http://git-wip-us.apache.org/repos/asf/hive/blob/0a88760f/ql/src/test/results/clientpositive/spark/orc_merge2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/orc_merge2.q.out b/ql/src/test/results/clientpositive/spark/orc_merge2.q.out new file mode 100644 index 0000000..b7f1a65 --- /dev/null +++ b/ql/src/test/results/clientpositive/spark/orc_merge2.q.out @@ -0,0 +1,268 @@ +PREHOOK: query: DROP TABLE orcfile_merge2a +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orcfile_merge2a +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE orcfile_merge2a (key INT, value STRING) + PARTITIONED BY (one string, two string, three string) + STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge2a +POSTHOOK: query: CREATE TABLE orcfile_merge2a (key INT, value STRING) + PARTITIONED BY (one string, two string, three string) + STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge2a +PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE orcfile_merge2a PARTITION (one='1', two, three) + SELECT key, value, PMOD(HASH(key), 10) as two, + PMOD(HASH(value), 10) as three + FROM src +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE orcfile_merge2a PARTITION (one='1', two, three) + SELECT key, value, PMOD(HASH(key), 10) as two, + PMOD(HASH(value), 10) as three + FROM src +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-1 + Spark +#### 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: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 10) (type: int), (hash(value) pmod 10) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge2a + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-0 + Move Operator + tables: + partition: + one 1 + three + two + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge2a + + Stage: Stage-2 + Stats-Aggr Operator + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge2a PARTITION (one='1', two, three) + SELECT key, value, PMOD(HASH(key), 10) as two, + PMOD(HASH(value), 10) as three + FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge2a@one=1 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge2a PARTITION (one='1', two, three) + SELECT key, value, PMOD(HASH(key), 10) as two, + PMOD(HASH(value), 10) as three + FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=0/three=2 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=0/three=8 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=1/three=3 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=1/three=9 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=2/three=0 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=2/three=4 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=3/three=1 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=3/three=5 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=4/three=2 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=4/three=6 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=5/three=3 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=5/three=7 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=6/three=4 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=6/three=8 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=7/three=5 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=7/three=9 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=8/three=0 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=8/three=6 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=9/three=1 +POSTHOOK: Output: default@orcfile_merge2a@one=1/two=9/three=7 +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=0,three=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=0,three=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=0,three=8).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=0,three=8).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=1,three=3).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=1,three=3).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=1,three=9).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=1,three=9).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=2,three=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=2,three=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=2,three=4).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=2,three=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=3,three=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=3,three=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=3,three=5).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=3,three=5).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=4,three=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=4,three=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=4,three=6).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=4,three=6).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=5,three=3).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=5,three=3).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=5,three=7).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=5,three=7).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=6,three=4).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=6,three=4).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=6,three=8).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=6,three=8).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=7,three=5).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=7,three=5).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=7,three=9).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=7,three=9).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=8,three=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=8,three=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=8,three=6).