5c9d375a4e195d5dd4019d5bf19125cac3478ad3
[hive.git] / ql / src / test / results / clientpositive / columnstats_partlvl.q.out
1 PREHOOK: query: DROP TABLE Employee_Part
2 PREHOOK: type: DROPTABLE
3 POSTHOOK: query: DROP TABLE Employee_Part
4 POSTHOOK: type: DROPTABLE
5 PREHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double)
6 row format delimited fields terminated by '|'  stored as textfile
7 PREHOOK: type: CREATETABLE
8 PREHOOK: Output: database:default
9 PREHOOK: Output: default@Employee_Part
10 POSTHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double)
11 row format delimited fields terminated by '|'  stored as textfile
12 POSTHOOK: type: CREATETABLE
13 POSTHOOK: Output: database:default
14 POSTHOOK: Output: default@Employee_Part
15 PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary=2000.0)
16 PREHOOK: type: LOAD
17 #### A masked pattern was here ####
18 PREHOOK: Output: default@employee_part
19 POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary=2000.0)
20 POSTHOOK: type: LOAD
21 #### A masked pattern was here ####
22 POSTHOOK: Output: default@employee_part
23 POSTHOOK: Output: default@employee_part@employeesalary=2000.0
24 PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary=4000.0)
25 PREHOOK: type: LOAD
26 #### A masked pattern was here ####
27 PREHOOK: Output: default@employee_part
28 POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee.dat" INTO TABLE Employee_Part partition(employeeSalary=4000.0)
29 POSTHOOK: type: LOAD
30 #### A masked pattern was here ####
31 POSTHOOK: Output: default@employee_part
32 POSTHOOK: Output: default@employee_part@employeesalary=4000.0
33 PREHOOK: query: explain 
34 analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID
35 PREHOOK: type: QUERY
36 POSTHOOK: query: explain 
37 analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID
38 POSTHOOK: type: QUERY
39 STAGE DEPENDENCIES:
40   Stage-0 is a root stage
41   Stage-1 depends on stages: Stage-0
42
43 STAGE PLANS:
44   Stage: Stage-0
45     Map Reduce
46       Map Operator Tree:
47           TableScan
48             alias: employee_part
49             Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
50             Select Operator
51               expressions: employeeid (type: int)
52               outputColumnNames: employeeid
53               Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
54               Group By Operator
55                 aggregations: compute_stats(employeeid, 'hll')
56                 keys: 2000.0 (type: double)
57                 mode: hash
58                 outputColumnNames: _col0, _col1
59                 Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
60                 Reduce Output Operator
61                   key expressions: 2000.0 (type: double)
62                   sort order: +
63                   Map-reduce partition columns: 2000.0 (type: double)
64                   Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
65                   value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
66       Reduce Operator Tree:
67         Group By Operator
68           aggregations: compute_stats(VALUE._col0)
69           keys: 2000.0 (type: double)
70           mode: mergepartial
71           outputColumnNames: _col0, _col1
72           Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
73           Select Operator
74             expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), 2000.0 (type: double)
75             outputColumnNames: _col0, _col1
76             Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
77             File Output Operator
78               compressed: false
79               Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
80               table:
81                   input format: org.apache.hadoop.mapred.SequenceFileInputFormat
82                   output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
83                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
84
85   Stage: Stage-1
86     Stats Work
87       Basic Stats Work:
88       Column Stats Desc:
89           Columns: employeeID
90           Column Types: int
91           Table: default.employee_part
92
93 PREHOOK: query: explain extended
94 analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID
95 PREHOOK: type: QUERY
96 POSTHOOK: query: explain extended
97 analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID
98 POSTHOOK: type: QUERY
99 STAGE DEPENDENCIES:
100   Stage-0 is a root stage
101   Stage-1 depends on stages: Stage-0
102
103 STAGE PLANS:
104   Stage: Stage-0
105     Map Reduce
106       Map Operator Tree:
107           TableScan
108             alias: employee_part
109             Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
110             Statistics Aggregation Key Prefix: default.employee_part/
111             GatherStats: true
112             Select Operator
113               expressions: employeeid (type: int)
114               outputColumnNames: employeeid
115               Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
116               Group By Operator
117                 aggregations: compute_stats(employeeid, 'hll')
118                 keys: 2000.0 (type: double)
119                 mode: hash
120                 outputColumnNames: _col0, _col1
121                 Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
122                 Reduce Output Operator
123                   key expressions: 2000.0 (type: double)
124                   null sort order: a
125                   sort order: +
126                   Map-reduce partition columns: 2000.0 (type: double)
127                   Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
128                   tag: -1
129                   value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
130                   auto parallelism: false
131       Path -> Alias:
132 #### A masked pattern was here ####
133       Path -> Partition:
