Saving all output to "!!{outputDirectory}!!/rcfile_merge1.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/rcfile_merge1.q
>>>  set hive.merge.rcfile.block.level=false;
No rows affected 
>>>  set hive.exec.dynamic.partition=true;
No rows affected 
>>>  set mapred.max.split.size=100;
No rows affected 
>>>  set mapref.min.split.size=1;
No rows affected 
>>>  
>>>  DROP TABLE rcfile_merge1;
No rows affected 
>>>  DROP TABLE rcfile_merge1b;
No rows affected 
>>>  
>>>  CREATE TABLE rcfile_merge1 (key INT, value STRING) 
PARTITIONED BY (ds STRING, part STRING) STORED AS RCFILE;
No rows affected 
>>>  CREATE TABLE rcfile_merge1b (key INT, value STRING) 
PARTITIONED BY (ds STRING, part STRING) STORED AS RCFILE;
No rows affected 
>>>  
>>>  -- Use non block-level merge
>>>  EXPLAIN 
INSERT OVERWRITE TABLE rcfile_merge1 PARTITION (ds='1', part) 
SELECT key, value, PMOD(HASH(key), 100) as part 
FROM src;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME rcfile_merge1) (TOK_PARTSPEC (TOK_PARTVAL ds '1') (TOK_PARTVAL part)))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value)) (TOK_SELEXPR (TOK_FUNCTION PMOD (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key)) 100) part))))'
''
'STAGE DEPENDENCIES:'
'  Stage-1 is a root stage'
'  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5'
'  Stage-4'
'  Stage-0 depends on stages: Stage-4, Stage-3, Stage-6'
'  Stage-2 depends on stages: Stage-0'
'  Stage-3'
'  Stage-5'
'  Stage-6 depends on stages: Stage-5'
''
'STAGE PLANS:'
'  Stage: Stage-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        src '
'          TableScan'
'            alias: src'
'            Select Operator'
'              expressions:'
'                    expr: key'
'                    type: string'
'                    expr: value'
'                    type: string'
'                    expr: pmod(hash(key), 100)'
'                    type: int'
'              outputColumnNames: _col0, _col1, _col2'
'              Select Operator'
'                expressions:'
'                      expr: UDFToInteger(_col0)'
'                      type: int'
'                      expr: _col1'
'                      type: string'
'                      expr: _col2'
'                      type: int'
'                outputColumnNames: _col0, _col1, _col2'
'                File Output Operator'
'                  compressed: false'
'                  GlobalTableId: 1'
'                  table:'
'                      input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat'
'                      output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
'                      serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
'                      name: rcfile_merge1.rcfile_merge1'
''
'  Stage: Stage-7'
'    Conditional Operator'
''
'  Stage: Stage-4'
'    Move Operator'
'      files:'
'          hdfs directory: true'
'          destination: pfile:!!{hive.exec.scratchdir}!!'
''
'  Stage: Stage-0'
'    Move Operator'
'      tables:'
'          partition:'
'            ds 1'
'            part '
'          replace: true'
'          table:'
'              input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat'
'              output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
'              serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
'              name: rcfile_merge1.rcfile_merge1'
''
'  Stage: Stage-2'
'    Stats-Aggr Operator'
''
'  Stage: Stage-3'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        pfile:!!{hive.exec.scratchdir}!! '
'            File Output Operator'
'              compressed: false'
'              GlobalTableId: 0'
'              table:'
'                  input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat'
'                  output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
'                  serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
'                  name: rcfile_merge1.rcfile_merge1'
''
'  Stage: Stage-5'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        pfile:!!{hive.exec.scratchdir}!! '
'            File Output Operator'
'              compressed: false'
'              GlobalTableId: 0'
'              table:'
'                  input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat'
'                  output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
'                  serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
'                  name: rcfile_merge1.rcfile_merge1'
''
'  Stage: Stage-6'
'    Move Operator'
'      files:'
'          hdfs directory: true'
'          destination: pfile:!!{hive.exec.scratchdir}!!'
