HIVE-11698: Add additional test for PointLookupOptimizer (Jesus Camacho Rodriguez, reviewed by Hari Sankar Sivarama Subramaniyan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/dbdd6116 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/dbdd6116 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/dbdd6116 Branch: refs/heads/beeline-cli Commit: dbdd6116bd9e25bdb5112d21fd40ec09d7f39adc Parents: f2056a1 Author: Jesus Camacho Rodriguez <jcama...@apache.org> Authored: Wed Sep 2 08:35:27 2015 +0200 Committer: Jesus Camacho Rodriguez <jcama...@apache.org> Committed: Wed Sep 2 08:35:37 2015 +0200 ---------------------------------------------------------------------- .../test/queries/clientpositive/pointlookup3.q | 41 + .../results/clientpositive/pointlookup3.q.out | 1394 ++++++++++++++++++ 2 files changed, 1435 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/dbdd6116/ql/src/test/queries/clientpositive/pointlookup3.q ---------------------------------------------------------------------- diff --git a/ql/src/test/queries/clientpositive/pointlookup3.q b/ql/src/test/queries/clientpositive/pointlookup3.q new file mode 100644 index 0000000..3daa94b --- /dev/null +++ b/ql/src/test/queries/clientpositive/pointlookup3.q @@ -0,0 +1,41 @@ +drop table pcr_t1; + +create table pcr_t1 (key int, value string) partitioned by (ds1 string, ds2 string); +insert overwrite table pcr_t1 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key; +insert overwrite table pcr_t1 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key; +insert overwrite table pcr_t1 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key; + +set hive.optimize.point.lookup.min=2; +set hive.optimize.point.lookup.extract=true; + +explain extended +select key, value, ds1, ds2 +from pcr_t1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2; + +explain extended +select key, value, ds1, ds2 +from pcr_t1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2; + +explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t1.key; + +explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t1.key; + +explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1; + +drop table pcr_t1; http://git-wip-us.apache.org/repos/asf/hive/blob/dbdd6116/ql/src/test/results/clientpositive/pointlookup3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/pointlookup3.q.out b/ql/src/test/results/clientpositive/pointlookup3.q.out new file mode 100644 index 0000000..4cfb97e --- /dev/null +++ b/ql/src/test/results/clientpositive/pointlookup3.q.out @@ -0,0 +1,1394 @@ +PREHOOK: query: drop table pcr_t1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table pcr_t1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table pcr_t1 (key int, value string) partitioned by (ds1 string, ds2 string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@pcr_t1 +POSTHOOK: query: create table pcr_t1 (key int, value string) partitioned by (ds1 string, ds2 string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@pcr_t1 +PREHOOK: query: insert overwrite table pcr_t1 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: query: insert overwrite table pcr_t1 partition (ds1='2000-04-08', ds2='2001-04-08') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1@ds1=2000-04-08/ds2=2001-04-08 +POSTHOOK: Lineage: pcr_t1 PARTITION(ds1=2000-04-08,ds2=2001-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1 PARTITION(ds1=2000-04-08,ds2=2001-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: query: insert overwrite table pcr_t1 partition (ds1='2000-04-09', ds2='2001-04-09') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1@ds1=2000-04-09/ds2=2001-04-09 +POSTHOOK: Lineage: pcr_t1 PARTITION(ds1=2000-04-09,ds2=2001-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1 PARTITION(ds1=2000-04-09,ds2=2001-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table pcr_t1 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@pcr_t1@ds1=2000-04-10/ds2=2001-04-10 +POSTHOOK: query: insert overwrite table pcr_t1 partition (ds1='2000-04-10', ds2='2001-04-10') select * from src where key < 20 order by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@pcr_t1@ds1=2000-04-10/ds2=2001-04-10 +POSTHOOK: Lineage: pcr_t1 PARTITION(ds1=2000-04-10,ds2=2001-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: pcr_t1 PARTITION(ds1=2000-04-10,ds2=2001-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1 +where (ds1='2000-04-08' and key=1) or (ds1='2000-04-09' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + pcr_t1 + 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_SELEXPR + TOK_TABLE_OR_COL + ds1 + TOK_SELEXPR + TOK_TABLE_OR_COL + ds2 + TOK_WHERE + or + and + = + TOK_TABLE_OR_COL + ds1 + '2000-04-08' + = + TOK_TABLE_OR_COL + key + 1 + and + = + TOK_TABLE_OR_COL + ds1 + '2000-04-09' + = + TOK_TABLE_OR_COL + key + 2 + TOK_ORDERBY + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + key + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + value + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + ds1 + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + ds2 + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: pcr_t1 + Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (struct(ds1,key)) IN (const struct('2000-04-08',1), const struct('2000-04-09',2)) (type: boolean) + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order: ++++ + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + tag: -1 + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1] + /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [pcr_t1] + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select key, value, ds1, ds2 +from pcr_t1 +where (ds1='2000-04-08' and ds2='2001-04-08' and key=1) or (ds1='2000-04-09' and ds2='2001-04-08' and key=2) +order by key, value, ds1, ds2 +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + pcr_t1 + 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_SELEXPR + TOK_TABLE_OR_COL + ds1 + TOK_SELEXPR + TOK_TABLE_OR_COL + ds2 + TOK_WHERE + or + and + and + = + TOK_TABLE_OR_COL + ds1 + '2000-04-08' + = + TOK_TABLE_OR_COL + ds2 + '2001-04-08' + = + TOK_TABLE_OR_COL + key + 1 + and + and + = + TOK_TABLE_OR_COL + ds1 + '2000-04-09' + = + TOK_TABLE_OR_COL + ds2 + '2001-04-08' + = + TOK_TABLE_OR_COL + key + 2 + TOK_ORDERBY + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + key + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + value + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + ds1 + TOK_TABSORTCOLNAMEASC + TOK_TABLE_OR_COL + ds2 + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: pcr_t1 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = 1) (type: boolean) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: value (type: string), ds1 (type: string) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: 1 (type: int), _col1 (type: string), _col2 (type: string), '2001-04-08' (type: string) + sort order: ++++ + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + tag: -1 + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [pcr_t1] + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: 1 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), '2001-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t1.key +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds2='2001-04-08' +order by t1.key +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_JOIN + TOK_TABREF + TOK_TABNAME + pcr_t1 + t1 + TOK_TABREF + TOK_TABNAME + pcr_t1 + t2 + and + and + = + . + TOK_TABLE_OR_COL + t1 + key + . + TOK_TABLE_OR_COL + t2 + key + = + . + TOK_TABLE_OR_COL + t1 + ds1 + '2000-04-08' + = + . + TOK_TABLE_OR_COL + t2 + ds2 + '2001-04-08' + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_ALLCOLREF + TOK_ORDERBY + TOK_TABSORTCOLNAMEASC + . + TOK_TABLE_OR_COL + t1 + key + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: value (type: string), ds2 (type: string) + auto parallelism: false + TableScan + alias: t2 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: value (type: string), ds1 (type: string) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [t1, t2] + Needs Tagging: true + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0, _col1, _col3, _col7, _col8, _col9 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col7 (type: int), _col8 (type: string), _col9 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4,_col5,_col6 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + GatherStats: false + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col6 (type: string) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10003 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4,_col5,_col6 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4,_col5,_col6 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Truncated Path -> Alias: +#### A masked pattern was here #### + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), VALUE._col5 (type: string), '2001-04-08' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t1.key +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +on t1.key=t2.key and t1.ds1='2000-04-08' and t2.ds1='2000-04-09' +order by t1.key +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_JOIN + TOK_TABREF + TOK_TABNAME + pcr_t1 + t1 + TOK_TABREF + TOK_TABNAME + pcr_t1 + t2 + and + and + = + . + TOK_TABLE_OR_COL + t1 + key + . + TOK_TABLE_OR_COL + t2 + key + = + . + TOK_TABLE_OR_COL + t1 + ds1 + '2000-04-08' + = + . + TOK_TABLE_OR_COL + t2 + ds1 + '2000-04-09' + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_ALLCOLREF + TOK_ORDERBY + TOK_TABSORTCOLNAMEASC + . + TOK_TABLE_OR_COL + t1 + key + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: value (type: string), ds2 (type: string) + auto parallelism: false + TableScan + alias: t2 + Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: value (type: string), ds2 (type: string) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [t1] + /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [t2] + Needs Tagging: true + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0, _col1, _col3, _col7, _col8, _col10 