134 #### A masked pattern was here ####
135           Partition
136             base file name: employeesalary=2000.0
137             input format: org.apache.hadoop.mapred.TextInputFormat
138             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
139             partition values:
140               employeesalary 2000.0
141             properties:
142               bucket_count -1
143               column.name.delimiter ,
144               columns employeeid,employeename
145               columns.comments 
146               columns.types int:string
147               field.delim |
148 #### A masked pattern was here ####
149               name default.employee_part
150               numFiles 1
151               numRows 0
152               partition_columns employeesalary
153               partition_columns.types double
154               rawDataSize 0
155               serialization.ddl struct employee_part { i32 employeeid, string employeename}
156               serialization.format |
157               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
158               totalSize 105
159 #### A masked pattern was here ####
160             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
161           
162               input format: org.apache.hadoop.mapred.TextInputFormat
163               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
164               properties:
165                 bucket_count -1
166                 column.name.delimiter ,
167                 columns employeeid,employeename
168                 columns.comments 
169                 columns.types int:string
170                 field.delim |
171 #### A masked pattern was here ####
172                 name default.employee_part
173                 partition_columns employeesalary
174                 partition_columns.types double
175                 serialization.ddl struct employee_part { i32 employeeid, string employeename}
176                 serialization.format |
177                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
178 #### A masked pattern was here ####
179               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
180               name: default.employee_part
181             name: default.employee_part
182       Truncated Path -> Alias:
183         /employee_part/employeesalary=2000.0 [employee_part]
184       Needs Tagging: false
185       Reduce Operator Tree:
186         Group By Operator
187           aggregations: compute_stats(VALUE._col0)
188           keys: 2000.0 (type: double)
189           mode: mergepartial
190           outputColumnNames: _col0, _col1
191           Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
192           Select Operator
193             expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), 2000.0 (type: double)
194             outputColumnNames: _col0, _col1
195             Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
196             File Output Operator
197               compressed: false
198               GlobalTableId: 0
199 #### A masked pattern was here ####
200               NumFilesPerFileSink: 1
201               Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
202 #### A masked pattern was here ####
203               table:
204                   input format: org.apache.hadoop.mapred.SequenceFileInputFormat
205                   output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
206                   properties:
207                     columns _col0,_col1
208                     columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:double
209                     escape.delim \
210                     hive.serialization.extend.additional.nesting.levels true
211                     serialization.escape.crlf true
212                     serialization.format 1
213                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
214                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
215               TotalFiles: 1
216               GatherStats: false
217               MultiFileSpray: false
218
219   Stage: Stage-1
220     Stats Work
221       Basic Stats Work:
222           Stats Aggregation Key Prefix: default.employee_part/
223       Column Stats Desc:
224           Columns: employeeID
225           Column Types: int
226           Table: default.employee_part
227           Is Table Level Stats: false
228
229 PREHOOK: query: analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID
230 PREHOOK: type: QUERY
231 PREHOOK: Input: default@employee_part
232 PREHOOK: Input: default@employee_part@employeesalary=2000.0
233 PREHOOK: Output: default@employee_part
234 PREHOOK: Output: default@employee_part@employeesalary=2000.0
235 #### A masked pattern was here ####
236 POSTHOOK: query: analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns employeeID
237 POSTHOOK: type: QUERY
238 POSTHOOK: Input: default@employee_part
239 POSTHOOK: Input: default@employee_part@employeesalary=2000.0
240 POSTHOOK: Output: default@employee_part
241 POSTHOOK: Output: default@employee_part@employeesalary=2000.0
242 #### A masked pattern was here ####
243 PREHOOK: query: describe formatted Employee_Part partition(employeeSalary=2000.0)
244 PREHOOK: type: DESCTABLE
245 PREHOOK: Input: default@employee_part
246 POSTHOOK: query: describe formatted Employee_Part partition(employeeSalary=2000.0)
247 POSTHOOK: type: DESCTABLE
248 POSTHOOK: Input: default@employee_part
249 # col_name              data_type               comment             
250 employeeid              int                                         
251 employeename            string                                      
252                  
253 # Partition Information          
254 # col_name              data_type               comment             
255 employeesalary          double                                      
256                  
257 # Detailed Partition Information                 
