diff --git a/examples/src/main/python/parquet_inputformat.py b/examples/src/main/python/parquet_inputformat.py
index 96ddac761d69821f80de417d9f75dfc3215ed25e..e1fd85b082c08a1d7cf843afefc02d5dcb2e556f 100644
--- a/examples/src/main/python/parquet_inputformat.py
+++ b/examples/src/main/python/parquet_inputformat.py
@@ -51,7 +51,7 @@ if __name__ == "__main__":
parquet_rdd = sc.newAPIHadoopFile(
path,
- 'parquet.avro.AvroParquetInputFormat',
+ 'org.apache.parquet.avro.AvroParquetInputFormat',
'java.lang.Void',
'org.apache.avro.generic.IndexedRecord',
valueConverter='org.apache.spark.examples.pythonconverters.IndexedRecordToJavaConverter')
diff --git a/pom.xml b/pom.xml
index bcb6ef96a1206f54ef24c60096d0d5880c65f4b2..abb9b5540034057aedcdae083b979493c45cee7e 100644
--- a/pom.xml
+++ b/pom.xml
@@ -136,7 +136,7 @@
<!-- Version used for internal directory structure -->
<hive.version.short>0.13.1</hive.version.short>
<derby.version>10.10.1.1</derby.version>
- <parquet.version>1.6.0rc3</parquet.version>
+ <parquet.version>1.7.0</parquet.version>
<jblas.version>1.2.4</jblas.version>
<jetty.version>8.1.14.v20131031</jetty.version>
<orbit.version>3.0.0.v201112011016</orbit.version>
@@ -1080,13 +1080,13 @@
</exclusions>
</dependency>
<dependency>
- <groupId>com.twitter</groupId>
+ <groupId>org.apache.parquet</groupId>
<artifactId>parquet-column</artifactId>
<version>${parquet.version}</version>
<scope>${parquet.deps.scope}</scope>
</dependency>
<dependency>
- <groupId>com.twitter</groupId>
+ <groupId>org.apache.parquet</groupId>
<artifactId>parquet-hadoop</artifactId>
<version>${parquet.version}</version>
<scope>${parquet.deps.scope}</scope>
diff --git a/sql/core/pom.xml b/sql/core/pom.xml
index 3192f81ffaecd040422bb2aa6b2d0f0e8f3974f0..ed75475a870678c5ef3b3251878a712760f5cf68 100644
--- a/sql/core/pom.xml
+++ b/sql/core/pom.xml
@@ -61,11 +61,11 @@
<scope>test</scope>
</dependency>
<dependency>
- <groupId>com.twitter</groupId>
+ <groupId>org.apache.parquet</groupId>
<artifactId>parquet-column</artifactId>
</dependency>
<dependency>
- <groupId>com.twitter</groupId>
+ <groupId>org.apache.parquet</groupId>
<artifactId>parquet-hadoop</artifactId>
</dependency>
<dependency>
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/DirectParquetOutputCommitter.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/DirectParquetOutputCommitter.scala
index f5ce2718bec4a523398bbc5dcf688b29fd246f2e..62c4e92ebec681cce0d222d43ae2044b7a8e5ea1 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/DirectParquetOutputCommitter.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/DirectParquetOutputCommitter.scala
@@ -21,9 +21,9 @@ import org.apache.hadoop.fs.Path
import org.apache.hadoop.mapreduce.{JobContext, TaskAttemptContext}
import org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
-import parquet.Log
-import parquet.hadoop.util.ContextUtil
-import parquet.hadoop.{ParquetFileReader, ParquetFileWriter, ParquetOutputCommitter, ParquetOutputFormat}
+import org.apache.parquet.Log
+import org.apache.parquet.hadoop.util.ContextUtil
+import org.apache.parquet.hadoop.{ParquetFileReader, ParquetFileWriter, ParquetOutputCommitter, ParquetOutputFormat}
private[parquet] class DirectParquetOutputCommitter(outputPath: Path, context: TaskAttemptContext)
extends ParquetOutputCommitter(outputPath, context) {
