http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/stats_list_bucket.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/stats_list_bucket.q.out b/ql/src/test/results/clientpositive/stats_list_bucket.q.out new file mode 100644 index 0000000..c34c414 --- /dev/null +++ b/ql/src/test/results/clientpositive/stats_list_bucket.q.out @@ -0,0 +1,189 @@ +PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) + +drop table stats_list_bucket +PREHOOK: type: DROPTABLE +POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) + +drop table stats_list_bucket +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table stats_list_bucket_1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table stats_list_bucket_1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table stats_list_bucket ( + c1 string, + c2 string +) partitioned by (ds string, hr string) +skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82')) +stored as directories +stored as rcfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@stats_list_bucket +POSTHOOK: query: create table stats_list_bucket ( + c1 string, + c2 string +) partitioned by (ds string, hr string) +skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82')) +stored as directories +stored as rcfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@stats_list_bucket +PREHOOK: query: -- Try partitioned table with list bucketing. +-- The stats should show 500 rows loaded, as many rows as the src table has. + +insert overwrite table stats_list_bucket partition (ds = '2008-04-08', hr = '11') + select key, value from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@stats_list_bucket@ds=2008-04-08/hr=11 +POSTHOOK: query: -- Try partitioned table with list bucketing. +-- The stats should show 500 rows loaded, as many rows as the src table has. + +insert overwrite table stats_list_bucket partition (ds = '2008-04-08', hr = '11') + select key, value from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@stats_list_bucket@ds=2008-04-08/hr=11 +POSTHOOK: Lineage: stats_list_bucket PARTITION(ds=2008-04-08,hr=11).c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: stats_list_bucket PARTITION(ds=2008-04-08,hr=11).c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: desc formatted stats_list_bucket partition (ds = '2008-04-08', hr = '11') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@stats_list_bucket +POSTHOOK: query: desc formatted stats_list_bucket partition (ds = '2008-04-08', hr = '11') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@stats_list_bucket +# col_name data_type comment + +c1 string +c2 string + +# Partition Information +# col_name data_type comment + +ds string +hr string + +# Detailed Partition Information +Partition Value: [2008-04-08, 11] +Database: default +Table: stats_list_bucket +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 + numRows 500 + rawDataSize 4812 + totalSize 5522 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Stored As SubDirectories: Yes +Skewed Columns: [c1, c2] +Skewed Values: [[466, val_466], [287, val_287], [82, val_82]] +#### A masked pattern was here #### +Skewed Value to Truncated Path: {[466, val_466]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=466/c2=val_466, [82, val_82]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=82/c2=val_82, [287, val_287]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=287/c2=val_287} +Storage Desc Params: + serialization.format 1 +PREHOOK: query: -- Also try non-partitioned table with list bucketing. +-- Stats should show the same number of rows. + +create table stats_list_bucket_1 ( + c1 string, + c2 string +) +skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82')) +stored as directories +stored as rcfile +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@stats_list_bucket_1 +POSTHOOK: query: -- Also try non-partitioned table with list bucketing. +-- Stats should show the same number of rows. + +create table stats_list_bucket_1 ( + c1 string, + c2 string +) +skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82')) +stored as directories +stored as rcfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@stats_list_bucket_1 +PREHOOK: query: insert overwrite table stats_list_bucket_1 + select key, value from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@stats_list_bucket_1 +POSTHOOK: query: insert overwrite table stats_list_bucket_1 + select key, value from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@stats_list_bucket_1 +POSTHOOK: Lineage: stats_list_bucket_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: stats_list_bucket_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: desc formatted stats_list_bucket_1 +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@stats_list_bucket_1 +POSTHOOK: query: desc formatted