EMR configuration that supports zeppelin, presto, hue, spark, and hive configured to access AWS Glue. Zeppelin is also configured to used an s3 bucket as a notebook store

configuration.json

[
   {
      "Classification":"spark-hive-site",
      "Properties":{
         "hive.metastore.client.factory.class":"com.amazonaws.glue.catalog.metastore.AWSGlueDataCatalogHiveClientFactory",
         "hive.metastore.schema.verification": "false"
      }
   },
   {
      "Classification":"hive-site",
      "Properties":{
         "hive.metastore.client.factory.class":"com.amazonaws.glue.catalog.metastore.AWSGlueDataCatalogHiveClientFactory",
         "hive.metastore.schema.verification": "false"
      }
   },
   {
      "Classification":"spark",
      "Properties":{
         "maximizeResourceAllocation": "true"
      }
   },
   {
      "Classification":"spark-defaults",
      "Properties":{
         "spark.driver.extraClassPath":"/usr/lib/hadoop-lzo/lib/:/usr/lib/hadoop/hadoop-aws.jar:/usr/share/aws/aws-java-sdk/:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/:/usr/share/aws/emr/emrfs/auxlib/:/usr/share/aws/emr/security/conf:/usr/share/aws/emr/security/lib/:/usr/share/aws/hmclient/lib/aws-glue-datacatalog-spark-client.jar:/usr/share/java/Hive-JSON-Serde/hive-openx-serde.jar:/usr/share/aws/sagemaker-spark-sdk/lib/sagemaker-spark-sdk.jar:/home/hadoop/extrajars/*",
         "spark.executor.extraClassPath":"/usr/lib/hadoop-lzo/lib/:/usr/lib/hadoop/hadoop-aws.jar:/usr/share/aws/aws-java-sdk/:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/:/usr/share/aws/emr/emrfs/auxlib/:/usr/share/aws/emr/security/conf:/usr/share/aws/emr/security/lib/:/usr/share/aws/hmclient/lib/aws-glue-datacatalog-spark-client.jar:/usr/share/java/Hive-JSON-Serde/hive-openx-serde.jar:/usr/share/aws/sagemaker-spark-sdk/lib/sagemaker-spark-sdk.jar:/home/hadoop/extrajars/*"
      }
   },
   {
      "Classification":"presto-connector-hive",
      "Properties":{
         "hive.metastore": "glue",
         "hive.parquet.use-column-names": "true"
      }
   },
   {
    "Classification": "zeppelin-env",
    "Properties": {

    },
    "Configurations": [
      {
        "Classification": "export",
        "Properties": {
          "ZEPPELIN_NOTEBOOK_S3_BUCKET": "${bucket}",
          "ZEPPELIN_NOTEBOOK_S3_USER": "global",
          "SPARK_SUBMIT_OPTIONS": "\"--jars ${jars}\"",
          "ZEPPELIN_NOTEBOOK_STORAGE": "\"org.apache.zeppelin.notebook.repo.S3NotebookRepo\""
        },
        "Configurations": [

        ]
      }
    ]
  }
]

deltalake-bootstrap.sh

#!/bin/bash

# Configure delta lake jar
mkdir -p /home/hadoop/extrajars
curl https://repo1.maven.org/maven2/io/delta/delta-core_2.12/0.6.1/delta-core_2.12-0.6.1.jar --output ${delta_jar_path}