Added: hive/trunk/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.8.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.8.out?rev=1647794&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.8.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.8.out Wed Dec 24 14:33:00 2014 @@ -0,0 +1,1127 @@ +PREHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge. +-- The following explains merge example used in this test case +-- DML will generated 2 partitions +-- ds=2008-04-08/hr=a1 +-- ds=2008-04-08/hr=b1 +-- without merge, each partition has more files +-- ds=2008-04-08/hr=a1 has 2 files +-- ds=2008-04-08/hr=b1 has 6 files +-- with merge each partition has more files +-- ds=2008-04-08/hr=a1 has 1 files +-- ds=2008-04-08/hr=b1 has 4 files +-- The following shows file size and name in each directory +-- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: +-- without merge +-- 155 000000_0 +-- 155 000001_0 +-- with merge +-- 254 000000_0 +-- hr=b1/key=103/value=val_103: +-- without merge +-- 99 000000_0 +-- 99 000001_0 +-- with merge +-- 142 000001_0 +-- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: +-- without merge +-- 5181 000000_0 +-- 5181 000001_0 +-- with merge +-- 5181 000000_0 +-- 5181 000001_0 +-- hr=b1/key=484/value=val_484 +-- without merge +-- 87 000000_0 +-- 87 000001_0 +-- with merge +-- 118 000002_0 + +-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) +-- SORT_QUERY_RESULTS +-- JAVA_VERSION_SPECIFIC_OUTPUT + +-- create a skewed table +create table list_bucketing_dynamic_part (key String, value String) + partitioned by (ds String, hr String) + skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103')) + stored as DIRECTORIES + STORED AS RCFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@list_bucketing_dynamic_part +POSTHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge. +-- The following explains merge example used in this test case +-- DML will generated 2 partitions +-- ds=2008-04-08/hr=a1 +-- ds=2008-04-08/hr=b1 +-- without merge, each partition has more files +-- ds=2008-04-08/hr=a1 has 2 files +-- ds=2008-04-08/hr=b1 has 6 files +-- with merge each partition has more files +-- ds=2008-04-08/hr=a1 has 1 files +-- ds=2008-04-08/hr=b1 has 4 files +-- The following shows file size and name in each directory +-- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: +-- without merge +-- 155 000000_0 +-- 155 000001_0 +-- with merge +-- 254 000000_0 +-- hr=b1/key=103/value=val_103: +-- without merge +-- 99 000000_0 +-- 99 000001_0 +-- with merge +-- 142 000001_0 +-- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME: +-- without merge +-- 5181 000000_0 +-- 5181 000001_0 +-- with merge +-- 5181 000000_0 +-- 5181 000001_0 +-- hr=b1/key=484/value=val_484 +-- without merge +-- 87 000000_0 +-- 87 000001_0 +-- with merge +-- 118 000002_0 + +-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) +-- SORT_QUERY_RESULTS +-- JAVA_VERSION_SPECIFIC_OUTPUT + +-- create a skewed table +create table list_bucketing_dynamic_part (key String, value String) + partitioned by (ds String, hr String) + skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103')) + stored as DIRECTORIES + STORED AS RCFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@list_bucketing_dynamic_part +PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. +explain extended +insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) +select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files. +explain extended +insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) +select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + srcpart + TOK_INSERT + TOK_DESTINATION + TOK_TAB + TOK_TABNAME + list_bucketing_dynamic_part + TOK_PARTSPEC + TOK_PARTVAL + ds + '2008-04-08' + TOK_PARTVAL + hr + TOK_SELECT + TOK_SELEXPR + TOK_TABLE_OR_COL + key + TOK_SELEXPR + TOK_TABLE_OR_COL + value + TOK_SELEXPR + TOK_FUNCTION + if + == + % + TOK_TABLE_OR_COL + key + 100 + 0 + 'a1' + 'b1' + TOK_WHERE + = + TOK_TABLE_OR_COL + ds + '2008-04-08' + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + Stage-2 depends on stages: Stage-0 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Static Partition Specification: ds=2008-04-08/ + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_dynamic_part + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### 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 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string 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.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### 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 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string 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.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart] + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 2008-04-08 + hr + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_dynamic_part + + Stage: Stage-2 + Stats-Aggr Operator +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) +select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08 +POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) +select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 +POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: -- check DML result +show partitions list_bucketing_dynamic_part +PREHOOK: type: SHOWPARTITIONS +PREHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: query: -- check DML result +show partitions list_bucketing_dynamic_part +POSTHOOK: type: SHOWPARTITIONS +POSTHOOK: Input: default@list_bucketing_dynamic_part +ds=2008-04-08/hr=a1 +ds=2008-04-08/hr=b1 +PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@list_bucketing_dynamic_part +# col_name data_type comment + +key string +value string + +# Partition Information +# col_name data_type comment + +ds string +hr string + +# Detailed Partition Information +Partition Value: [2008-04-08, a1] +Database: default +Table: list_bucketing_dynamic_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 2 + numRows 16 + rawDataSize 136 + totalSize 310 +#### 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: [key, value] +Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@list_bucketing_dynamic_part +# col_name data_type comment + +key string +value string + +# Partition Information +# col_name data_type comment + +ds string +hr string + +# Detailed Partition Information +Partition Value: [2008-04-08, b1] +Database: default +Table: list_bucketing_dynamic_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 6 + numRows 984 + rawDataSize 9488 + totalSize 10734 +#### 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: [key, value] +Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] +#### A masked pattern was here #### +Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103} +Storage Desc Params: + serialization.format 1 +PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files. +explain extended +insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) +select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files. +explain extended +insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) +select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + srcpart + TOK_INSERT + TOK_DESTINATION + TOK_TAB + TOK_TABNAME + list_bucketing_dynamic_part + TOK_PARTSPEC + TOK_PARTVAL + ds + '2008-04-08' + TOK_PARTVAL + hr + TOK_SELECT + TOK_SELEXPR + TOK_TABLE_OR_COL + key + TOK_SELEXPR + TOK_TABLE_OR_COL + value + TOK_SELEXPR + TOK_FUNCTION + if + == + % + TOK_TABLE_OR_COL + key + 100 + 0 + 'a1' + 'b1' + TOK_WHERE + = + TOK_TABLE_OR_COL + ds + '2008-04-08' + + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: srcpart + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Select Operator + expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 1 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Static Partition Specification: ds=2008-04-08/ + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_dynamic_part + TotalFiles: 1 + GatherStats: true + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: hr=11 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 11 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### 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 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string 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.srcpart + name: default.srcpart +#### A masked pattern was here #### + Partition + base file name: hr=12 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 2008-04-08 + hr 12 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + numFiles 1 + numRows 500 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 5312 + serialization.ddl struct srcpart { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 5812 +#### 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 'default','default' + columns.types string:string +#### A masked pattern was here #### + name default.srcpart + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct srcpart { string 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.srcpart + name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart] + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 2008-04-08 + hr + replace: true +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_dynamic_part + + Stage: Stage-2 + Stats-Aggr Operator +#### A masked pattern was here #### + + Stage: Stage-3 + Merge File Operator + Map Operator Tree: + RCFile Merge Operator + merge level: block + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_dynamic_part + name: default.list_bucketing_dynamic_part + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + Truncated Path -> Alias: +#### A masked pattern was here #### + + Stage: Stage-5 + Merge File Operator + Map Operator Tree: + RCFile Merge Operator + merge level: block + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_dynamic_part + name: default.list_bucketing_dynamic_part + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + Truncated Path -> Alias: +#### A masked pattern was here #### + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) +select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08 +POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr) +select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 +POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: -- check DML result +show partitions list_bucketing_dynamic_part +PREHOOK: type: SHOWPARTITIONS +PREHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: query: -- check DML result +show partitions list_bucketing_dynamic_part +POSTHOOK: type: SHOWPARTITIONS +POSTHOOK: Input: default@list_bucketing_dynamic_part +ds=2008-04-08/hr=a1 +ds=2008-04-08/hr=b1 +PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@list_bucketing_dynamic_part +# col_name data_type comment + +key string +value string + +# Partition Information +# col_name data_type comment + +ds string +hr string + +# Detailed Partition Information +Partition Value: [2008-04-08, a1] +Database: default +Table: list_bucketing_dynamic_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 16 + rawDataSize 136 + totalSize 254 +#### 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: [key, value] +Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@list_bucketing_dynamic_part +# col_name data_type comment + +key string +value string + +# Partition Information +# col_name data_type comment + +ds string +hr string + +# Detailed Partition Information +Partition Value: [2008-04-08, b1] +Database: default +Table: list_bucketing_dynamic_part +#### A masked pattern was here #### +Protect Mode: None +#### A masked pattern was here #### +Partition Parameters: + COLUMN_STATS_ACCURATE true + numFiles 4 + numRows 984 + rawDataSize 9488 + totalSize 10622 +#### 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: [key, value] +Skewed Values: [[484, val_484], [51, val_14], [103, val_103]] +#### A masked pattern was here #### +Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103} +Storage Desc Params: + serialization.format 1 +PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +1000 +PREHOOK: query: select count(*) from list_bucketing_dynamic_part +PREHOOK: type: QUERY +PREHOOK: Input: default@list_bucketing_dynamic_part +PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 +PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from list_bucketing_dynamic_part +POSTHOOK: type: QUERY +POSTHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 +POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 +#### A masked pattern was here #### +1000 +PREHOOK: query: explain extended +select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484' +PREHOOK: type: QUERY +POSTHOOK: query: explain extended +select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484' +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + +TOK_QUERY + TOK_FROM + TOK_TABREF + TOK_TABNAME + list_bucketing_dynamic_part + TOK_INSERT + TOK_DESTINATION + TOK_DIR + TOK_TMP_FILE + TOK_SELECT + TOK_SELEXPR + TOK_ALLCOLREF + TOK_WHERE + and + = + TOK_TABLE_OR_COL + key + '484' + = + TOK_TABLE_OR_COL + value + 'val_484' + + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Partition Description: + Partition + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + partition values: + ds 2008-04-08 + hr a1 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + numFiles 1 + numRows 16 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 136 + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + totalSize 254 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_dynamic_part + name: default.list_bucketing_dynamic_part + Partition + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + partition values: + ds 2008-04-08 + hr b1 + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + numFiles 4 + numRows 984 + partition_columns ds/hr + partition_columns.types string:string + rawDataSize 9488 + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + totalSize 10622 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + + input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat + output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat + properties: + bucket_count -1 + columns key,value + columns.comments + columns.types string:string +#### A masked pattern was here #### + name default.list_bucketing_dynamic_part + partition_columns ds/hr + partition_columns.types string:string + serialization.ddl struct list_bucketing_dynamic_part { string key, string value} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe + name: default.list_bucketing_dynamic_part + name: default.list_bucketing_dynamic_part + Processor Tree: + TableScan + alias: list_bucketing_dynamic_part + Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = '484') and (value = 'val_484')) (type: boolean) + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + ListSink + +PREHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484' +PREHOOK: type: QUERY +PREHOOK: Input: default@list_bucketing_dynamic_part +PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 +PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 +#### A masked pattern was here #### +POSTHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1 +POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1 +#### A masked pattern was here #### +484 val_484 2008-04-08 b1 +484 val_484 2008-04-08 b1 +PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +484 val_484 2008-04-08 11 +484 val_484 2008-04-08 12 +PREHOOK: query: -- clean up +drop table list_bucketing_dynamic_part +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@list_bucketing_dynamic_part +PREHOOK: Output: default@list_bucketing_dynamic_part +POSTHOOK: query: -- clean up +drop table list_bucketing_dynamic_part +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@list_bucketing_dynamic_part +POSTHOOK: Output: default@list_bucketing_dynamic_part
Added: hive/trunk/ql/src/test/results/clientpositive/plan_json.q.java1.7.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/plan_json.q.java1.7.out?rev=1647794&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/plan_json.q.java1.7.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/plan_json.q.java1.7.out Wed Dec 24 14:33:00 2014 @@ -0,0 +1,13 @@ +PREHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query + +-- JAVA_VERSION_SPECIFIC_OUTPUT + +EXPLAIN FORMATTED SELECT count(1) FROM src +PREHOOK: type: QUERY +POSTHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query + +-- JAVA_VERSION_SPECIFIC_OUTPUT + +EXPLAIN FORMATTED SELECT count(1) FROM src +POSTHOOK: type: QUERY +{"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Reduce Operator Tree:":{"Group By Operator":{"mode:":"mergepartial","aggregations:":["count(VALUE._col0)"],"outputColumnNames:":["_col0"],"children":{"Select Operator":{"expressions:":"_col0 (type: bigint)","outputColumnNames:":["_col0"],"children":{"File Output Operator":{"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","compressed:":"false","table:":{"serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe","input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"}}},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Map Operator Tree:":[{"TableScan":{"alias:":"src","children":{"Select Operator":{"expressions:":"1 (type: int)","outputColumnNames:":["_col0"],"children":{"Group By Operator":{"mode:": "hash","aggregations:":["count(_col0)"],"outputColumnNames:":["_col0"],"children":{"Reduce Output Operator":{"sort order:":"","value expressions:":"_col0 (type: bigint)","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE"}},"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE"}}]}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}},"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}}} Added: hive/trunk/ql/src/test/results/clientpositive/plan_json.q.java1.8.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/plan_json.q.java1.8.out?rev=1647794&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/plan_json.q.java1.8.