From 25a53f1a63fd3c4059d4ff9e818367a4073e381f Mon Sep 17 00:00:00 2001
From: Yuming Wang <yumwang@ebay.com>
Date: Sat, 27 Mar 2021 07:56:29 -0700
Subject: [PATCH] [SPARK-34542][BUILD] Upgrade Parquet to 1.12.0

Parquet 1.12.0 New Feature
- PARQUET-41 - Add bloom filters to parquet statistics
- PARQUET-1373 - Encryption key management tools
- PARQUET-1396 - Example of using EncryptionPropertiesFactory and DecryptionPropertiesFactory
- PARQUET-1622 - Add BYTE_STREAM_SPLIT encoding
- PARQUET-1784 - Column-wise configuration
- PARQUET-1817 - Crypto Properties Factory
- PARQUET-1854 - Properties-Driven Interface to Parquet Encryption

Parquet 1.12.0 release notes:
https://github.com/apache/parquet-mr/blob/apache-parquet-1.12.0/CHANGES.md

- Bloom filters to improve filter performance
- ZSTD enhancement

No.

Existing unit test.

Closes #31649 from wangyum/SPARK-34542.

Lead-authored-by: Yuming Wang <yumwang@ebay.com>
Co-authored-by: Yuming Wang <yumwang@apache.org>
Signed-off-by: Dongjoon Hyun <dhyun@apple.com>
---
 dev/deps/spark-deps-hadoop-2.7-hive-2.3              | 12 ++++++------
 dev/deps/spark-deps-hadoop-3.2-hive-2.3              | 12 ++++++------
 pom.xml                                              |  4 ++--
 .../org/apache/spark/sql/hive/StatisticsSuite.scala  |  2 +-
 4 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/dev/deps/spark-deps-hadoop-2.7-hive-2.3 b/dev/deps/spark-deps-hadoop-2.7-hive-2.3
index 0544f5f2c3310..976de7a95e210 100644
--- a/dev/deps/spark-deps-hadoop-2.7-hive-2.3
+++ b/dev/deps/spark-deps-hadoop-2.7-hive-2.3
@@ -201,12 +201,12 @@ orc-shims/1.6.11//orc-shims-1.6.11.jar
 oro/2.0.8//oro-2.0.8.jar
 osgi-resource-locator/1.0.3//osgi-resource-locator-1.0.3.jar
 paranamer/2.8//paranamer-2.8.jar
-parquet-column/1.10.1//parquet-column-1.10.1.jar
-parquet-common/1.10.1//parquet-common-1.10.1.jar
-parquet-encoding/1.10.1//parquet-encoding-1.10.1.jar
-parquet-format/2.4.0//parquet-format-2.4.0.jar
-parquet-hadoop/1.10.1//parquet-hadoop-1.10.1.jar
-parquet-jackson/1.10.1//parquet-jackson-1.10.1.jar
+parquet-column/1.12.0//parquet-column-1.12.0.jar
+parquet-common/1.12.0//parquet-common-1.12.0.jar
+parquet-encoding/1.12.0//parquet-encoding-1.12.0.jar
+parquet-format-structures/1.12.0//parquet-format-structures-1.12.0.jar
+parquet-hadoop/1.12.0//parquet-hadoop-1.12.0.jar
+parquet-jackson/1.12.0//parquet-jackson-1.12.0.jar
 protobuf-java/2.5.0//protobuf-java-2.5.0.jar
 py4j/0.10.9//py4j-0.10.9.jar
 pyrolite/4.30//pyrolite-4.30.jar
diff --git a/dev/deps/spark-deps-hadoop-3.2-hive-2.3 b/dev/deps/spark-deps-hadoop-3.2-hive-2.3
index 5258904c9c38a..a81de4b21a795 100644
--- a/dev/deps/spark-deps-hadoop-3.2-hive-2.3
+++ b/dev/deps/spark-deps-hadoop-3.2-hive-2.3
@@ -214,12 +214,12 @@ orc-shims/1.6.11//orc-shims-1.6.11.jar
 oro/2.0.8//oro-2.0.8.jar
 osgi-resource-locator/1.0.3//osgi-resource-locator-1.0.3.jar
 paranamer/2.8//paranamer-2.8.jar
-parquet-column/1.10.1//parquet-column-1.10.1.jar
-parquet-common/1.10.1//parquet-common-1.10.1.jar
-parquet-encoding/1.10.1//parquet-encoding-1.10.1.jar
-parquet-format/2.4.0//parquet-format-2.4.0.jar
-parquet-hadoop/1.10.1//parquet-hadoop-1.10.1.jar
-parquet-jackson/1.10.1//parquet-jackson-1.10.1.jar
+parquet-column/1.12.0//parquet-column-1.12.0.jar
+parquet-common/1.12.0//parquet-common-1.12.0.jar
+parquet-encoding/1.12.0//parquet-encoding-1.12.0.jar
+parquet-format-structures/1.12.0//parquet-format-structures-1.12.0.jar
+parquet-hadoop/1.12.0//parquet-hadoop-1.12.0.jar
+parquet-jackson/1.12.0//parquet-jackson-1.12.0.jar
 protobuf-java/2.5.0//protobuf-java-2.5.0.jar
 py4j/0.10.9//py4j-0.10.9.jar
 pyrolite/4.30//pyrolite-4.30.jar
diff --git a/pom.xml b/pom.xml
index 1b1cdfc605efd..4189658a59b47 100644
--- a/pom.xml
+++ b/pom.xml
@@ -136,7 +136,7 @@
     <!-- note that this should be compatible with Kafka brokers version 0.10 and up -->
     <kafka.version>2.6.0</kafka.version>
     <derby.version>10.12.1.1</derby.version>
-    <parquet.version>1.10.1</parquet.version>
+    <parquet.version>1.12.0</parquet.version>
     <orc.version>1.6.11</orc.version>
     <jetty.version>9.4.36.v20210114</jetty.version>
     <jakartaservlet.version>4.0.3</jakartaservlet.version>
@@ -2131,7 +2131,7 @@
             <groupId>${hive.group}</groupId>
             <artifactId>hive-service-rpc</artifactId>
           </exclusion>
-          <!-- parquet-hadoop-bundle:1.8.1 conflict with 1.10.1 -->
+          <!-- parquet-hadoop-bundle:1.8.1 conflict with 1.12.0 -->
           <exclusion>
             <groupId>org.apache.parquet</groupId>
             <artifactId>parquet-hadoop-bundle</artifactId>
diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
index ab831111be513..c1277e46082ba 100644
--- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
+++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
@@ -1529,7 +1529,7 @@ class StatisticsSuite extends StatisticsCollectionTestBase with TestHiveSingleto
         Seq(tbl, ext_tbl).foreach { tblName =>
           sql(s"INSERT INTO $tblName VALUES (1, 'a', '2019-12-13')")
 
-          val expectedSize = 601
+          val expectedSize = 657
           // analyze table
           sql(s"ANALYZE TABLE $tblName COMPUTE STATISTICS NOSCAN")
           var tableStats = getTableStats(tblName)