Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -300,6 +300,12 @@
<enabled>false</enabled>
</snapshots>
</repository>
<repository>
<id>jitpack.io</id>
<url>https://jitpack.io</url>
<name>Jitpack.io repository</name>
<!-- needed for brotli-codec -->
</repository>
</repositories>
<pluginRepositories>
<pluginRepository>
Expand Down
4 changes: 3 additions & 1 deletion project/SparkBuild.scala
Original file line number Diff line number Diff line change
Expand Up @@ -274,7 +274,9 @@ object SparkBuild extends PomBuild {
"gcs-maven-central-mirror" at "https://maven-central.storage-download.googleapis.com/maven2/",
DefaultMavenRepository,
Resolver.mavenLocal,
Resolver.file("ivyLocal", file(Path.userHome.absolutePath + "/.ivy2/local"))(Resolver.ivyStylePatterns)
Resolver.file("ivyLocal", file(Path.userHome.absolutePath + "/.ivy2/local"))(Resolver.ivyStylePatterns),
// needed for brotli-codec
"jitpack.io" at "https://jitpack.io"
),
externalResolvers := resolvers.value,
otherResolvers := SbtPomKeys.mvnLocalRepository(dotM2 => Seq(Resolver.file("dotM2", dotM2))).value,
Expand Down
6 changes: 6 additions & 0 deletions sql/core/pom.xml
Original file line number Diff line number Diff line change
Expand Up @@ -178,6 +178,12 @@
<artifactId>htmlunit-driver</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.github.rdblue</groupId>
<artifactId>brotli-codec</artifactId>
<version>0.1.1</version>
<scope>test</scope>
</dependency>
</dependencies>
<build>
<outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory>
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,75 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/

package org.apache.spark.sql.execution.datasources

import org.apache.spark.sql.QueryTest
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.{SharedSparkSession, SQLTestUtils}

trait FileSourceCodecSuite extends QueryTest with SQLTestUtils with SharedSparkSession {

protected def format: String
protected val codecConfigName: String
protected def availableCodecs: Seq[String]

def testWithAllCodecs(name: String)(f: => Unit): Unit = {
for (codec <- availableCodecs) {
test(s"$name - file source $format - codec: $codec") {
withSQLConf(codecConfigName -> codec) {
f
}
}
}
}

testWithAllCodecs("write and read") {
withTempPath { dir =>
testData
.repartition(5)
.write
.format(format)
.save(dir.getCanonicalPath)

val df = spark.read.format(format).load(dir.getCanonicalPath)
checkAnswer(df, testData)
}
}
}

class ParquetCodecSuite extends FileSourceCodecSuite {

override def format: String = "parquet"
override val codecConfigName: String = SQLConf.PARQUET_COMPRESSION.key
// Exclude "lzo" because it is GPL-licenced so not included in Hadoop.
// TODO(SPARK-36669): "lz4" codec fails due to HADOOP-17891.
override protected def availableCodecs: Seq[String] =
if (System.getProperty("os.arch") == "aarch64") {
// Exclude "brotli" due to PARQUET-1975.
Seq("none", "uncompressed", "snappy", "gzip", "zstd")
} else {
Seq("none", "uncompressed", "snappy", "gzip", "brotli", "zstd")
}
}

class OrcCodecSuite extends FileSourceCodecSuite {

override def format: String = "orc"
override val codecConfigName: String = SQLConf.ORC_COMPRESSION.key
override protected def availableCodecs = Seq("none", "uncompressed", "snappy",
"zlib", "zstd", "lz4", "lzo")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

we don't have GPL licence issue here for lzo?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't add extra dependency for Orc lzo codec. I think it uses aircompressor for lzo too.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, Apache ORC uses io.airlift.compress.lzo.LzoCompressor and io.airlift.compress.lzo.LzoDecompressor.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FYI, I have an unfinished PR to Hadoop to support LZO using aircompressor. apache/hadoop#2159

}