258 Partition Value:        [2000.0]                 
259 Database:               default                  
260 Table:                  employee_part            
261 #### A masked pattern was here ####
262 Partition Parameters:            
263         COLUMN_STATS_ACCURATE   {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"employeeid\":\"true\"}}
264         numFiles                1                   
265         numRows                 13                  
266         rawDataSize             92                  
267         totalSize               105                 
268 #### A masked pattern was here ####
269                  
270 # Storage Information            
271 SerDe Library:          org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe       
272 InputFormat:            org.apache.hadoop.mapred.TextInputFormat         
273 OutputFormat:           org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat       
274 Compressed:             No                       
275 Num Buckets:            -1                       
276 Bucket Columns:         []                       
277 Sort Columns:           []                       
278 Storage Desc Params:             
279         field.delim             |                   
280         serialization.format    |                   
281 PREHOOK: query: explain 
282 analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID
283 PREHOOK: type: QUERY
284 POSTHOOK: query: explain 
285 analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID
286 POSTHOOK: type: QUERY
287 STAGE DEPENDENCIES:
288   Stage-0 is a root stage
289   Stage-1 depends on stages: Stage-0
290
291 STAGE PLANS:
292   Stage: Stage-0
293     Map Reduce
294       Map Operator Tree:
295           TableScan
296             alias: employee_part
297             Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
298             Select Operator
299               expressions: employeeid (type: int)
300               outputColumnNames: employeeid
301               Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
302               Group By Operator
303                 aggregations: compute_stats(employeeid, 'hll')
304                 keys: 4000.0 (type: double)
305                 mode: hash
306                 outputColumnNames: _col0, _col1
307                 Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
308                 Reduce Output Operator
309                   key expressions: 4000.0 (type: double)
310                   sort order: +
311                   Map-reduce partition columns: 4000.0 (type: double)
312                   Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
313                   value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
314       Reduce Operator Tree:
315         Group By Operator
316           aggregations: compute_stats(VALUE._col0)
317           keys: 4000.0 (type: double)
318           mode: mergepartial
319           outputColumnNames: _col0, _col1
320           Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
321           Select Operator
322             expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), 4000.0 (type: double)
323             outputColumnNames: _col0, _col1
324             Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
325             File Output Operator
326               compressed: false
327               Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
328               table:
329                   input format: org.apache.hadoop.mapred.SequenceFileInputFormat
330                   output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
331                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
332
333   Stage: Stage-1
334     Stats Work
335       Basic Stats Work:
336       Column Stats Desc:
337           Columns: employeeID
338           Column Types: int
339           Table: default.employee_part
340
341 PREHOOK: query: explain extended
342 analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID
343 PREHOOK: type: QUERY
344 POSTHOOK: query: explain extended
345 analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID
346 POSTHOOK: type: QUERY
347 STAGE DEPENDENCIES:
348   Stage-0 is a root stage
349   Stage-1 depends on stages: Stage-0
350
351 STAGE PLANS:
352   Stage: Stage-0
353     Map Reduce
354       Map Operator Tree:
355           TableScan
356             alias: employee_part
357             Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
358             Statistics Aggregation Key Prefix: default.employee_part/
359             GatherStats: true
360             Select Operator
361               expressions: employeeid (type: int)
362               outputColumnNames: employeeid
363               Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
364               Group By Operator
365                 aggregations: compute_stats(employeeid, 'hll')
366                 keys: 4000.0 (type: double)
367                 mode: hash
368                 outputColumnNames: _col0, _col1
369                 Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
370                 Reduce Output Operator
371                   key expressions: 4000.0 (type: double)
372                   null sort order: a
373                   sort order: +
374                   Map-reduce partition columns: 4000.0 (type: double)
375                   Statistics: Num rows: 3 Data size: 1050 Basic stats: COMPLETE Column stats: NONE
376                   tag: -1
377                   value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
378                   auto parallelism: false
379       Path -> Alias:
380 #### A masked pattern was here ####
381       Path -> Partition:
382 #### A masked pattern was here ####
383           Partition
384             base file name: employeesalary=4000.0
385             input format: org.apache.hadoop.mapred.TextInputFormat
