You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by he...@apache.org on 2010/02/28 21:00:11 UTC

svn commit: r917283 - in /hadoop/hive/trunk: contrib/src/test/queries/clientpositive/serde_typedbytes5.q contrib/src/test/results/clientpositive/serde_typedbytes5.q.out data/scripts/cat.py

Author: heyongqiang
Date: Sun Feb 28 20:00:11 2010
New Revision: 917283

URL: http://svn.apache.org/viewvc?rev=917283&view=rev
Log:
HIVE-1204. typedbytes: writing to stderr kills the mapper.(namit via He Yongqiang)

Added:
    hadoop/hive/trunk/contrib/src/test/queries/clientpositive/serde_typedbytes5.q
    hadoop/hive/trunk/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out
    hadoop/hive/trunk/data/scripts/cat.py

Added: hadoop/hive/trunk/contrib/src/test/queries/clientpositive/serde_typedbytes5.q
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/contrib/src/test/queries/clientpositive/serde_typedbytes5.q?rev=917283&view=auto
==============================================================================
--- hadoop/hive/trunk/contrib/src/test/queries/clientpositive/serde_typedbytes5.q (added)
+++ hadoop/hive/trunk/contrib/src/test/queries/clientpositive/serde_typedbytes5.q Sun Feb 28 20:00:11 2010
@@ -0,0 +1,29 @@
+add jar ../build/contrib/hive_contrib.jar;
+
+drop table dest1;
+CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE;
+
+EXPLAIN
+FROM (
+  FROM src
+  SELECT TRANSFORM(src.key, src.value) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDWRITER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordWriter'
+  USING 'python ../data/scripts/cat.py'
+  AS (tkey, tvalue) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDREADER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordReader'
+) tmap
+INSERT OVERWRITE TABLE dest1 SELECT tkey, tvalue;
+
+FROM (
+  FROM src
+  SELECT TRANSFORM(src.key, src.value) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDWRITER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordWriter'
+  USING 'python ../data/scripts/cat.py'
+  AS (tkey, tvalue) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDREADER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordReader'
+) tmap
+INSERT OVERWRITE TABLE dest1 SELECT tkey, tvalue;
+
+SELECT dest1.* FROM dest1;
+
+drop table dest1;