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/plan_json.q.java1.8.out Wed Dec 24 14:33:00 2014 @@ -0,0 +1,13 @@ +PREHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query + +-- JAVA_VERSION_SPECIFIC_OUTPUT + +EXPLAIN FORMATTED SELECT count(1) FROM src +PREHOOK: type: QUERY +POSTHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query + +-- JAVA_VERSION_SPECIFIC_OUTPUT + +EXPLAIN FORMATTED SELECT count(1) FROM src +POSTHOOK: type: QUERY +{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Select Operator":{"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","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"}}},"outputColumnNames:":["_col0"],"expressions:":"_col0 (type: bigint)"}},"outputColumnNames:":["_col0"]}},"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size : 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Select Operator":{"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Group By Operator":{"aggregations:":["count(_col0)"],"mode:":"hash","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Reduce Output Operator":{"value expressions:":"_col0 (type: bigint)","sort order:":"","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE"}},"outputColumnNames:":["_col0"]}},"outputColumnNames:":["_col0"],"expressions:":"1 (type: int)"}}}}]}},"Stage-0":{"Fetch Operator":{"Processor Tree:":{"ListSink":{}},"limit:":"-1"}}}} Added: hive/trunk/ql/src/test/results/clientpositive/tez/join0.q.java1.7.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/tez/join0.q.java1.7.out?rev=1647794&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/tez/join0.q.java1.7.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/tez/join0.q.java1.7.out Wed Dec 24 14:33:00 2014 @@ -0,0 +1,236 @@ +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT + +EXPLAIN +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT + +EXPLAIN +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key < 10) (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 + Reduce Output Operator + sort order: + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Map 4 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key < 10) (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 + Reduce Output Operator + sort order: + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order: ++++ + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 182 Data size: 1939 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN FORMATTED +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN FORMATTED +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +#### A masked pattern was here #### +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 9 val_9 +0 val_0 9 val_9 +0 val_0 9 val_9 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 2 val_2 +2 val_2 4 val_4 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 8 val_8 +2 val_2 9 val_9 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 2 val_2 +4 val_4 4 val_4 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 8 val_8 +4 val_4 9 val_9 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 9 val_9 +5 val_5 9 val_9 +5 val_5 9 val_9 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 2 val_2 +8 val_8 4 val_4 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 8 val_8 +8 val_8 9 val_9 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 2 val_2 +9 val_9 4 val_4 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 8 val_8 +9 val_9 9 val_9 Added: hive/trunk/ql/src/test/results/clientpositive/tez/join0.q.java1.8.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/tez/join0.q.java1.8.out?rev=1647794&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/tez/join0.q.java1.8.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/tez/join0.q.java1.8.out Wed Dec 24 14:33:00 2014 @@ -0,0 +1,236 @@ +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT + +EXPLAIN +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT + +EXPLAIN +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key < 10) (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 + Reduce Output Operator + sort order: + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Map 4 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key < 10) (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 + Reduce Output Operator + sort order: + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order: ++++ + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 182 Data size: 1939 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN FORMATTED +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN FORMATTED +SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +#### A masked pattern was here #### +Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT src1.key as k1, src1.value as v1, + src2.key as k2, src2.value as v2 FROM + (SELECT * FROM src WHERE src.key < 10) src1 + JOIN + (SELECT * FROM src WHERE src.key < 10) src2 + SORT BY k1, v1, k2, v2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 0 val_0 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 2 val_2 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 4 val_4 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 5 val_5 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 8 val_8 +0 val_0 9 val_9 +0 val_0 9 val_9 +0 val_0 9 val_9 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 0 val_0 +2 val_2 2 val_2 +2 val_2 4 val_4 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 5 val_5 +2 val_2 8 val_8 +2 val_2 9 val_9 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 0 val_0 +4 val_4 2 val_2 +4 val_4 4 val_4 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 5 val_5 +4 val_4 8 val_8 +4 val_4 9 val_9 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 0 val_0 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 2 val_2 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 4 val_4 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 5 val_5 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 8 val_8 +5 val_5 9 val_9 +5 val_5 9 val_9 +5 val_5 9 val_9 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 0 val_0 +8 val_8 2 val_2 +8 val_8 4 val_4 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 5 val_5 +8 val_8 8 val_8 +8 val_8 9 val_9 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 0 val_0 +9 val_9 2 val_2 +9 val_9 4 val_4 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 5 val_5 +9 val_9 8 val_8 +9 val_9 9 val_9