386             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
387             partition values:
388               employeesalary 4000.0
389             properties:
390               bucket_count -1
391               column.name.delimiter ,
392               columns employeeid,employeename
393               columns.comments 
394               columns.types int:string
395               field.delim |
396 #### A masked pattern was here ####
397               name default.employee_part
398               numFiles 1
399               numRows 0
400               partition_columns employeesalary
401               partition_columns.types double
402               rawDataSize 0
403               serialization.ddl struct employee_part { i32 employeeid, string employeename}
404               serialization.format |
405               serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
406               totalSize 105
407 #### A masked pattern was here ####
408             serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
409           
410               input format: org.apache.hadoop.mapred.TextInputFormat
411               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
412               properties:
413                 bucket_count -1
414                 column.name.delimiter ,
415                 columns employeeid,employeename
416                 columns.comments 
417                 columns.types int:string
418                 field.delim |
419 #### A masked pattern was here ####
420                 name default.employee_part
421                 partition_columns employeesalary
422                 partition_columns.types double
423                 serialization.ddl struct employee_part { i32 employeeid, string employeename}
424                 serialization.format |
425                 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
426 #### A masked pattern was here ####
427               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
428               name: default.employee_part
429             name: default.employee_part
430       Truncated Path -> Alias:
431         /employee_part/employeesalary=4000.0 [employee_part]
432       Needs Tagging: false
433       Reduce Operator Tree:
434         Group By Operator
435           aggregations: compute_stats(VALUE._col0)
436           keys: 4000.0 (type: double)
437           mode: mergepartial
438           outputColumnNames: _col0, _col1
439           Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
440           Select Operator
441             expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), 4000.0 (type: double)
442             outputColumnNames: _col0, _col1
443             Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
444             File Output Operator
445               compressed: false
446               GlobalTableId: 0
447 #### A masked pattern was here ####
448               NumFilesPerFileSink: 1
449               Statistics: Num rows: 1 Data size: 350 Basic stats: COMPLETE Column stats: NONE
450 #### A masked pattern was here ####
451               table:
452                   input format: org.apache.hadoop.mapred.SequenceFileInputFormat
453                   output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
454                   properties:
455                     columns _col0,_col1
456                     columns.types struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:double
457                     escape.delim \
458                     hive.serialization.extend.additional.nesting.levels true
459                     serialization.escape.crlf true
460                     serialization.format 1
461                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
462                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
463               TotalFiles: 1
464               GatherStats: false
465               MultiFileSpray: false
466
467   Stage: Stage-1
468     Stats Work
469       Basic Stats Work:
470           Stats Aggregation Key Prefix: default.employee_part/
471       Column Stats Desc:
472           Columns: employeeID
473           Column Types: int
474           Table: default.employee_part
475           Is Table Level Stats: false
476
477 PREHOOK: query: analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID
478 PREHOOK: type: QUERY
479 PREHOOK: Input: default@employee_part
480 PREHOOK: Input: default@employee_part@employeesalary=4000.0
481 PREHOOK: Output: default@employee_part
482 PREHOOK: Output: default@employee_part@employeesalary=4000.0
483 #### A masked pattern was here ####
484 POSTHOOK: query: analyze table Employee_Part partition (employeeSalary=4000.0) compute statistics for columns employeeID
485 POSTHOOK: type: QUERY
486 POSTHOOK: Input: default@employee_part
487 POSTHOOK: Input: default@employee_part@employeesalary=4000.0
488 POSTHOOK: Output: default@employee_part
489 POSTHOOK: Output: default@employee_part@employeesalary=4000.0
490 #### A masked pattern was here ####
491 PREHOOK: query: explain 
492 analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns
493 PREHOOK: type: QUERY
494 POSTHOOK: query: explain 
495 analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns
496 POSTHOOK: type: QUERY
497 STAGE DEPENDENCIES:
498   Stage-0 is a root stage
499   Stage-1 depends on stages: Stage-0
500
501 STAGE PLANS:
502   Stage: Stage-0
503     Map Reduce
504       Map Operator Tree:
505           TableScan
506             alias: employee_part
507             Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE
508             Select Operator
509               expressions: employeeid (type: int), employeename (type: string)
510               outputColumnNames: employeeid, employeename
511               Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE
512               Group By Operator
513                 aggregations: compute_stats(employeeid, 'hll'), compute_stats(employeename, 'hll')