Added: hadoop/hive/trunk/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out?rev=917283&view=auto
==============================================================================
--- hadoop/hive/trunk/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out (added)
+++ hadoop/hive/trunk/contrib/src/test/results/clientpositive/serde_typedbytes5.q.out Sun Feb 28 20:00:11 2010
@@ -0,0 +1,666 @@
+PREHOOK: query: drop table dest1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table dest1
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest1
+PREHOOK: query: EXPLAIN
+FROM (
+  FROM src
+  SELECT TRANSFORM(src.key, src.value) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDWRITER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordWriter'
+  USING 'python ../data/scripts/cat.py'
+  AS (tkey, tvalue) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDREADER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordReader'
+) tmap
+INSERT OVERWRITE TABLE dest1 SELECT tkey, tvalue
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+FROM (
+  FROM src
+  SELECT TRANSFORM(src.key, src.value) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDWRITER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordWriter'
+  USING 'python ../data/scripts/cat.py'
+  AS (tkey, tvalue) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDREADER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordReader'
+) tmap
+INSERT OVERWRITE TABLE dest1 SELECT tkey, tvalue
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+  (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF src)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TRANSFORM (TOK_EXPLIST (. (TOK_TABLE_OR_COL src) key) (. (TOK_TABLE_OR_COL src) value)) (TOK_SERDE (TOK_SERDENAME 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe')) (TOK_RECORDWRITER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordWriter') 'python ../data/scripts/cat.py' (TOK_SERDE (TOK_SERDENAME 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe')) (TOK_RECORDREADER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordReader') (TOK_ALIASLIST tkey tvalue)))))) tmap)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL tkey)) (TOK_SELEXPR (TOK_TABLE_OR_COL tvalue)))))
+
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-4 depends on stages: Stage-1 , consists of Stage-3, Stage-2
+  Stage-3
+  Stage-0 depends on stages: Stage-3, Stage-2
+  Stage-2
+
+STAGE PLANS:
+  Stage: Stage-1
+    Map Reduce
+      Alias -> Map Operator Tree:
+        tmap:src 
+          TableScan
+            alias: src
+            Select Operator
+              expressions:
+                    expr: key
+                    type: string
+                    expr: value
+                    type: string
+              outputColumnNames: _col0, _col1
+              Transform Operator
+                command: python ../data/scripts/cat.py
+                output info:
+                    input format: org.apache.hadoop.mapred.TextInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                Select Operator
+                  expressions:
+                        expr: _col0
+                        type: string
+                        expr: _col1
+                        type: string
+                  outputColumnNames: _col0, _col1
+                  Select Operator
+                    expressions:
+                          expr: UDFToInteger(_col0)
+                          type: int
+                          expr: _col1
+                          type: string
+                    outputColumnNames: _col0, _col1
+                    File Output Operator
+                      compressed: false
+                      GlobalTableId: 1
+                      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: dest1
+
+  Stage: Stage-4
+    Conditional Operator
+
+  Stage: Stage-3
+    Move Operator
+      files:
+          hdfs directory: true
+          destination: file:/data/users/njain/hive1/hive1/build/contrib/scratchdir/hive_2010-02-26_16-46-00_966_8770926542722067748/10000
+
+  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: dest1
+
+  Stage: Stage-2
+    Map Reduce
+      Alias -> Map Operator Tree:
+        file:/data/users/njain/hive1/hive1/build/contrib/scratchdir/hive_2010-02-26_16-46-00_966_8770926542722067748/10002 
+            Reduce Output Operator
+              sort order: 
+              Map-reduce partition columns:
+                    expr: rand()
