PREHOOK: query: DROP TABLE IF EXISTS UserVisits_web_text_none PREHOOK: type: DROPTABLE POSTHOOK: query: DROP TABLE IF EXISTS UserVisits_web_text_none POSTHOOK: type: DROPTABLE PREHOOK: query: CREATE TABLE UserVisits_web_text_none ( sourceIP string, destURL string, visitDate string, adRevenue float, userAgent string, cCode string, lCode string, sKeyword string, avgTimeOnSite int) row format delimited fields terminated by '|' stored as textfile PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE UserVisits_web_text_none ( sourceIP string, destURL string, visitDate string, adRevenue float, userAgent string, cCode string, lCode string, sKeyword string, avgTimeOnSite int) row format delimited fields terminated by '|' stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@UserVisits_web_text_none PREHOOK: query: LOAD DATA LOCAL INPATH "../data/files/UserVisits.dat" INTO TABLE UserVisits_web_text_none PREHOOK: type: LOAD PREHOOK: Output: default@uservisits_web_text_none POSTHOOK: query: LOAD DATA LOCAL INPATH "../data/files/UserVisits.dat" INTO TABLE UserVisits_web_text_none POSTHOOK: type: LOAD POSTHOOK: Output: default@uservisits_web_text_none PREHOOK: query: explain analyze table UserVisits_web_text_none compute statistics for columns sourceIP, avgTimeOnSite, adRevenue PREHOOK: type: QUERY POSTHOOK: query: explain analyze table UserVisits_web_text_none compute statistics for columns sourceIP, avgTimeOnSite, adRevenue POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_ANALYZE (TOK_TAB (TOK_TABNAME UserVisits_web_text_none)) (TOK_TABCOLNAME sourceIP avgTimeOnSite adRevenue)) STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Alias -> Map Operator Tree: uservisits_web_text_none TableScan alias: uservisits_web_text_none Select Operator expressions: expr: sourceip type: string expr: avgtimeonsite type: int expr: adrevenue type: float outputColumnNames: sourceip, avgtimeonsite, adrevenue Group By Operator aggregations: expr: compute_stats(sourceip, 16) expr: compute_stats(avgtimeonsite, 16) expr: compute_stats(adrevenue, 16) bucketGroup: false mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator sort order: tag: -1 value expressions: expr: _col0 type: struct expr: _col1 type: struct expr: _col2 type: struct Reduce Operator Tree: Group By Operator aggregations: expr: compute_stats(VALUE._col0) expr: compute_stats(VALUE._col1) expr: compute_stats(VALUE._col2) bucketGroup: false mode: mergepartial outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: struct expr: _col1 type: struct expr: _col2 type: struct outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: sourceIP, avgTimeOnSite, adRevenue Column Types: string, int, float Table: UserVisits_web_text_none PREHOOK: query: explain extended analyze table UserVisits_web_text_none compute statistics for columns sourceIP, avgTimeOnSite, adRevenue PREHOOK: type: QUERY POSTHOOK: query: explain extended analyze table UserVisits_web_text_none compute statistics for columns sourceIP, avgTimeOnSite, adRevenue POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_ANALYZE (TOK_TAB (TOK_TABNAME UserVisits_web_text_none)) (TOK_TABCOLNAME sourceIP avgTimeOnSite adRevenue)) STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Alias -> Map Operator Tree: uservisits_web_text_none TableScan alias: uservisits_web_text_none GatherStats: false Select Operator expressions: expr: sourceip type: string expr: avgtimeonsite type: int expr: adrevenue type: float outputColumnNames: sourceip, avgtimeonsite, adrevenue Group By Operator aggregations: expr: compute_stats(sourceip, 16) expr: compute_stats(avgtimeonsite, 16) expr: compute_stats(adrevenue, 16) bucketGroup: false mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator sort order: tag: -1 value expressions: expr: _col0 type: struct expr: _col1 type: struct expr: _col2 type: struct Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: uservisits_web_text_none input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns sourceip,desturl,visitdate,adrevenue,useragent,ccode,lcode,skeyword,avgtimeonsite columns.types string:string:string:float:string:string:string:string:int field.delim | #### A masked pattern was here #### name default.uservisits_web_text_none numFiles 1 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct uservisits_web_text_none { string sourceip, string desturl, string visitdate, float adrevenue, string useragent, string ccode, string lcode, string skeyword, i32 