You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2015/06/26 23:39:58 UTC
[3/4] hive git commit: HIVE-11032: Enable more tests for grouping by
skewed data [Spark Branch] (Mohit via Xuefu)
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby4_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby4_map_skew.q.out b/ql/src/test/results/clientpositive/spark/groupby4_map_skew.q.out
new file mode 100644
index 0000000..535e770
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby4_map_skew.q.out
@@ -0,0 +1,93 @@
+PREHOOK: query: CREATE TABLE dest1(key INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: CREATE TABLE dest1(key INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1)
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 1)
+#### 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: COMPLETE
+ Select Operator
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: final
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 4 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
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.key EXPRESSION []
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+500
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby4_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby4_noskew.q.out b/ql/src/test/results/clientpositive/spark/groupby4_noskew.q.out
new file mode 100644
index 0000000..18ee5c7
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby4_noskew.q.out
@@ -0,0 +1,104 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1) GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1) GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 31)
+#### 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
+ Select Operator
+ expressions: substr(key, 1, 1) (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1) GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1) GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby5.q.out b/ql/src/test/results/clientpositive/spark/groupby5.q.out
new file mode 100644
index 0000000..d7d2140
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby5.q.out
@@ -0,0 +1,433 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest1
+SELECT src.key, sum(substr(src.value,5))
+FROM src
+GROUP BY src.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest1
+SELECT src.key, sum(substr(src.value,5))
+FROM src
+GROUP BY src.key
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (GROUP, 2)
+#### 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
+ Select Operator
+ expressions: key (type: string), substr(value, 5) (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: rand() (type: double)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: partial1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: final
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest1
+SELECT src.key, sum(substr(src.value,5))
+FROM src
+GROUP BY src.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest1
+SELECT src.key, sum(substr(src.value,5))
+FROM src
+GROUP BY src.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+0 0.0
+10 10.0
+100 200.0
+103 206.0
+104 208.0
+105 105.0
+11 11.0
+111 111.0
+113 226.0
+114 114.0
+116 116.0
+118 236.0
+119 357.0
+12 24.0
+120 240.0
+125 250.0
+126 126.0
+128 384.0
+129 258.0
+131 131.0
+133 133.0
+134 268.0
+136 136.0
+137 274.0
+138 552.0
+143 143.0
+145 145.0
+146 292.0
+149 298.0
+15 30.0
+150 150.0
+152 304.0
+153 153.0
+155 155.0
+156 156.0
+157 157.0
+158 158.0
+160 160.0
+162 162.0
+163 163.0
+164 328.0
+165 330.0
+166 166.0
+167 501.0
+168 168.0
+169 676.0
+17 17.0
+170 170.0
+172 344.0
+174 348.0
+175 350.0
+176 352.0
+177 177.0
+178 178.0
+179 358.0
+18 36.0
+180 180.0
+181 181.0
+183 183.0
+186 186.0
+187 561.0
+189 189.0
+19 19.0
+190 190.0
+191 382.0
+192 192.0
+193 579.0
+194 194.0
+195 390.0
+196 196.0
+197 394.0
+199 597.0
+2 2.0
+20 20.0
+200 400.0
+201 201.0
+202 202.0
+203 406.0
+205 410.0
+207 414.0
+208 624.0
+209 418.0
+213 426.0
+214 214.0
+216 432.0
+217 434.0
+218 218.0
+219 438.0
+221 442.0
+222 222.0
+223 446.0
+224 448.0
+226 226.0
+228 228.0
+229 458.0
+230 1150.0
+233 466.0
+235 235.0
+237 474.0
+238 476.0
+239 478.0
+24 48.0
+241 241.0
+242 484.0
+244 244.0
+247 247.0
+248 248.0
+249 249.0