stats_list_bucket_1 +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@stats_list_bucket_1 +# col_name data_type comment + +c1 string +c2 string + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} + numFiles 4 + numRows 500 + rawDataSize 4812 + totalSize 5522 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Stored As SubDirectories: Yes +Skewed Columns: [c1, c2] +Skewed Values: [[466, val_466], [287, val_287], [82, val_82]] +#### A masked pattern was here #### +Skewed Value to Truncated Path: {[466, val_466]=/stats_list_bucket_1/c1=466/c2=val_466, [287, val_287]=/stats_list_bucket_1/c1=287/c2=val_287, [82, val_82]=/stats_list_bucket_1/c1=82/c2=val_82} +Storage Desc Params: + serialization.format 1 +PREHOOK: query: drop table stats_list_bucket +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@stats_list_bucket +PREHOOK: Output: default@stats_list_bucket +POSTHOOK: query: drop table stats_list_bucket +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@stats_list_bucket +POSTHOOK: Output: default@stats_list_bucket +PREHOOK: query: drop table stats_list_bucket_1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@stats_list_bucket_1 +PREHOOK: Output: default@stats_list_bucket_1 +POSTHOOK: query: drop table stats_list_bucket_1 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@stats_list_bucket_1 +POSTHOOK: Output: default@stats_list_bucket_1
http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out b/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out deleted file mode 100644 index 652acbb..0000000 --- a/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out +++ /dev/null @@ -1,220 +0,0 @@ -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - -desc function str_to_map -PREHOOK: type: DESCFUNCTION -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - -desc function str_to_map -POSTHOOK: type: DESCFUNCTION -str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text -PREHOOK: query: desc function extended str_to_map -PREHOOK: type: DESCFUNCTION -POSTHOOK: query: desc function extended str_to_map -POSTHOOK: type: DESCFUNCTION -str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text -Split text into key-value pairs using two delimiters. The first delimiter seperates pairs, and the second delimiter sperates key and value. If only one parameter is given, default delimiters are used: ',' as delimiter1 and '=' as delimiter2. -PREHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 -PREHOOK: type: QUERY -POSTHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: str_to_map('a=1,b=2,c=3',',','=')['a'] (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -1 -1 -1 -PREHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3 -PREHOOK: type: QUERY -POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: str_to_map('a:1,b:2,c:3') (type: map<string,string>) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -{"b":"2","a":"1","c":"3"} -{"b":"2","a":"1","c":"3"} -{"b":"2","a":"1","c":"3"} -PREHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 -PREHOOK: type: QUERY -POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map<string,string>) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -{"b":"2","a":"1","c":"3"} -{"b":"2","a":"1","c":"3"} -{"b":"2","a":"1","c":"3"} -PREHOOK: query: explain select str_to_map(t.ss,',',':')['a'] -from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t -limit 3 -PREHOOK: type: QUERY -POSTHOOK: query: explain select str_to_map(t.ss,',',':')['a'] -from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t -limit 3 -POSTHOOK: type: QUERY -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: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'a:1,b:2,c:3' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Transform Operator - command: cat - output info: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: str_to_map(_col0,',',':')['a'] (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - ListSink - -PREHOOK: query: select str_to_map(t.ss,',',':')['a'] -from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t -limit 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map(t.ss,',',':')['a'] -from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t -limit 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -1 -1 -1 -PREHOOK: query: drop table tbl_s2m -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table tbl_s2m -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows) -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@tbl_s2m -POSTHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows) -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tbl_s2m -POSTHOOK: Lineage: tbl_s2m.t SIMPLE [] -PREHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_s2m -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_s2m -#### A masked pattern was here #### -444 -444 -444 -PREHOOK: query: drop table tbl_s2m -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@tbl_s2m -PREHOOK: Output: default@tbl_s2m -POSTHOOK: query: drop table tbl_s2m -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@tbl_s2m -POSTHOOK: Output: default@tbl_s2m http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/str_to_map.