You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2015/11/19 03:37:49 UTC
[3/3] hive git commit: HIVE-12091: Merge file doesn't work for ORC
table when running on Spark. [Spark Branch] (Rui reviewed by Xuefu)
HIVE-12091: Merge file doesn't work for ORC table when running on Spark. [Spark Branch] (Rui reviewed by Xuefu)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/74b039bc
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/74b039bc
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/74b039bc
Branch: refs/heads/branch-1
Commit: 74b039bc21cd4152358a85fbebfaa57cd1ec6ce2
Parents: c5b6b8d
Author: Rui Li <ru...@intel.com>
Authored: Wed Oct 14 10:25:16 2015 +0800
Committer: Xuefu Zhang <xz...@Cloudera.com>
Committed: Wed Nov 18 18:37:38 2015 -0800
----------------------------------------------------------------------
.../test/resources/testconfiguration.properties | 11 +
.../hive/ql/exec/spark/SparkPlanGenerator.java | 16 +
ql/src/test/queries/clientpositive/orc_merge1.q | 2 +
ql/src/test/queries/clientpositive/orc_merge2.q | 1 +
ql/src/test/queries/clientpositive/orc_merge3.q | 1 +
ql/src/test/queries/clientpositive/orc_merge4.q | 2 +
ql/src/test/queries/clientpositive/orc_merge5.q | 3 +
ql/src/test/queries/clientpositive/orc_merge6.q | 3 +
ql/src/test/queries/clientpositive/orc_merge7.q | 3 +
ql/src/test/queries/clientpositive/orc_merge8.q | 2 +
ql/src/test/queries/clientpositive/orc_merge9.q | 1 +
.../clientpositive/orc_merge_incompat1.q | 1 +
.../clientpositive/orc_merge_incompat2.q | 1 +
.../clientpositive/spark/orc_merge1.q.out | 485 +++++++++++++++
.../clientpositive/spark/orc_merge2.q.out | 268 ++++++++
.../clientpositive/spark/orc_merge3.q.out | 207 +++++++
.../clientpositive/spark/orc_merge4.q.out | 231 +++++++
.../clientpositive/spark/orc_merge5.q.out | 334 ++++++++++
.../clientpositive/spark/orc_merge6.q.out | 508 +++++++++++++++
.../clientpositive/spark/orc_merge7.q.out | 619 +++++++++++++++++++
.../clientpositive/spark/orc_merge8.q.out | 130 ++++
.../clientpositive/spark/orc_merge9.q.out | 186 ++++++
.../spark/orc_merge_incompat1.q.out | 240 +++++++
.../spark/orc_merge_incompat2.q.out | 370 +++++++++++
24 files changed, 3625 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/itests/src/test/resources/testconfiguration.properties
----------------------------------------------------------------------
diff --git a/itests/src/test/resources/testconfiguration.properties b/itests/src/test/resources/testconfiguration.properties
index 88dac04..caa8484 100644
--- a/itests/src/test/resources/testconfiguration.properties
+++ b/itests/src/test/resources/testconfiguration.properties
@@ -1138,6 +1138,17 @@ miniSparkOnYarn.query.files=auto_sortmerge_join_16.q,\
load_fs2.q,\
load_hdfs_file_with_space_in_the_name.q,\
optrstat_groupby.q,\
+ orc_merge1.q,\
+ orc_merge2.q,\
+ orc_merge3.q,\
+ orc_merge4.q,\
+ orc_merge5.q,\
+ orc_merge6.q,\
+ orc_merge7.q,\
+ orc_merge8.q,\
+ orc_merge9.q,\
+ orc_merge_incompat1.q,\
+ orc_merge_incompat2.q,\
parallel_orderby.q,\
ql_rewrite_gbtoidx.q,\
ql_rewrite_gbtoidx_cbo_1.q,\
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkPlanGenerator.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkPlanGenerator.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkPlanGenerator.java
index 762ce7d..d2c5245 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkPlanGenerator.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkPlanGenerator.java
@@ -18,6 +18,7 @@
package org.apache.hadoop.hive.ql.exec.spark;
+import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
@@ -27,6 +28,7 @@ import com.google.common.base.Preconditions;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hive.common.JavaUtils;
import org.apache.hadoop.hive.ql.io.merge.MergeFileMapper;
@@ -220,6 +222,20 @@ public class SparkPlanGenerator {
byte[] confBytes = KryoSerializer.serializeJobConf(newJobConf);
boolean caching = isCachingWork(work, sparkWork);
if (work instanceof MapWork) {
+ // Create tmp dir for MergeFileWork
+ if (work instanceof MergeFileWork) {
+ Path outputPath = ((MergeFileWork) work).getOutputDir();
+ Path tempOutPath = Utilities.toTempPath(outputPath);
+ FileSystem fs = outputPath.getFileSystem(jobConf);
+ try {
+ if (!fs.exists(tempOutPath)) {
+ fs.mkdirs(tempOutPath);
+ }
+ } catch (IOException e) {
+ throw new RuntimeException(
+ "Can't make path " + outputPath + " : " + e.getMessage());
+ }
+ }
MapTran mapTran = new MapTran(caching);
HiveMapFunction mapFunc = new HiveMapFunction(confBytes, sparkReporter);
mapTran.setMapFunction(mapFunc);
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge1.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge1.q b/ql/src/test/queries/clientpositive/orc_merge1.q
index 1c0bf41..5ffe210 100644
