB");



LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/2000_UniqData.csv' into table uniqdata OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1');LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/2000_UniqData.csv' into table uniqdata OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1');


ALTER TABLE uniqdata RENAME TO uniqdata1;


alter table uniqdata1 drop columns(ACTIVE_EMUI_VERSION);


alter table uniqdata1 add columns(ACTIVE_EMUI_VERSION string) TBLPROPERTIES('DICTIONARY_EXCLUDE'='ACTIVE_EMUI_VERSION', 'DEFAULT.VALUE.(ACTIVE_EMUI_VERSION'='abcd');


select distinct(ACTIVE_EMUI_VERSION) from uniqdata1 ;

Results:

0: jdbc:hive2://192.168.2.126:10000> alter table uniqdata1 drop columns(ACTIVE_EMUI_VERSION);
Error: java.lang.RuntimeException: Column active_emui_version does not exists in the table default.uniqdata1 (state=,code=0)
0: jdbc:hive2://192.168.2.126:10000>
0: jdbc:hive2://192.168.2.126:10000> alter table uniqdata1 add columns(ACTIVE_EMUI_VERSION string) TBLPROPERTIES('DICTIONARY_EXCLUDE'='ACTIVE_EMUI_VERSION', 'DEFAULT.VALUE.(ACTIVE_EMUI_VERSION'='abcd');
+---------+--+
| Result  |
+---------+--+
+---------+--+
No rows selected (0.308 seconds)
0: jdbc:hive2://192.168.2.126:10000> select distinct(ACTIVE_EMUI_VERSION) from uniqdata1 ;
+----------------------+--+
| ACTIVE_EMUI_VERSION  |
+----------------------+--+
| NULL                 |
+----------------------+--+
1 row selected (0.88 seconds)
0: jdbc:hive2://192.168.2.126:10000>

> After adding column using alter query, when we put any column in "Dictionary Exclude" then perform select query on that column then it will throws an exception.
> ----------------------------------------------------------------------------------------------------------------------------------------------------------------
>
>                 Key: CARBONDATA-864
>                 URL: https://issues.apache.org/jira/browse/CARBONDATA-864
>             Project: CarbonData
>          Issue Type: Bug
>    Affects Versions: 1.1.0-incubating
>         Environment: Spark2.1
>            Reporter: SWATI RAO
>         Attachments: 2000_UniqData.csv, error.png
>
>
> CREATE TABLE uniqdata (CUST_ID int,CUST_NAME String,ACTIVE_EMUI_VERSION string, DOB timestamp, DOJ timestamp, BIGINT_COLUMN1 bigint,BIGINT_COLUMN2 bigint,DECIMAL_COLUMN1 decimal(30,10), DECIMAL_COLUMN2 decimal(36,10),Double_COLUMN1 double, Double_COLUMN2 double,INTEGER_COLUMN1 int) STORED BY 'org.apache.carbondata.format' TBLPROPERTIES ("TABLE_BLOCKSIZE"= "256 MB");
> LOAD DATA INPATH 'HDFS_URL/BabuStore/Data/uniqdata/2000_UniqData.csv' into table uniqdata OPTIONS('DELIMITER'=',' , 'QUOTECHAR'='"','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='CUST_ID,CUST_NAME,ACTIVE_EMUI_VERSION,DOB,DOJ,BIGINT_COLUMN1,BIGINT_COLUMN2,DECIMAL_COLUMN1,DECIMAL_COLUMN2,Double_COLUMN1,Double_COLUMN2,INTEGER_COLUMN1');
> ALTER TABLE uniqdata RENAME TO uniqdata1;
> alter table uniqdata1 add columns(dict int) TBLPROPERTIES('DICTIONARY_INCLUDE'='dict','DEFAULT.VALUE.dict'= '9999');
> select distinct(dict) from uniqdata1 ;
> when we perform select query on "DICTIONARY_INCLUDE" it is working
> but when we perform select query on "DICTIONARY_EXCLUDE" then it will throws an exception:
> alter table uniqdata1 add columns(nodict string) TBLPROPERTIES('DICTIONARY_EXCLUDE'='nodict', 'DEFAULT.VALUE.NoDict'= 'abcd');
> select distinct(nodict) from uniqdata1 ;
> 0: jdbc:hive2://192.168.2.126:10000> select distinct(nodict) from uniqdata1 ;
> Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 21.0 failed 1 times, most recent failure: Lost task 0.0 in stage 21.0 (TID 419, localhost, executor driver): java.lang.ArrayIndexOutOfBoundsException: 4186
> at org.apache.spark.sql.execution.vectorized.OnHeapColumnVector.putByteArray(OnHeapColumnVector.java:401)
> at org.apache.spark.sql.execution.vectorized.ColumnVector.putByteArray(ColumnVector.java:569)
> at org.apache.carbondata.spark.vectorreader.ColumnarVectorWrapper.putBytes(ColumnarVectorWrapper.java:77)
> at org.apache.carbondata.spark.vectorreader.ColumnarVectorWrapper.putBytes(ColumnarVectorWrapper.java:83)
> at org.apache.carbondata.core.scan.collector.impl.RestructureBasedVectorResultCollector.fillNoDictionaryData(RestructureBasedVectorResultCollector.java:167)
> at org.apache.carbondata.core.scan.collector.impl.RestructureBasedVectorResultCollector.fillDataForNonExistingDimensions(RestructureBasedVectorResultCollector.java:122)
> at org.apache.carbondata.core.scan.collector.impl.RestructureBasedVectorResultCollector.collectVectorBatch(RestructureBasedVectorResultCollector.java:97)
> at org.apache.carbondata.core.scan.processor.impl.DataBlockIteratorImpl.processNextBatch(DataBlockIteratorImpl.java:65)
> at org.apache.carbondata.core.scan.result.iterator.VectorDetailQueryResultIterator.processNextBatch(VectorDetailQueryResultIterator.java:46)
> at org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.nextBatch(VectorizedCarbonRecordReader.java:246)
> at org.apache.carbondata.spark.vectorreader.VectorizedCarbonRecordReader.nextKeyValue(VectorizedCarbonRecordReader.java:140)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.hasNext(CarbonScanRDD.scala:222)
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.scan_nextBatch$(Unknown Source)
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown Source)
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
> at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
> at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
> at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
> at org.apache.spark.scheduler.Task.run(Task.scala:99)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)