Author: hashutosh
Date: Tue May 27 18:48:39 2014
New Revision: 1597848
URL: http://svn.apache.org/r1597848
Log:
HIVE-3756 : alter table set fileformat should set serde too (Chinna Rao Lalam
via Ashutosh Chauhan)
Modified:
hive/trunk/hcatalog/core/src/test/java/org/apache/hive/hcatalog/cli/TestUseDatabase.java
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/DDLSemanticAnalyzer.java
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
hive/trunk/ql/src/test/queries/clientpositive/exim_04_evolved_parts.q
hive/trunk/ql/src/test/queries/clientpositive/parquet_serde.q
hive/trunk/ql/src/test/results/clientpositive/exim_04_evolved_parts.q.out
hive/trunk/ql/src/test/results/clientpositive/parquet_serde.q.out
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat.q.out
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat3.q.out
Modified:
hive/trunk/hcatalog/core/src/test/java/org/apache/hive/hcatalog/cli/TestUseDatabase.java
URL:
http://svn.apache.org/viewvc/hive/trunk/hcatalog/core/src/test/java/org/apache/hive/hcatalog/cli/TestUseDatabase.java?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
---
hive/trunk/hcatalog/core/src/test/java/org/apache/hive/hcatalog/cli/TestUseDatabase.java
(original)
+++
hive/trunk/hcatalog/core/src/test/java/org/apache/hive/hcatalog/cli/TestUseDatabase.java
Tue May 27 18:48:39 2014
@@ -68,8 +68,10 @@ public class TestUseDatabase extends Tes
assertEquals(0, response.getResponseCode());
assertNull(response.getErrorMessage());
- response = hcatDriver.run("alter table " + tblName + " set fileformat
INPUTFORMAT 'org.apache.hadoop.hive.ql.io.RCFileInputFormat' OUTPUTFORMAT " +
- "'org.apache.hadoop.hive.ql.io.RCFileOutputFormat' inputdriver
'mydriver' outputdriver 'yourdriver'");
+ response = hcatDriver.run("alter table " + tblName + " set fileformat "
+ + "INPUTFORMAT 'org.apache.hadoop.hive.ql.io.RCFileInputFormat' "
+ + "OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.RCFileOutputFormat' "
+ + "serde
'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe' inputdriver
'mydriver' outputdriver 'yourdriver'");
assertEquals(0, response.getResponseCode());
assertNull(response.getErrorMessage());
Modified:
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/DDLSemanticAnalyzer.java
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/DDLSemanticAnalyzer.java?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
---
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/DDLSemanticAnalyzer.java
(original)
+++
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/DDLSemanticAnalyzer.java
Tue May 27 18:48:39 2014
@@ -1328,9 +1328,12 @@ public class DDLSemanticAnalyzer extends
.getText());
outputFormat = unescapeSQLString(((ASTNode) child.getChild(1)).getToken()
.getText());
+ serde = unescapeSQLString(((ASTNode) child.getChild(2)).getToken()
+ .getText());
try {
Class.forName(inputFormat);
Class.forName(outputFormat);
+ Class.forName(serde);
} catch (ClassNotFoundException e) {
throw new SemanticException(e);
}
@@ -1347,10 +1350,12 @@ public class DDLSemanticAnalyzer extends
case HiveParser.TOK_TBLSEQUENCEFILE:
inputFormat = SEQUENCEFILE_INPUT;
outputFormat = SEQUENCEFILE_OUTPUT;
+ serde =
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.class.getName();
break;
case HiveParser.TOK_TBLTEXTFILE:
inputFormat = TEXTFILE_INPUT;
outputFormat = TEXTFILE_OUTPUT;
+ serde =
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe.class.getName();
break;
case HiveParser.TOK_TBLRCFILE:
inputFormat = RCFILE_INPUT;
Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
(original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g Tue May
27 18:48:39 2014
@@ -1270,8 +1270,8 @@ fileFormat
| KW_RCFILE -> ^(TOK_TBLRCFILE)
| KW_ORCFILE -> ^(TOK_TBLORCFILE)
| KW_PARQUETFILE -> ^(TOK_TBLPARQUETFILE)
- | KW_INPUTFORMAT inFmt=StringLiteral KW_OUTPUTFORMAT outFmt=StringLiteral
(KW_INPUTDRIVER inDriver=StringLiteral KW_OUTPUTDRIVER outDriver=StringLiteral)?
- -> ^(TOK_TABLEFILEFORMAT $inFmt $outFmt $inDriver? $outDriver?)
+ | KW_INPUTFORMAT inFmt=StringLiteral KW_OUTPUTFORMAT outFmt=StringLiteral
KW_SERDE serdeCls=StringLiteral (KW_INPUTDRIVER inDriver=StringLiteral
KW_OUTPUTDRIVER outDriver=StringLiteral)?
