This is an automated email from the ASF dual-hosted git repository.
dkuzmenko 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 87d3d595934 HIVE-27980: Iceberg: Compaction: Add support for OPTIMIZE
TABLE syntax (Dmitriy Fingerman, reviewed by Attila Turoczy, Ayush Saxena,
Butao Zhang)
87d3d595934 is described below
commit 87d3d595934f998562ed3bbc525b140a74ffbdd5
Author: Dmitriy Fingerman <[email protected]>
AuthorDate: Tue Feb 13 09:46:43 2024 -0500
HIVE-27980: Iceberg: Compaction: Add support for OPTIMIZE TABLE syntax
(Dmitriy Fingerman, reviewed by Attila Turoczy, Ayush Saxena, Butao Zhang)
Closes #5028
---
.../iceberg_optimize_table_unpartitioned.q | 58 ++++
.../iceberg_optimize_table_unpartitioned.q.out | 310 +++++++++++++++++++++
.../test/resources/testconfiguration.properties | 3 +-
.../hadoop/hive/ql/parse/AlterClauseParser.g | 14 +
.../apache/hadoop/hive/ql/parse/HiveLexerParent.g | 1 +
.../org/apache/hadoop/hive/ql/parse/HiveParser.g | 1 +
.../hadoop/hive/ql/parse/IdentifiersParser.g | 1 +
7 files changed, 387 insertions(+), 1 deletion(-)
diff --git
a/iceberg/iceberg-handler/src/test/queries/positive/iceberg_optimize_table_unpartitioned.q
b/iceberg/iceberg-handler/src/test/queries/positive/iceberg_optimize_table_unpartitioned.q
new file mode 100644
index 00000000000..5fbc108125e
--- /dev/null
+++
b/iceberg/iceberg-handler/src/test/queries/positive/iceberg_optimize_table_unpartitioned.q
@@ -0,0 +1,58 @@
+-- SORT_QUERY_RESULTS
+-- Mask neededVirtualColumns due to non-strict order
+--! qt:replace:/(\s+neededVirtualColumns:\s)(.*)/$1#Masked#/
+-- Mask the totalSize value as it can have slight variability, causing test
flakiness
+--! qt:replace:/(\s+totalSize\s+)\S+(\s+)/$1#Masked#$2/
+-- Mask random uuid
+--! qt:replace:/(\s+uuid\s+)\S+(\s*)/$1#Masked#$2/
+-- Mask a random snapshot id
+--! qt:replace:/(\s+current-snapshot-id\s+)\S+(\s*)/$1#Masked#/
+-- Mask added file size
+--! qt:replace:/(\S\"added-files-size\\\":\\\")(\d+)(\\\")/$1#Masked#$3/
+-- Mask total file size
+--! qt:replace:/(\S\"total-files-size\\\":\\\")(\d+)(\\\")/$1#Masked#$3/
+-- Mask current-snapshot-timestamp-ms
+--! qt:replace:/(\s+current-snapshot-timestamp-ms\s+)\S+(\s*)/$1#Masked#$2/
+-- Mask the enqueue time which is based on current time
+--!
