PREHOOK: query: create table tmp_srcpart like srcpart PREHOOK: type: CREATETABLE POSTHOOK: query: create table tmp_srcpart like srcpart POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@tmp_srcpart PREHOOK: query: insert overwrite table tmp_srcpart partition (ds='2008-04-08', hr='11') select key, value from srcpart where ds='2008-04-08' and hr='11' PREHOOK: type: QUERY PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Output: default@tmp_srcpart@ds=2008-04-08/hr=11 POSTHOOK: query: insert overwrite table tmp_srcpart partition (ds='2008-04-08', hr='11') select key, value from srcpart where ds='2008-04-08' and hr='11' POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@tmp_srcpart@ds=2008-04-08/hr=11 POSTHOOK: Lineage: tmp_srcpart PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: tmp_srcpart PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: explain create table tmp_unionall as SELECT count(1) as counts, key, value FROM ( SELECT key, value FROM srcpart a WHERE a.ds='2008-04-08' and a.hr='11' UNION ALL SELECT key, key as value FROM ( SELECT distinct key FROM ( SELECT key, value FROM tmp_srcpart a WHERE a.ds='2008-04-08' and a.hr='11' UNION ALL SELECT key, value FROM tmp_srcpart b WHERE b.ds='2008-04-08' and b.hr='11' )t ) master_table ) a GROUP BY key, value PREHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: query: explain create table tmp_unionall as SELECT count(1) as counts, key, value FROM ( SELECT key, value FROM srcpart a WHERE a.ds='2008-04-08' and a.hr='11' UNION ALL SELECT key, key as value FROM ( SELECT distinct key FROM ( SELECT key, value FROM tmp_srcpart a WHERE a.ds='2008-04-08' and a.hr='11' UNION ALL SELECT key, value FROM tmp_srcpart b WHERE b.ds='2008-04-08' and b.hr='11' )t ) master_table ) a GROUP BY key, value POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Lineage: tmp_srcpart PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: tmp_srcpart PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] ABSTRACT SYNTAX TREE: (TOK_CREATETABLE (TOK_TABNAME tmp_unionall) TOK_LIKETABLE (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME srcpart) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (= (. (TOK_TABLE_OR_COL a) ds) '2008-04-08') (= (. (TOK_TABLE_OR_COL a) hr) '11'))))) (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp_srcpart) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (= (. (TOK_TABLE_OR_COL a) ds) '2008-04-08') (= (. (TOK_TABLE_OR_COL a) hr) '11'))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp_srcpart) b)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_WHERE (and (= (. (TOK_TABLE_OR_COL b) ds) '2008-04-08') (= (. (TOK_TABLE_OR_COL b) hr) '11')))))) t)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECTDI (TOK_SELEXPR (TOK_TABLE_OR_COL key))))) master_table)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL key) value))))) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1) counts) (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL value))) (TOK_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL value))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 Stage-6 depends on stages: Stage-0 Stage-3 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: null-subquery2:a-subquery2:master_table-subquery1:t-subquery1:a TableScan alias: a Select Operator expressions: expr: key type: string expr: value type: string outputColumnNames: _col0, _col1 Union Select Operator expressions: expr: _col0 type: string outputColumnNames: _col0 Group By Operator bucketGroup: false keys: expr: _col0 type: string mode: hash outputColumnNames: _col0 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + Map-reduce partition columns: expr: _col0 type: string tag: -1 null-subquery2:a-subquery2:master_table-subquery2:t-subquery2:b TableScan alias: b Select Operator expressions: expr: key type: string expr: value type: string outputColumnNames: _col0, _col1 Union Select Operator expressions: expr: _col0 type: string outputColumnNames: _col0 Group By Operator bucketGroup: false keys: expr: _col0 type: string mode: hash outputColumnNames: _col0 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: mergepartial outputColumnNames: _col0 Select Operator expressions: expr: _col0 type: string outputColumnNames: _col0 Select Operator expressions: expr: _col0 type: string expr: _col0 type: string outputColumnNames: _col0, _col1 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: #### A masked pattern was here #### TableScan Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: string outputColumnNames: _col0, _col1 Group By Operator aggregations: expr: count(1) bucketGroup: false keys: expr: _col0 type: string expr: _col1 type: string mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string sort order: ++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 type: string tag: -1 value expressions: expr: _col2 type: bigint null-subquery1:a-subquery1:a TableScan alias: a Select Operator expressions: expr: key type: string expr: value type: string outputColumnNames: _col0, _col1 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: string outputColumnNames: _col0, _col1 Group By Operator aggregations: expr: count(1) bucketGroup: false keys: expr: _col0 type: string expr: _col1 type: string mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string sort order: ++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 type: string tag: -1 value expressions: expr: _col2 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string mode: mergepartial outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col2 type: bigint expr: _col0 type: string expr: _col1 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat name: default.tmp_unionall Stage: Stage-0 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-6 Create Table Operator: Create Table columns: counts bigint, key string, value string if not exists: false input format: org.apache.hadoop.mapred.TextInputFormat # buckets: -1 output format: org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat name: tmp_unionall isExternal: false Stage: Stage-3 Stats-Aggr Operator