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=8,three=6).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=9,three=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=9,three=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=9,three=7).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge2a PARTITION(one=1,two=9,three=7).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge2a +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge2a +PREHOOK: Input: default@orcfile_merge2a@one=1/two=0/three=2 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=0/three=8 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=1/three=3 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=1/three=9 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=2/three=0 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=2/three=4 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=3/three=1 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=3/three=5 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=4/three=2 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=4/three=6 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=5/three=3 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=5/three=7 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=6/three=4 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=6/three=8 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=7/three=5 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=7/three=9 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=8/three=0 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=8/three=6 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=9/three=1 +PREHOOK: Input: default@orcfile_merge2a@one=1/two=9/three=7 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(*) USING 'tr \t _' AS (c) + FROM orcfile_merge2a +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge2a +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=0/three=2 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=0/three=8 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=1/three=3 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=1/three=9 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=2/three=0 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=2/three=4 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=3/three=1 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=3/three=5 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=4/three=2 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=4/three=6 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=5/three=3 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=5/three=7 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=6/three=4 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=6/three=8 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=7/three=5 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=7/three=9 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=8/three=0 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=8/three=6 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=9/three=1 +POSTHOOK: Input: default@orcfile_merge2a@one=1/two=9/three=7 +#### A masked pattern was here #### +-4209012844 +PREHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value, '1', PMOD(HASH(key), 10), + PMOD(HASH(value), 10)) USING 'tr \t _' AS (c) + FROM src +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@src +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value, '1', PMOD(HASH(key), 10), + PMOD(HASH(value), 10)) USING 'tr \t _' AS (c) + FROM src +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +#### A masked pattern was here #### +-4209012844 +PREHOOK: query: DROP TABLE orcfile_merge2a +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge2a +PREHOOK: Output: default@orcfile_merge2a +POSTHOOK: query: DROP TABLE orcfile_merge2a +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orcfile_merge2a +POSTHOOK: Output: default@orcfile_merge2a
http://git-wip-us.apache.org/repos/asf/hive/blob/0a88760f/ql/src/test/results/clientpositive/spark/orc_merge3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/orc_merge3.q.out b/ql/src/test/results/clientpositive/spark/orc_merge3.q.out new file mode 100644 index 0000000..81a6013 --- /dev/null +++ b/ql/src/test/results/clientpositive/spark/orc_merge3.q.out @@ -0,0 +1,207 @@ +PREHOOK: query: DROP TABLE orcfile_merge3a +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orcfile_merge3a +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE orcfile_merge3b +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orcfile_merge3b +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE orcfile_merge3a (key int, value string) + PARTITIONED BY (ds string) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge3a +POSTHOOK: query: CREATE TABLE orcfile_merge3a (key int, value string) + PARTITIONED BY (ds string) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge3a +PREHOOK: query: CREATE TABLE orcfile_merge3b (key int, value string) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge3b +POSTHOOK: query: CREATE TABLE orcfile_merge3b (key int, value string) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge3b +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='1') + SELECT * FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge3a@ds=1 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='1') + SELECT * FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge3a@ds=1 +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='2') + SELECT * FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge3a@ds=2 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='2') + SELECT * FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge3a@ds=2 +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE orcfile_merge3b + SELECT key, value FROM orcfile_merge3a +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE orcfile_merge3b + SELECT key, value FROM orcfile_merge3a +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-1 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orcfile_merge3a + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge3b + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orcfile_merge3b + + Stage: Stage-2 + Stats-Aggr Operator + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3b + SELECT key, value FROM orcfile_merge3a +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge3a +PREHOOK: Input: default@orcfile_merge3a@ds=1 +PREHOOK: Input: default@orcfile_merge3a@ds=2 +PREHOOK: Output: default@orcfile_merge3b +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3b + SELECT key, value FROM orcfile_merge3a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge3a +POSTHOOK: Input: default@orcfile_merge3a@ds=1 +POSTHOOK: Input: default@orcfile_merge3a@ds=2 +POSTHOOK: Output: default@orcfile_merge3b +POSTHOOK: Lineage: orcfile_merge3b.key SIMPLE [(orcfile_merge3a)orcfile_merge3a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: orcfile_merge3b.value SIMPLE [(orcfile_merge3a)orcfile_merge3a.FieldSchema(name:value, type:string, comment:null), ] +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) + FROM orcfile_merge3a +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge3a +PREHOOK: Input: default@orcfile_merge3a@ds=1 +PREHOOK: Input: default@orcfile_merge3a@ds=2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) + FROM orcfile_merge3a +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge3a +POSTHOOK: Input: default@orcfile_merge3a@ds=1 +POSTHOOK: Input: default@orcfile_merge3a@ds=2 +#### A masked pattern was here #### +14412220296 +PREHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) + FROM orcfile_merge3b +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge3b +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) + FROM orcfile_merge3b +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge3b +#### A masked pattern was here #### +14412220296 +PREHOOK: query: DROP TABLE orcfile_merge3a +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge3a +PREHOOK: Output: default@orcfile_merge3a +POSTHOOK: query: DROP TABLE orcfile_merge3a +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orcfile_merge3a +POSTHOOK: Output: default@orcfile_merge3a +PREHOOK: query: DROP TABLE orcfile_merge3b +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge3b +PREHOOK: Output: default@orcfile_merge3b +POSTHOOK: query: DROP TABLE orcfile_merge3b +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orcfile_merge3b +POSTHOOK: Output: default@orcfile_merge3b http://git-wip-us.apache.org/repos/asf/hive/blob/0a88760f/ql/src/test/results/clientpositive/spark/orc_merge4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/orc_merge4.q.out b/ql/src/test/results/clientpositive/spark/orc_merge4.q.out new file mode 100644 index 0000000..8d433b0 --- /dev/null +++ b/ql/src/test/results/clientpositive/spark/orc_merge4.q.out @@ -0,0 +1,231 @@ +PREHOOK: query: DROP TABLE orcfile_merge3a +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orcfile_merge3a +POSTHOOK: type: DROPTABLE +PREHOOK: query: DROP TABLE orcfile_merge3b +PREHOOK: type: DROPTABLE +POSTHOOK: query: DROP TABLE orcfile_merge3b +POSTHOOK: type: DROPTABLE +PREHOOK: query: CREATE TABLE orcfile_merge3a (key int, value string) + PARTITIONED BY (ds string) STORED AS ORC +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge3a +POSTHOOK: query: CREATE TABLE orcfile_merge3a (key int, value string) + PARTITIONED BY (ds string) STORED AS ORC +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge3a +PREHOOK: query: CREATE TABLE orcfile_merge3b (key int, value string) STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orcfile_merge3b +POSTHOOK: query: CREATE TABLE orcfile_merge3b (key int, value string) STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orcfile_merge3b +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='1') + SELECT * FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge3a@ds=1 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='1') + SELECT * FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge3a@ds=1 +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='1') + SELECT * FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge3a@ds=1 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='1') + SELECT * FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge3a@ds=1 +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='2') + SELECT * FROM src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@orcfile_merge3a@ds=2 +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='2') + SELECT * FROM src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@orcfile_merge3a@ds=2 +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: orcfile_merge3a PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +Found 1 items +#### A masked pattern was here #### +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE orcfile_merge3b + SELECT key, value FROM orcfile_merge3a +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE orcfile_merge3b + SELECT key, value FROM orcfile_merge3a +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-1 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orcfile_merge3a + Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 94000 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.orcfile_merge3b + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + 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.orcfile_merge3b + + Stage: Stage-2 + Stats-Aggr Operator + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Map Operator Tree: + TableScan + File Output Operator + compressed: false + 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.orcfile_merge3b + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Map Operator Tree: + TableScan + File Output Operator + compressed: false + 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.orcfile_merge3b + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3b + SELECT key, value FROM orcfile_merge3a +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge3a +PREHOOK: Input: default@orcfile_merge3a@ds=1 +PREHOOK: Input: default@orcfile_merge3a@ds=2 +PREHOOK: Output: default@orcfile_merge3b +POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge3b + SELECT key, value FROM orcfile_merge3a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge3a +POSTHOOK: Input: default@orcfile_merge3a@ds=1 +POSTHOOK: Input: default@orcfile_merge3a@ds=2 +POSTHOOK: Output: default@orcfile_merge3b +POSTHOOK: Lineage: orcfile_merge3b.key SIMPLE [(orcfile_merge3a)orcfile_merge3a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: orcfile_merge3b.value SIMPLE [(orcfile_merge3a)orcfile_merge3a.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) + FROM orcfile_merge3a +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge3a +PREHOOK: Input: default@orcfile_merge3a@ds=1 +PREHOOK: Input: default@orcfile_merge3a@ds=2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) + FROM orcfile_merge3a +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge3a +POSTHOOK: Input: default@orcfile_merge3a@ds=1 +POSTHOOK: Input: default@orcfile_merge3a@ds=2 +#### A masked pattern was here #### +14412220296 +PREHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) + FROM orcfile_merge3b +) t +PREHOOK: type: QUERY +PREHOOK: Input: default@orcfile_merge3b +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(c)) FROM ( + SELECT TRANSFORM(key, value) USING 'tr \t _' AS (c) + FROM orcfile_merge3b +) t +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orcfile_merge3b +#### A masked pattern was here #### +14412220296 +PREHOOK: query: DROP TABLE orcfile_merge3a +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge3a +PREHOOK: Output: default@orcfile_merge3a +POSTHOOK: query: DROP TABLE orcfile_merge3a +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orcfile_merge3a +POSTHOOK: Output: default@orcfile_merge3a +PREHOOK: query: DROP TABLE orcfile_merge3b +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@orcfile_merge3b +PREHOOK: Output: default@orcfile_merge3b +POSTHOOK: query: DROP TABLE orcfile_merge3b +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@orcfile_merge3b +POSTHOOK: Output: default@orcfile_merge3b http://git-wip-us.apache.org/repos/asf/hive/blob/0a88760f/ql/src/test/results/clientpositive/spark/orc_merge5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/orc_merge5.q.out b/ql/src/test/results/clientpositive/spark/orc_merge5.q.out new file mode 100644 index 0000000..83721f5 --- /dev/null +++ b/ql/src/test/results/clientpositive/spark/orc_merge5.q.out @@ -0,0 +1,334 @@ +PREHOOK: query: -- SORT_QUERY_RESULTS + +create table orc_merge5 (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_merge5 +POSTHOOK: query: -- SORT_QUERY_RESULTS + +create table orc_merge5 (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_merge5 +PREHOOK: query: create table orc_merge5b (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: create table orc_merge5b (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_merge5b +PREHOOK: query: load data local inpath '../../data/files/orc_split_elim.orc' into table orc_merge5 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@orc_merge5 +POSTHOOK: query: load data local inpath '../../data/files/orc_split_elim.orc' into table orc_merge5 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@orc_merge5 +PREHOOK: query: -- 3 mappers +explain insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +POSTHOOK: query: -- 3 mappers +explain insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +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 +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orc_merge5 + filterExpr: (userid <= 13) (type: boolean) + Statistics: Num rows: 919 Data size: 246402 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (userid <= 13) (type: boolean) + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5b + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5b + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5b +POSTHOOK: Lineage: orc_merge5b.decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5b.string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: -- 3 files total +analyze table orc_merge5b compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5b +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: -- 3 files total +analyze table orc_merge5b compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5b +POSTHOOK: Output: default@orc_merge5b +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: select * from orc_merge5b +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5b +#### A masked pattern was here #### +POSTHOOK: query: select * from orc_merge5b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5b +#### A masked pattern was here #### +13 bar 80.0 2 1969-12-31 16:00:05 +2 foo 0.8 1 1969-12-31 16:00:00 +5 eat 0.8 6 1969-12-31 16:00:20 +PREHOOK: query: -- 3 mappers +explain insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +POSTHOOK: query: -- 3 mappers +explain insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-1 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orc_merge5 + filterExpr: (userid <= 13) (type: boolean) + Statistics: Num rows: 919 Data size: 