You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@bigtop.apache.org by ab...@apache.org on 2011/07/19 21:45:54 UTC
svn commit: r1148501 [18/47] - in /incubator/bigtop: branches/ tags/ trunk/
trunk/docs/ trunk/src/ trunk/src/pkg/ trunk/src/pkg/common/
trunk/src/pkg/common/flume/ trunk/src/pkg/common/hadoop/
trunk/src/pkg/common/hadoop/conf.pseudo/ trunk/src/pkg/comm...
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/bucketmapjoin5/out
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/bucketmapjoin5/out?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/bucketmapjoin5/out (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/bucketmapjoin5/out Tue Jul 19 19:44:48 2011
@@ -0,0 +1,781 @@
+CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+
+load data local inpath 'seed_data_files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket20.txt
+
+load data local inpath 'seed_data_files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket21.txt
+
+
+CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+
+load data local inpath 'seed_data_files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket20.txt
+
+load data local inpath 'seed_data_files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket21.txt
+
+load data local inpath 'seed_data_files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket22.txt
+
+load data local inpath 'seed_data_files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket23.txt
+
+load data local inpath 'seed_data_files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-09')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket20.txt
+
+load data local inpath 'seed_data_files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-09')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket21.txt
+
+load data local inpath 'seed_data_files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-09')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket22.txt
+
+load data local inpath 'seed_data_files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-09')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket23.txt
+
+
+CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+
+load data local inpath 'seed_data_files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket22.txt
+
+load data local inpath 'seed_data_files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket23.txt
+
+load data local inpath 'seed_data_files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-09')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket22.txt
+
+load data local inpath 'seed_data_files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-09')
+Copying file: file:/var/lib/hudson/workspace/Nightly-smoke-testing-monster/examples/hive/target/seed_data_files/srcbucket23.txt
+
+
+create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint)
+
+create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint)
+set hive.optimize.bucketmapjoin = true
+
+create table bucketmapjoin_tmp_result (key string , value1 string, value2 string)
+
+
+explain extended
+insert overwrite table bucketmapjoin_tmp_result
+select /*+mapjoin(a)*/ a.key, a.value, b.value
+from srcbucket_mapjoin a join srcbucket_mapjoin_part b
+on a.key=b.key
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value)))))
+
+STAGE DEPENDENCIES:
+ Stage-7 is a root stage
+ Stage-1 depends on stages: Stage-7
+ Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3
+ Stage-4
+ Stage-0 depends on stages: Stage-4, Stage-3
+ Stage-2 depends on stages: Stage-0
+ Stage-3
+
+STAGE PLANS:
+ Stage: Stage-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ a
+ TableScan
+ alias: a
+ GatherStats: false
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+ Bucket Mapjoin Context:
+ Alias Bucket Base File Name Mapping:
+ a {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt], srcbucket22.txt=[srcbucket20.txt], srcbucket23.txt=[srcbucket21.txt], ds=2008-04-09/srcbucket20.txt=[srcbucket20.txt], ds=2008-04-09/srcbucket21.txt=[srcbucket21.txt], ds=2008-04-09/srcbucket22.txt=[srcbucket20.txt], ds=2008-04-09/srcbucket23.txt=[srcbucket21.txt]}
+ Alias Bucket File Name Mapping:
+ a {hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket20.txt=[hdfs://monster01.sf.cloudera.
