Skip to content

Compatibility changes for Spark2.2 #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
abmeena wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Compatibility changes for Spark2.2 #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 7 additions & 15 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,17 +7,6 @@
<version>1.0.0</version>
<packaging>jar</packaging>

<distributionManagement>
<snapshotRepository>
<id>ossrh</id>
<url>https://oss.sonatype.org/content/repositories/snapshots</url>
</snapshotRepository>
<repository>
<id>ossrh</id>
<url>https://oss.sonatype.org/service/local/staging/deploy/maven2/</url>
</repository>
</distributionManagement>

<name>${project.groupId}:${project.artifactId}</name>
<description>An application designed to be used as a command line utility for compacting files using the Spark framework.</description>
<url>http://maven.apache.org</url>
Expand Down Expand Up @@ -122,6 +111,9 @@
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-gpg-plugin</artifactId>
<configuration>
<skip>true</skip>
</configuration>
<version>1.5</version>
<executions>
<execution>
Expand All @@ -140,17 +132,17 @@
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.10</artifactId>
<version>1.5.2</version>
<version>2.2.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.10</artifactId>
<version>1.5.2</version>
<version>2.2.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.6.4</version>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>commons-cli</groupId>
Expand All @@ -172,4 +164,4 @@
</repository>
</repositories>

</project>
</project>
10 changes: 5 additions & 5 deletions src/main/java/com/github/KeithSSmith/spark_compaction/Compact.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.SQLContext;

public class Compact {
Expand Down Expand Up @@ -180,13 +180,13 @@ public void compact(String inputPath, String outputPath) throws IOException {
textFile.coalesce(this.splitSize).saveAsTextFile(outputPath);
} else if (this.outputSerialization.equals(PARQUET)) {
SQLContext sqlContext = new SQLContext(sc);
DataFrame parquetFile = sqlContext.read().parquet(this.concatInputPath(inputPath));
Dataset parquetFile = sqlContext.read().parquet(this.concatInputPath(inputPath));
parquetFile.coalesce(this.splitSize).write().parquet(outputPath);
} else if (this.outputSerialization.equals(AVRO)) {
// For this to work the files must end in .avro
// Another issue is that when using compression the compression codec extension is not being added to the file name.
SQLContext sqlContext = new SQLContext(sc);
DataFrame avroFile = sqlContext.read().format("com.databricks.spark.avro").load(this.concatInputPath(inputPath));
Dataset avroFile = sqlContext.read().format("com.databricks.spark.avro").load(this.concatInputPath(inputPath));
avroFile.coalesce(this.splitSize).write().format("com.databricks.spark.avro").save(outputPath);
} else {
System.out.println("Did not match any serialization type: text, parquet, or avro. Recieved: " +
Expand All @@ -207,12 +207,12 @@ public void compact(String[] args) throws IOException {
textFile.coalesce(this.splitSize).saveAsTextFile(outputPath);
} else if (this.outputSerialization.equals(PARQUET)) {
SQLContext sqlContext = new SQLContext(sc);
DataFrame parquetFile = sqlContext.read().parquet(this.concatInputPath(inputPath));
Dataset parquetFile = sqlContext.read().parquet(this.concatInputPath(inputPath));
parquetFile.coalesce(this.splitSize).write().parquet(outputPath);
} else if (this.outputSerialization.equals(AVRO)) {
// For this to work the files must end in .avro
SQLContext sqlContext = new SQLContext(sc);
DataFrame avroFile = sqlContext.read().format("com.databricks.spark.avro").load(this.concatInputPath(inputPath));
Dataset avroFile = sqlContext.read().format("com.databricks.spark.avro").load(this.concatInputPath(inputPath));
avroFile.coalesce(this.splitSize).write().format("com.databricks.spark.avro").save(outputPath);
} else {
System.out.println("Did not match any serialization type: text, parquet, or avro. Recieved: " +
Expand Down