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetConverter.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetConverter.scala
index caa9f045537d06f902333f9c25cf432a516b8680..85c2ce740fe5207d313d2713861114eb36c15fac 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetConverter.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetConverter.scala
@@ -23,9 +23,9 @@ import java.util.{TimeZone, Calendar}
import scala.collection.mutable.{Buffer, ArrayBuffer, HashMap}
import jodd.datetime.JDateTime
-import parquet.column.Dictionary
-import parquet.io.api.{PrimitiveConverter, GroupConverter, Binary, Converter}
-import parquet.schema.MessageType
+import org.apache.parquet.column.Dictionary
+import org.apache.parquet.io.api.{PrimitiveConverter, GroupConverter, Binary, Converter}
+import org.apache.parquet.schema.MessageType
import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.parquet.CatalystConverter.FieldType
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetFilters.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetFilters.scala
index f0f4e7d147e75eaa38516cb71c9bf89839f2fdcc..88ae88e9684c8b6ac5ad9e9f8b5a6d2364c65b39 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetFilters.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetFilters.scala
@@ -21,11 +21,11 @@ import java.nio.ByteBuffer
import com.google.common.io.BaseEncoding
import org.apache.hadoop.conf.Configuration
-import parquet.filter2.compat.FilterCompat
-import parquet.filter2.compat.FilterCompat._
-import parquet.filter2.predicate.FilterApi._
-import parquet.filter2.predicate.{FilterApi, FilterPredicate}
-import parquet.io.api.Binary
+import org.apache.parquet.filter2.compat.FilterCompat
+import org.apache.parquet.filter2.compat.FilterCompat._
+import org.apache.parquet.filter2.predicate.FilterApi._
+import org.apache.parquet.filter2.predicate.{FilterApi, FilterPredicate}
+import org.apache.parquet.io.api.Binary
import org.apache.spark.SparkEnv
import org.apache.spark.sql.catalyst.expressions._
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetRelation.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetRelation.scala
index fcb9513ab66f63eab7500f832c2934d89c3e13bf..09088ee91106c215dd0798efd32956a185ea99b2 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetRelation.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetRelation.scala
@@ -24,9 +24,9 @@ import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.fs.permission.FsAction
import org.apache.spark.sql.types.{StructType, DataType}
-import parquet.hadoop.{ParquetOutputCommitter, ParquetOutputFormat}
-import parquet.hadoop.metadata.CompressionCodecName
-import parquet.schema.MessageType
+import org.apache.parquet.hadoop.{ParquetOutputCommitter, ParquetOutputFormat}
+import org.apache.parquet.hadoop.metadata.CompressionCodecName
+import org.apache.parquet.schema.MessageType
import org.apache.spark.sql.{DataFrame, SQLContext}
import org.apache.spark.sql.catalyst.analysis.{MultiInstanceRelation, UnresolvedException}
@@ -107,7 +107,7 @@ private[sql] object ParquetRelation {
//
// Therefore we need to force the class to be loaded.
// This should really be resolved by Parquet.
- Class.forName(classOf[parquet.Log].getName)
+ Class.forName(classOf[org.apache.parquet.Log].getName)
// Note: Logger.getLogger("parquet") has a default logger
// that appends to Console which needs to be cleared.