514                 keys: 2000.0 (type: double)
515                 mode: hash
516                 outputColumnNames: _col0, _col1, _col2
517                 Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE
518                 Reduce Output Operator
519                   key expressions: 2000.0 (type: double)
520                   sort order: +
521                   Map-reduce partition columns: 2000.0 (type: double)
522                   Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE
523                   value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
524       Reduce Operator Tree:
525         Group By Operator
526           aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
527           keys: 2000.0 (type: double)
528           mode: mergepartial
529           outputColumnNames: _col0, _col1, _col2
530           Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
531           Select Operator
532             expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), 2000.0 (type: double)
533             outputColumnNames: _col0, _col1, _col2
534             Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
535             File Output Operator
536               compressed: false
537               Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
538               table:
539                   input format: org.apache.hadoop.mapred.SequenceFileInputFormat
540                   output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
541                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
542
543   Stage: Stage-1
544     Stats Work
545       Basic Stats Work:
546       Column Stats Desc:
547           Columns: employeeid, employeename
548           Column Types: int, string
549           Table: default.employee_part
550
551 PREHOOK: query: analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns
552 PREHOOK: type: QUERY
553 PREHOOK: Input: default@employee_part
554 PREHOOK: Input: default@employee_part@employeesalary=2000.0
555 PREHOOK: Output: default@employee_part
556 PREHOOK: Output: default@employee_part@employeesalary=2000.0
557 #### A masked pattern was here ####
558 POSTHOOK: query: analyze table Employee_Part partition (employeeSalary=2000.0) compute statistics for columns
559 POSTHOOK: type: QUERY
560 POSTHOOK: Input: default@employee_part
561 POSTHOOK: Input: default@employee_part@employeesalary=2000.0
562 POSTHOOK: Output: default@employee_part
563 POSTHOOK: Output: default@employee_part@employeesalary=2000.0
564 #### A masked pattern was here ####
565 PREHOOK: query: describe formatted Employee_Part partition (employeeSalary=2000.0) employeeID
566 PREHOOK: type: DESCTABLE
567 PREHOOK: Input: default@employee_part
568 POSTHOOK: query: describe formatted Employee_Part partition (employeeSalary=2000.0) employeeID
569 POSTHOOK: type: DESCTABLE
570 POSTHOOK: Input: default@employee_part
571 col_name                employeeID                                                                                       
572 data_type               int                                                                                              
573 min                     16                                                                                               
574 max                     34                                                                                               
575 num_nulls               1                                                                                                
576 distinct_count          12                                                                                               
577 avg_col_len                                                                                                              
578 max_col_len                                                                                                              
579 num_trues                                                                                                                
580 num_falses                                                                                                               
581 bitVector               HL                                                                                               
582 comment                 from deserializer                                                                                
583 PREHOOK: query: describe formatted Employee_Part partition (employeeSalary=2000.0) employeeName
584 PREHOOK: type: DESCTABLE
585 PREHOOK: Input: default@employee_part
586 POSTHOOK: query: describe formatted Employee_Part partition (employeeSalary=2000.0) employeeName
587 POSTHOOK: type: DESCTABLE
588 POSTHOOK: Input: default@employee_part
589 col_name                employeeName                                                                                     
590 data_type               string                                                                                           
591 min                                                                                                                      
592 max                                                                                                                      
593 num_nulls               1                                                                                                
594 distinct_count          12                                                                                               
595 avg_col_len             4.3076923076923075                                                                               
596 max_col_len             6                                                                                                
597 num_trues                                                                                                                