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/str_to_map.q.java1.8.out b/ql/src/test/results/clientpositive/str_to_map.q.java1.8.out deleted file mode 100644 index 23b0cbb..0000000 --- a/ql/src/test/results/clientpositive/str_to_map.q.java1.8.out +++ /dev/null @@ -1,219 +0,0 @@ -PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - -desc function str_to_map -PREHOOK: type: DESCFUNCTION -POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT - -desc function str_to_map -POSTHOOK: type: DESCFUNCTION -str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text -PREHOOK: query: desc function extended str_to_map -PREHOOK: type: DESCFUNCTION -POSTHOOK: query: desc function extended str_to_map -POSTHOOK: type: DESCFUNCTION -str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text -Split text into key-value pairs using two delimiters. The first delimiter seperates pairs, and the second delimiter sperates key and value. If only one parameter is given, default delimiters are used: ',' as delimiter1 and '=' as delimiter2. -PREHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 -PREHOOK: type: QUERY -POSTHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: str_to_map('a=1,b=2,c=3',',','=')['a'] (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -1 -1 -1 -PREHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3 -PREHOOK: type: QUERY -POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: str_to_map('a:1,b:2,c:3') (type: map<string,string>) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 460000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -{"a":"1","b":"2","c":"3"} -{"a":"1","b":"2","c":"3"} -{"a":"1","b":"2","c":"3"} -PREHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 -PREHOOK: type: QUERY -POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map<string,string>) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 460000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE - ListSink - -PREHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -{"a":"1","b":"2","c":"3"} -{"a":"1","b":"2","c":"3"} -{"a":"1","b":"2","c":"3"} -PREHOOK: query: explain select str_to_map(t.ss,',',':')['a'] -from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t -limit 3 -PREHOOK: type: QUERY -POSTHOOK: query: explain select str_to_map(t.ss,',',':')['a'] -from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t -limit 3 -POSTHOOK: type: QUERY -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: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: 'a:1,b:2,c:3' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Transform Operator - command: cat - output info: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: str_to_map(_col0,',',':')['a'] (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 3 - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: 3 - Processor Tree: - ListSink - -PREHOOK: query: select str_to_map(t.ss,',',':')['a'] -from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t -limit 3 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map(t.ss,',',':')['a'] -from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t -limit 3 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -1 -1 -1 -PREHOOK: query: drop table tbl_s2m -PREHOOK: type: DROPTABLE -POSTHOOK: query: drop table tbl_s2m -POSTHOOK: type: DROPTABLE -PREHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows) -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@tbl_s2m -POSTHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows) -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tbl_s2m -PREHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl_s2m -#### A masked pattern was here #### -POSTHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl_s2m -#### A masked pattern was here #### -444 -444 -444 -PREHOOK: query: drop table tbl_s2m -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@tbl_s2m -PREHOOK: Output: default@tbl_s2m -POSTHOOK: query: drop table tbl_s2m -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@tbl_s2m -POSTHOOK: Output: default@tbl_s2m http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/str_to_map.