Saving all output to "!!{outputDirectory}!!/groupby4.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/groupby4.q >>> set hive.map.aggr=false; No rows affected >>> set hive.groupby.skewindata=true; No rows affected >>> >>> CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE; No rows affected >>> >>> EXPLAIN FROM src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1) GROUP BY substr(src.key,1,1); 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1))) (TOK_GROUPBY (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-2 depends on stages: Stage-1' ' Stage-0 depends on stages: Stage-2' ' Stage-3 depends on stages: Stage-0' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' src ' ' TableScan' ' alias: src' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' outputColumnNames: key' ' Reduce Output Operator' ' key expressions:' ' expr: substr(key, 1, 1)' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: rand()' ' type: double' ' tag: -1' ' Reduce Operator Tree:' ' Group By Operator' ' bucketGroup: false' ' keys:' ' expr: KEY._col0' ' type: string' ' mode: partial1' ' outputColumnNames: _col0' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.SequenceFileInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat' '' ' Stage: Stage-2' ' Map Reduce' ' Alias -> Map Operator Tree:' ' file:!!{hive.exec.scratchdir}!! ' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: -1' ' Reduce Operator Tree:' ' Group By Operator' ' bucketGroup: false' ' keys:' ' expr: KEY._col0' ' type: string' ' mode: final' ' outputColumnNames: _col0' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' outputColumnNames: _col0' ' File Output Operator' ' compressed: false' ' GlobalTableId: 1' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: groupby4.dest1' '' ' Stage: Stage-0' ' Move Operator' ' tables:' ' replace: true' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: groupby4.dest1' '' ' Stage: Stage-3' ' Stats-Aggr Operator' '' '' 94 rows selected >>> >>> FROM src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1) GROUP BY substr(src.key,1,1); '_c0' No rows selected >>> >>> SELECT dest1.* FROM dest1; 'c1' '0' '1' '2' '3' '4' '5' '6' '7' '8' '9' 10 rows selected >>> >>> !record