598 num_falses                                                                                                               
599 bitVector               HL                                                                                               
600 comment                 from deserializer                                                                                
601 PREHOOK: query: explain 
602 analyze table Employee_Part  compute statistics for columns
603 PREHOOK: type: QUERY
604 POSTHOOK: query: explain 
605 analyze table Employee_Part  compute statistics for columns
606 POSTHOOK: type: QUERY
607 STAGE DEPENDENCIES:
608   Stage-0 is a root stage
609   Stage-1 depends on stages: Stage-0
610
611 STAGE PLANS:
612   Stage: Stage-0
613     Map Reduce
614       Map Operator Tree:
615           TableScan
616             alias: employee_part
617             Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE
618             Select Operator
619               expressions: employeeid (type: int), employeename (type: string), employeesalary (type: double)
620               outputColumnNames: employeeid, employeename, employeesalary
621               Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE
622               Group By Operator
623                 aggregations: compute_stats(employeeid, 'hll'), compute_stats(employeename, 'hll')
624                 keys: employeesalary (type: double)
625                 mode: hash
626                 outputColumnNames: _col0, _col1, _col2
627                 Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE
628                 Reduce Output Operator
629                   key expressions: _col0 (type: double)
630                   sort order: +
631                   Map-reduce partition columns: _col0 (type: double)
632                   Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE
633                   value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
634       Reduce Operator Tree:
635         Group By Operator
636           aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
637           keys: KEY._col0 (type: double)
638           mode: mergepartial
639           outputColumnNames: _col0, _col1, _col2
640           Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE
641           Select Operator
642             expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: double)
643             outputColumnNames: _col0, _col1, _col2
644             Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE
645             File Output Operator
646               compressed: false
647               Statistics: Num rows: 13 Data size: 92 Basic stats: COMPLETE Column stats: NONE
648               table:
649                   input format: org.apache.hadoop.mapred.SequenceFileInputFormat
650                   output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
651                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
652
653   Stage: Stage-1
654     Stats Work
655       Basic Stats Work:
656       Column Stats Desc:
657           Columns: employeeid, employeename
658           Column Types: int, string
659           Table: default.employee_part
660
661 PREHOOK: query: analyze table Employee_Part  compute statistics for columns
662 PREHOOK: type: QUERY
663 PREHOOK: Input: default@employee_part
664 PREHOOK: Input: default@employee_part@employeesalary=2000.0
665 PREHOOK: Input: default@employee_part@employeesalary=4000.0
666 PREHOOK: Output: default@employee_part
667 PREHOOK: Output: default@employee_part@employeesalary=2000.0
668 PREHOOK: Output: default@employee_part@employeesalary=4000.0
669 #### A masked pattern was here ####
670 POSTHOOK: query: analyze table Employee_Part  compute statistics for columns
671 POSTHOOK: type: QUERY
672 POSTHOOK: Input: default@employee_part
673 POSTHOOK: Input: default@employee_part@employeesalary=2000.0
674 POSTHOOK: Input: default@employee_part@employeesalary=4000.0
675 POSTHOOK: Output: default@employee_part
676 POSTHOOK: Output: default@employee_part@employeesalary=2000.0
677 POSTHOOK: Output: default@employee_part@employeesalary=4000.0
678 #### A masked pattern was here ####
679 PREHOOK: query: describe formatted Employee_Part partition(employeeSalary=2000.0) employeeID
680 PREHOOK: type: DESCTABLE
681 PREHOOK: Input: default@employee_part
682 POSTHOOK: query: describe formatted Employee_Part partition(employeeSalary=2000.0) employeeID
683 POSTHOOK: type: DESCTABLE
684 POSTHOOK: Input: default@employee_part
685 col_name                employeeID                                                                                       
686 data_type               int                                                                                              
687 min                     16                                                                                               
688 max                     34                                                                                               
689 num_nulls               1                                                                                                
690 distinct_count          12                                                                                               
691 avg_col_len                                                                                                              
692 max_col_len                                                                                                              
693 num_trues                                                                                                                
694 num_falses                                                                                                               
695 bitVector               HL                                                                                               
696 comment                 from deserializer                                                                                