avgtimeonsite} serialization.format | serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 7060 #### 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 sourceip,desturl,visitdate,adrevenue,useragent,ccode,lcode,skeyword,avgtimeonsite columns.types string:string:string:float:string:string:string:string:int field.delim | #### A masked pattern was here #### name default.uservisits_web_text_none numFiles 1 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct uservisits_web_text_none { string sourceip, string desturl, string visitdate, float adrevenue, string useragent, string ccode, string lcode, string skeyword, i32 avgtimeonsite} serialization.format | serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 7060 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.uservisits_web_text_none name: default.uservisits_web_text_none Truncated Path -> Alias: /uservisits_web_text_none [uservisits_web_text_none] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: expr: compute_stats(VALUE._col0) expr: compute_stats(VALUE._col1) expr: compute_stats(VALUE._col2) bucketGroup: false mode: mergepartial outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: struct expr: _col1 type: struct expr: _col2 type: struct outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2 columns.types struct:struct:struct escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: sourceIP, avgTimeOnSite, adRevenue Column Types: string, int, float Table: UserVisits_web_text_none Is Table Level Stats: true PREHOOK: query: analyze table UserVisits_web_text_none compute statistics for columns sourceIP, avgTimeOnSite, adRevenue PREHOOK: type: QUERY PREHOOK: Input: default@uservisits_web_text_none #### A masked pattern was here #### POSTHOOK: query: analyze table UserVisits_web_text_none compute statistics for columns sourceIP, avgTimeOnSite, adRevenue POSTHOOK: type: QUERY POSTHOOK: Input: default@uservisits_web_text_none #### A masked pattern was here #### PREHOOK: query: CREATE TABLE empty_tab( a int, b double, c string, d boolean, e binary) row format delimited fields terminated by '|' stored as textfile PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE empty_tab( a int, b double, c string, d boolean, e binary) row format delimited fields terminated by '|' stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@empty_tab PREHOOK: query: explain analyze table empty_tab compute statistics for columns a,b,c,d,e PREHOOK: type: QUERY POSTHOOK: query: explain analyze table empty_tab compute statistics for columns a,b,c,d,e POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_ANALYZE (TOK_TAB (TOK_TABNAME empty_tab)) (TOK_TABCOLNAME a b c d e)) STAGE DEPENDENCIES: Stage-0 is a root stage Stage-1 is a root stage STAGE PLANS: Stage: Stage-0 Map Reduce Alias -> Map Operator Tree: empty_tab TableScan alias: empty_tab Select Operator expressions: expr: a type: int expr: b type: double expr: c type: string expr: d type: boolean expr: e type: binary outputColumnNames: a, b, c, d, e Group By Operator aggregations: expr: compute_stats(a, 16) expr: compute_stats(b, 16) expr: compute_stats(c, 16) expr: compute_stats(d, 16) expr: compute_stats(e, 16) bucketGroup: false mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Reduce Output Operator sort order: tag: -1 value expressions: expr: _col0 type: struct expr: _col1 type: struct expr: _col2 type: struct expr: _col3 type: struct expr: _col4 type: struct Reduce Operator Tree: Group By Operator aggregations: expr: compute_stats(VALUE._col0) expr: compute_stats(VALUE._col1) expr: compute_stats(VALUE._col2) expr: compute_stats(VALUE._col3) expr: compute_stats(VALUE._col4) bucketGroup: false mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Select Operator expressions: expr: _col0 type: struct expr: _col1 type: struct expr: _col2 type: struct expr: _col3 type: struct expr: _col4 type: struct outputColumnNames: _col0, _col1, _col2, _col3, _col4 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Stage: Stage-1 Column Stats Work Column Stats Desc: Columns: a, b, c, d, e Column Types: int, double, string, boolean, binary Table: empty_tab PREHOOK: query: analyze table empty_tab compute statistics for columns a,b,c,d,e PREHOOK: type: QUERY PREHOOK: Input: default@empty_tab #### A masked pattern was here #### POSTHOOK: query: analyze table empty_tab compute statistics for columns a,b,c,d,e POSTHOOK: type: QUERY POSTHOOK: Input: default@empty_tab #### A masked pattern was here ####