Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Amazon DocumentDB connections

You can use Amazon Glue for Spark to read from and write to tables in Amazon DocumentDB. You can connect to Amazon DocumentDB using credentials stored in Amazon Secrets Manager through a Amazon Glue connection.

For more information about Amazon DocumentDB, consult the Amazon DocumentDB documentation.

Reading and writing to Amazon DocumentDB collections

The following Python script demonstrates using connection types and connection options for reading and writing to Amazon DocumentDB.

import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext, SparkConf
from awsglue.context import GlueContext
from awsglue.job import Job
import time

## @params: [JOB_NAME]
args = getResolvedOptions(sys.argv, ['JOB_NAME'])

sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session

job = Job(glueContext)
job.init(args['JOB_NAME'], args)

output_path = "s3://some_bucket/output/" + str(time.time()) + "/"
documentdb_uri = "mongodb://<mongo-instanced-ip-address>:27017"
documentdb_write_uri = "mongodb://<mongo-instanced-ip-address>:27017"

read_docdb_options = {
    "uri": documentdb_uri,
    "database": "test",
    "collection": "coll",
    "username": "username",
    "password": "1234567890",
    "ssl": "true",
    "ssl.domain_match": "false",
    "partitioner": "MongoSamplePartitioner",
    "partitionerOptions.partitionSizeMB": "10",
    "partitionerOptions.partitionKey": "_id"
}

write_documentdb_options = {
    "retryWrites": "false",
    "uri": documentdb_write_uri,
    "database": "test",
    "collection": "coll",
    "username": "username",
    "password": "pwd"
}

# Get DynamicFrame from  DocumentDB
dynamic_frame2 = glueContext.create_dynamic_frame.from_options(connection_type="documentdb",
                                                               connection_options=read_docdb_options)

# Write DynamicFrame to MongoDB and DocumentDB
glueContext.write_dynamic_frame.from_options(dynamic_frame2, connection_type="documentdb",
                                             connection_options=write_documentdb_options)

job.commit()

The following Scala script demonstrates using connection types and connection options for reading and writing to Amazon DocumentDB.

import com.amazonaws.services.glue.GlueContext
import com.amazonaws.services.glue.MappingSpec
import com.amazonaws.services.glue.errors.CallSite
import com.amazonaws.services.glue.util.GlueArgParser
import com.amazonaws.services.glue.util.Job
import com.amazonaws.services.glue.util.JsonOptions
import com.amazonaws.services.glue.DynamicFrame
import org.apache.spark.SparkContext
import scala.collection.JavaConverters._

object GlueApp {
  val DOC_URI: String = "mongodb://<mongo-instanced-ip-address>:27017"
  val DOC_WRITE_URI: String = "mongodb://<mongo-instanced-ip-address>:27017"
  lazy val documentDBJsonOption = jsonOptions(DOC_URI)
  lazy val writeDocumentDBJsonOption = jsonOptions(DOC_WRITE_URI)
  def main(sysArgs: Array[String]): Unit = {
    val spark: SparkContext = new SparkContext()
    val glueContext: GlueContext = new GlueContext(spark)
    val args = GlueArgParser.getResolvedOptions(sysArgs, Seq("JOB_NAME").toArray)
    Job.init(args("JOB_NAME"), glueContext, args.asJava)

    // Get DynamicFrame from DocumentDB
    val resultFrame2: DynamicFrame = glueContext.getSource("documentdb", documentDBJsonOption).getDynamicFrame()

    // Write DynamicFrame to DocumentDB
    glueContext.getSink("documentdb", writeJsonOption).writeDynamicFrame(resultFrame2)

    Job.commit()
  }

  private def jsonOptions(uri: String): JsonOptions = {
    new JsonOptions(
      s"""{"uri": "${uri}",
         |"database":"test",
         |"collection":"coll",
         |"username": "username",
         |"password": "pwd",
         |"ssl":"true",
         |"ssl.domain_match":"false",
         |"partitioner": "MongoSamplePartitioner",
         |"partitionerOptions.partitionSizeMB": "10",
         |"partitionerOptions.partitionKey": "_id"}""".stripMargin)
  }
}

Amazon DocumentDB connection option reference

Designates a connection to Amazon DocumentDB (with MongoDB compatibility).

Connection options differ for a source connection and a sink connection.

"connectionType": "Documentdb" as source

Use the following connection options with "connectionType": "documentdb" as a source:

"connectionType": "Documentdb" as sink

Use the following connection options with "connectionType": "documentdb" as a sink: