Spark DataFrame をサポートする DynamoDB コネクタ

import sys
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job
from awsglue.utils import getResolvedOptions

args = getResolvedOptions(sys.argv, ["JOB_NAME"])
glue_context= GlueContext(SparkContext.getOrCreate())
spark = glueContext.spark_session
job = Job(glue_context)
job.init(args["JOB_NAME"], args)

# Read from DynamoDB
df = spark.read.format("dynamodb") \
    .option("dynamodb.input.tableName", "test-source") \
    .option("dynamodb.throughput.read.ratio", "0.5") \
    .option("dynamodb.consistentRead", "false") \
    .load()

print(df.rdd.getNumPartitions())

# Write to DynamoDB
df.write \
  .format("dynamodb") \
  .option("dynamodb.output.tableName", "test-sink") \
  .option("dynamodb.throughput.write.ratio", "0.5") \
  .option("dynamodb.item.size.check.enabled", "true") \
  .save()

job.commit()

import com.amazonaws.services.glue.GlueContext
import com.amazonaws.services.glue.util.GlueArgParser
import com.amazonaws.services.glue.util.Job
import org.apache.spark.SparkContext
import scala.collection.JavaConverters._

object GlueApp {
  def main(sysArgs: Array[String]): Unit = {
    
    val glueContext = new GlueContext(SparkContext.getOrCreate())
    val spark = glueContext.getSparkSession
    val args = GlueArgParser.getResolvedOptions(sysArgs, Seq("JOB_NAME").toArray)
    Job.init(args("JOB_NAME"), glueContext, args.asJava)

    val df = spark.read
      .format("dynamodb")
      .option("dynamodb.input.tableName", "test-source")
      .option("dynamodb.throughput.read.ratio", "0.5")
      .option("dynamodb.consistentRead", "false")
      .load()

    print(df.rdd.getNumPartitions)

    df.write
      .format("dynamodb")
      .option("dynamodb.output.tableName", "test-sink")
      .option("dynamodb.throughput.write.ratio", "0.5")
      .option("dynamodb.item.size.check.enabled", "true")
      .save()

    job.commit()
  }
}

import com.amazonaws.services.glue.GlueContext
import com.amazonaws.services.glue.util.{GlueArgParser, Job}
import org.apache.spark.SparkContext
import glue.spark.dynamodb.DynamoDBExport
import scala.collection.JavaConverters._

object GlueApp {
  def main(sysArgs: Array[String]): Unit = {
    val glueContext = new GlueContext(SparkContext.getOrCreate())
    val spark = glueContext.getSparkSession
    val args = GlueArgParser.getResolvedOptions(sysArgs, Seq("JOB_NAME").toArray)
    Job.init(args("JOB_NAME"), glueContext, args.asJava)
    
    val options = Map(
      "dynamodb.export" -> "ddb",
      "dynamodb.tableArn" -> "arn:aws:dynamodb:us-east-1:123456789012:table/my-table",
      "dynamodb.s3.bucket" -> "my-s3-bucket",
      "dynamodb.s3.prefix" -> "my-s3-prefix",
      "dynamodb.simplifyDDBJson" -> "true"
    )
    val df = DynamoDBExport.fullExport(spark, options)
    
    print(df.rdd.getNumPartitions)
    df.count()
    
    Job.commit()
  }
}