''
''
105 rows selected 
>>>  INSERT OVERWRITE TABLE rcfile_merge1 PARTITION (ds='1', part) 
SELECT key, value, PMOD(HASH(key), 100) as part 
FROM src;
'_col0','_col1','_col2'
No rows selected 
>>>  
>>>  set hive.merge.rcfile.block.level=true;
No rows affected 
>>>  EXPLAIN 
INSERT OVERWRITE TABLE rcfile_merge1b PARTITION (ds='1', part) 
SELECT key, value, PMOD(HASH(key), 100) as part 
FROM src;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME rcfile_merge1b) (TOK_PARTSPEC (TOK_PARTVAL ds '1') (TOK_PARTVAL part)))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value)) (TOK_SELEXPR (TOK_FUNCTION PMOD (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key)) 100) part))))'
''
'STAGE DEPENDENCIES:'
'  Stage-1 is a root stage'
'  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5'
'  Stage-4'
'  Stage-0 depends on stages: Stage-4, Stage-3, Stage-6'
'  Stage-2 depends on stages: Stage-0'
'  Stage-3'
'  Stage-5'
'  Stage-6 depends on stages: Stage-5'
''
'STAGE PLANS:'
'  Stage: Stage-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        src '
'          TableScan'
'            alias: src'
'            Select Operator'
'              expressions:'
'                    expr: key'
'                    type: string'
'                    expr: value'
'                    type: string'
'                    expr: pmod(hash(key), 100)'
'                    type: int'
'              outputColumnNames: _col0, _col1, _col2'
'              Select Operator'
'                expressions:'
'                      expr: UDFToInteger(_col0)'
'                      type: int'
'                      expr: _col1'
'                      type: string'
'                      expr: _col2'
'                      type: int'
'                outputColumnNames: _col0, _col1, _col2'
'                File Output Operator'
'                  compressed: false'
'                  GlobalTableId: 1'
'                  table:'
'                      input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat'
'                      output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
'                      serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
'                      name: rcfile_merge1.rcfile_merge1b'
''
'  Stage: Stage-7'
'    Conditional Operator'
''
'  Stage: Stage-4'
'    Move Operator'
'      files:'
'          hdfs directory: true'
'          destination: pfile:!!{hive.exec.scratchdir}!!'
''
'  Stage: Stage-0'
'    Move Operator'
'      tables:'
'          partition:'
'            ds 1'
'            part '
'          replace: true'
'          table:'
'              input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat'
'              output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat'
'              serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe'
'              name: rcfile_merge1.rcfile_merge1b'
''
'  Stage: Stage-2'
'    Stats-Aggr Operator'
''
'  Stage: Stage-3'
'    Block level merge'
''
'  Stage: Stage-5'
'    Block level merge'
''
'  Stage: Stage-6'
'    Move Operator'
'      files:'
'          hdfs directory: true'
'          destination: pfile:!!{hive.exec.scratchdir}!!'
''
''
85 rows selected 
>>>  INSERT OVERWRITE TABLE rcfile_merge1b PARTITION (ds='1', part) 
SELECT key, value, PMOD(HASH(key), 100) as part 
FROM src;
'_col0','_col1','_col2'
No rows selected 
>>>  
>>>  -- Verify
>>>  SELECT SUM(HASH(c)) FROM ( 
SELECT TRANSFORM(*) USING 'tr \t _' AS (c) 
FROM rcfile_merge1 WHERE ds='1' 
) t;
'_c0'
'59521204047'
1 row selected 
>>>  SELECT SUM(HASH(c)) FROM ( 
SELECT TRANSFORM(*) USING 'tr \t _' AS (c) 
FROM rcfile_merge1b WHERE ds='1' 
) t;
'_c0'
'59521204047'
1 row selected 
>>>  
>>>  DROP TABLE rcfile_merge1;
No rows affected 
>>>  DROP TABLE rcfile_merge1b;
No rows affected 
>>>  !record