--- a/ql/src/test/queries/clientpositive/orc_merge1.q
+++ b/ql/src/test/queries/clientpositive/orc_merge1.q
@@ -9,6 +9,7 @@ set tez.grouping.max-size=2000;
set hive.merge.tezfiles=false;
set hive.merge.mapfiles=false;
set hive.merge.mapredfiles=false;
+set hive.merge.sparkfiles=false;
-- SORT_QUERY_RESULTS
@@ -38,6 +39,7 @@ dfs -ls ${hiveconf:hive.metastore.warehouse.dir}/orcfile_merge1/ds=1/part=0/;
set hive.merge.tezfiles=true;
set hive.merge.mapfiles=true;
set hive.merge.mapredfiles=true;
+set hive.merge.sparkfiles=true;
-- auto-merge slow way
EXPLAIN
INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part)
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge2.q b/ql/src/test/queries/clientpositive/orc_merge2.q
index 9ffc4bc..11a7ee1 100644
--- a/ql/src/test/queries/clientpositive/orc_merge2.q
+++ b/ql/src/test/queries/clientpositive/orc_merge2.q
@@ -1,6 +1,7 @@
set hive.merge.orcfile.stripe.level=true;
set hive.exec.dynamic.partition=true;
set hive.exec.dynamic.partition.mode=nonstrict;
+set hive.merge.sparkfiles=true;
DROP TABLE orcfile_merge2a;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge3.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge3.q b/ql/src/test/queries/clientpositive/orc_merge3.q
index 444ea65..32a6e77 100644
--- a/ql/src/test/queries/clientpositive/orc_merge3.q
+++ b/ql/src/test/queries/clientpositive/orc_merge3.q
@@ -1,4 +1,5 @@
set hive.merge.orcfile.stripe.level=true;
+set hive.merge.sparkfiles=true;
DROP TABLE orcfile_merge3a;
DROP TABLE orcfile_merge3b;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge4.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge4.q b/ql/src/test/queries/clientpositive/orc_merge4.q
index 769d4d3..0ce3507 100644
--- a/ql/src/test/queries/clientpositive/orc_merge4.q
+++ b/ql/src/test/queries/clientpositive/orc_merge4.q
@@ -8,12 +8,14 @@ CREATE TABLE orcfile_merge3a (key int, value string)
CREATE TABLE orcfile_merge3b (key int, value string) STORED AS TEXTFILE;
set hive.merge.mapfiles=false;
+set hive.merge.sparkfiles=false;
INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='1')
SELECT * FROM src;
dfs -ls ${hiveconf:hive.metastore.warehouse.dir}/orcfile_merge3a/ds=1/;
set hive.merge.mapfiles=true;
+set hive.merge.sparkfiles=true;
INSERT OVERWRITE TABLE orcfile_merge3a PARTITION (ds='1')
SELECT * FROM src;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge5.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge5.q b/ql/src/test/queries/clientpositive/orc_merge5.q
index 9682347..65a1a3b 100644
--- a/ql/src/test/queries/clientpositive/orc_merge5.q
+++ b/ql/src/test/queries/clientpositive/orc_merge5.q
@@ -16,6 +16,7 @@ set hive.merge.mapredfiles=false;
set hive.compute.splits.in.am=true;
set tez.grouping.min-size=1000;
set tez.grouping.max-size=50000;
+set hive.merge.sparkfiles=false;
-- 3 mappers
explain insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13;
@@ -30,6 +31,7 @@ set hive.merge.orcfile.stripe.level=true;
set hive.merge.tezfiles=true;
set hive.merge.mapfiles=true;
set hive.merge.mapredfiles=true;
+set hive.merge.sparkfiles=true;
-- 3 mappers
explain insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13;
@@ -44,6 +46,7 @@ set hive.merge.orcfile.stripe.level=false;
set hive.merge.tezfiles=false;
set hive.merge.mapfiles=false;
set hive.merge.mapredfiles=false;
+set hive.merge.sparkfiles=false;
insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13;
analyze table orc_merge5b compute statistics noscan;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge6.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge6.q b/ql/src/test/queries/clientpositive/orc_merge6.q
index cddc73a..7522741 100644
--- a/ql/src/test/queries/clientpositive/orc_merge6.q
+++ b/ql/src/test/queries/clientpositive/orc_merge6.q
@@ -17,6 +17,7 @@ set hive.merge.mapredfiles=false;
set hive.compute.splits.in.am=true;
set tez.grouping.min-size=1000;
set tez.grouping.max-size=50000;
+set hive.merge.sparkfiles=false;
-- 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;
@@ -35,6 +36,7 @@ set hive.merge.orcfile.stripe.level=true;
set hive.merge.tezfiles=true;
set hive.merge.mapfiles=true;
set hive.merge.mapredfiles=true;
+set hive.merge.sparkfiles=true;
-- 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;
@@ -53,6 +55,7 @@ set hive.merge.orcfile.stripe.level=false;
set hive.merge.tezfiles=false;
set hive.merge.mapfiles=false;
set hive.merge.mapredfiles=false;
+set hive.merge.sparkfiles=false;
insert overwrite table orc_merge5a partition (year="2000",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13;
insert overwrite table orc_merge5a partition (year="2001",hour=24) select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge7.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge7.q b/ql/src/test/queries/clientpositive/orc_merge7.q