697 PREHOOK: query: describe formatted Employee_Part partition(employeeSalary=4000.0) employeeID
698 PREHOOK: type: DESCTABLE
699 PREHOOK: Input: default@employee_part
700 POSTHOOK: query: describe formatted Employee_Part partition(employeeSalary=4000.0) employeeID
701 POSTHOOK: type: DESCTABLE
702 POSTHOOK: Input: default@employee_part
703 col_name                employeeID                                                                                       
704 data_type               int                                                                                              
705 min                     16                                                                                               
706 max                     34                                                                                               
707 num_nulls               1                                                                                                
708 distinct_count          12                                                                                               
709 avg_col_len                                                                                                              
710 max_col_len                                                                                                              
711 num_trues                                                                                                                
712 num_falses                                                                                                               
713 bitVector               HL                                                                                               
714 comment                 from deserializer                                                                                
715 PREHOOK: query: explain 
716 analyze table Employee_Part  compute statistics for columns
717 PREHOOK: type: QUERY
718 POSTHOOK: query: explain 
719 analyze table Employee_Part  compute statistics for columns
720 POSTHOOK: type: QUERY
721 STAGE DEPENDENCIES:
722   Stage-0 is a root stage
723   Stage-1 depends on stages: Stage-0
724
725 STAGE PLANS:
726   Stage: Stage-0
727     Map Reduce
728       Map Operator Tree:
729           TableScan
730             alias: employee_part
731             Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE
732             Select Operator
733               expressions: employeeid (type: int), employeename (type: string)
734               outputColumnNames: employeeid, employeename
735               Statistics: Num rows: 26 Data size: 184 Basic stats: COMPLETE Column stats: NONE
736               Group By Operator
737                 aggregations: compute_stats(employeeid, 'hll'), compute_stats(employeename, 'hll')
738                 mode: hash
739                 outputColumnNames: _col0, _col1
740                 Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
741                 Reduce Output Operator
742                   sort order: 
743                   Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
744                   value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
745       Reduce Operator Tree:
746         Group By Operator
747           aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
748           mode: mergepartial
749           outputColumnNames: _col0, _col1
750           Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
751           File Output Operator
752             compressed: false
753             Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
754             table:
755                 input format: org.apache.hadoop.mapred.SequenceFileInputFormat
756                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
757                 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
758
759   Stage: Stage-1
760     Stats Work
761       Basic Stats Work:
762       Column Stats Desc:
763           Columns: employeeid, employeename
764           Column Types: int, string
765           Table: default.employee_part
766
767 PREHOOK: query: analyze table Employee_Part  compute statistics for columns
768 PREHOOK: type: QUERY
769 PREHOOK: Input: default@employee_part
770 PREHOOK: Input: default@employee_part@employeesalary=2000.0
771 PREHOOK: Input: default@employee_part@employeesalary=4000.0
772 PREHOOK: Output: default@employee_part
773 PREHOOK: Output: default@employee_part@employeesalary=2000.0
774 PREHOOK: Output: default@employee_part@employeesalary=4000.0
775 #### A masked pattern was here ####
776 POSTHOOK: query: analyze table Employee_Part  compute statistics for columns
777 POSTHOOK: type: QUERY
778 POSTHOOK: Input: default@employee_part
779 POSTHOOK: Input: default@employee_part@employeesalary=2000.0
780 POSTHOOK: Input: default@employee_part@employeesalary=4000.0
781 POSTHOOK: Output: default@employee_part
782 POSTHOOK: Output: default@employee_part@employeesalary=2000.0
783 POSTHOOK: Output: default@employee_part@employeesalary=4000.0
784 #### A masked pattern was here ####
785 PREHOOK: query: describe formatted Employee_Part employeeID
786 PREHOOK: type: DESCTABLE
787 PREHOOK: Input: default@employee_part
788 POSTHOOK: query: describe formatted Employee_Part employeeID
789 POSTHOOK: type: DESCTABLE
790 POSTHOOK: Input: default@employee_part
791 col_name                employeeID                                                                                       
792 data_type               int                                                                                              
793 min                     16                                                                                               
794 max                     34                                                                                               