com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket21.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket22.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket23.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
+ Alias Bucket Output File Name Mapping:
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt 0
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt 1
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt 2
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt 3
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket20.txt 0
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket21.txt 1
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket22.txt 2
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09/srcbucket23.txt 3
+
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ b
+ TableScan
+ alias: b
+ GatherStats: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1, _col5
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col5
+ type: string
+ outputColumnNames: _col0, _col1, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col5
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ directory: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10002
+ NumFilesPerFileSink: 1
+ Stats Publishing Key Prefix: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10000/
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691359
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Local Work:
+ Map Reduce Local Work
+ Needs Tagging: false
+ Path -> Alias:
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 [b]
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09 [b]
+ Path -> Partition:
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types int:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-08
+ name default.srcbucket_mapjoin_part
+ partition_columns ds
+ serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691354
+ 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 4
+ bucket_field_name key
+ columns key,value
+ columns.types int:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part
+ name default.srcbucket_mapjoin_part
+ partition_columns ds
+ serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691354
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcbucket_mapjoin_part
+ name: default.srcbucket_mapjoin_part
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types int:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part/ds=2008-04-09
+ name default.srcbucket_mapjoin_part
+ partition_columns ds
+ serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691354
+ 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 4
+ bucket_field_name key
+ columns key,value
+ columns.types int:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part
+ name default.srcbucket_mapjoin_part
+ partition_columns ds
+ serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691354
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcbucket_mapjoin_part
+ name: default.srcbucket_mapjoin_part
+
+ Stage: Stage-5
+ Conditional Operator
+
+ Stage: Stage-4
+ Move Operator
+ files:
+ hdfs directory: true
+ source: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10002
+ destination: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10000
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ source: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10000
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691359
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ tmp directory: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10001
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+ Stats Aggregation Key Prefix: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10000/
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10002
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ directory: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10000
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691359
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Needs Tagging: false
+ Path -> Alias:
+ hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10002 [hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10002]
+ Path -> Partition:
+ hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-55-59_802_8749339940103211895/-ext-10002
+ Partition
+ base file name: -ext-10002
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691359
+ 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,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691359
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ name: default.bucketmapjoin_tmp_result
+
+
+
+
+insert overwrite table bucketmapjoin_tmp_result
+select /*+mapjoin(a)*/ a.key, a.value, b.value
+from srcbucket_mapjoin a join srcbucket_mapjoin_part b
+on a.key=b.key
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+
+
+select count(1) from bucketmapjoin_tmp_result
+928
+
+insert overwrite table bucketmapjoin_hash_result_1
+select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_hash_result_1
+set hive.optimize.bucketmapjoin = false
+
+insert overwrite table bucketmapjoin_tmp_result
+select /*+mapjoin(a)*/ a.key, a.value, b.value
+from srcbucket_mapjoin a join srcbucket_mapjoin_part b
+on a.key=b.key
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+
+
+select count(1) from bucketmapjoin_tmp_result
+928
+
+insert overwrite table bucketmapjoin_hash_result_2
+select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_hash_result_2
+
+
+select a.key-b.key, a.value1-b.value1, a.value2-b.value2
+from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