@@ -127,7 +127,7 @@ private[sql] object ParquetRelation {
type RowType = org.apache.spark.sql.catalyst.expressions.GenericMutableRow
// The compression type
- type CompressionType = parquet.hadoop.metadata.CompressionCodecName
+ type CompressionType = org.apache.parquet.hadoop.metadata.CompressionCodecName
// The parquet compression short names
val shortParquetCompressionCodecNames = Map(
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala
index cb7ae246d0d75734dbf63f16b211fa0d610a835a..1e694f2feabeece937483103b52c256d45c46e86 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableOperations.scala
@@ -33,13 +33,13 @@ import org.apache.hadoop.fs.{BlockLocation, FileStatus, Path}
import org.apache.hadoop.mapreduce._
import org.apache.hadoop.mapreduce.lib.input.{FileInputFormat => NewFileInputFormat}
import org.apache.hadoop.mapreduce.lib.output.{FileOutputCommitter, FileOutputFormat => NewFileOutputFormat}
-import parquet.hadoop._
-import parquet.hadoop.api.ReadSupport.ReadContext
-import parquet.hadoop.api.{InitContext, ReadSupport}
-import parquet.hadoop.metadata.GlobalMetaData
-import parquet.hadoop.util.ContextUtil
-import parquet.io.ParquetDecodingException
-import parquet.schema.MessageType
+import org.apache.parquet.hadoop._
+import org.apache.parquet.hadoop.api.ReadSupport.ReadContext
+import org.apache.parquet.hadoop.api.{InitContext, ReadSupport}
+import org.apache.parquet.hadoop.metadata.GlobalMetaData
+import org.apache.parquet.hadoop.util.ContextUtil
+import org.apache.parquet.io.ParquetDecodingException
+import org.apache.parquet.schema.MessageType
import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.mapred.SparkHadoopMapRedUtil
@@ -78,7 +78,7 @@ private[sql] case class ParquetTableScan(
}.toArray
protected override def doExecute(): RDD[Row] = {
- import parquet.filter2.compat.FilterCompat.FilterPredicateCompat
+ import org.apache.parquet.filter2.compat.FilterCompat.FilterPredicateCompat
val sc = sqlContext.sparkContext
val job = new Job(sc.hadoopConfiguration)
@@ -136,7 +136,7 @@ private[sql] case class ParquetTableScan(
baseRDD.mapPartitionsWithInputSplit { case (split, iter) =>
val partValue = "([^=]+)=([^=]+)".r
val partValues =
- split.asInstanceOf[parquet.hadoop.ParquetInputSplit]
+ split.asInstanceOf[org.apache.parquet.hadoop.ParquetInputSplit]
.getPath
.toString
.split("/")
@@ -378,7 +378,7 @@ private[sql] case class InsertIntoParquetTable(
* to imported ones.
*/
private[parquet] class AppendingParquetOutputFormat(offset: Int)
- extends parquet.hadoop.ParquetOutputFormat[Row] {
+ extends org.apache.parquet.hadoop.ParquetOutputFormat[Row] {
// override to accept existing directories as valid output directory
override def checkOutputSpecs(job: JobContext): Unit = {}
var committer: OutputCommitter = null
@@ -431,7 +431,7 @@ private[parquet] class AppendingParquetOutputFormat(offset: Int)
* RecordFilter we want to use.
*/
private[parquet] class FilteringParquetRowInputFormat
- extends parquet.hadoop.ParquetInputFormat[Row] with Logging {
+ extends org.apache.parquet.hadoop.ParquetInputFormat[Row] with Logging {
private var fileStatuses = Map.empty[Path, FileStatus]
@@ -439,7 +439,7 @@ private[parquet] class FilteringParquetRowInputFormat
inputSplit: InputSplit,
taskAttemptContext: TaskAttemptContext): RecordReader[Void, Row] = {
- import parquet.filter2.compat.FilterCompat.NoOpFilter
+ import org.apache.parquet.filter2.compat.FilterCompat.NoOpFilter
val readSupport: ReadSupport[Row] = new RowReadSupport()
@@ -501,7 +501,7 @@ private[parquet] class FilteringParquetRowInputFormat
globalMetaData = new GlobalMetaData(globalMetaData.getSchema,
mergedMetadata, globalMetaData.getCreatedBy)