index 7e0d352..f875331 100644
--- a/ql/src/test/queries/clientpositive/orc_merge7.q
+++ b/ql/src/test/queries/clientpositive/orc_merge7.q
@@ -21,6 +21,7 @@ set tez.grouping.max-size=50000;
set hive.exec.dynamic.partition=true;
set hive.exec.dynamic.partition.mode=nonstrict;
set hive.optimize.sort.dynamic.partition=false;
+set hive.merge.sparkfiles=false;
-- 3 mappers
explain insert overwrite table orc_merge5a partition (st) select userid,string1,subtype,decimal1,ts,subtype from orc_merge5;
@@ -39,6 +40,7 @@ set hive.merge.orcfile.stripe.level=true;
set hive.merge.tezfiles=true;
set hive.merge.mapfiles=true;
set hive.merge.mapredfiles=true;
+set hive.merge.sparkfiles=true;
-- 3 mappers
explain insert overwrite table orc_merge5a partition (st) select userid,string1,subtype,decimal1,ts,subtype from orc_merge5;
@@ -57,6 +59,7 @@ set hive.merge.orcfile.stripe.level=false;
set hive.merge.tezfiles=false;
set hive.merge.mapfiles=false;
set hive.merge.mapredfiles=false;
+set hive.merge.sparkfiles=false;
insert overwrite table orc_merge5a partition (st) select userid,string1,subtype,decimal1,ts,subtype from orc_merge5;
insert overwrite table orc_merge5a partition (st) select userid,string1,subtype,decimal1,ts,subtype from orc_merge5;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge8.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge8.q b/ql/src/test/queries/clientpositive/orc_merge8.q
index 61ea4bf..30a892b 100644
--- a/ql/src/test/queries/clientpositive/orc_merge8.q
+++ b/ql/src/test/queries/clientpositive/orc_merge8.q
@@ -30,6 +30,7 @@ set hive.merge.orcfile.stripe.level=false;
set hive.merge.tezfiles=false;
set hive.merge.mapfiles=false;
set hive.merge.mapredfiles=false;
+set hive.merge.sparkfiles=false;
insert overwrite table alltypes_orc select * from alltypes;
insert into table alltypes_orc select * from alltypes;
@@ -40,6 +41,7 @@ set hive.merge.orcfile.stripe.level=true;
set hive.merge.tezfiles=true;
set hive.merge.mapfiles=true;
set hive.merge.mapredfiles=true;
+set hive.merge.sparkfiles=true;
alter table alltypes_orc concatenate;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge9.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge9.q b/ql/src/test/queries/clientpositive/orc_merge9.q
index 010b5a1..5f387ba 100644
--- a/ql/src/test/queries/clientpositive/orc_merge9.q
+++ b/ql/src/test/queries/clientpositive/orc_merge9.q
@@ -15,6 +15,7 @@ set hive.merge.orcfile.stripe.level=true;
set hive.merge.tezfiles=true;
set hive.merge.mapfiles=true;
set hive.merge.mapredfiles=true;
+set hive.merge.sparkfiles=true;
select count(*) from ts_merge;
alter table ts_merge concatenate;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge_incompat1.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge_incompat1.q b/ql/src/test/queries/clientpositive/orc_merge_incompat1.q
index 0348948..861d8d4 100644
--- a/ql/src/test/queries/clientpositive/orc_merge_incompat1.q
+++ b/ql/src/test/queries/clientpositive/orc_merge_incompat1.q
@@ -9,6 +9,7 @@ SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat;
set hive.merge.orcfile.stripe.level=false;
set hive.merge.mapfiles=false;
set hive.merge.mapredfiles=false;
+set hive.merge.sparkfiles=false;
-- 3 mappers
explain insert overwrite table orc_merge5b select userid,string1,subtype,decimal1,ts from orc_merge5 where userid<=13;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/queries/clientpositive/orc_merge_incompat2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/orc_merge_incompat2.q b/ql/src/test/queries/clientpositive/orc_merge_incompat2.q
index 5deec3c..6bfcaee 100644
--- a/ql/src/test/queries/clientpositive/orc_merge_incompat2.q
+++ b/ql/src/test/queries/clientpositive/orc_merge_incompat2.q
@@ -21,6 +21,7 @@ set tez.am.grouping.max-size=50000;
set hive.exec.dynamic.partition=true;
set hive.exec.dynamic.partition.mode=nonstrict;
set hive.optimize.sort.dynamic.partition=false;
+set hive.merge.sparkfiles=false;
explain insert overwrite table orc_merge5a partition (st) select userid,string1,subtype,decimal1,ts,subtype from orc_merge5;
set hive.exec.orc.default.row.index.stride=1000;
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/ql/src/test/results/clientpositive/spark/orc_merge1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/orc_merge1.q.out b/ql/src/test/results/clientpositive/spark/orc_merge1.q.out
new file mode 100644
index 0000000..86df0a7
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/orc_merge1.q.out
@@ -0,0 +1,485 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+DROP TABLE orcfile_merge1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+DROP TABLE orcfile_merge1
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE orcfile_merge1b
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE orcfile_merge1b
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE orcfile_merge1c
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE orcfile_merge1c
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE orcfile_merge1 (key INT, value STRING)
+ PARTITIONED BY (ds STRING, part STRING) STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@orcfile_merge1
+POSTHOOK: query: CREATE TABLE orcfile_merge1 (key INT, value STRING)
+ PARTITIONED BY (ds STRING, part STRING) STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@orcfile_merge1
+PREHOOK: query: CREATE TABLE orcfile_merge1b (key INT, value STRING)
+ PARTITIONED BY (ds STRING, part STRING) STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@orcfile_merge1b
+POSTHOOK: query: CREATE TABLE orcfile_merge1b (key INT, value STRING)
+ PARTITIONED BY (ds STRING, part STRING) STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@orcfile_merge1b
+PREHOOK: query: CREATE TABLE orcfile_merge1c (key INT, value STRING)
+ PARTITIONED BY (ds STRING, part STRING) STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@orcfile_merge1c
+POSTHOOK: query: CREATE TABLE orcfile_merge1c (key INT, value STRING)
+ PARTITIONED BY (ds STRING, part STRING) STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@orcfile_merge1c
+PREHOOK: query: -- merge disabled
+EXPLAIN
+ INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- merge disabled
+EXPLAIN
+ INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+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: 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 2) (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ 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_merge1
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 1
+ part
+ 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_merge1
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@orcfile_merge1@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1 PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@orcfile_merge1@ds=1/part=0
+POSTHOOK: Output: default@orcfile_merge1@ds=1/part=1
+POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1 PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+Found 2 items
+#### A masked pattern was here ####
+PREHOOK: query: -- auto-merge slow way
+EXPLAIN
+ INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- auto-merge slow way
+EXPLAIN
+ INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ 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 2) (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ 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_merge1b
+
+ 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:
+ ds 1
+ part
+ 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_merge1b
+
+ 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.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_merge1b
+
+ 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.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_merge1b
+
+ Stage: Stage-6
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+PREHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@orcfile_merge1b@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1b PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@orcfile_merge1b@ds=1/part=0
+POSTHOOK: Output: default@orcfile_merge1b@ds=1/part=1
+POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1b PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+Found 1 items
+#### A masked pattern was here ####
+PREHOOK: query: -- auto-merge fast way
+EXPLAIN
+ INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- auto-merge fast way
+EXPLAIN
+ INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ 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 2) (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ 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_merge1c
+
+ 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:
+ ds 1
+ part
+ 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_merge1c
+
+ 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_merge1c PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@orcfile_merge1c@ds=1
+POSTHOOK: query: INSERT OVERWRITE TABLE orcfile_merge1c PARTITION (ds='1', part)
+ SELECT key, value, PMOD(HASH(key), 2) as part
+ FROM src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@orcfile_merge1c@ds=1/part=0
+POSTHOOK: Output: default@orcfile_merge1c@ds=1/part=1
+POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=0).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=0).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: orcfile_merge1c PARTITION(ds=1,part=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+Found 1 items
+#### A masked pattern was here ####
+PREHOOK: query: -- Verify
+SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c)
+ FROM orcfile_merge1 WHERE ds='1'
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcfile_merge1
+PREHOOK: Input: default@orcfile_merge1@ds=1/part=0
+PREHOOK: Input: default@orcfile_merge1@ds=1/part=1
+#### A masked pattern was here ####
+POSTHOOK: query: -- Verify
+SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c)
+ FROM orcfile_merge1 WHERE ds='1'
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcfile_merge1
+POSTHOOK: Input: default@orcfile_merge1@ds=1/part=0
+POSTHOOK: Input: default@orcfile_merge1@ds=1/part=1
+#### A masked pattern was here ####
+-21975308766
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c)
+ FROM orcfile_merge1b WHERE ds='1'
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcfile_merge1b
+PREHOOK: Input: default@orcfile_merge1b@ds=1/part=0
+PREHOOK: Input: default@orcfile_merge1b@ds=1/part=1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c)
+ FROM orcfile_merge1b WHERE ds='1'
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcfile_merge1b
+POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=0
+POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=1
+#### A masked pattern was here ####
+-21975308766
+PREHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c)
+ FROM orcfile_merge1c WHERE ds='1'
+) t
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcfile_merge1c
+PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0
+PREHOOK: Input: default@orcfile_merge1c@ds=1/part=1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(c)) FROM (
+ SELECT TRANSFORM(*) USING 'tr \t _' AS (c)
+ FROM orcfile_merge1c WHERE ds='1'
+) t
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcfile_merge1c
+POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=0
+POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=1
+#### A masked pattern was here ####
+-21975308766
+PREHOOK: query: select count(*) from orcfile_merge1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcfile_merge1
+PREHOOK: Input: default@orcfile_merge1@ds=1/part=0
+PREHOOK: Input: default@orcfile_merge1@ds=1/part=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from orcfile_merge1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcfile_merge1
+POSTHOOK: Input: default@orcfile_merge1@ds=1/part=0
+POSTHOOK: Input: default@orcfile_merge1@ds=1/part=1
+#### A masked pattern was here ####
+500
+PREHOOK: query: select count(*) from orcfile_merge1b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcfile_merge1b
+PREHOOK: Input: default@orcfile_merge1b@ds=1/part=0
+PREHOOK: Input: default@orcfile_merge1b@ds=1/part=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from orcfile_merge1b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcfile_merge1b
+POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=0
+POSTHOOK: Input: default@orcfile_merge1b@ds=1/part=1
+#### A masked pattern was here ####
+500
+PREHOOK: query: select count(*) from orcfile_merge1c
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcfile_merge1c
+PREHOOK: Input: default@orcfile_merge1c@ds=1/part=0
+PREHOOK: Input: default@orcfile_merge1c@ds=1/part=1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from orcfile_merge1c
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcfile_merge1c
+POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=0
+POSTHOOK: Input: default@orcfile_merge1c@ds=1/part=1
+#### A masked pattern was here ####
+500
+PREHOOK: query: DROP TABLE orcfile_merge1
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@orcfile_merge1
+PREHOOK: Output: default@orcfile_merge1
+POSTHOOK: query: DROP TABLE orcfile_merge1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@orcfile_merge1
+POSTHOOK: Output: default@orcfile_merge1
+PREHOOK: query: DROP TABLE orcfile_merge1b
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@orcfile_merge1b
+PREHOOK: Output: default@orcfile_merge1b
+POSTHOOK: query: DROP TABLE orcfile_merge1b
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@orcfile_merge1b
+POSTHOOK: Output: default@orcfile_merge1b
+PREHOOK: query: DROP TABLE orcfile_merge1c
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@orcfile_merge1c
+PREHOOK: Output: default@orcfile_merge1c
+POSTHOOK: query: DROP TABLE orcfile_merge1c
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@orcfile_merge1c
+POSTHOOK: Output: default@orcfile_merge1c
http://git-wip-us.apache.org/repos/asf/hive/blob/74b039bc/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/74b039bc/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/74b039bc/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/74b039bc/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