+ -> ^(TOK_TABLEFILEFORMAT $inFmt $outFmt $serdeCls $inDriver? $outDriver?)
| genericSpec=identifier -> ^(TOK_FILEFORMAT_GENERIC $genericSpec)
;
Modified: hive/trunk/ql/src/test/queries/clientpositive/exim_04_evolved_parts.q
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/exim_04_evolved_parts.q?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/exim_04_evolved_parts.q
(original)
+++ hive/trunk/ql/src/test/queries/clientpositive/exim_04_evolved_parts.q Tue
May 27 18:48:39 2014
@@ -13,10 +13,13 @@ alter table exim_employee add columns (e
alter table exim_employee clustered by (emp_sex, emp_dept) sorted by (emp_id
desc) into 5 buckets;
alter table exim_employee add partition (emp_country='in', emp_state='tn');
-alter table exim_employee set serde
"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe" with serdeproperties
('serialization.format'='2');
alter table exim_employee set fileformat
- inputformat "org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat"
- outputformat
"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat";
+ inputformat "org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat"
+ outputformat "org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat"
+ serde
"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe";
+
+;
+alter table exim_employee set serde
"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe" with serdeproperties
('serialization.format'='2');
alter table exim_employee add partition (emp_country='in', emp_state='ka');
dfs ${system:test.dfs.mkdir}
target/tmp/ql/test/data/exports/exim_employee/temp;
@@ -36,4 +39,4 @@ dfs -rmr target/tmp/ql/test/data/exports
select * from exim_employee;
drop table exim_employee;
-drop database importer;
\ No newline at end of file
+drop database importer;
Modified: hive/trunk/ql/src/test/queries/clientpositive/parquet_serde.q
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/parquet_serde.q?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/parquet_serde.q (original)
+++ hive/trunk/ql/src/test/queries/clientpositive/parquet_serde.q Tue May 27
18:48:39 2014
@@ -22,7 +22,7 @@ ALTER TABLE parquet_mixed_fileformat set
ALTER TABLE parquet_mixed_fileformat
SET FILEFORMAT
INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
- OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat';
+ OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat' SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe';
DESCRIBE FORMATTED parquet_mixed_fileformat;
DESCRIBE FORMATTED parquet_mixed_fileformat PARTITION (dateint=20140330);
Modified:
hive/trunk/ql/src/test/results/clientpositive/exim_04_evolved_parts.q.out
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/exim_04_evolved_parts.q.out?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/exim_04_evolved_parts.q.out
(original)
+++ hive/trunk/ql/src/test/results/clientpositive/exim_04_evolved_parts.q.out
Tue May 27 18:48:39 2014
@@ -38,26 +38,28 @@ POSTHOOK: query: alter table exim_employ
POSTHOOK: type: ALTERTABLE_ADDPARTS
POSTHOOK: Output: default@exim_employee
POSTHOOK: Output: default@exim_employee@emp_country=in/emp_state=tn
-PREHOOK: query: alter table exim_employee set serde
"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe" with serdeproperties
('serialization.format'='2')
-PREHOOK: type: ALTERTABLE_SERIALIZER
-PREHOOK: Input: default@exim_employee
-PREHOOK: Output: default@exim_employee
-POSTHOOK: query: alter table exim_employee set serde
"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe" with serdeproperties
('serialization.format'='2')
-POSTHOOK: type: ALTERTABLE_SERIALIZER
-POSTHOOK: Input: default@exim_employee
-POSTHOOK: Output: default@exim_employee
PREHOOK: query: alter table exim_employee set fileformat
- inputformat "org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat"
+ inputformat "org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat"
outputformat "org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat"
+ serde "org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"
PREHOOK: type: ALTERTABLE_FILEFORMAT
PREHOOK: Input: default@exim_employee
PREHOOK: Output: default@exim_employee
POSTHOOK: query: alter table exim_employee set fileformat
- inputformat "org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat"
+ inputformat "org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat"
outputformat "org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat"
+ serde "org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"
POSTHOOK: type: ALTERTABLE_FILEFORMAT
POSTHOOK: Input: default@exim_employee
POSTHOOK: Output: default@exim_employee
+PREHOOK: query: alter table exim_employee set serde
"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe" with serdeproperties
('serialization.format'='2')
+PREHOOK: type: ALTERTABLE_SERIALIZER
+PREHOOK: Input: default@exim_employee
+PREHOOK: Output: default@exim_employee
+POSTHOOK: query: alter table exim_employee set serde
"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe" with serdeproperties
('serialization.format'='2')
+POSTHOOK: type: ALTERTABLE_SERIALIZER
+POSTHOOK: Input: default@exim_employee
+POSTHOOK: Output: default@exim_employee
PREHOOK: query: alter table exim_employee add partition (emp_country='in',
emp_state='ka')
PREHOOK: type: ALTERTABLE_ADDPARTS
PREHOOK: Output: default@exim_employee
Modified: hive/trunk/ql/src/test/results/clientpositive/parquet_serde.q.out
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/parquet_serde.q.out?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/parquet_serde.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/parquet_serde.q.out Tue May
27 18:48:39 2014
@@ -105,14 +105,14 @@ POSTHOOK: Output: default@parquet_mixed_
PREHOOK: query: ALTER TABLE parquet_mixed_fileformat
SET FILEFORMAT
INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
- OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
+ OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat' SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
PREHOOK: type: ALTERTABLE_FILEFORMAT
PREHOOK: Input: default@parquet_mixed_fileformat
PREHOOK: Output: default@parquet_mixed_fileformat
POSTHOOK: query: ALTER TABLE parquet_mixed_fileformat
SET FILEFORMAT
INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
- OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
+ OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat' SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
POSTHOOK: type: ALTERTABLE_FILEFORMAT
POSTHOOK: Input: default@parquet_mixed_fileformat
POSTHOOK: Output: default@parquet_mixed_fileformat
Modified:
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat.q.out
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat.q.out?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
---
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat.q.out
(original)
+++
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat.q.out
Tue May 27 18:48:39 2014
@@ -400,8 +400,8 @@ columns:struct columns { string key, str
partitioned:true
partitionColumns:struct partition_columns { string dt}
totalNumberFiles:3
-totalFileSize:1379
-maxFileSize:888
+totalFileSize:1094
+maxFileSize:603
minFileSize:216
#### A masked pattern was here ####
@@ -469,9 +469,9 @@ columns:struct columns { string key, str
partitioned:true
partitionColumns:struct partition_columns { string dt}
totalNumberFiles:1
-totalFileSize:888
-maxFileSize:888
-minFileSize:888
+totalFileSize:603
+maxFileSize:603
+minFileSize:603
#### A masked pattern was here ####
PREHOOK: query: select key from partition_test_partitioned where dt=100
Modified:
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
---
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out
(original)
+++
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat2.q.out
Tue May 27 18:48:39 2014
@@ -83,14 +83,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: partition_test_partitioned
- Statistics: Num rows: 75 Data size: 523 Basic stats: COMPLETE
Column stats: NONE
+ Statistics: Num rows: 75 Data size: 548 Basic stats: COMPLETE
Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string), dt (type:
string), BLOCK__OFFSET__INSIDE__FILE (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 75 Data size: 523 Basic stats: COMPLETE
Column stats: NONE
+ Statistics: Num rows: 75 Data size: 548 Basic stats: COMPLETE
Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 75 Data size: 523 Basic stats: COMPLETE
Column stats: NONE
+ Statistics: Num rows: 75 Data size: 548 Basic stats: COMPLETE
Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -217,11 +217,11 @@ STAGE PLANS:
Processor Tree:
TableScan
alias: partition_test_partitioned
- Statistics: Num rows: 75 Data size: 523 Basic stats: COMPLETE Column
stats: NONE
+ Statistics: Num rows: 75 Data size: 548 Basic stats: COMPLETE Column
stats: NONE
Select Operator
expressions: key (type: string), value (type: string), dt (type:
string), BLOCK__OFFSET__INSIDE__FILE (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 75 Data size: 523 Basic stats: COMPLETE
Column stats: NONE
+ Statistics: Num rows: 75 Data size: 548 Basic stats: COMPLETE
Column stats: NONE
ListSink
PREHOOK: query: select * from partition_test_partitioned where dt >=100 and dt
<= 102
Modified:
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat3.q.out
URL:
http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat3.q.out?rev=1597848&r1=1597847&r2=1597848&view=diff
==============================================================================
---
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat3.q.out
(original)
+++
hive/trunk/ql/src/test/results/clientpositive/partition_wise_fileformat3.q.out
Tue May 27 18:48:39 2014
@@ -80,9 +80,9 @@ columns:struct columns { string key, str
partitioned:true
partitionColumns:struct partition_columns { string dt}
totalNumberFiles:1
-totalFileSize:888
-maxFileSize:888
-minFileSize:888
+totalFileSize:603
+maxFileSize:603
+minFileSize:603
#### A masked pattern was here ####
PREHOOK: query: select key from partition_test_partitioned where dt=102
@@ -156,9 +156,9 @@ columns:struct columns { string key, str
partitioned:true
partitionColumns:struct partition_columns { string dt}
totalNumberFiles:1
-totalFileSize:888
-maxFileSize:888
-minFileSize:888
+totalFileSize:603
+maxFileSize:603
+minFileSize:603
#### A masked pattern was here ####
PREHOOK: query: select key from partition_test_partitioned where dt=101