+on a.key = b.key
+0 0 0
+set hive.optimize.bucketmapjoin = true
+
+explain extended
+insert overwrite table bucketmapjoin_tmp_result
+select /*+mapjoin(a)*/ a.key, a.value, b.value
+from srcbucket_mapjoin a join srcbucket_mapjoin_part_2 b
+on a.key=b.key
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part_2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value)))))
+
+STAGE DEPENDENCIES:
+ Stage-7 is a root stage
+ Stage-1 depends on stages: Stage-7
+ Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3
+ Stage-4
+ Stage-0 depends on stages: Stage-4, Stage-3
+ Stage-2 depends on stages: Stage-0
+ Stage-3
+
+STAGE PLANS:
+ Stage: Stage-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ a
+ TableScan
+ alias: a
+ GatherStats: false
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+ Bucket Mapjoin Context:
+ Alias Bucket Base File Name Mapping:
+ a {srcbucket22.txt=[srcbucket20.txt], srcbucket23.txt=[srcbucket21.txt], ds=2008-04-09/srcbucket22.txt=[srcbucket20.txt], ds=2008-04-09/srcbucket23.txt=[srcbucket21.txt]}
+ Alias Bucket File Name Mapping:
+ a {hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09/srcbucket22.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket20.txt], hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09/srcbucket23.txt=[hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
+ Alias Bucket Output File Name Mapping:
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt 0
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt 1
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09/srcbucket22.txt 0
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09/srcbucket23.txt 1
+
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ b
+ TableScan
+ alias: b
+ GatherStats: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1, _col5
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col5
+ type: string
+ outputColumnNames: _col0, _col1, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col5
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ directory: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10002
+ NumFilesPerFileSink: 1
+ Stats Publishing Key Prefix: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10000/
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ numFiles 1
+ numPartitions 0
+ numRows 0
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 17966
+ transient_lastDdlTime 1301691422
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Local Work:
+ Map Reduce Local Work
+ Needs Tagging: false
+ Path -> Alias:
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08 [b]
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09 [b]
+ Path -> Partition:
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types int:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08
+ name default.srcbucket_mapjoin_part_2
+ partition_columns ds
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691357
+ 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 2
+ bucket_field_name key
+ columns key,value
+ columns.types int:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_2
+ partition_columns ds
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691357
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_2
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types int:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-09
+ name default.srcbucket_mapjoin_part_2
+ partition_columns ds
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691357
+ 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 2
+ bucket_field_name key
+ columns key,value
+ columns.types int:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_2
+ partition_columns ds
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301691357
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_2
+
+ Stage: Stage-5
+ Conditional Operator
+
+ Stage: Stage-4
+ Move Operator
+ files:
+ hdfs directory: true
+ source: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10002
+ destination: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10000
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ source: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10000
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ numFiles 1
+ numPartitions 0
+ numRows 0
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 17966
+ transient_lastDdlTime 1301691422
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ tmp directory: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10001
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+ Stats Aggregation Key Prefix: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10000/
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10002
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ directory: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10000
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ numFiles 1
+ numPartitions 0
+ numRows 0
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 17966
+ transient_lastDdlTime 1301691422
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Needs Tagging: false
+ Path -> Alias:
+ hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10002 [hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10002]
+ Path -> Partition:
+ hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_13-57-41_645_9053634577540746990/-ext-10002
+ Partition
+ base file name: -ext-10002
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ numFiles 1
+ numPartitions 0
+ numRows 0
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 17966