+252 252.0
+255 510.0
+256 512.0
+257 257.0
+258 258.0
+26 52.0
+260 260.0
+262 262.0
+263 263.0
+265 530.0
+266 266.0
+27 27.0
+272 544.0
+273 819.0
+274 274.0
+275 275.0
+277 1108.0
+278 556.0
+28 28.0
+280 560.0
+281 562.0
+282 564.0
+283 283.0
+284 284.0
+285 285.0
+286 286.0
+287 287.0
+288 576.0
+289 289.0
+291 291.0
+292 292.0
+296 296.0
+298 894.0
+30 30.0
+302 302.0
+305 305.0
+306 306.0
+307 614.0
+308 308.0
+309 618.0
+310 310.0
+311 933.0
+315 315.0
+316 948.0
+317 634.0
+318 954.0
+321 642.0
+322 644.0
+323 323.0
+325 650.0
+327 981.0
+33 33.0
+331 662.0
+332 332.0
+333 666.0
+335 335.0
+336 336.0
+338 338.0
+339 339.0
+34 34.0
+341 341.0
+342 684.0
+344 688.0
+345 345.0
+348 1740.0
+35 105.0
+351 351.0
+353 706.0
+356 356.0
+360 360.0
+362 362.0
+364 364.0
+365 365.0
+366 366.0
+367 734.0
+368 368.0
+369 1107.0
+37 74.0
+373 373.0
+374 374.0
+375 375.0
+377 377.0
+378 378.0
+379 379.0
+382 764.0
+384 1152.0
+386 386.0
+389 389.0
+392 392.0
+393 393.0
+394 394.0
+395 790.0
+396 1188.0
+397 794.0
+399 798.0
+4 4.0
+400 400.0
+401 2005.0
+402 402.0
+403 1209.0
+404 808.0
+406 1624.0
+407 407.0
+409 1227.0
+41 41.0
+411 411.0
+413 826.0
+414 828.0
+417 1251.0
+418 418.0
+419 419.0
+42 84.0
+421 421.0
+424 848.0
+427 427.0
+429 858.0
+43 43.0
+430 1290.0
+431 1293.0
+432 432.0
+435 435.0
+436 436.0
+437 437.0
+438 1314.0
+439 878.0
+44 44.0
+443 443.0
+444 444.0
+446 446.0
+448 448.0
+449 449.0
+452 452.0
+453 453.0
+454 1362.0
+455 455.0
+457 457.0
+458 916.0
+459 918.0
+460 460.0
+462 924.0
+463 926.0
+466 1398.0
+467 467.0
+468 1872.0
+469 2345.0
+47 47.0
+470 470.0
+472 472.0
+475 475.0
+477 477.0
+478 956.0
+479 479.0
+480 1440.0
+481 481.0
+482 482.0
+483 483.0
+484 484.0
+485 485.0
+487 487.0
+489 1956.0
+490 490.0
+491 491.0
+492 984.0
+493 493.0
+494 494.0
+495 495.0
+496 496.0
+497 497.0
+498 1494.0
+5 15.0
+51 102.0
+53 53.0
+54 54.0
+57 57.0
+58 116.0
+64 64.0
+65 65.0
+66 66.0
+67 134.0
+69 69.0
+70 210.0
+72 144.0
+74 74.0
+76 152.0
+77 77.0
+78 78.0
+8 8.0
+80 80.0
+82 82.0
+83 166.0
+84 168.0
+85 85.0
+86 86.0
+87 87.0
+9 9.0
+90 270.0
+92 92.0
+95 190.0
+96 96.0
+97 194.0
+98 196.0
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby5_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby5_map.q.out b/ql/src/test/results/clientpositive/spark/groupby5_map.q.out
new file mode 100644
index 0000000..e775921
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby5_map.q.out
@@ -0,0 +1,95 @@
+PREHOOK: query: CREATE TABLE dest1(key INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: CREATE TABLE dest1(key INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key)
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 1)
+#### 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
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+130091
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby5_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby5_map_skew.q.out b/ql/src/test/results/clientpositive/spark/groupby5_map_skew.q.out
new file mode 100644
index 0000000..5c58934
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby5_map_skew.q.out
@@ -0,0 +1,95 @@
+PREHOOK: query: CREATE TABLE dest1(key INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: CREATE TABLE dest1(key INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key)
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 1)
+#### 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
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: final
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT sum(src.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+130091
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby5_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby5_noskew.q.out b/ql/src/test/results/clientpositive/spark/groupby5_noskew.q.out
new file mode 100644
index 0000000..5be29fe
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby5_noskew.q.out
@@ -0,0 +1,418 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest1
+SELECT src.key, sum(substr(src.value,5))
+FROM src
+GROUP BY src.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest1
+SELECT src.key, sum(substr(src.value,5))
+FROM src
+GROUP BY src.key