qt:replace:/(MAJOR\s+succeeded\s+)[a-zA-Z0-9\-\.\s+]+(\s+manual)/$1#Masked#$2/
+-- Mask compaction id as they will be allocated in parallel threads
+--! qt:replace:/^[0-9]/#Masked#/
+
+set hive.llap.io.enabled=true;
+set hive.vectorized.execution.enabled=true;
+set hive.optimize.shared.work.merge.ts.schema=true;
+
+create table ice_orc (
+ first_name string,
+ last_name string
+ )
+stored by iceberg stored as orc
+tblproperties ('format-version'='2');
+
+insert into ice_orc VALUES ('fn1','ln1');
+insert into ice_orc VALUES ('fn2','ln2');
+insert into ice_orc VALUES ('fn3','ln3');
+insert into ice_orc VALUES ('fn4','ln4');
+insert into ice_orc VALUES ('fn5','ln5');
+insert into ice_orc VALUES ('fn6','ln6');
+insert into ice_orc VALUES ('fn7','ln7');
+
+update ice_orc set last_name = 'ln1a' where first_name='fn1';
+update ice_orc set last_name = 'ln2a' where first_name='fn2';
+update ice_orc set last_name = 'ln3a' where first_name='fn3';
+update ice_orc set last_name = 'ln4a' where first_name='fn4';
+update ice_orc set last_name = 'ln5a' where first_name='fn5';
+update ice_orc set last_name = 'ln6a' where first_name='fn6';
+update ice_orc set last_name = 'ln7a' where first_name='fn7';
+
+delete from ice_orc where last_name in ('ln5a', 'ln6a', 'ln7a');
+
+select * from ice_orc;
+describe formatted ice_orc;
+
+explain optimize table ice_orc rewrite data;
+optimize table ice_orc rewrite data;
+
+select * from ice_orc;
+describe formatted ice_orc;
+show compactions;
\ No newline at end of file
diff --git
a/iceberg/iceberg-handler/src/test/results/positive/llap/iceberg_optimize_table_unpartitioned.q.out
b/iceberg/iceberg-handler/src/test/results/positive/llap/iceberg_optimize_table_unpartitioned.q.out
new file mode 100644
index 00000000000..a4ea671dd05
--- /dev/null
+++
b/iceberg/iceberg-handler/src/test/results/positive/llap/iceberg_optimize_table_unpartitioned.q.out
@@ -0,0 +1,310 @@
+PREHOOK: query: create table ice_orc (
+ first_name string,
+ last_name string
+ )
+stored by iceberg stored as orc
+tblproperties ('format-version'='2')
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: create table ice_orc (
+ first_name string,
+ last_name string
+ )
+stored by iceberg stored as orc
+tblproperties ('format-version'='2')
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: insert into ice_orc VALUES ('fn1','ln1')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: insert into ice_orc VALUES ('fn1','ln1')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: insert into ice_orc VALUES ('fn2','ln2')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: insert into ice_orc VALUES ('fn2','ln2')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: insert into ice_orc VALUES ('fn3','ln3')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: insert into ice_orc VALUES ('fn3','ln3')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: insert into ice_orc VALUES ('fn4','ln4')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: insert into ice_orc VALUES ('fn4','ln4')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: insert into ice_orc VALUES ('fn5','ln5')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: insert into ice_orc VALUES ('fn5','ln5')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: insert into ice_orc VALUES ('fn6','ln6')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: insert into ice_orc VALUES ('fn6','ln6')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: insert into ice_orc VALUES ('fn7','ln7')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: insert into ice_orc VALUES ('fn7','ln7')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: update ice_orc set last_name = 'ln1a' where first_name='fn1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: update