+ transient_lastDdlTime 1301691422
+ 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,value1,value2
+ columns.types string:string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_tmp_result
+ name default.bucketmapjoin_tmp_result
+ numFiles 1
+ numPartitions 0
+ numRows 0
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 17966
+ transient_lastDdlTime 1301691422
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ name: default.bucketmapjoin_tmp_result
+
+
+
+
+insert overwrite table bucketmapjoin_tmp_result
+select /*+mapjoin(a)*/ a.key, a.value, b.value
+from srcbucket_mapjoin a join srcbucket_mapjoin_part_2 b
+on a.key=b.key
+
+
+select count(1) from bucketmapjoin_tmp_result
+928
+
+insert overwrite table bucketmapjoin_hash_result_1
+select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_hash_result_1
+set hive.optimize.bucketmapjoin = false
+
+insert overwrite table bucketmapjoin_tmp_result
+select /*+mapjoin(a)*/ a.key, a.value, b.value
+from srcbucket_mapjoin a join srcbucket_mapjoin_part_2 b
+on a.key=b.key
+
+
+select count(1) from bucketmapjoin_tmp_result
+928
+
+insert overwrite table bucketmapjoin_hash_result_2
+select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/bucketmapjoin_hash_result_2
+
+
+select a.key-b.key, a.value1-b.value1, a.value2-b.value2
+from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
+on a.key = b.key
+0 0 0
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/drop_multi_partitions/in
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/drop_multi_partitions/in?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/drop_multi_partitions/in (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/drop_multi_partitions/in Tue Jul 19 19:44:48 2011
@@ -0,0 +1,17 @@
+create table mp (a string) partitioned by (b string, c string);
+
+alter table mp add partition (b='1', c='1');
+alter table mp add partition (b='1', c='2');
+alter table mp add partition (b='2', c='2');
+
+show partitions mp;
+
+explain extended alter table mp drop partition (b='1');
+alter table mp drop partition (b='1');
+
+show partitions mp;
+
+set hive.exec.drop.ignorenonexistent=false;
+alter table mp drop if exists partition (b='3');
+
+show partitions mp;
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/drop_multi_partitions/out
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/drop_multi_partitions/out?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/drop_multi_partitions/out (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/drop_multi_partitions/out Tue Jul 19 19:44:48 2011
@@ -0,0 +1,43 @@
+create table mp (a string) partitioned by (b string, c string)
+
+
+alter table mp add partition (b='1', c='1')
+
+alter table mp add partition (b='1', c='2')
+
+alter table mp add partition (b='2', c='2')
+
+
+show partitions mp
+b=1/c=1
+b=1/c=2
+b=2/c=2
+
+
+explain extended alter table mp drop partition (b='1')
+ABSTRACT SYNTAX TREE:
+ (TOK_ALTERTABLE_DROPPARTS mp (TOK_PARTSPEC (TOK_PARTVAL b '1')))
+
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Drop Table Operator:
+ Drop Table
+ table: mp
+
+
+
+alter table mp drop partition (b='1')
+
+
+show partitions mp
+b=2/c=2
+set hive.exec.drop.ignorenonexistent=false
+
+alter table mp drop if exists partition (b='3')
+
+
+show partitions mp
+b=2/c=2
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/filter
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/filter?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/filter (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/filter Tue Jul 19 19:44:48 2011
@@ -0,0 +1,3 @@
+sed -re 's#hdfs://[^/]*/#hdfs://HADOOP/#' \
+ -e 's#hdfs://.*/-(ext|mr)-1000#hdfs://HADOOP/-\1-1000#' \
+ -e 's#transient_lastDdlTime [0-9]*#transient_lastDdlTime JUSTNOW#'
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/in
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/in?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/in (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/in Tue Jul 19 19:44:48 2011
@@ -0,0 +1,20 @@
+set hive.map.aggr=true;
+set hive.groupby.skewindata=false;
+set mapred.reduce.tasks=31;
+
+CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, C3 INT, c4 INT) STORED AS TEXTFILE;
+
+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);
+
+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);
+
+SELECT dest1.* FROM dest1;
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/out
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/out?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/out (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/groupby_map_ppr_multi_distinct/out Tue Jul 19 19:44:48 2011
@@ -0,0 +1,283 @@
+set hive.map.aggr=true
+set hive.groupby.skewindata=false
+set mapred.reduce.tasks=31
+
+
+CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, C3 INT, c4 INT) STORED AS TEXTFILE
+
+
+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)
+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
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src
+ TableScan
+ alias: src
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (ds = '2008-04-08')
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(DISTINCT substr(value, 5))
+ expr: sum(substr(value, 5))
+ expr: sum(DISTINCT substr(value, 5))
+ expr: count(DISTINCT value)
+ bucketGroup: false
+ keys:
+ expr: substr(key, 1, 1)
+ type: string
+ expr: substr(value, 5)
+ type: string
+ expr: value
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col3
+ type: bigint
+ expr: _col4
+ type: double
+ expr: _col5
+ type: double