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/str_to_map.q.out b/ql/src/test/results/clientpositive/str_to_map.q.out new file mode 100644 index 0000000..30c98db --- /dev/null +++ b/ql/src/test/results/clientpositive/str_to_map.q.out @@ -0,0 +1,216 @@ +PREHOOK: query: desc function str_to_map +PREHOOK: type: DESCFUNCTION +POSTHOOK: query: desc function str_to_map +POSTHOOK: type: DESCFUNCTION +str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text +PREHOOK: query: desc function extended str_to_map +PREHOOK: type: DESCFUNCTION +POSTHOOK: query: desc function extended str_to_map +POSTHOOK: type: DESCFUNCTION +str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text +Split text into key-value pairs using two delimiters. The first delimiter seperates pairs, and the second delimiter sperates key and value. If only one parameter is given, default delimiters are used: ',' as delimiter1 and '=' as delimiter2. +PREHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 +PREHOOK: type: QUERY +POSTHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: str_to_map('a=1,b=2,c=3',',','=')['a'] (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE + ListSink + +PREHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +1 +1 +1 +PREHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3 +PREHOOK: type: QUERY +POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: str_to_map('a:1,b:2,c:3') (type: map<string,string>) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE + ListSink + +PREHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +{"a":"1","b":"2","c":"3"} +{"a":"1","b":"2","c":"3"} +{"a":"1","b":"2","c":"3"} +PREHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 +PREHOOK: type: QUERY +POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map<string,string>) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE + ListSink + +PREHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +{"a":"1","b":"2","c":"3"} +{"a":"1","b":"2","c":"3"} +{"a":"1","b":"2","c":"3"} +PREHOOK: query: explain select str_to_map(t.ss,',',':')['a'] +from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t +limit 3 +PREHOOK: type: QUERY +POSTHOOK: query: explain select str_to_map(t.ss,',',':')['a'] +from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t +limit 3 +POSTHOOK: type: QUERY +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: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 'a:1,b:2,c:3' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Transform Operator + command: cat + output info: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: str_to_map(_col0,',',':')['a'] (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE + Limit + Number of rows: 3 + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 3 + Processor Tree: + ListSink + +PREHOOK: query: select str_to_map(t.ss,',',':')['a'] +from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t +limit 3 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: select str_to_map(t.ss,',',':')['a'] +from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t +limit 3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +1 +1 +1 +PREHOOK: query: drop table tbl_s2m +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table tbl_s2m +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows) +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl_s2m +POSTHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows) +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl_s2m +POSTHOOK: Lineage: tbl_s2m.t SIMPLE [] +PREHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl_s2m +#### A masked pattern was here #### +POSTHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl_s2m +#### A masked pattern was here #### +444 +444 +444 +PREHOOK: query: drop table tbl_s2m +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@tbl_s2m +PREHOOK: Output: default@tbl_s2m +POSTHOOK: query: drop table tbl_s2m +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@tbl_s2m +POSTHOOK: Output: default@tbl_s2m http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out b/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out deleted file mode 100644 index 279843b..0000000 --- a/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out +++ /dev/null @@ -1,999 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS --- JAVA_VERSION_SPECIFIC_OUTPUT - -CREATE TABLE src_4( - key STRING, - value STRING -) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src_4 -POSTHOOK: query: -- SORT_QUERY_RESULTS --- JAVA_VERSION_SPECIFIC_OUTPUT - -CREATE TABLE src_4( - key STRING, - value STRING -) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_4 -RUN: Stage-0:DDL -PREHOOK: query: CREATE TABLE src_5( - key STRING, - value STRING -) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src_5 -POSTHOOK: query: CREATE TABLE src_5( - key STRING, - value STRING -) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_5 -RUN: Stage-0:DDL -Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: explain -from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -PREHOOK: type: QUERY -POSTHOOK: query: explain -from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-10 is a root stage - Stage-2 depends on stages: Stage-10 - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 - Stage-6 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-6 - Stage-7 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: 0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string), value (type: string) - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - TableScan - alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col5 is null (type: boolean) - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - 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: default.src_5 - - Stage: Stage-1 - 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: default.src_5 - - Stage: Stage-5 - Stats-Aggr Operator - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: key (type: string), value (type: string) - sort order: ++ - Map-reduce partition columns: key (type: string), value (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 key (type: string), value (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - 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: default.src_4 - - 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: default.src_4 - - Stage: Stage-7 - Stats-Aggr Operator - -Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_4 -PREHOOK: Output: default@src_5 -POSTHOOK: query: from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_4 -POSTHOOK: Output: default@src_5 -POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] -RUN: Stage-10:MAPRED -RUN: Stage-2:MAPRED -RUN: Stage-3:MAPRED -RUN: Stage-6:MAPRED -RUN: Stage-4:MAPRED -RUN: Stage-0:MOVE -RUN: Stage-1:MOVE -RUN: Stage-7:STATS -RUN: Stage-5:STATS -PREHOOK: query: select * from src_4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_4 -#### A masked pattern was here #### -90 val_90 -90 val_90 -90 val_90 -92 val_92 -95 val_95 -95 val_95 -96 val_96 -97 val_97 -97 val_97 -98 val_98 -98 val_98 -PREHOOK: query: select * from src_5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_5 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -10 val_10 -100 val_100 -100 val_100 -103 val_103 -103 val_103 -104 val_104 -104 val_104 -105 val_105 -11 val_11 -111 val_111 -113 val_113 -113 val_113 -114 val_114 -116 val_116 -118 val_118 -118 val_118 -119 val_119 -119 val_119 -119 val_119 -12 val_12 -12 val_12 -120 val_120 -120 val_120 -125 val_125 -125 val_125 -126 val_126 -128 val_128 -128 val_128 -128 val_128 -129 val_129 -129 val_129 -131 val_131 -133 val_133 -134 val_134 -134 val_134 -136 val_136 -137 val_137 -137 val_137 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -143 val_143 -145 val_145 -146 val_146 -146 val_146 -149 val_149 -149 val_149 -15 val_15 -15 val_15 -150 val_150 -152 val_152 -152 val_152 -153 val_153 -155 val_155 -156 val_156 -157 val_157 -158 val_158 -160 val_160 -162 val_162 -163 val_163 -164 val_164 -164 val_164 -165 val_165 -165 val_165 -166 val_166 -167 val_167 -167 val_167 -167 val_167 -168 val_168 -169 val_169 -169 val_169 -169 val_169 -169 val_169 -17 val_17 -170 val_170 -172 val_172 -172 val_172 -174 val_174 -174 val_174 -175 val_175 -175 val_175 -176 val_176 -176 val_176 -177 val_177 -178 val_178 -179 val_179 -179 val_179 -18 val_18 -18 val_18 -180 val_180 -181 val_181 -183 val_183 -186 val_186 -187 val_187 -187 val_187 -187 val_187 -189 val_189 -19 val_19 -190 val_190 -191 val_191 -191 val_191 -192 val_192 -193 val_193 -193 val_193 -193 val_193 -194 val_194 -195 val_195 -195 val_195 -196 val_196 -197 val_197 -197 val_197 -199 val_199 -199 val_199 -199 val_199 -2 val_2 -Warning: Map Join MAPJOIN[55][bigTable=b] in task 'Stage-13:MAPRED' is a cross product -Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: explain -from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -PREHOOK: type: QUERY -POSTHOOK: query: explain -from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-10 is a root stage - Stage-14 depends on stages: Stage-10 , consists of Stage-17, Stage-2 - Stage-17 has a backup stage: Stage-2 - Stage-13 depends on stages: Stage-17 - Stage-15 depends on stages: Stage-2, Stage-13 - Stage-12 depends on stages: Stage-15 - Stage-0 depends on stages: Stage-12 - Stage-7 depends on stages: Stage-0 - Stage-16 depends on stages: Stage-2, Stage-13 - Stage-4 depends on stages: Stage-16 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 - Stage-2 - -STAGE PLANS: - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key > '2') and key is null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: 0 (type: bigint) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-14 - Conditional Operator - - Stage: Stage-17 - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME - TableScan - HashTable Sink Operator - keys: - 0 - 1 - - Stage: Stage-13 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Local Work: - Map Reduce Local Work - - Stage: Stage-15 - Map Reduce Local Work - Alias -> Map Local Tables: - sq_1:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - sq_1:a - TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key > '9') and value is not null) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 key (type: string), value (type: string) - 1 _col0 (type: string), _col1 (type: string) - - Stage: Stage-12 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 key (type: string), value (type: string) - 1 _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - 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: default.src_4 - Local Work: - Map Reduce Local Work - - 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: default.src_4 - - Stage: Stage-7 - Stats-Aggr Operator - - Stage: Stage-16 - Map Reduce Local Work - Alias -> Map Local Tables: - sq_2:s1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - sq_2:s1 - TableScan - alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key > '2') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col5 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col5 is null (type: boolean) - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE - 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: default.src_5 - - Stage: Stage-1 - 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: default.src_5 - - Stage: Stage-5 - Stats-Aggr Operator - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: key (type: string), value (type: string) - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Semi Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - -Warning: Map Join MAPJOIN[55][bigTable=b] in task 'Stage-13:MAPRED' is a cross product -Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@src_4 -PREHOOK: Output: default@src_5 -POSTHOOK: query: from src b -INSERT OVERWRITE TABLE src_4 - select * - where b.key in - (select a.key - from src a - where b.value = a.value and a.key > '9' - ) -INSERT OVERWRITE TABLE src_5 - select * - where b.key not in ( select key from src s1 where s1.key > '2') - order by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@src_4 -POSTHOOK: Output: default@src_5 -POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ] -RUN: Stage-10:MAPRED -RUN: Stage-14:CONDITIONAL -RUN: Stage-17:MAPREDLOCAL -RUN: Stage-13:MAPRED -RUN: Stage-15:MAPREDLOCAL -RUN: Stage-16:MAPREDLOCAL -RUN: Stage-12:MAPRED -RUN: Stage-4:MAPRED -RUN: Stage-0:MOVE -RUN: Stage-1:MOVE -RUN: Stage-7:STATS -RUN: Stage-5:STATS -PREHOOK: query: select * from src_4 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_4 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_4 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_4 -#### A masked pattern was here #### -90 val_90 -90 val_90 -90 val_90 -92 val_92 -95 val_95 -95 val_95 -96 val_96 -97 val_97 -97 val_97 -98 val_98 -98 val_98 -PREHOOK: query: select * from src_5 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_5 -#### A masked pattern was here #### -POSTHOOK: query: select * from src_5 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_5 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -10 val_10 -100 val_100 -100 val_100 -103 val_103 -103 val_103 -104 val_104 -104 val_104 -105 val_105 -11 val_11 -111 val_111 -113 val_113 -113 val_113 -114 val_114 -116 val_116 -118 val_118 -118 val_118 -119 val_119 -119 val_119 -119 val_119 -12 val_12 -12 val_12 -120 val_120 -120 val_120 -125 val_125 -125 val_125 -126 val_126 -128 val_128 -128 val_128 -128 val_128 -129 val_129 -129 val_129 -131 val_131 -133 val_133 -134 val_134 -134 val_134 -136 val_136 -137 val_137 -137 val_137 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -143 val_143 -145 val_145 -146 val_146 -146 val_146 -149 val_149 -149 val_149 -15 val_15 -15 val_15 -150 val_150 -152 val_152 -152 val_152 -153 val_153 -155 val_155 -156 val_156 -157 val_157 -158 val_158 -160 val_160 -162 val_162 -163 val_163 -164 val_164 -164 val_164 -165 val_165 -165 val_165 -166 val_166 -167 val_167 -167 val_167 -167 val_167 -168 val_168 -169 val_169 -169 val_169 -169 val_169 -169 val_169 -17 val_17 -170 val_170 -172 val_172 -172 val_172 -174 val_174 -174 val_174 -175 val_175 -175 val_175 -176 val_176 -176 val_176 -177 val_177 -178 val_178 -179 val_179 -179 val_179 -18 val_18 -18 val_18 -180 val_180 -181 val_181 -183 val_183 -186 val_186 -187 val_187 -187 val_187 -187 val_187 -189 val_189 -19 val_19 -190 val_190 -191 val_191 -191 val_191 -192 val_192 -193 val_193 -193 val_193 -193 val_193 -194 val_194 -195 val_195 -195 val_195 -196 val_196 -197 val_197 -197 val_197 -199 val_199 -199 val_199 -199 val_199 -2 val_2