ice_orc set last_name = 'ln1a' where first_name='fn1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: update ice_orc set last_name = 'ln2a' where first_name='fn2'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: update ice_orc set last_name = 'ln2a' where first_name='fn2'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: update ice_orc set last_name = 'ln3a' where first_name='fn3'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: update ice_orc set last_name = 'ln3a' where first_name='fn3'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: update ice_orc set last_name = 'ln4a' where first_name='fn4'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: update ice_orc set last_name = 'ln4a' where first_name='fn4'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: update ice_orc set last_name = 'ln5a' where first_name='fn5'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: update ice_orc set last_name = 'ln5a' where first_name='fn5'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: update ice_orc set last_name = 'ln6a' where first_name='fn6'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: update ice_orc set last_name = 'ln6a' where first_name='fn6'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: update ice_orc set last_name = 'ln7a' where first_name='fn7'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: update ice_orc set last_name = 'ln7a' where first_name='fn7'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: delete from ice_orc where last_name in ('ln5a', 'ln6a', 'ln7a')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+#### A masked pattern was here ####
+POSTHOOK: query: delete from ice_orc where last_name in ('ln5a', 'ln6a',
'ln7a')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+#### A masked pattern was here ####
+PREHOOK: query: select * from ice_orc
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+#### A masked pattern was here ####
+POSTHOOK: query: select * from ice_orc
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+#### A masked pattern was here ####
+fn1 ln1a
+fn2 ln2a
+fn3 ln3a
+fn4 ln4a
+PREHOOK: query: describe formatted ice_orc
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@ice_orc
+POSTHOOK: query: describe formatted ice_orc
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@ice_orc
+# col_name data_type comment
+first_name string
+last_name string
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: EXTERNAL_TABLE
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ EXTERNAL TRUE
+ bucketing_version 2
+ current-schema
{\"type\":\"struct\",\"schema-id\":0,\"fields\":[{\"id\":1,\"name\":\"first_name\",\"required\":false,\"type\":\"string\"},{\"id\":2,\"name\":\"last_name\",\"required\":false,\"type\":\"string\"}]}
+ current-snapshot-id #Masked#
+ current-snapshot-summary
{\"deleted-data-files\":\"3\",\"deleted-records\":\"3\",\"removed-files-size\":\"1131\",\"changed-partition-count\":\"1\",\"total-records\":\"11\",\"total-files-size\":\"#Masked#\",\"total-data-files\":\"11\",\"total-delete-files\":\"7\",\"total-position-deletes\":\"7\",\"total-equality-deletes\":\"0\"}
+ current-snapshot-timestamp-ms #Masked#
+ format-version 2
+ iceberg.orc.files.only true
+#### A masked pattern was here ####
+ numFiles 11
+ numRows 11
+ parquet.compression zstd
+#### A masked pattern was here ####
+ rawDataSize 0
+ serialization.format 1
+ snapshot-count 15
+ storage_handler
org.apache.iceberg.mr.hive.HiveIcebergStorageHandler
+ table_type ICEBERG
+ totalSize #Masked#
+#### A masked pattern was here ####
+ uuid #Masked#
+ write.delete.mode merge-on-read
+ write.format.default orc
+ write.merge.mode merge-on-read
+ write.update.mode merge-on-read
+
+# Storage Information
+SerDe Library: org.apache.iceberg.mr.hive.HiveIcebergSerDe