+ expr: _col6
+ type: bigint
+ Needs Tagging: false
+ Path -> Alias:
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=11 [src]
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=12 [src]
+ Path -> Partition:
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=11
+ 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:
+ bucket_count -1
+ columns key,value
+ columns.types string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=11
+ name default.srcpart
+ partition_columns ds/hr
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301676822
+ 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.types string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcpart
+ name default.srcpart
+ partition_columns ds/hr
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301676822
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=12
+ 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:
+ bucket_count -1
+ columns key,value
+ columns.types string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcpart/ds=2008-04-08/hr=12
+ name default.srcpart
+ partition_columns ds/hr
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301676822
+ 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.types string:string
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/srcpart
+ name default.srcpart
+ partition_columns ds/hr
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ transient_lastDdlTime 1301676822
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(DISTINCT KEY._col1:0._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(DISTINCT KEY._col1:1._col0)
+ expr: count(DISTINCT KEY._col1:2._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: concat(_col0, _col2)
+ type: string
+ expr: _col3
+ type: double
+ expr: _col4
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: _col2
+ type: string
+ expr: UDFToInteger(_col3)
+ type: int
+ expr: UDFToInteger(_col4)
+ type: int
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ directory: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_10-08-20_880_8656529853875888350/-ext-10000
+ NumFilesPerFileSink: 1
+ Stats Publishing Key Prefix: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_10-08-20_880_8656529853875888350/-ext-10000/
+ 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.types string:int:string:int:int
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/dest1
+ 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
+ transient_lastDdlTime 1301677700
+ 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
+ source: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_10-08-20_880_8656529853875888350/-ext-10000
+ 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.types string:int:string:int:int
+ file.inputformat org.apache.hadoop.mapred.TextInputFormat
+ file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ location hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/dest1
+ 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
+ transient_lastDdlTime 1301677700
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+ tmp directory: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_10-08-20_880_8656529853875888350/-ext-10001
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+ Stats Aggregation Key Prefix: hdfs://monster01.sf.cloudera.com:17020/tmp/hive-hudson/hive_2011-04-01_10-08-20_880_8656529853875888350/-ext-10000/
+
+
+
+
+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)
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/dest1
+
+
+SELECT dest1.* FROM dest1
+0 1 00.0 0 1
+1 71 132828.0 10044 71
+2 69 251142.0 15780 69
+3 62 364008.0 20119 62
+4 74 4105526.0 30965 74
+5 6 5794.0 278 6
+6 5 6796.0 331 5
+7 6 71470.0 447 6
+8 8 81524.0 595 8
+9 7 92094.0 577 7
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/filter
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/filter?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/filter (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/filter Tue Jul 19 19:44:48 2011
@@ -0,0 +1,6 @@
+sed -re 's#hdfs://.*/-(ext|mr)-1000#hdfs://HADOOP/-\1-1000#' |
+sed -e 's#hdfs://[^/]*/#hdfs://HADOOP/#' \
+ -e 's#owner:[^,]*,#owner:BORG,#' \
+ -e 's#createTime:[0-9]*,#createTime:JUSTNOW#' \
+ -e 's#location:hdfs://[^/]*/#location:hdfs://HADOOP/#' \
+ -e 's#transient_lastDdlTime=[0-9]*}#transient_lastDdlTime=JUSTNOW}#'
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/in
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/in?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/in (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/in Tue Jul 19 19:44:48 2011
@@ -0,0 +1,52 @@
+drop index src_index_2 on src;
+drop index src_index_3 on src;
+drop index src_index_4 on src;
+drop index src_index_5 on src;
+drop index src_index_6 on src;
+drop index src_index_7 on src;
+drop index src_index_8 on src;
+drop index src_index_9 on src;
+drop table `_t`;
+
+create index src_index_2 on table src(key) as 'compact' WITH DEFERRED REBUILD;
+desc extended default__src_src_index_2__;
+
+create index src_index_3 on table src(key) as 'compact' WITH DEFERRED REBUILD in table src_idx_src_index_3;
+desc extended src_idx_src_index_3;
+
+create index src_index_4 on table src(key) as 'compact' WITH DEFERRED REBUILD ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' STORED AS TEXTFILE;
+desc extended default__src_src_index_4__;
+
+create index src_index_5 on table src(key) as 'compact' WITH DEFERRED REBUILD ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' ESCAPED BY '\\';
+desc extended default__src_src_index_5__;