795 num_nulls               2                                                                                                
796 distinct_count          12                                                                                               
797 avg_col_len                                                                                                              
798 max_col_len                                                                                                              
799 num_trues                                                                                                                
800 num_falses                                                                                                               
801 bitVector               HL                                                                                               
802 comment                 from deserializer                                                                                
803 COLUMN_STATS_ACCURATE   {\"COLUMN_STATS\":{\"employeeid\":\"true\",\"employeename\":\"true\"}}                                                                           
804 PREHOOK: query: create database if not exists dummydb
805 PREHOOK: type: CREATEDATABASE
806 PREHOOK: Output: database:dummydb
807 POSTHOOK: query: create database if not exists dummydb
808 POSTHOOK: type: CREATEDATABASE
809 POSTHOOK: Output: database:dummydb
810 PREHOOK: query: use dummydb
811 PREHOOK: type: SWITCHDATABASE
812 PREHOOK: Input: database:dummydb
813 POSTHOOK: query: use dummydb
814 POSTHOOK: type: SWITCHDATABASE
815 POSTHOOK: Input: database:dummydb
816 PREHOOK: query: analyze table default.Employee_Part partition (employeeSalary=2000.0) compute statistics for columns
817 PREHOOK: type: QUERY
818 PREHOOK: Input: default@employee_part
819 PREHOOK: Input: default@employee_part@employeesalary=2000.0
820 PREHOOK: Output: default@employee_part
821 PREHOOK: Output: default@employee_part@employeesalary=2000.0
822 #### A masked pattern was here ####
823 POSTHOOK: query: analyze table default.Employee_Part partition (employeeSalary=2000.0) compute statistics for columns
824 POSTHOOK: type: QUERY
825 POSTHOOK: Input: default@employee_part
826 POSTHOOK: Input: default@employee_part@employeesalary=2000.0
827 POSTHOOK: Output: default@employee_part
828 POSTHOOK: Output: default@employee_part@employeesalary=2000.0
829 #### A masked pattern was here ####
830 PREHOOK: query: describe formatted default.Employee_Part partition (employeeSalary=2000.0) employeeID
831 PREHOOK: type: DESCTABLE
832 PREHOOK: Input: default@employee_part
833 POSTHOOK: query: describe formatted default.Employee_Part partition (employeeSalary=2000.0) employeeID
834 POSTHOOK: type: DESCTABLE
835 POSTHOOK: Input: default@employee_part
836 col_name                employeeID                                                                                       
837 data_type               int                                                                                              
838 min                     16                                                                                               
839 max                     34                                                                                               
840 num_nulls               1                                                                                                
841 distinct_count          12                                                                                               
842 avg_col_len                                                                                                              
843 max_col_len                                                                                                              
844 num_trues                                                                                                                
845 num_falses                                                                                                               
846 bitVector               HL                                                                                               
847 comment                 from deserializer                                                                                
848 COLUMN_STATS_ACCURATE   {\"COLUMN_STATS\":{\"employeeid\":\"true\",\"employeename\":\"true\"}}                                                                           
849 PREHOOK: query: analyze table default.Employee_Part  compute statistics for columns
850 PREHOOK: type: QUERY
851 PREHOOK: Input: default@employee_part
852 PREHOOK: Input: default@employee_part@employeesalary=2000.0
853 PREHOOK: Input: default@employee_part@employeesalary=4000.0
854 PREHOOK: Output: default@employee_part
855 PREHOOK: Output: default@employee_part@employeesalary=2000.0
856 PREHOOK: Output: default@employee_part@employeesalary=4000.0
857 #### A masked pattern was here ####
858 POSTHOOK: query: analyze table default.Employee_Part  compute statistics for columns
859 POSTHOOK: type: QUERY
860 POSTHOOK: Input: default@employee_part
861 POSTHOOK: Input: default@employee_part@employeesalary=2000.0
862 POSTHOOK: Input: default@employee_part@employeesalary=4000.0
863 POSTHOOK: Output: default@employee_part
864 POSTHOOK: Output: default@employee_part@employeesalary=2000.0
865 POSTHOOK: Output: default@employee_part@employeesalary=4000.0
866 #### A masked pattern was here ####
867 PREHOOK: query: use default
868 PREHOOK: type: SWITCHDATABASE
869 PREHOOK: Input: database:default
870 POSTHOOK: query: use default
871 POSTHOOK: type: SWITCHDATABASE
872 POSTHOOK: Input: database:default
873 PREHOOK: query: drop database dummydb
874 PREHOOK: type: DROPDATABASE
875 PREHOOK: Input: database:dummydb
876 PREHOOK: Output: database:dummydb
877 POSTHOOK: query: drop database dummydb
878 POSTHOOK: type: DROPDATABASE
879 POSTHOOK: Input: database:dummydb
880 POSTHOOK: Output: database:dummydb