246402 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (userid <= 13) (type: boolean) + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5b + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5b + + Stage: Stage-2 + Stats-Aggr Operator + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5b +POSTHOOK: Lineage: orc_merge5b.decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5b.string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: -- 1 file after merging +analyze table orc_merge5b compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5b +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: -- 1 file after merging +analyze table orc_merge5b compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5b +POSTHOOK: Output: default@orc_merge5b +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: select * from orc_merge5b +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5b +#### A masked pattern was here #### +POSTHOOK: query: select * from orc_merge5b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5b +#### A masked pattern was here #### +13 bar 80.0 2 1969-12-31 16:00:05 +2 foo 0.8 1 1969-12-31 16:00:00 +5 eat 0.8 6 1969-12-31 16:00:20 +PREHOOK: query: insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5b +POSTHOOK: Lineage: orc_merge5b.decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5b.string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5b.userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: analyze table orc_merge5b compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5b +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: analyze table orc_merge5b compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5b +POSTHOOK: Output: default@orc_merge5b +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: select * from orc_merge5b +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5b +#### A masked pattern was here #### +POSTHOOK: query: select * from orc_merge5b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5b +#### A masked pattern was here #### +13 bar 80.0 2 1969-12-31 16:00:05 +2 foo 0.8 1 1969-12-31 16:00:00 +5 eat 0.8 6 1969-12-31 16:00:20 +PREHOOK: query: explain alter table orc_merge5b concatenate +PREHOOK: type: ALTER_TABLE_MERGE +POSTHOOK: query: explain alter table orc_merge5b concatenate +POSTHOOK: type: ALTER_TABLE_MERGE +STAGE DEPENDENCIES: + Stage-0 is a root stage + Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-0 + + Stage: Stage-1 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5b + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: alter table orc_merge5b concatenate +PREHOOK: type: ALTER_TABLE_MERGE +PREHOOK: Input: default@orc_merge5b +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: alter table orc_merge5b concatenate +POSTHOOK: type: ALTER_TABLE_MERGE +POSTHOOK: Input: default@orc_merge5b +POSTHOOK: Output: default@orc_merge5b +PREHOOK: query: -- 1 file after merging +analyze table orc_merge5b compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5b +PREHOOK: Output: default@orc_merge5b +POSTHOOK: query: -- 1 file after merging +analyze table orc_merge5b compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5b +POSTHOOK: Output: default@orc_merge5b +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: select * from orc_merge5b +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5b +#### A masked pattern was here #### +POSTHOOK: query: select * from orc_merge5b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5b +#### A masked pattern was here #### +13 bar 80.0 2 1969-12-31 16:00:05 +2 foo 0.8 1 1969-12-31 16:00:00 +5 eat 0.8 6 1969-12-31 16:00:20 http://git-wip-us.apache.org/repos/asf/hive/blob/0a88760f/ql/src/test/results/clientpositive/spark/orc_merge6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/orc_merge6.q.out b/ql/src/test/results/clientpositive/spark/orc_merge6.q.out new file mode 100644 index 0000000..b9b3960 --- /dev/null +++ b/ql/src/test/results/clientpositive/spark/orc_merge6.q.out @@ -0,0 +1,508 @@ +PREHOOK: query: -- SORT_QUERY_RESULTS + +-- orc file merge tests for static partitions +create table orc_merge5 (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_merge5 +POSTHOOK: query: -- SORT_QUERY_RESULTS + +-- orc file merge tests for static partitions +create table orc_merge5 (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_merge5 +PREHOOK: query: create table orc_merge5a (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) partitioned by (year string, hour int) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@orc_merge5a +POSTHOOK: query: create table orc_merge5a (userid bigint, string1 string, subtype double, decimal1 decimal, ts timestamp) partitioned by (year string, hour int) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@orc_merge5a +PREHOOK: query: load data local inpath '../../data/files/orc_split_elim.orc' into table orc_merge5 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@orc_merge5 +POSTHOOK: query: load data local inpath '../../data/files/orc_split_elim.orc' into table orc_merge5 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@orc_merge5 +PREHOOK: query: -- 3 mappers +explain insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +POSTHOOK: query: -- 3 mappers +explain insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +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 +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orc_merge5 + filterExpr: (userid <= 13) (type: boolean) + Statistics: Num rows: 919 Data size: 246402 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (userid <= 13) (type: boolean) + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5a + + Stage: Stage-0 + Move Operator + tables: + partition: + hour 24 + year 2000 + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5a + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: query: insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: insert overwrite table orc_merge5a partition (year="2001",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: query: insert overwrite table orc_merge5a partition (year="2001",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: -- 3 files total +analyze table orc_merge5a partition(year="2000",hour=24) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: query: -- 3 files total +analyze table orc_merge5a partition(year="2000",hour=24) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2000/hour=24 +PREHOOK: query: analyze table orc_merge5a partition(year="2001",hour=24) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: query: analyze table orc_merge5a partition(year="2001",hour=24) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2001/hour=24 +Found 3 items +#### A masked pattern was here #### +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: show partitions orc_merge5a +PREHOOK: type: SHOWPARTITIONS +PREHOOK: Input: default@orc_merge5a +POSTHOOK: query: show partitions orc_merge5a +POSTHOOK: type: SHOWPARTITIONS +POSTHOOK: Input: default@orc_merge5a +year=2000/hour=24 +year=2001/hour=24 +PREHOOK: query: select * from orc_merge5a +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Input: default@orc_merge5a@year=2000/hour=24 +PREHOOK: Input: default@orc_merge5a@year=2001/hour=24 +#### A masked pattern was here #### +POSTHOOK: query: select * from orc_merge5a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Input: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: Input: default@orc_merge5a@year=2001/hour=24 +#### A masked pattern was here #### +13 bar 80.0 2 1969-12-31 16:00:05 2000 24 +13 bar 80.0 2 1969-12-31 16:00:05 2001 24 +2 foo 0.8 1 1969-12-31 16:00:00 2000 24 +2 foo 0.8 1 1969-12-31 16:00:00 2001 24 +5 eat 0.8 6 1969-12-31 16:00:20 2000 24 +5 eat 0.8 6 1969-12-31 16:00:20 2001 24 +PREHOOK: query: -- 3 mappers +explain insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +POSTHOOK: query: -- 3 mappers +explain insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 + Stage-4 + Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 + Stage-2 depends on stages: Stage-0 + Stage-3 + Stage-5 + Stage-6 depends on stages: Stage-5 + +STAGE PLANS: + Stage: Stage-1 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: orc_merge5 + filterExpr: (userid <= 13) (type: boolean) + Statistics: Num rows: 919 Data size: 246402 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (userid <= 13) (type: boolean) + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(10,0)), ts (type: timestamp) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 306 Data size: 82044 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5a + + Stage: Stage-7 + Conditional Operator + + Stage: Stage-4 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + + Stage: Stage-0 + Move Operator + tables: + partition: + hour 24 + year 2000 + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5a + + Stage: Stage-2 + Stats-Aggr Operator + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Spark Merge File Work + Merge File Operator + Map Operator Tree: + ORC File Merge Operator + merge level: stripe + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + + Stage: Stage-6 + Move Operator + files: + hdfs directory: true +#### A masked pattern was here #### + +PREHOOK: query: insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: query: insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: insert overwrite table orc_merge5a partition (year="2001",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: query: insert overwrite table orc_merge5a partition (year="2001",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: -- 1 file after merging +analyze table orc_merge5a partition(year="2000",hour=24) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: query: -- 1 file after merging +analyze table orc_merge5a partition(year="2000",hour=24) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2000/hour=24 +PREHOOK: query: analyze table orc_merge5a partition(year="2001",hour=24) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: query: analyze table orc_merge5a partition(year="2001",hour=24) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2001/hour=24 +Found 1 items +#### A masked pattern was here #### +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: show partitions orc_merge5a +PREHOOK: type: SHOWPARTITIONS +PREHOOK: Input: default@orc_merge5a +POSTHOOK: query: show partitions orc_merge5a +POSTHOOK: type: SHOWPARTITIONS +POSTHOOK: Input: default@orc_merge5a +year=2000/hour=24 +year=2001/hour=24 +PREHOOK: query: select * from orc_merge5a +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Input: default@orc_merge5a@year=2000/hour=24 +PREHOOK: Input: default@orc_merge5a@year=2001/hour=24 +#### A masked pattern was here #### +POSTHOOK: query: select * from orc_merge5a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Input: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: Input: default@orc_merge5a@year=2001/hour=24 +#### A masked pattern was here #### +13 bar 80.0 2 1969-12-31 16:00:05 2000 24 +13 bar 80.0 2 1969-12-31 16:00:05 2001 24 +2 foo 0.8 1 1969-12-31 16:00:00 2000 24 +2 foo 0.8 1 1969-12-31 16:00:00 2001 24 +5 eat 0.8 6 1969-12-31 16:00:20 2000 24 +5 eat 0.8 6 1969-12-31 16:00:20 2001 24 +PREHOOK: query: insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: query: insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2000,hour=24).userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: insert overwrite table orc_merge5a partition (year="2001",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5 +PREHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: query: insert overwrite table orc_merge5a partition (year="2001",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5 +POSTHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).decimal1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:decimal1, type:decimal(10,0), comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).string1 SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:string1, type:string, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).subtype SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:subtype, type:double, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).ts SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:ts, type:timestamp, comment:null), ] +POSTHOOK: Lineage: orc_merge5a PARTITION(year=2001,hour=24).userid SIMPLE [(orc_merge5)orc_merge5.FieldSchema(name:userid, type:bigint, comment:null), ] +PREHOOK: query: analyze table orc_merge5a partition(year="2000",hour=24) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: query: analyze table orc_merge5a partition(year="2000",hour=24) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2000/hour=24 +PREHOOK: query: analyze table orc_merge5a partition(year="2001",hour=24) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: query: analyze table orc_merge5a partition(year="2001",hour=24) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2001/hour=24 +Found 3 items +#### A masked pattern was here #### +Found 3 items +#### A masked pattern was here #### +PREHOOK: query: show partitions orc_merge5a +PREHOOK: type: SHOWPARTITIONS +PREHOOK: Input: default@orc_merge5a +POSTHOOK: query: show partitions orc_merge5a +POSTHOOK: type: SHOWPARTITIONS +POSTHOOK: Input: default@orc_merge5a +year=2000/hour=24 +year=2001/hour=24 +PREHOOK: query: select * from orc_merge5a +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Input: default@orc_merge5a@year=2000/hour=24 +PREHOOK: Input: default@orc_merge5a@year=2001/hour=24 +#### A masked pattern was here #### +POSTHOOK: query: select * from orc_merge5a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Input: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: Input: default@orc_merge5a@year=2001/hour=24 +#### A masked pattern was here #### +13 bar 80.0 2 1969-12-31 16:00:05 2000 24 +13 bar 80.0 2 1969-12-31 16:00:05 2001 24 +2 foo 0.8 1 1969-12-31 16:00:00 2000 24 +2 foo 0.8 1 1969-12-31 16:00:00 2001 24 +5 eat 0.8 6 1969-12-31 16:00:20 2000 24 +5 eat 0.8 6 1969-12-31 16:00:20 2001 24 +PREHOOK: query: explain alter table orc_merge5a partition(year="2000",hour=24) concatenate +PREHOOK: type: ALTER_PARTITION_MERGE +POSTHOOK: query: explain alter table orc_merge5a partition(year="2000",hour=24) concatenate +POSTHOOK: type: ALTER_PARTITION_MERGE +STAGE DEPENDENCIES: + Stage-0 is a root stage + Stage-1 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-0 + + Stage: Stage-1 + Move Operator + tables: + partition: + hour 24 + year 2000 + replace: true + table: + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.orc_merge5a + + Stage: Stage-2 + Stats-Aggr Operator + +PREHOOK: query: alter table orc_merge5a partition(year="2000",hour=24) concatenate +PREHOOK: type: ALTER_PARTITION_MERGE +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: query: alter table orc_merge5a partition(year="2000",hour=24) concatenate +POSTHOOK: type: ALTER_PARTITION_MERGE +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2000/hour=24 +PREHOOK: query: alter table orc_merge5a partition(year="2001",hour=24) concatenate +PREHOOK: type: ALTER_PARTITION_MERGE +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: query: alter table orc_merge5a partition(year="2001",hour=24) concatenate +POSTHOOK: type: ALTER_PARTITION_MERGE +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2001/hour=24 +PREHOOK: query: -- 1 file after merging +analyze table orc_merge5a partition(year="2000",hour=24) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: query: -- 1 file after merging +analyze table orc_merge5a partition(year="2000",hour=24) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2000/hour=24 +PREHOOK: query: analyze table orc_merge5a partition(year="2001",hour=24) compute statistics noscan +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a +PREHOOK: Output: default@orc_merge5a@year=2001/hour=24 +POSTHOOK: query: analyze table orc_merge5a partition(year="2001",hour=24) compute statistics noscan +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a +POSTHOOK: Output: default@orc_merge5a@year=2001/hour=24 +Found 1 items +#### A masked pattern was here #### +Found 1 items +#### A masked pattern was here #### +PREHOOK: query: show partitions orc_merge5a +PREHOOK: type: SHOWPARTITIONS +PREHOOK: Input: default@orc_merge5a +POSTHOOK: query: show partitions orc_merge5a +POSTHOOK: type: SHOWPARTITIONS +POSTHOOK: Input: default@orc_merge5a +year=2000/hour=24 +year=2001/hour=24 +PREHOOK: query: select * from orc_merge5a +PREHOOK: type: QUERY +PREHOOK: Input: default@orc_merge5a +PREHOOK: Input: default@orc_merge5a@year=2000/hour=24 +PREHOOK: Input: default@orc_merge5a@year=2001/hour=24 +#### A masked pattern was here #### +POSTHOOK: query: select * from orc_merge5a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc_merge5a +POSTHOOK: Input: default@orc_merge5a@year=2000/hour=24 +POSTHOOK: Input: default@orc_merge5a@year=2001/hour=24 +#### A masked pattern was here #### +13 bar 80.0 2 1969-12-31 16:00:05 2000 24 +13 bar 80.0 2 1969-12-31 16:00:05 2001 24 +2 foo 0.8 1 1969-12-31 16:00:00 2000 24 +2 foo 0.8 1 1969-12-31 16:00:00 2001 24 +5 eat 0.8 6 1969-12-31 16:00:20 2000 24 +5 eat 0.8 6 1969-12-31 16:00:20 2001 24