+
+create index src_index_6 on table src(key) as 'compact' WITH DEFERRED REBUILD STORED AS RCFILE;
+desc extended default__src_src_index_6__;
+
+create index src_index_7 on table src(key) as 'compact' WITH DEFERRED REBUILD in table src_idx_src_index_7 STORED AS RCFILE;
+desc extended src_idx_src_index_7;
+
+create index src_index_8 on table src(key) as 'compact' WITH DEFERRED REBUILD IDXPROPERTIES ("prop1"="val1", "prop2"="val2");
+desc extended default__src_src_index_8__;
+
+create index src_index_9 on table src(key) as 'compact' WITH DEFERRED REBUILD TBLPROPERTIES ("prop1"="val1", "prop2"="val2");
+desc extended default__src_src_index_9__;
+
+create table `_t`(`_i` int, `_j` int);
+create index x on table `_t`(`_j`) as 'compact' WITH DEFERRED REBUILD;
+alter index x on `_t` rebuild;
+
+create index x2 on table `_t`(`_i`,`_j`) as 'compact' WITH DEFERRED
+REBUILD;
+alter index x2 on `_t` rebuild;
+
+drop index src_index_2 on src;
+drop index src_index_3 on src;
+drop index src_index_4 on src;
+drop index src_index_5 on src;
+drop index src_index_6 on src;
+drop index src_index_7 on src;
+drop index src_index_8 on src;
+drop index src_index_9 on src;
+drop table `_t`;
+
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/out
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/out?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/out (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/index_creation/out Tue Jul 19 19:44:48 2011
@@ -0,0 +1,131 @@
+drop index src_index_2 on src
+
+drop index src_index_3 on src
+
+drop index src_index_4 on src
+
+drop index src_index_5 on src
+
+drop index src_index_6 on src
+
+drop index src_index_7 on src
+
+drop index src_index_8 on src
+
+drop index src_index_9 on src
+
+drop table `_t`
+
+
+create index src_index_2 on table src(key) as 'compact' WITH DEFERRED REBUILD
+
+desc extended default__src_src_index_2__
+key string
+_bucketname string
+_offsets array<bigint>
+
+Detailed Table Information Table(tableName:default__src_src_index_2__, dbName:default, owner:null, createTime:1301677813, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:_bucketname, type:string, comment:), FieldSchema(name:_offsets, type:array<bigint>, comment:)], location:hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/default__src_src_index_2__, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[], sortCols:[Order(col:key, order:1)], parameters:{}), partitionKeys:[], parameters:{transient_lastDdlTime=1301677813}, viewOriginalText:null, viewExpandedText:null, tableType:INDEX_TABLE)
+
+
+create index src_index_3 on table src(key) as 'compact' WITH DEFERRED REBUILD in table src_idx_src_index_3
+
+desc extended src_idx_src_index_3
+key string
+_bucketname string
+_offsets array<bigint>
+
+Detailed Table Information Table(tableName:src_idx_src_index_3, dbName:default, owner:null, createTime:1301677813, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:_bucketname, type:string, comment:), FieldSchema(name:_offsets, type:array<bigint>, comment:)], location:hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/src_idx_src_index_3, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[], sortCols:[Order(col:key, order:1)], parameters:{}), partitionKeys:[], parameters:{transient_lastDdlTime=1301677813}, viewOriginalText:null, viewExpandedText:null, tableType:INDEX_TABLE)
+
+
+create index src_index_4 on table src(key) as 'compact' WITH DEFERRED REBUILD ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' STORED AS TEXTFILE
+
+desc extended default__src_src_index_4__
+key string
+_bucketname string
+_offsets array<bigint>
+
+Detailed Table Information Table(tableName:default__src_src_index_4__, dbName:default, owner:null, createTime:1301677814, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:_bucketname, type:string, comment:), FieldSchema(name:_offsets, type:array<bigint>, comment:)], location:hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/default__src_src_index_4__, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format= , field.delim=
+
+
+create index src_index_5 on table src(key) as 'compact' WITH DEFERRED REBUILD ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' ESCAPED BY '\\'
+
+desc extended default__src_src_index_5__
+key string
+_bucketname string
+_offsets array<bigint>
+
+Detailed Table Information Table(tableName:default__src_src_index_5__, dbName:default, owner:null, createTime:1301677814, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:_bucketname, type:string, comment:), FieldSchema(name:_offsets, type:array<bigint>, comment:)], location:hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/default__src_src_index_5__, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{escape.delim=\, serialization.format= , field.delim=
+
+
+create index src_index_6 on table src(key) as 'compact' WITH DEFERRED REBUILD STORED AS RCFILE
+
+desc extended default__src_src_index_6__
+key string from deserializer
+_bucketname string from deserializer
+_offsets array<bigint> from deserializer
+
+Detailed Table Information Table(tableName:default__src_src_index_6__, dbName:default, owner:null, createTime:1301677814, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:_bucketname, type:string, comment:), FieldSchema(name:_offsets, type:array<bigint>, comment:)], location:hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/default__src_src_index_6__, inputFormat:org.apache.hadoop.hive.ql.io.RCFileInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.RCFileOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe, parameters:{serialization.format=1}), bucketCols:[], sortCols:[Order(col:key, order:1)], parameters:{}), partitionKeys:[], parameters:{transient_lastDdlTime=1301677814}, viewOriginalText:null, viewExpandedText:null, tableType:INDEX_TABLE)
