Skip to content
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

Jump to bottom

Add full end to end #224

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Add full end to end #224

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
aab410b
Add full end to end
edwardcapriolo May 27, 2021
93a00f5
Added to wrong file
edwardcapriolo May 27, 2021
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
59 changes: 59 additions & 0 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,6 +225,65 @@
</resources>

<plugins>
<plugin>
<groupId>com.googlecode.maven-download-plugin</groupId>
<artifactId>download-maven-plugin</artifactId>
<version>1.6.1</version>
<executions>
<execution>
<id>install-schemaReg</id>
<phase>test-compile</phase>
<goals>
<goal>artifact</goal>
</goals>
</execution>
</executions>
<configuration>
<artifactId>spring-schema-registry-embedded</artifactId>
<groupId>com.github.mvallim</groupId>
<version>1.0.0</version>
<unpack>false</unpack>
<outputDirectory>${project.build.directory}</outputDirectory>
</configuration>
</plugin>
<plugin>
<groupId>com.bazaarvoice.maven.plugins</groupId>
<artifactId>process-exec-maven-plugin</artifactId>
<version>0.4</version>
<executions>
<execution>
<id>cleanup-test</id>
<phase>validate</phase>
<goals>
<goal>stop-all</goal>
</goals>
</execution>
<execution>
<id>start-jar</id>
<phase>process-test-classes</phase>
<goals>
<goal>start</goal>
</goals>
<configuration>
<name>schemaReg</name>
<arguments>
<argument>java</argument>
<argument>-jar</argument>
<argument>-Xms64m</argument>
<argument>-Xmx128m</argument>
<argument>spring-schema-registry-embedded-1.0.0.jar</argument>
</arguments>
</configuration>
</execution>
<execution>
<id>stop-test</id>
<phase>prepare-package</phase>
<goals>
<goal>stop-all</goal>
</goals>
</execution>
</executions>
</plugin>
<!-- the Maven Scala plugin will compile Scala source files -->
<plugin>
<groupId>net.alchim31.maven</groupId>
Expand Down
3 changes: 2 additions & 1 deletion src/main/scala/za/co/absa/abris/examples/ConfluentKafkaAvroWriter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
package za.co.absa.abris.examples

import org.apache.spark.sql.catalyst.encoders.RowEncoder
import org.apache.spark.sql.functions.struct
import org.apache.spark.sql.functions.{col, struct}
import org.apache.spark.sql.{DataFrame, Encoder, Row, SparkSession}
import za.co.absa.abris.avro.format.SparkAvroConversions
import za.co.absa.abris.avro.parsing.utils.AvroSchemaUtils
Expand Down Expand Up @@ -67,6 +67,7 @@ object ConfluentKafkaAvroWriter {
.option("kafka.bootstrap.servers", "localhost:9092")
.option("topic", kafkaTopicName)
.save()

}

private def generateRandomDataFrame(spark: SparkSession): DataFrame = {
Expand Down
74 changes: 74 additions & 0 deletions src/test/scala/za/co/absa/abris/avro/endtoend/FullSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,74 @@
package za.co.absa.abris.avro.endtoend

import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.execution.streaming.MemoryStream
import org.apache.spark.sql.functions.{col, struct}
import org.scalatest.FlatSpec
import za.co.absa.abris.avro.functions.to_avro
import za.co.absa.abris.avro.parsing.utils.AvroSchemaUtils
import za.co.absa.abris.config.AbrisConfig
import za.co.absa.abris.examples.ConfluentKafkaAvroWriter.kafkaTopicName

import java.net.Socket
import java.nio.charset.StandardCharsets

case class SimulatedKakfaRow(key: Array[Byte], value: Array[Byte])
class FullSpec extends FlatSpec {

it should "work end to end" in {
assume(hostPortInUse("localhost", 8081))
val spark = SparkSession.builder().appName("end2end").master("local[1]").getOrCreate()
implicit val ctx = spark.sqlContext
import spark.implicits._
val events = MemoryStream[SimulatedKakfaRow]
events.addData(SimulatedKakfaRow("key".getBytes(StandardCharsets.UTF_8),
"""{"a":"b", "c", 1} """.getBytes(StandardCharsets.UTF_8)))

val dataFrame = events.toDF()
val allColumns = struct(dataFrame.columns.head, dataFrame.columns.tail: _*)

val schema = AvroSchemaUtils.toAvroSchema(dataFrame)
val abrisConfig = AbrisConfig
.toConfluentAvro
.provideAndRegisterSchema(schema.toString)
.usingTopicNameStrategy(kafkaTopicName)
.usingSchemaRegistry("http://localhost:8081")

val avroFrame = dataFrame.select(to_avro(allColumns, abrisConfig) as 'value)

avroFrame
.write
.format("kafka")
.option("kafka.bootstrap.servers", "localhost:9092")
.option("topic", kafkaTopicName)
.save()


val readConfig = AbrisConfig
.fromConfluentAvro
.downloadReaderSchemaByLatestVersion
.andTopicNameStrategy(kafkaTopicName)
.usingSchemaRegistry("http://localhost:8081")

import za.co.absa.abris.avro.functions.from_avro
val deserialized = dataFrame.select(from_avro(col("value"), readConfig) as 'data)

deserialized.printSchema()

deserialized
.writeStream
.format("console")
.option("truncate", "false")
.start()
.awaitTermination(5000)


}

def hostPortInUse(host: String, port: Int): Boolean = {
scala.util.Try[Boolean] {
new Socket(host, port).close()
true
}.getOrElse(false)
}
}