This is an automated email from the ASF dual-hosted git repository.
aasha pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new 11ee73c HIVE-25579. LOAD overwrite appends rather than ovewriting.
(#2687)(Ayush Saxena, reviewed by Anurag Shekhar)
11ee73c is described below
commit 11ee73c1cce91b7b64f305e940656ae717fba836
Author: Ayush Saxena <ayushsax...@apache.org>
AuthorDate: Mon Oct 4 09:43:17 2021 +0530
HIVE-25579. LOAD overwrite appends rather than ovewriting. (#2687)(Ayush
Saxena, reviewed by Anurag Shekhar)
---
.../hadoop/hive/ql/parse/LoadSemanticAnalyzer.java | 7 +-
.../queries/clientpositive/load_data_using_job.q | 14 +++-
.../clientpositive/llap/load_data_using_job.q.out | 92 ++++++++++++++++++++++
3 files changed, 111 insertions(+), 2 deletions(-)
diff --git
a/ql/src/java/org/apache/hadoop/hive/ql/parse/LoadSemanticAnalyzer.java
b/ql/src/java/org/apache/hadoop/hive/ql/parse/LoadSemanticAnalyzer.java
index f003476..7ed6d1b 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/LoadSemanticAnalyzer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/LoadSemanticAnalyzer.java
@@ -518,7 +518,12 @@ public class LoadSemanticAnalyzer extends SemanticAnalyzer
{
// Step 2 : create the Insert query
StringBuilder rewrittenQueryStr = new StringBuilder();
- rewrittenQueryStr.append("insert into table ");
+ if (isOverWrite) {
+ rewrittenQueryStr.append("insert overwrite table ");
+ } else {
+ rewrittenQueryStr.append("insert into table ");
+ }
+
rewrittenQueryStr.append(getFullTableNameForSQL((ASTNode)(tableTree.getChild(0))));
addPartitionColsToInsert(table.getPartCols(), inpPartSpec,
rewrittenQueryStr);
rewrittenQueryStr.append(" select * from ");
diff --git a/ql/src/test/queries/clientpositive/load_data_using_job.q
b/ql/src/test/queries/clientpositive/load_data_using_job.q
index a2d45e5..a328ff9 100644
--- a/ql/src/test/queries/clientpositive/load_data_using_job.q
+++ b/ql/src/test/queries/clientpositive/load_data_using_job.q
@@ -109,4 +109,16 @@ CREATE TABLE orc_test_txn (`id` integer, name string, dept
string) PARTITIONED B
explain load data local inpath '../../data/files/load_data_job_acid' into
table orc_test_txn;
load data local inpath '../../data/files/load_data_job_acid' into table
orc_test_txn;
-select * from orc_test_txn;
\ No newline at end of file
+select * from orc_test_txn;
+
+-- Test Load Overwrite.
+
+load data local inpath '../../data/files/load_data_job_acid' OVERWRITE into
table orc_test_txn;
+
+select count(*) from orc_test_txn;
+select * from orc_test_txn;
+
+load data local inpath '../../data/files/load_data_job_acid' OVERWRITE into
table orc_test_txn;
+
+select count(*) from orc_test_txn;
+select * from orc_test_txn;
diff --git a/ql/src/test/results/clientpositive/llap/load_data_using_job.q.out
b/ql/src/test/results/clientpositive/llap/load_data_using_job.q.out
index c94931e..67e2c91 100644
--- a/ql/src/test/results/clientpositive/llap/load_data_using_job.q.out
+++ b/ql/src/test/results/clientpositive/llap/load_data_using_job.q.out
@@ -3232,3 +3232,95 @@ POSTHOOK: Input: default@orc_test_txn@year=2018
10 Haley CSE 2018
8 Henry CSE 2016
9 Harris CSE 2017
+#### A masked pattern was here ####
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orc_test_txn__temp_table_for_load_data__
+PREHOOK: Output: default@orc_test_txn
+#### A masked pattern was here ####
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orc_test_txn__temp_table_for_load_data__
+POSTHOOK: Output: default@orc_test_txn
+POSTHOOK: Output: default@orc_test_txn@year=2016
+POSTHOOK: Output: default@orc_test_txn@year=2017
+POSTHOOK: Output: default@orc_test_txn@year=2018
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2016).dept SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:dept,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2016).id SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:id,
type:int, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2016).name SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:name,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2017).dept SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:dept,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2017).id SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:id,
type:int, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2017).name SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:name,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2018).dept SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:dept,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2018).id SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:id,
type:int, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2018).name SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:name,
type:string, comment:null), ]
+PREHOOK: query: select count(*) from orc_test_txn
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orc_test_txn
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from orc_test_txn
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orc_test_txn
+#### A masked pattern was here ####
+3
+PREHOOK: query: select * from orc_test_txn
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orc_test_txn
+PREHOOK: Input: default@orc_test_txn@year=2016
+PREHOOK: Input: default@orc_test_txn@year=2017
+PREHOOK: Input: default@orc_test_txn@year=2018
+#### A masked pattern was here ####
+POSTHOOK: query: select * from orc_test_txn
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orc_test_txn
+POSTHOOK: Input: default@orc_test_txn@year=2016
+POSTHOOK: Input: default@orc_test_txn@year=2017
+POSTHOOK: Input: default@orc_test_txn@year=2018
+#### A masked pattern was here ####
+10 Haley CSE 2018
+8 Henry CSE 2016
+9 Harris CSE 2017
+#### A masked pattern was here ####
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orc_test_txn__temp_table_for_load_data__
+PREHOOK: Output: default@orc_test_txn
+#### A masked pattern was here ####
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orc_test_txn__temp_table_for_load_data__
+POSTHOOK: Output: default@orc_test_txn
+POSTHOOK: Output: default@orc_test_txn@year=2016
+POSTHOOK: Output: default@orc_test_txn@year=2017
+POSTHOOK: Output: default@orc_test_txn@year=2018
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2016).dept SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:dept,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2016).id SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:id,
type:int, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2016).name SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:name,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2017).dept SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:dept,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2017).id SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:id,
type:int, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2017).name SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:name,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2018).dept SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:dept,
type:string, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2018).id SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:id,
type:int, comment:null), ]
+POSTHOOK: Lineage: orc_test_txn PARTITION(year=2018).name SIMPLE
[(orc_test_txn__temp_table_for_load_data__)orc_test_txn__temp_table_for_load_data__.FieldSchema(name:name,
type:string, comment:null), ]
+PREHOOK: query: select count(*) from orc_test_txn
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orc_test_txn
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from orc_test_txn
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orc_test_txn
+#### A masked pattern was here ####
+3
+PREHOOK: query: select * from orc_test_txn
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orc_test_txn
+PREHOOK: Input: default@orc_test_txn@year=2016
+PREHOOK: Input: default@orc_test_txn@year=2017
+PREHOOK: Input: default@orc_test_txn@year=2018
+#### A masked pattern was here ####
+POSTHOOK: query: select * from orc_test_txn
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orc_test_txn
+POSTHOOK: Input: default@orc_test_txn@year=2016
+POSTHOOK: Input: default@orc_test_txn@year=2017
+POSTHOOK: Input: default@orc_test_txn@year=2018
+#### A masked pattern was here ####
+10 Haley CSE 2018
+8 Henry CSE 2016
+9 Harris CSE 2017