- val readContext = getReadSupport(configuration).init(
+ val readContext = ParquetInputFormat.getReadSupportInstance(configuration).init(
new InitContext(configuration,
globalMetaData.getKeyValueMetaData,
globalMetaData.getSchema))
@@ -531,8 +531,8 @@ private[parquet] class FilteringParquetRowInputFormat
minSplitSize: JLong,
readContext: ReadContext): JList[ParquetInputSplit] = {
- import parquet.filter2.compat.FilterCompat.Filter
- import parquet.filter2.compat.RowGroupFilter
+ import org.apache.parquet.filter2.compat.FilterCompat.Filter
+ import org.apache.parquet.filter2.compat.RowGroupFilter
import org.apache.spark.sql.parquet.FilteringParquetRowInputFormat.blockLocationCache
@@ -547,7 +547,7 @@ private[parquet] class FilteringParquetRowInputFormat
// https://github.com/apache/incubator-parquet-mr/pull/17
// is resolved
val generateSplits =
- Class.forName("parquet.hadoop.ClientSideMetadataSplitStrategy")
+ Class.forName("org.apache.parquet.hadoop.ClientSideMetadataSplitStrategy")
.getDeclaredMethods.find(_.getName == "generateSplits").getOrElse(
sys.error(s"Failed to reflectively invoke ClientSideMetadataSplitStrategy.generateSplits"))
generateSplits.setAccessible(true)
@@ -612,7 +612,7 @@ private[parquet] class FilteringParquetRowInputFormat
// https://github.com/apache/incubator-parquet-mr/pull/17
// is resolved
val generateSplits =
- Class.forName("parquet.hadoop.TaskSideMetadataSplitStrategy")
+ Class.forName("org.apache.parquet.hadoop.TaskSideMetadataSplitStrategy")
.getDeclaredMethods.find(_.getName == "generateTaskSideMDSplits").getOrElse(
sys.error(
s"Failed to reflectively invoke TaskSideMetadataSplitStrategy.generateTaskSideMDSplits"))
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableSupport.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableSupport.scala
index 70a220cc43ab9fab0e0fa22020febdd96b1f0f93..89db408b1c3826dbfa2ee39844be6a9dafc355dc 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableSupport.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTableSupport.scala
@@ -20,12 +20,12 @@ package org.apache.spark.sql.parquet
import java.util.{HashMap => JHashMap}
import org.apache.hadoop.conf.Configuration
-import parquet.column.ParquetProperties
-import parquet.hadoop.ParquetOutputFormat
-import parquet.hadoop.api.ReadSupport.ReadContext
-import parquet.hadoop.api.{ReadSupport, WriteSupport}
-import parquet.io.api._
-import parquet.schema.MessageType
+import org.apache.parquet.column.ParquetProperties
+import org.apache.parquet.hadoop.ParquetOutputFormat
+import org.apache.parquet.hadoop.api.ReadSupport.ReadContext
+import org.apache.parquet.hadoop.api.{ReadSupport, WriteSupport}
+import org.apache.parquet.io.api._
+import org.apache.parquet.schema.MessageType
import org.apache.spark.Logging
import org.apache.spark.sql.catalyst.expressions.{Attribute, Row}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala
index f8a5d845493363270e5ce4d31a8d33574a4dcfbf..ba2a35b74ef8253c579fc7a65fd04fba0aa6e431 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/ParquetTypes.scala
@@ -25,13 +25,13 @@ import scala.util.Try
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.hadoop.mapreduce.Job
-import parquet.format.converter.ParquetMetadataConverter
-import parquet.hadoop.metadata.{FileMetaData, ParquetMetadata}
-import parquet.hadoop.util.ContextUtil
-import parquet.hadoop.{Footer, ParquetFileReader, ParquetFileWriter}
-import parquet.schema.PrimitiveType.{PrimitiveTypeName => ParquetPrimitiveTypeName}
-import parquet.schema.Type.Repetition
-import parquet.schema.{ConversionPatterns, DecimalMetadata, GroupType => ParquetGroupType, MessageType, OriginalType => ParquetOriginalType, PrimitiveType => ParquetPrimitiveType, Type => ParquetType, Types => ParquetTypes}