+                    type: double
+              tag: -1
+              value expressions:
+                    expr: key
+                    type: int
+                    expr: value
+                    type: string
+      Reduce Operator Tree:
+        Extract
+          File Output Operator
+            compressed: false
+            GlobalTableId: 0
+            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: dest1
+
+
+PREHOOK: query: FROM (
+  FROM src
+  SELECT TRANSFORM(src.key, src.value) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDWRITER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordWriter'
+  USING 'python ../data/scripts/cat.py'
+  AS (tkey, tvalue) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDREADER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordReader'
+) tmap
+INSERT OVERWRITE TABLE dest1 SELECT tkey, tvalue
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+POSTHOOK: query: FROM (
+  FROM src
+  SELECT TRANSFORM(src.key, src.value) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDWRITER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordWriter'
+  USING 'python ../data/scripts/cat.py'
+  AS (tkey, tvalue) ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.TypedBytesSerDe'
+  RECORDREADER 'org.apache.hadoop.hive.contrib.util.typedbytes.TypedBytesRecordReader'
+) tmap
+INSERT OVERWRITE TABLE dest1 SELECT tkey, tvalue
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+PREHOOK: query: SELECT dest1.* FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+PREHOOK: Output: file:/data/users/njain/hive1/hive1/build/contrib/scratchdir/hive_2010-02-26_16-46-05_557_2000233677894920906/10000
+POSTHOOK: query: SELECT dest1.* FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+POSTHOOK: Output: file:/data/users/njain/hive1/hive1/build/contrib/scratchdir/hive_2010-02-26_16-46-05_557_2000233677894920906/10000
+238	val_238
+86	val_86
+311	val_311
+27	val_27
+165	val_165
+409	val_409
+255	val_255
+278	val_278
+98	val_98
+484	val_484
+265	val_265
+193	val_193
+401	val_401
+150	val_150
+273	val_273
+224	val_224
+369	val_369
+66	val_66
+128	val_128
+213	val_213
+146	val_146
+406	val_406
+429	val_429
+374	val_374
+152	val_152
+469	val_469
+145	val_145
+495	val_495
+37	val_37
+327	val_327
+281	val_281
+277	val_277
+209	val_209
+15	val_15
+82	val_82
+403	val_403
+166	val_166
+417	val_417
+430	val_430
+252	val_252
+292	val_292
+219	val_219
+287	val_287
+153	val_153
+193	val_193
+338	val_338
+446	val_446
+459	val_459
+394	val_394
+237	val_237
+482	val_482
+174	val_174
+413	val_413
+494	val_494
+207	val_207
+199	val_199
+466	val_466
+208	val_208
+174	val_174
+399	val_399
+396	val_396
+247	val_247
+417	val_417
+489	val_489
+162	val_162
+377	val_377
+397	val_397
+309	val_309
+365	val_365
+266	val_266
+439	val_439
+342	val_342
+367	val_367
+325	val_325
+167	val_167
+195	val_195
+475	val_475
+17	val_17
+113	val_113
+155	val_155
+203	val_203
+339	val_339
+0	val_0
+455	val_455
+128	val_128
+311	val_311
+316	val_316
+57	val_57
+302	val_302
+205	val_205
+149	val_149
+438	val_438
+345	val_345
+129	val_129
+170	val_170
+20	val_20
+489	val_489
+157	val_157
+378	val_378
+221	val_221
+92	val_92
+111	val_111
+47	val_47
+72	val_72
+4	val_4
+280	val_280
+35	val_35
+427	val_427
+277	val_277
+208	val_208
+356	val_356
+399	val_399
+169	val_169
+382	val_382
+498	val_498
+125	val_125
+386	val_386
+437	val_437
+469	val_469
+192	val_192
+286	val_286
+187	val_187
+176	val_176
+54	val_54
+459	val_459
+51	val_51
+138	val_138
+103	val_103
+239	val_239
+213	val_213
+216	val_216
+430	val_430
+278	val_278
+176	val_176
+289	val_289
+221	val_221
+65	val_65
+318	val_318
+332	val_332
+311	val_311
+275	val_275
+137	val_137
+241	val_241
+83	val_83
+333	val_333
+180	val_180
+284	val_284
+12	val_12
+230	val_230
+181	val_181
+67	val_67
+260	val_260
+404	val_404
+384	val_384
+489	val_489
+353	val_353
+373	val_373
+272	val_272
+138	val_138
+217	val_217
+84	val_84
+348	val_348
+466	val_466
+58	val_58
+8	val_8
+411	val_411
+230	val_230
+208	val_208
+348	val_348
+24	val_24
+463	val_463
+431	val_431
+179	val_179
+172	val_172
+42	val_42
+129	val_129
+158	val_158
+119	val_119
+496	val_496
+0	val_0
+322	val_322
+197	val_197
+468	val_468
+393	val_393
+454	val_454
+100	val_100
+298	val_298
+199	val_199
+191	val_191
+418	val_418
+96	val_96
+26	val_26
+165	val_165
+327	val_327
+230	val_230
+205	val_205
+120	val_120
+131	val_131
+51	val_51
+404	val_404
+43	val_43
+436	val_436
+156	val_156
+469	val_469
