[SPARK-26677][BUILD] Update Parquet to 1.10.1 with notEq pushdown fix.

## What changes were proposed in this pull request?

Update to Parquet Java 1.10.1.

## How was this patch tested?

Added a test from HyukjinKwon that validates the notEq case from SPARK-26677.

Closes apache#23704 from rdblue/SPARK-26677-fix-noteq-parquet-bug.

Lead-authored-by: Ryan Blue <[email protected]>
Co-authored-by: Hyukjin Kwon <[email protected]>
Co-authored-by: Ryan Blue <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>
(cherry picked from commit f72d217)
Signed-off-by: Dongjoon Hyun <[email protected]>

Author: 2 people

dev/deps/spark-deps-hadoop-2.7

@@ -160,13 +160,13 @@ orc-shims-1.5.4.jar
 oro-2.0.8.jar
 osgi-resource-locator-1.0.1.jar
 paranamer-2.8.jar
-parquet-column-1.10.0.jar
-parquet-common-1.10.0.jar
-parquet-encoding-1.10.0.jar
+parquet-column-1.10.1.jar
+parquet-common-1.10.1.jar
+parquet-encoding-1.10.1.jar
 parquet-format-2.4.0.jar
-parquet-hadoop-1.10.0.jar
+parquet-hadoop-1.10.1.jar
 parquet-hadoop-bundle-1.6.0.jar
-parquet-jackson-1.10.0.jar
+parquet-jackson-1.10.1.jar
 protobuf-java-2.5.0.jar
 py4j-0.10.7.jar
 pyrolite-4.13.jar

dev/deps/spark-deps-hadoop-3.1

@@ -178,13 +178,13 @@ orc-shims-1.5.4.jar
 oro-2.0.8.jar
 osgi-resource-locator-1.0.1.jar
 paranamer-2.8.jar
-parquet-column-1.10.0.jar
-parquet-common-1.10.0.jar
-parquet-encoding-1.10.0.jar
+parquet-column-1.10.1.jar
+parquet-common-1.10.1.jar
+parquet-encoding-1.10.1.jar
 parquet-format-2.4.0.jar
-parquet-hadoop-1.10.0.jar
+parquet-hadoop-1.10.1.jar
 parquet-hadoop-bundle-1.6.0.jar
-parquet-jackson-1.10.0.jar
+parquet-jackson-1.10.1.jar
 protobuf-java-2.5.0.jar
 py4j-0.10.7.jar
 pyrolite-4.13.jar

pom.xml

@@ -131,7 +131,7 @@
     <!-- Version used for internal directory structure -->
     <hive.version.short>3.0.0.1</hive.version.short>
     <derby.version>10.12.1.1</derby.version>
-    <parquet.version>1.10.0</parquet.version>
+    <parquet.version>1.10.1</parquet.version>
     <orc.version>1.5.4</orc.version>
     <orc.classifier></orc.classifier>
     <hive.parquet.version>1.6.0</hive.parquet.version>

sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala

@@ -891,6 +891,21 @@ class ParquetQuerySuite extends QueryTest with ParquetTest with SharedSQLContext
       }
     }
   }
+
+  test("SPARK-26677: negated null-safe equality comparison should not filter matched row groups") {
+    (true :: false :: Nil).foreach { vectorized =>
+      withSQLConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED.key -> vectorized.toString) {
+        withTempPath { path =>
+          // Repeated values for dictionary encoding.
+          Seq(Some("A"), Some("A"), None).toDF.repartition(1)
+            .write.parquet(path.getAbsolutePath)
+          val df = spark.read.parquet(path.getAbsolutePath)
+          checkAnswer(stripSparkFilter(df.where("NOT (value <=> 'A')")), df)
+        }
+      }
+    }
+  }
+
 }
 
 object TestingUDT {