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col7 (type: int), _col8 (type: string), _col10 (type: string) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4,_col5,_col7 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + GatherStats: false + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: string), _col7 (type: string) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10003 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4,_col5,_col7 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col3,_col4,_col5,_col7 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Truncated Path -> Alias: +#### A masked pattern was here #### + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: string), '2000-04-09' (type: string), VALUE._col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join JOIN[4][tables = [t1, t2]] in Stage 'Stage-1:MAPRED' is a cross product +PREHOOK: query: explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * +from pcr_t1 t1 join pcr_t1 t2 +where (t1.ds1='2000-04-08' and t2.key=1) or (t1.ds1='2000-04-09' and t2.key=2) +order by t2.key, t2.value, t1.ds1 +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_JOIN + TOK_TABREF + TOK_TABNAME + pcr_t1 + t1 + TOK_TABREF + TOK_TABNAME + pcr_t1 + t2 + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_ALLCOLREF + TOK_WHERE + or + and + = + . + TOK_TABLE_OR_COL + t1 + ds1 + '2000-04-08' + = + . + TOK_TABLE_OR_COL + t2 + key + 1 + and + = + . + TOK_TABLE_OR_COL + t1 + ds1 + '2000-04-09' + = + . + TOK_TABLE_OR_COL + t2 + key + 2 + TOK_ORDERBY + TOK_TABSORTCOLNAMEASC + . + TOK_TABLE_OR_COL + t2 + key + TOK_TABSORTCOLNAMEASC + . + TOK_TABLE_OR_COL + t2 + value + TOK_TABSORTCOLNAMEASC + . + TOK_TABLE_OR_COL + t1 + ds1 + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Reduce Output Operator + sort order: + Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE + tag: 0 + value expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + auto parallelism: false + TableScan + alias: t2 + Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Reduce Output Operator + sort order: + Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE + tag: 1 + value expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-08 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-08 + ds2 2001-04-08 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-09 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-09 + ds2 2001-04-09 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 +#### A masked pattern was here #### + Partition + base file name: ds2=2001-04-10 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds1 2000-04-10 + ds2 2001-04-10 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + numFiles 1 + numRows 20 + partition_columns ds1/ds2 + partition_columns.types string:string + rawDataSize 160 + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 180 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types int:string +#### A masked pattern was here #### + name default.pcr_t1 + partition_columns ds1/ds2 + partition_columns.types string:string + serialization.ddl struct pcr_t1 { i32 key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.pcr_t1 + name: default.pcr_t1 + Truncated Path -> Alias: + /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [t1, t2] + /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [t1, t2] + /pcr_t1/ds1=2000-04-10/ds2=2001-04-10 [t2] + Needs Tagging: true + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col7, _col8, _col9, _col10 + Statistics: Num rows: 66 Data size: 528 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((_col2) IN ('2000-04-08', '2000-04-09') and (struct(_col7,_col2)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09'))) (type: boolean) + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col7 (type: int), _col8 (type: string), _col9 (type: string), _col10 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int,string,string,string,int,string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + GatherStats: false + Reduce Output Operator + key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string) + sort order: +++ + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string) + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10003 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int,string,string,string,int,string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int,string,string,string,int,string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Truncated Path -> Alias: +#### A masked pattern was here #### + Needs Tagging: false + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7 + columns.types int:string:string:string:int:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: drop table pcr_t1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@pcr_t1 +PREHOOK: Output: default@pcr_t1 +POSTHOOK: query: drop table pcr_t1 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@pcr_t1 +POSTHOOK: Output: default@pcr_t1