+468	val_468
+308	val_308
+95	val_95
+196	val_196
+288	val_288
+481	val_481
+457	val_457
+98	val_98
+282	val_282
+197	val_197
+187	val_187
+318	val_318
+318	val_318
+409	val_409
+470	val_470
+137	val_137
+369	val_369
+316	val_316
+169	val_169
+413	val_413
+85	val_85
+77	val_77
+0	val_0
+490	val_490
+87	val_87
+364	val_364
+179	val_179
+118	val_118
+134	val_134
+395	val_395
+282	val_282
+138	val_138
+238	val_238
+419	val_419
+15	val_15
+118	val_118
+72	val_72
+90	val_90
+307	val_307
+19	val_19
+435	val_435
+10	val_10
+277	val_277
+273	val_273
+306	val_306
+224	val_224
+309	val_309
+389	val_389
+327	val_327
+242	val_242
+369	val_369
+392	val_392
+272	val_272
+331	val_331
+401	val_401
+242	val_242
+452	val_452
+177	val_177
+226	val_226
+5	val_5
+497	val_497
+402	val_402
+396	val_396
+317	val_317
+395	val_395
+58	val_58
+35	val_35
+336	val_336
+95	val_95
+11	val_11
+168	val_168
+34	val_34
+229	val_229
+233	val_233
+143	val_143
+472	val_472
+322	val_322
+498	val_498
+160	val_160
+195	val_195
+42	val_42
+321	val_321
+430	val_430
+119	val_119
+489	val_489
+458	val_458
+78	val_78
+76	val_76
+41	val_41
+223	val_223
+492	val_492
+149	val_149
+449	val_449
+218	val_218
+228	val_228
+138	val_138
+453	val_453
+30	val_30
+209	val_209
+64	val_64
+468	val_468
+76	val_76
+74	val_74
+342	val_342
+69	val_69
+230	val_230
+33	val_33
+368	val_368
+103	val_103
+296	val_296
+113	val_113
+216	val_216
+367	val_367
+344	val_344
+167	val_167
+274	val_274
+219	val_219
+239	val_239
+485	val_485
+116	val_116
+223	val_223
+256	val_256
+263	val_263
+70	val_70
+487	val_487
+480	val_480
+401	val_401
+288	val_288
+191	val_191
+5	val_5
+244	val_244
+438	val_438
+128	val_128
+467	val_467
+432	val_432
+202	val_202
+316	val_316
+229	val_229
+469	val_469
+463	val_463
+280	val_280
+2	val_2
+35	val_35
+283	val_283
+331	val_331
+235	val_235
+80	val_80
+44	val_44
+193	val_193
+321	val_321
+335	val_335
+104	val_104
+466	val_466
+366	val_366
+175	val_175
+403	val_403
+483	val_483
+53	val_53
+105	val_105
+257	val_257
+406	val_406
+409	val_409
+190	val_190
+406	val_406
+401	val_401
+114	val_114
+258	val_258
+90	val_90
+203	val_203
+262	val_262
+348	val_348
+424	val_424
+12	val_12
+396	val_396
+201	val_201
+217	val_217
+164	val_164
+431	val_431
+454	val_454
+478	val_478
+298	val_298
+125	val_125
+431	val_431
+164	val_164
+424	val_424
+187	val_187
+382	val_382
+5	val_5
+70	val_70
+397	val_397
+480	val_480
+291	val_291
+24	val_24
+351	val_351
+255	val_255
+104	val_104
+70	val_70
+163	val_163
+438	val_438
+119	val_119
+414	val_414
+200	val_200
+491	val_491
+237	val_237
+439	val_439
+360	val_360
+248	val_248
+479	val_479
+305	val_305
+417	val_417
+199	val_199
+444	val_444
+120	val_120
+429	val_429
+169	val_169
+443	val_443
+323	val_323
+325	val_325
+277	val_277
+230	val_230
+478	val_478
+178	val_178
+468	val_468
+310	val_310
+317	val_317
+333	val_333
+493	val_493
+460	val_460
+207	val_207
+249	val_249
+265	val_265
+480	val_480
+83	val_83
+136	val_136
+353	val_353
+172	val_172
+214	val_214
+462	val_462
+233	val_233
+406	val_406
+133	val_133
+175	val_175
+189	val_189
+454	val_454
+375	val_375
+401	val_401
+421	val_421
+407	val_407
+384	val_384
+256	val_256
+26	val_26
+134	val_134
+67	val_67
+384	val_384
+379	val_379
+18	val_18
+462	val_462
+492	val_492
+100	val_100
+298	val_298
+9	val_9
+341	val_341
+498	val_498
+146	val_146
+458	val_458
+362	val_362
+186	val_186
+285	val_285
+348	val_348
+167	val_167
+18	val_18
+273	val_273
+183	val_183
+281	val_281
+344	val_344
+97	val_97
+469	val_469
+315	val_315
+84	val_84
+28	val_28
+37	val_37
+448	val_448
+152	val_152
+348	val_348
+307	val_307
+194	val_194
+414	val_414
+477	val_477
+222	val_222
+126	val_126
+90	val_90
+169	val_169
+403	val_403
+400	val_400
+200	val_200
+97	val_97
+PREHOOK: query: drop table dest1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table dest1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Output: default@dest1

Added: hadoop/hive/trunk/data/scripts/cat.py
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/data/scripts/cat.py?rev=917283&view=auto
==============================================================================
--- hadoop/hive/trunk/data/scripts/cat.py (added)
+++ hadoop/hive/trunk/data/scripts/cat.py Sun Feb 28 20:00:11 2010
@@ -0,0 +1,11 @@
+import sys, re
+import datetime
+import os
+
+table_name=None
+if os.environ.has_key('hive_streaming_tablename'):
+  table_name=os.environ['hive_streaming_tablename']
+
+for line in sys.stdin:
+  print line
+  print >> sys.stderr, "dummy"