Amazon Web Services 文档中描述的 Amazon Web Services 服务或功能可能因区域而异。要查看适用于中国区域的差异，请参阅 中国的 Amazon Web Services 服务入门 (PDF)。

Amazon DocumentDB 连接

您可以使用 Amazon Glue for Spark 读取和写入 Amazon DocumentDB 中的表。您可以通过 Amazon Glue 连接使用存储在 Amazon Secrets Manager 中的凭证连接到 Amazon DocumentDB。

有关 Amazon DocumentDB 的更多信息，请参阅 Amazon DocumentDB 文档。

读取和写入 Amazon DocumentDB 集合

以下 Python 脚本展示了如何使用连接类型和连接选项来读写 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()

以下 Scala 脚本展示了如何使用连接类型和连接选项来读写 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 连接选项参考

指定与 Amazon DocumentDB (with MongoDB compatibility) 的连接。

源连接和接收器连接的连接选项不同。

"connectionType": "documentdb" as Source

将 "connectionType": "documentdb" 用作源时可使用以下连接选项：

"connectionType": "documentdb" as Sink

将 "connectionType": "documentdb" 用作连接器时可使用以下连接选项：