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 31)
+#### 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
+ Select Operator
+ expressions: key (type: string), substr(value, 5) (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest1
+SELECT src.key, sum(substr(src.value,5))
+FROM src
+GROUP BY src.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest1
+SELECT src.key, sum(substr(src.value,5))
+FROM src
+GROUP BY src.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+0 0.0
+10 10.0
+100 200.0
+103 206.0
+104 208.0
+105 105.0
+11 11.0
+111 111.0
+113 226.0
+114 114.0
+116 116.0
+118 236.0
+119 357.0
+12 24.0
+120 240.0
+125 250.0
+126 126.0
+128 384.0
+129 258.0
+131 131.0
+133 133.0
+134 268.0
+136 136.0
+137 274.0
+138 552.0
+143 143.0
+145 145.0
+146 292.0
+149 298.0
+15 30.0
+150 150.0
+152 304.0
+153 153.0
+155 155.0
+156 156.0
+157 157.0
+158 158.0
+160 160.0
+162 162.0
+163 163.0
+164 328.0
+165 330.0
+166 166.0
+167 501.0
+168 168.0
+169 676.0
+17 17.0
+170 170.0
+172 344.0
+174 348.0
+175 350.0
+176 352.0
+177 177.0
+178 178.0
+179 358.0
+18 36.0
+180 180.0
+181 181.0
+183 183.0
+186 186.0
+187 561.0
+189 189.0
+19 19.0
+190 190.0
+191 382.0
+192 192.0
+193 579.0
+194 194.0
+195 390.0
+196 196.0
+197 394.0
+199 597.0
+2 2.0
+20 20.0
+200 400.0
+201 201.0
+202 202.0
+203 406.0
+205 410.0
+207 414.0
+208 624.0
+209 418.0
+213 426.0
+214 214.0
+216 432.0
+217 434.0
+218 218.0
+219 438.0
+221 442.0
+222 222.0
+223 446.0
+224 448.0
+226 226.0
+228 228.0
+229 458.0
+230 1150.0
+233 466.0
+235 235.0
+237 474.0
+238 476.0
+239 478.0
+24 48.0
+241 241.0
+242 484.0
+244 244.0
+247 247.0
+248 248.0
+249 249.0
+252 252.0
+255 510.0
+256 512.0
+257 257.0
+258 258.0
+26 52.0
+260 260.0
+262 262.0
+263 263.0
+265 530.0
+266 266.0
+27 27.0
+272 544.0
+273 819.0
+274 274.0
+275 275.0
+277 1108.0
+278 556.0
+28 28.0
+280 560.0
+281 562.0
+282 564.0
+283 283.0
+284 284.0
+285 285.0
+286 286.0
+287 287.0
+288 576.0
+289 289.0
+291 291.0
+292 292.0
+296 296.0
+298 894.0
+30 30.0
+302 302.0
+305 305.0
+306 306.0
+307 614.0
+308 308.0
+309 618.0
+310 310.0
+311 933.0
+315 315.0
+316 948.0
+317 634.0
+318 954.0
+321 642.0
+322 644.0
+323 323.0
+325 650.0
+327 981.0
+33 33.0
+331 662.0
+332 332.0
+333 666.0
+335 335.0
+336 336.0
+338 338.0
+339 339.0
+34 34.0
+341 341.0
+342 684.0
+344 688.0
+345 345.0
+348 1740.0
+35 105.0
+351 351.0
+353 706.0
+356 356.0
+360 360.0
+362 362.0
+364 364.0
+365 365.0
+366 366.0
+367 734.0
+368 368.0
+369 1107.0
+37 74.0
+373 373.0
+374 374.0
+375 375.0
+377 377.0
+378 378.0
+379 379.0
+382 764.0
+384 1152.0
+386 386.0
+389 389.0
+392 392.0
+393 393.0
+394 394.0
+395 790.0
+396 1188.0
+397 794.0
+399 798.0
+4 4.0
+400 400.0
+401 2005.0
+402 402.0
+403 1209.0
+404 808.0
+406 1624.0
+407 407.0
+409 1227.0
+41 41.0
+411 411.0
+413 826.0
+414 828.0
+417 1251.0
+418 418.0
+419 419.0
+42 84.0
+421 421.0
+424 848.0
+427 427.0
+429 858.0
+43 43.0
+430 1290.0
+431 1293.0
+432 432.0
+435 435.0
+436 436.0
+437 437.0
+438 1314.0
+439 878.0
+44 44.0
+443 443.0
+444 444.0
+446 446.0
+448 448.0
+449 449.0
+452 452.0
+453 453.0
+454 1362.0
+455 455.0
+457 457.0
+458 916.0
+459 918.0
+460 460.0
+462 924.0
+463 926.0
+466 1398.0
+467 467.0
+468 1872.0
+469 2345.0
+47 47.0
+470 470.0
+472 472.0
+475 475.0
+477 477.0
+478 956.0
+479 479.0
+480 1440.0
+481 481.0
+482 482.0
+483 483.0
+484 484.0
+485 485.0
+487 487.0
+489 1956.0
+490 490.0
+491 491.0
+492 984.0
+493 493.0
+494 494.0
+495 495.0
+496 496.0
+497 497.0
+498 1494.0
+5 15.0
+51 102.0
+53 53.0
+54 54.0
+57 57.0
+58 116.0
+64 64.0
+65 65.0
+66 66.0
+67 134.0
+69 69.0
+70 210.0
+72 144.0
+74 74.0
+76 152.0
+77 77.0
+78 78.0
+8 8.0
+80 80.0
+82 82.0
+83 166.0
+84 168.0
+85 85.0
+86 86.0
+87 87.0
+9 9.0
+90 270.0
+92 92.0
+95 190.0
+96 96.0
+97 194.0
+98 196.0
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby6.q.out b/ql/src/test/results/clientpositive/spark/groupby6.q.out
new file mode 100644
index 0000000..c3caccd
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby6.q.out
@@ -0,0 +1,113 @@
+PREHOOK: query: CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (GROUP, 2)
+#### 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
+ Select Operator
+ expressions: substr(value, 5, 1) (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: rand() (type: double)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: partial1
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: final
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+4
+8
+6
+0
+2
+7
+5
+9
+3
+1
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby6_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby6_map.q.out b/ql/src/test/results/clientpositive/spark/groupby6_map.q.out
new file mode 100644
index 0000000..77af675
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby6_map.q.out
@@ -0,0 +1,109 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 31)
+#### 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
+ Select Operator
+ expressions: substr(value, 5, 1) (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby6_map_skew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby6_map_skew.q.out b/ql/src/test/results/clientpositive/spark/groupby6_map_skew.q.out
new file mode 100644
index 0000000..527bf14
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby6_map_skew.q.out
@@ -0,0 +1,122 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 31)
+ Reducer 3 <- Reducer 2 (GROUP, 31)
+#### 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
+ Select Operator
+ expressions: substr(value, 5, 1) (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: rand() (type: double)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: partials
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: final
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby6_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby6_noskew.q.out b/ql/src/test/results/clientpositive/spark/groupby6_noskew.q.out
new file mode 100644
index 0000000..2d8fb74
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby6_noskew.q.out
@@ -0,0 +1,104 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE dest1(c1 STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+POSTHOOK: type: QUERY
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 31)
+#### 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
+ Select Operator
+ expressions: substr(value, 5, 1) (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM src
+INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(src.value,5,1)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out b/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out
new file mode 100644
index 0000000..9a5c832
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby_grouping_id2.q.out
@@ -0,0 +1,230 @@
+PREHOOK: query: CREATE TABLE T1(key INT, value INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@T1
+POSTHOOK: query: CREATE TABLE T1(key INT, value INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@T1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/groupby_groupingid.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/groupby_groupingid.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@t1
+PREHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+NULL NULL 0 6
+1 1 3 1
+2 NULL 1 1
+2 2 3 1
+3 3 3 1
+4 NULL 1 1
+1 NULL 1 2
+1 NULL 3 1
+3 NULL 1 2
+3 NULL 3 1
+4 5 3 1
+PREHOOK: query: SELECT GROUPING__ID, count(*)
+FROM
+(
+SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP
+) t
+GROUP BY GROUPING__ID
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT GROUPING__ID, count(*)
+FROM
+(
+SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP
+) t
+GROUP BY GROUPING__ID
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+0 1
+3 6
+1 4
+PREHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1
+JOIN
+(SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2
+ON t1.GROUPING__ID = t2.GROUPING__ID
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1
+JOIN
+(SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2
+ON t1.GROUPING__ID = t2.GROUPING__ID
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+0 0
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+PREHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+1 NULL 3 1
+1 NULL 1 2
+NULL NULL 0 6
+4 5 3 1
+3 NULL 3 1
+3 NULL 1 2
+4 NULL 1 1
+2 NULL 1 1
+2 2 3 1
+1 1 3 1
+3 3 3 1
+PREHOOK: query: SELECT GROUPING__ID, count(*)
+FROM
+(
+SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP
+) t
+GROUP BY GROUPING__ID
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT GROUPING__ID, count(*)
+FROM
+(
+SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP
+) t
+GROUP BY GROUPING__ID
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+0 1
+3 6
+1 4
+PREHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1
+JOIN
+(SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2
+ON t1.GROUPING__ID = t2.GROUPING__ID
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT t1.GROUPING__ID, t2.GROUPING__ID FROM (SELECT GROUPING__ID FROM T1 GROUP BY key,value WITH ROLLUP) t1
+JOIN
+(SELECT GROUPING__ID FROM T1 GROUP BY key, value WITH ROLLUP) t2
+ON t1.GROUPING__ID = t2.GROUPING__ID
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+0 0
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+1 1
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
+3 3
http://git-wip-us.apache.org/repos/asf/hive/blob/e0a5f3fd/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out
new file mode 100644
index 0000000..01ea4ea
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out
@@ -0,0 +1,346 @@
+PREHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN EXTENDED
+FROM srcpart src
+INSERT OVERWRITE TABLE dest1
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value)
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN EXTENDED
+FROM srcpart src
+INSERT OVERWRITE TABLE dest1
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value)
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_TABREF
+ TOK_TABNAME
+ srcpart
+ src
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_TAB
+ TOK_TABNAME
+ dest1
+ TOK_SELECT
+ TOK_SELEXPR
+ TOK_FUNCTION
+ substr
+ .
+ TOK_TABLE_OR_COL
+ src
+ key
+ 1
+ 1
+ TOK_SELEXPR
+ TOK_FUNCTIONDI
+ count
+ TOK_FUNCTION
+ substr
+ .
+ TOK_TABLE_OR_COL
+ src
+ value
+ 5
+ TOK_SELEXPR
+ TOK_FUNCTION
+ concat
+ TOK_FUNCTION
+ substr
+ .
+ TOK_TABLE_OR_COL
+ src
+ key
+ 1
+ 1
+ TOK_FUNCTION
+ sum
+ TOK_FUNCTION
+ substr
+ .
+ TOK_TABLE_OR_COL
+ src
+ value
+ 5
+ TOK_SELEXPR
+ TOK_FUNCTIONDI
+ sum
+ TOK_FUNCTION
+ substr
+ .
+ TOK_TABLE_OR_COL
+ src
+ value
+ 5
+ TOK_SELEXPR
+ TOK_FUNCTIONDI
+ count
+ .
+ TOK_TABLE_OR_COL
+ src
+ value
+ TOK_WHERE
+ =
+ .
+ TOK_TABLE_OR_COL
+ src
+ ds
+ '2008-04-08'
+ TOK_GROUPBY
+ TOK_FUNCTION
+ substr
+ .
+ TOK_TABLE_OR_COL
+ src
+ key
+ 1
+ 1
+
+
+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
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: 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 [src]
+ /srcpart/ds=2008-04-08/hr=12 [src]
+ Reducer 2
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(DISTINCT KEY._col1:0._col0), sum(KEY._col1:0._col0), sum(DISTINCT KEY._col1:1._col0), count(DISTINCT KEY._col1:2._col0)
+ keys: KEY._col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,c1,c2,c3,c4
+ columns.comments
+ columns.types string:int:string:int:int
+#### A masked pattern was here ####
+ name default.dest1
+ serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4}
+ 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.dest1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,c1,c2,c3,c4
+ columns.comments
+ columns.types string:int:string:int:int
+#### A masked pattern was here ####
+ name default.dest1
+ serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4}
+ 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.dest1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: FROM srcpart src
+INSERT OVERWRITE TABLE dest1
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value)
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+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@dest1
+POSTHOOK: query: FROM srcpart src
+INSERT OVERWRITE TABLE dest1
+SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value)
+WHERE src.ds = '2008-04-08'
+GROUP BY substr(src.key,1,1)
+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@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.null, ]
+POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+0 1 00.0 0 1
+2 69 251142.0 15780 69
+4 74 4105526.0 30965 74
+6 5 6796.0 331 5
+8 8 81524.0 595 8
+1 71 132828.0 10044 71
+3 62 364008.0 20119 62
+5 6 5794.0 278 6
+7 6 71470.0 447 6
+9 7 92094.0 577 7