+InputFormat: org.apache.iceberg.mr.hive.HiveIcebergInputFormat
+OutputFormat: org.apache.iceberg.mr.hive.HiveIcebergOutputFormat
+Compressed: No
+Sort Columns: []
+PREHOOK: query: explain optimize table ice_orc rewrite data
+PREHOOK: type: ALTERTABLE_COMPACT
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: explain optimize table ice_orc rewrite data
+POSTHOOK: type: ALTERTABLE_COMPACT
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Compact
+ compaction type: major
+ table name: default.ice_orc
+ numberOfBuckets: 0
+ table name: default.ice_orc
+ blocking: true
+
+PREHOOK: query: optimize table ice_orc rewrite data
+PREHOOK: type: ALTERTABLE_COMPACT
+PREHOOK: Input: default@ice_orc
+PREHOOK: Output: default@ice_orc
+POSTHOOK: query: optimize table ice_orc rewrite data
+POSTHOOK: type: ALTERTABLE_COMPACT
+POSTHOOK: Input: default@ice_orc
+POSTHOOK: Output: default@ice_orc
+PREHOOK: query: select * from ice_orc
+PREHOOK: type: QUERY
+PREHOOK: Input: default@ice_orc
+#### A masked pattern was here ####
+POSTHOOK: query: select * from ice_orc
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@ice_orc
+#### A masked pattern was here ####
+fn1 ln1a
+fn2 ln2a
+fn3 ln3a
+fn4 ln4a
+PREHOOK: query: describe formatted ice_orc
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@ice_orc
+POSTHOOK: query: describe formatted ice_orc
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@ice_orc
+# col_name data_type comment
+first_name string
+last_name string
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: EXTERNAL_TABLE
+Table Parameters:
+ COLUMN_STATS_ACCURATE
{\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"first_name\":\"true\",\"last_name\":\"true\"}}
+ EXTERNAL TRUE
+ bucketing_version 2
+ current-schema
{\"type\":\"struct\",\"schema-id\":0,\"fields\":[{\"id\":1,\"name\":\"first_name\",\"required\":false,\"type\":\"string\"},{\"id\":2,\"name\":\"last_name\",\"required\":false,\"type\":\"string\"}]}
+ current-snapshot-id #Masked#
+ current-snapshot-summary
{\"replace-partitions\":\"true\",\"added-data-files\":\"1\",\"added-records\":\"4\",\"added-files-size\":\"#Masked#\",\"changed-partition-count\":\"1\",\"total-records\":\"4\",\"total-files-size\":\"#Masked#\",\"total-data-files\":\"1\",\"total-delete-files\":\"0\",\"total-position-deletes\":\"0\",\"total-equality-deletes\":\"0\"}
+ current-snapshot-timestamp-ms #Masked#
+ format-version 2
+ iceberg.orc.files.only true
+#### A masked pattern was here ####
+ numFiles 1
+ numRows 4
+ parquet.compression zstd
+#### A masked pattern was here ####
+ rawDataSize 0
+ serialization.format 1
+ snapshot-count 17
+ storage_handler
org.apache.iceberg.mr.hive.HiveIcebergStorageHandler
+ table_type ICEBERG
+ totalSize #Masked#
+#### A masked pattern was here ####
+ uuid #Masked#
+ write.delete.mode merge-on-read
+ write.format.default orc
+ write.merge.mode merge-on-read
+ write.update.mode merge-on-read
+
+# Storage Information
+SerDe Library: org.apache.iceberg.mr.hive.HiveIcebergSerDe
+InputFormat: org.apache.iceberg.mr.hive.HiveIcebergInputFormat
+OutputFormat: org.apache.iceberg.mr.hive.HiveIcebergOutputFormat
+Compressed: No
+Sort Columns: []
+PREHOOK: query: show compactions
+PREHOOK: type: SHOW COMPACTIONS
+POSTHOOK: query: show compactions
+POSTHOOK: type: SHOW COMPACTIONS
+CompactionId Database Table Partition Type State Worker
host Worker Enqueue Time Start Time Duration(ms) HadoopJobId
Error message Initiator host Initiator Pool name TxnId Next
TxnId Commit Time Highest WriteId
+#Masked# default ice_orc --- MAJOR succeeded #Masked#
manual default 0 0 0 ---
diff --git a/itests/src/test/resources/testconfiguration.properties
b/itests/src/test/resources/testconfiguration.properties
index 65b705d6518..290f4e3acad 100644
