Generate Athena database documentation with SchemaSpy

athena.properties

description=AWS Athena
type=athena
driver=com.simba.athena.jdbc42.Driver
connectionSpec=jdbc:awsathena://athena.<region>.amazonaws.com:443;S3OutputLocation=<S3OutputLocation>
# eg: region=ca-central-1

tableTypes=TABLES,TABLE,MANAGED_TABLE,EXTERNAL_TABLE

generate-athena-doc.sh

#!/bin/bash
# for configuration / customization details:
# see http://schemaspy.readthedocs.io/en/latest/configuration.html#databasetype
# see https://hub.docker.com/r/schemaspy/schemaspy/
# see https://s3.amazonaws.com/athena-downloads/drivers/JDBC/SimbaAthenaJDBC-2.0.27.1000/doc/Simba+Athena+JDBC+Connector+Install+and+Configuration+Guide.pdf
# see https://docs.aws.amazon.com/athena/latest/ug/connect-with-jdbc.html
# see https://blog.jetbrains.com/datagrip/2018/05/25/using-aws-athena-from-intellij-based-ide/
#
echo "***  Reading AWS access key and secrets..."
AWS_KEY=`awk -F "=" '/^aws_access_key_id/ {gsub(/[ \t]/, "", $2); print $2}' ~/.aws/credentials`
AWS_SECRET=`awk -F "=" '/^aws_secret_access_key/ {gsub(/[ \t]/, "", $2); print $2}' ~/.aws/credentials`

echo "*** Launching schema spy"
ATHENA_REGION=ca-central-1
S3_OUTPUT_LOCATION="s3://aws-athena-query-results-638085509885-ca-central-1/"
SCHEMA=mvp-flink-data
SCHEMASPY_OPTIONS="-t athena -norows -region $ATHENA_REGION -S3OutputLocation $S3_OUTPUT_LOCATION -db AwsDataCatalog -s $SCHEMA"

mkdir -p doc/athena
docker run --rm -it \
    -v $HOME/opt:/drivers \
    -v $HOME/opt/athena.properties:/athena.properties \
    -v `pwd`/doc/athena:/output \
    schemaspy/schemaspy \
    $SCHEMASPY_OPTIONS \
    -u $AWS_KEY -p $AWS_SECRET