+
+
+create index src_index_7 on table src(key) as 'compact' WITH DEFERRED REBUILD in table src_idx_src_index_7 STORED AS RCFILE
+
+desc extended src_idx_src_index_7
+key string from deserializer
+_bucketname string from deserializer
+_offsets array<bigint> from deserializer
+
+Detailed Table Information Table(tableName:src_idx_src_index_7, dbName:default, owner:null, createTime:1301677815, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:_bucketname, type:string, comment:), FieldSchema(name:_offsets, type:array<bigint>, comment:)], location:hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/src_idx_src_index_7, inputFormat:org.apache.hadoop.hive.ql.io.RCFileInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.RCFileOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe, parameters:{serialization.format=1}), bucketCols:[], sortCols:[Order(col:key, order:1)], parameters:{}), partitionKeys:[], parameters:{transient_lastDdlTime=1301677815}, viewOriginalText:null, viewExpandedText:null, tableType:INDEX_TABLE)
+
+
+create index src_index_8 on table src(key) as 'compact' WITH DEFERRED REBUILD IDXPROPERTIES ("prop1"="val1", "prop2"="val2")
+
+desc extended default__src_src_index_8__
+key string
+_bucketname string
+_offsets array<bigint>
+
+Detailed Table Information Table(tableName:default__src_src_index_8__, dbName:default, owner:null, createTime:1301677815, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:_bucketname, type:string, comment:), FieldSchema(name:_offsets, type:array<bigint>, comment:)], location:hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/default__src_src_index_8__, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[], sortCols:[Order(col:key, order:1)], parameters:{}), partitionKeys:[], parameters:{transient_lastDdlTime=1301677815}, viewOriginalText:null, viewExpandedText:null, tableType:INDEX_TABLE)
+
+
+create index src_index_9 on table src(key) as 'compact' WITH DEFERRED REBUILD TBLPROPERTIES ("prop1"="val1", "prop2"="val2")
+
+desc extended default__src_src_index_9__
+key string
+_bucketname string
+_offsets array<bigint>
+
+Detailed Table Information Table(tableName:default__src_src_index_9__, dbName:default, owner:null, createTime:1301677815, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:_bucketname, type:string, comment:), FieldSchema(name:_offsets, type:array<bigint>, comment:)], location:hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/default__src_src_index_9__, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.IgnoreKeyTextOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[], sortCols:[Order(col:key, order:1)], parameters:{}), partitionKeys:[], parameters:{prop2=val2, prop1=val1, transient_lastDdlTime=1301677815}, viewOriginalText:null, viewExpandedText:null, tableType:INDEX_TABLE)
+
+
+create table `_t`(`_i` int, `_j` int)
+
+create index x on table `_t`(`_j`) as 'compact' WITH DEFERRED REBUILD
+
+alter index x on `_t` rebuild
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/default___t_x__
+
+
+create index x2 on table `_t`(`_i`,`_j`) as 'compact' WITH DEFERRED
+REBUILD
+
+alter index x2 on `_t` rebuild
+Deleted hdfs://monster01.sf.cloudera.com:17020/user/hive/warehouse/default___t_x2__
+
+
+drop index src_index_2 on src
+
+drop index src_index_3 on src
+
+drop index src_index_4 on src
+
+drop index src_index_5 on src
+
+drop index src_index_6 on src
+
+drop index src_index_7 on src
+
+drop index src_index_8 on src
+
+drop index src_index_9 on src
+
+drop table `_t`
Added: incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/join19/in
URL: http://svn.apache.org/viewvc/incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/join19/in?rev=1148501&view=auto
==============================================================================
--- incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/join19/in (added)
+++ incubator/bigtop/trunk/test/src/smokes/hive/src/test/resources/scripts/ql/join19/in Tue Jul 19 19:44:48 2011
@@ -0,0 +1,58 @@
+CREATE TABLE triples (foo string, subject string, predicate string, object string, foo2 string);
+
+EXPLAIN
+SELECT t11.subject, t22.object , t33.subject , t55.object, t66.object
+FROM
+(
+SELECT t1.subject
+FROM triples t1
+WHERE
+t1.predicate='http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL'
+AND
+t1.object='http://ontos/OntosMiner/Common.English/ontology#Citation'
+) t11
+JOIN
+(
+SELECT t2.subject , t2.object
+FROM triples t2
+WHERE
+t2.predicate='http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL'
+) t22
+ON (t11.subject=t22.subject)
+JOIN
+(
+SELECT t3.subject , t3.object
+FROM triples t3
+WHERE
+t3.predicate='http://www.ontosearch.com/2007/12/ontosofa-ns#_from'
+
+) t33
+ON (t11.subject=t33.object)
+JOIN
+(
+SELECT t4.subject
+FROM triples t4
+WHERE
+t4.predicate='http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL'
+AND
+t4.object='http://ontos/OntosMiner/Common.English/ontology#Author'
+
+) t44
+ON (t44.subject=t33.subject)
+JOIN
+(
+SELECT t5.subject, t5.object
+FROM triples t5
+WHERE
+t5.predicate='http://www.ontosearch.com/2007/12/ontosofa-ns#_to'
+) t55
+ON (t55.subject=t44.subject)
+JOIN
+(
+SELECT t6.subject, t6.object
+FROM triples t6
+WHERE
+t6.predicate='http://sofa.semanticweb.org/sofa/v1.0/system#__LABEL_REL'
+) t66
+ON (t66.subject=t55.object);
+