--- a/itests/src/test/resources/testconfiguration.properties
+++ b/itests/src/test/resources/testconfiguration.properties
@@ -421,7 +421,8 @@ iceberg.llap.query.compactor.files=\
iceberg_major_compaction_partition_evolution.q,\
iceberg_major_compaction_partitioned.q,\
iceberg_major_compaction_schema_evolution.q,\
- iceberg_major_compaction_unpartitioned.q
+ iceberg_major_compaction_unpartitioned.q,\
+ iceberg_optimize_table_unpartitioned.q
iceberg.llap.only.query.files=\
llap_iceberg_read_orc.q,\
diff --git
a/parser/src/java/org/apache/hadoop/hive/ql/parse/AlterClauseParser.g
b/parser/src/java/org/apache/hadoop/hive/ql/parse/AlterClauseParser.g
index 8e8ec4e33f9..873a28eb05c 100644
--- a/parser/src/java/org/apache/hadoop/hive/ql/parse/AlterClauseParser.g
+++ b/parser/src/java/org/apache/hadoop/hive/ql/parse/AlterClauseParser.g
@@ -52,6 +52,7 @@ alterStatement
| KW_ALTER KW_MATERIALIZED KW_VIEW tableNameTree=tableName
alterMaterializedViewStatementSuffix[$tableNameTree.tree] ->
alterMaterializedViewStatementSuffix
| KW_ALTER (KW_DATABASE|KW_SCHEMA) alterDatabaseStatementSuffix ->
alterDatabaseStatementSuffix
| KW_ALTER KW_DATACONNECTOR alterDataConnectorStatementSuffix ->
alterDataConnectorStatementSuffix
+ | KW_OPTIMIZE KW_TABLE tableName optimizeTableStatementSuffix ->
^(TOK_ALTERTABLE tableName optimizeTableStatementSuffix)
;
alterTableStatementSuffix
@@ -99,6 +100,19 @@ alterTblPartitionStatementSuffix[boolean partition]
| alterStatementSuffixAddCol
| alterStatementSuffixUpdateColumns
;
+
+optimizeTableStatementSuffix
+@init { gParent.pushMsg("optimize table statement suffix", state); }
+@after { gParent.popMsg(state); }
+ : optimizeTblRewriteDataSuffix
+ ;
+
+optimizeTblRewriteDataSuffix
+@init { gParent.msgs.push("compaction request"); }
+@after { gParent.msgs.pop(); }
+ : KW_REWRITE KW_DATA
+ -> ^(TOK_ALTERTABLE_COMPACT Identifier["'MAJOR'"] TOK_BLOCKING)
+ ;
alterStatementPartitionKeyType
@init {gParent.msgs.push("alter partition key type"); }
diff --git a/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveLexerParent.g
b/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveLexerParent.g
index a26d66d214d..078cd561b1b 100644
--- a/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveLexerParent.g
+++ b/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveLexerParent.g
@@ -402,6 +402,7 @@ KW_CHERRY_PICK: 'CHERRY-PICK';
KW_ORPHAN_FILES: 'ORPHAN-FILES';
KW_OLDER: 'OLDER';
KW_THAN: 'THAN';
+KW_OPTIMIZE: 'OPTIMIZE';
// Operators
// NOTE: if you add a new function/operator, add it to sysFuncNames so that
describe function _FUNC_ will work.
diff --git a/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
b/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
index 586ea34af3e..d9cdac0c0d1 100644
--- a/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
+++ b/parser/src/java/org/apache/hadoop/hive/ql/parse/HiveParser.g
@@ -594,6 +594,7 @@ import org.apache.hadoop.hive.conf.HiveConf;
xlateMap.put("KW_EXCEPT", "EXCEPT");
xlateMap.put("KW_LOAD", "LOAD");
xlateMap.put("KW_DATA", "DATA");
+ xlateMap.put("KW_OPTIMIZE", "OPTIMIZE");
xlateMap.put("KW_INPATH", "INPATH");
xlateMap.put("KW_IS", "IS");
xlateMap.put("KW_NULL", "NULL");
diff --git
a/parser/src/java/org/apache/hadoop/hive/ql/parse/IdentifiersParser.g
b/parser/src/java/org/apache/hadoop/hive/ql/parse/IdentifiersParser.g
index fc34da64389..37b7c4b0ee0 100644
--- a/parser/src/java/org/apache/hadoop/hive/ql/parse/IdentifiersParser.g
+++ b/parser/src/java/org/apache/hadoop/hive/ql/parse/IdentifiersParser.g
@@ -987,6 +987,7 @@ nonReserved
| KW_BRANCH | KW_SNAPSHOTS | KW_RETAIN | KW_RETENTION
| KW_TAG
| KW_FAST_FORWARD
+ | KW_OPTIMIZE
;
//The following SQL2011 reserved keywords are used as function name only, but
not as identifiers.