+import org.apache.parquet.format.converter.ParquetMetadataConverter
+import org.apache.parquet.hadoop.metadata.{FileMetaData, ParquetMetadata}
+import org.apache.parquet.hadoop.util.ContextUtil
+import org.apache.parquet.hadoop.{Footer, ParquetFileReader, ParquetFileWriter}
+import org.apache.parquet.schema.PrimitiveType.{PrimitiveTypeName => ParquetPrimitiveTypeName}
+import org.apache.parquet.schema.Type.Repetition
+import org.apache.parquet.schema.{ConversionPatterns, DecimalMetadata, GroupType => ParquetGroupType, MessageType, OriginalType => ParquetOriginalType, PrimitiveType => ParquetPrimitiveType, Type => ParquetType, Types => ParquetTypes}
import org.apache.spark.Logging
import org.apache.spark.sql.AnalysisException
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala
index bf55e2383ab56b719cae6e829546605ac40eb90d..5dda440240e60c08b7b8d2e7daa523c6cb5661d1 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/newParquet.scala
@@ -29,10 +29,10 @@ import org.apache.hadoop.fs.{FileStatus, Path}
import org.apache.hadoop.io.Writable
import org.apache.hadoop.mapreduce._
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
-import parquet.filter2.predicate.FilterApi
-import parquet.hadoop._
-import parquet.hadoop.metadata.CompressionCodecName
-import parquet.hadoop.util.ContextUtil
+import org.apache.parquet.filter2.predicate.FilterApi
+import org.apache.parquet.hadoop._
+import org.apache.parquet.hadoop.metadata.CompressionCodecName
+import org.apache.parquet.hadoop.util.ContextUtil
import org.apache.spark.{Partition => SparkPartition, SerializableWritable, Logging, SparkException}
import org.apache.spark.broadcast.Broadcast
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/parquet/timestamp/NanoTime.scala b/sql/core/src/main/scala/org/apache/spark/sql/parquet/timestamp/NanoTime.scala
index 70bcca7526aaeda295a391d05f400ad438792d43..4d5ed211ad0c0f460007ec3a0c5ed603b7e914da 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/parquet/timestamp/NanoTime.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/parquet/timestamp/NanoTime.scala
@@ -19,8 +19,8 @@ package org.apache.spark.sql.parquet.timestamp
import java.nio.{ByteBuffer, ByteOrder}
-import parquet.Preconditions
-import parquet.io.api.{Binary, RecordConsumer}
+import org.apache.parquet.Preconditions
+import org.apache.parquet.io.api.{Binary, RecordConsumer}
private[parquet] class NanoTime extends Serializable {
private var julianDay = 0
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/sources/commands.scala b/sql/core/src/main/scala/org/apache/spark/sql/sources/commands.scala
index 71f016b1f14dedabb88a6663ba92edbac5a5ae03..e9932c09107dbbf7c5fd9877cadc415c8dd273e4 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/sources/commands.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/sources/commands.scala
@@ -24,7 +24,7 @@ import scala.collection.mutable
import org.apache.hadoop.fs.Path
import org.apache.hadoop.mapreduce._
import org.apache.hadoop.mapreduce.lib.output.{FileOutputCommitter => MapReduceFileOutputCommitter, FileOutputFormat}
-import parquet.hadoop.util.ContextUtil
+import org.apache.parquet.hadoop.util.ContextUtil
import org.apache.spark._
import org.apache.spark.mapred.SparkHadoopMapRedUtil
diff --git a/sql/core/src/test/resources/log4j.properties b/sql/core/src/test/resources/log4j.properties
index 28e90b9520b2cbd2fb14c6d2f3b29478a9c6b03b..12fb128149d324872d8a4644070c2f8ccb4f8808 100644
--- a/sql/core/src/test/resources/log4j.properties
+++ b/sql/core/src/test/resources/log4j.properties
@@ -36,11 +36,11 @@ log4j.appender.FA.layout.ConversionPattern=%d{HH:mm:ss.SSS} %t %p %c{1}: %m%n
log4j.appender.FA.Threshold = INFO
# Some packages are noisy for no good reason.
-log4j.additivity.parquet.hadoop.ParquetRecordReader=false
-log4j.logger.parquet.hadoop.ParquetRecordReader=OFF
+log4j.additivity.org.apache.parquet.hadoop.ParquetRecordReader=false
+log4j.logger.org.apache.parquet.hadoop.ParquetRecordReader=OFF
-log4j.additivity.parquet.hadoop.ParquetOutputCommitter=false
-log4j.logger.parquet.hadoop.ParquetOutputCommitter=OFF
+log4j.additivity.org.apache.parquet.hadoop.ParquetOutputCommitter=false
+log4j.logger.org.apache.parquet.hadoop.ParquetOutputCommitter=OFF
log4j.additivity.org.apache.hadoop.hive.serde2.lazy.LazyStruct=false
log4j.logger.org.apache.hadoop.hive.serde2.lazy.LazyStruct=OFF
@@ -52,5 +52,5 @@ log4j.additivity.hive.ql.metadata.Hive=false
log4j.logger.hive.ql.metadata.Hive=OFF
# Parquet related logging
-log4j.logger.parquet.hadoop=WARN
+log4j.logger.org.apache.parquet.hadoop=WARN
log4j.logger.org.apache.spark.sql.parquet=INFO
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala
index bdc2ebabc5e9a366910d9dbaf2bcc609bce986b9..4aa5bcb7fdbca8dd110c81e865d6ea47e6652970 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala
@@ -18,8 +18,8 @@
package org.apache.spark.sql.parquet
import org.scalatest.BeforeAndAfterAll
-import parquet.filter2.predicate.Operators._
-import parquet.filter2.predicate.{FilterPredicate, Operators}
+import org.apache.parquet.filter2.predicate.Operators._
+import org.apache.parquet.filter2.predicate.{FilterPredicate, Operators}
import org.apache.spark.sql.catalyst.dsl.expressions._
import org.apache.spark.sql.catalyst.expressions._
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala
index dd48bb350f26dbe665b30e1e3002fbd7e3812af2..7f7c2cc1a6c26b8b67f47625b00fefa03aee507f 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala
@@ -24,14 +24,14 @@ import scala.reflect.runtime.universe.TypeTag
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, Path}
import org.scalatest.BeforeAndAfterAll
-import parquet.example.data.simple.SimpleGroup
-import parquet.example.data.{Group, GroupWriter}
-import parquet.hadoop.api.WriteSupport
-import parquet.hadoop.api.WriteSupport.WriteContext
-import parquet.hadoop.metadata.{ParquetMetadata, FileMetaData, CompressionCodecName}
-import parquet.hadoop.{Footer, ParquetFileWriter, ParquetWriter}
-import parquet.io.api.RecordConsumer
-import parquet.schema.{MessageType, MessageTypeParser}
+import org.apache.parquet.example.data.simple.SimpleGroup
+import org.apache.parquet.example.data.{Group, GroupWriter}
+import org.apache.parquet.hadoop.api.WriteSupport
+import org.apache.parquet.hadoop.api.WriteSupport.WriteContext
+import org.apache.parquet.hadoop.metadata.{ParquetMetadata, FileMetaData, CompressionCodecName}
+import org.apache.parquet.hadoop.{Footer, ParquetFileWriter, ParquetWriter}
+import org.apache.parquet.io.api.RecordConsumer
+import org.apache.parquet.schema.{MessageType, MessageTypeParser}
import org.apache.spark.sql.catalyst.ScalaReflection
import org.apache.spark.sql.catalyst.expressions.Row
@@ -400,7 +400,7 @@ class ParquetIOSuiteBase extends QueryTest with ParquetTest {
}
finally {
configuration.set("spark.sql.parquet.output.committer.class",
- "parquet.hadoop.ParquetOutputCommitter")
+ "org.apache.parquet.hadoop.ParquetOutputCommitter")
}
}
}
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala
index caec2a6f254890c07f539a78095d8ca09664f355..8b1745124b8e13d81b48fadb918c0fc73199242e 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetSchemaSuite.scala
@@ -20,7 +20,7 @@ package org.apache.spark.sql.parquet
import scala.reflect.ClassTag
import scala.reflect.runtime.universe.TypeTag
-import parquet.schema.MessageTypeParser
+import org.apache.parquet.schema.MessageTypeParser
import org.apache.spark.SparkFunSuite
import org.apache.spark.sql.catalyst.ScalaReflection