Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix broken glue-etl-jobs sample #154

Merged
merged 1 commit into from
Oct 21, 2022
Merged

Fix broken glue-etl-jobs sample #154

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion glue-etl-jobs/job.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,9 @@ def main():
m_df = dfc.select(df_name)
print("Writing to Postgres table:", df_name)
glueContext.write_dynamic_frame.from_jdbc_conf(
frame = m_df, catalog_connection = "c1",
frame = m_df,
# should be same as CONNECTION_NAME in the bash script
catalog_connection = "glue-etl-cluster1-connection",
connection_options = {"dbtable": df_name, "database": "test"},
redshift_tmp_dir = redshift_temp_dir)

Expand Down
38 changes: 19 additions & 19 deletions glue-etl-jobs/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,45 +3,45 @@
BUCKET=glue-pyspark-test
JOB_NAME=test-job1
S3_URL=s3://$BUCKET/job.py
CLUSTER_IDENTIFIER=glue-etl-cluster1
CONNECTION_NAME=glue-etl-cluster1-connection

echo Putting PySpark script to test S3 bucket ...
awslocal s3 mb s3://$BUCKET
awslocal s3 cp job.py $S3_URL
awslocal s3 mb s3://glue-sample-target
awslocal s3 mb "s3://$BUCKET"
awslocal s3 cp "job.py" "$S3_URL"
awslocal s3 mb "s3://glue-sample-target"

cluster_identifier=glue_etl_cluster1
awslocal rds create-db-cluster --db-cluster-identifier "$CLUSTER_IDENTIFIER" --engine aurora-postgresql --database-name test

awslocal rds create-db-cluster --db-cluster-identifier $cluster_identifier --engine aurora-postgresql --database-name test

db_port=$(awslocal rds describe-db-clusters --db-cluster-identifier $cluster_identifier) | jq -r '.DBClusters[0].Port'
db_port=$(awslocal rds describe-db-clusters --db-cluster-identifier "$CLUSTER_IDENTIFIER" | jq -r '.DBClusters[0].Port')
echo Using local RDS database on port $db_port ...

echo Creating Glue databases and tables ...
awslocal glue create-database --database-input '{"Name": "legislators"}'
awslocal glue create-table --database legislators \
--table-input '{"Name":"memberships_json", "Parameters": {"connectionName": "$cluster_identifier"}, "StorageDescriptor": {"Location": "test.memberships"}}'
--table-input '{"Name": "memberships_json", "Parameters": {"connectionName": "'$CONNECTION_NAME'"}, "StorageDescriptor": {"Location": "test.memberships"}}'
awslocal glue create-table --database legislators \
--table-input '{"Name":"persons_json", "Parameters": {"connectionName": "$cluster_identifier"}, "StorageDescriptor": {"Location": "test.persons"}}'
--table-input '{"Name": "persons_json", "Parameters": {"connectionName": "'$CONNECTION_NAME'"}, "StorageDescriptor": {"Location": "test.persons"}}'
awslocal glue create-table --database legislators \
--table-input '{"Name":"organizations_json", "Parameters": {"connectionName": "$cluster_identifier"}, "StorageDescriptor": {"Location": "test.organizations"}}'
--table-input '{"Name": "organizations_json", "Parameters": {"connectionName": "'$CONNECTION_NAME'"}, "StorageDescriptor": {"Location": "test.organizations"}}'
awslocal glue create-connection \
--connection-input '{"Name":"$cluster_identifier", "ConnectionType": "JDBC", "ConnectionProperties": {"USERNAME": "test", "PASSWORD": "test", "JDBC_CONNECTION_URL": "jdbc:postgresql://localhost.localstack.cloud:'$db_port'"}}'
--connection-input '{"Name": "'$CONNECTION_NAME'", "ConnectionType": "JDBC", "ConnectionProperties": {"USERNAME": "test", "PASSWORD": "test", "JDBC_CONNECTION_URL": "jdbc:postgresql://localhost.localstack.cloud:'$db_port'"}}'

secret=$(awslocal secretsmanager create-secret --name mysecret --secret-string "12345678" | jq -r ".ARN")

echo Creating Postgres database tables with data ...
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$cluster_identifier --secret-arn $secret --sql 'CREATE TABLE IF NOT EXISTS persons(id varchar, name varchar)'
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$cluster_identifier --secret-arn $secret --sql 'CREATE TABLE IF NOT EXISTS organizations(org_id varchar, org_name varchar)'
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$cluster_identifier --secret-arn $secret --sql 'CREATE TABLE IF NOT EXISTS memberships(person_id varchar, organization_id varchar)'
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$cluster_identifier --secret-arn $secret --sql "insert into persons(id, name) VALUES('p1', 'person 1')"
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$cluster_identifier --secret-arn $secret --sql "insert into organizations(org_id, org_name) VALUES('o1', 'org1')"
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$cluster_identifier --secret-arn $secret --sql "insert into memberships(person_id, organization_id) VALUES('p1', 'o1')"
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$cluster_identifier --secret-arn $secret --sql 'CREATE TABLE IF NOT EXISTS hist_root(id varchar, name varchar, org_id varchar, org_name varchar, person_id varchar, organization_id varchar)'
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$CLUSTER_IDENTIFIER --secret-arn $secret --sql 'CREATE TABLE IF NOT EXISTS persons(id varchar, name varchar)'
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$CLUSTER_IDENTIFIER --secret-arn $secret --sql 'CREATE TABLE IF NOT EXISTS organizations(org_id varchar, org_name varchar)'
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$CLUSTER_IDENTIFIER --secret-arn $secret --sql 'CREATE TABLE IF NOT EXISTS memberships(person_id varchar, organization_id varchar)'
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$CLUSTER_IDENTIFIER --secret-arn $secret --sql "insert into persons(id, name) VALUES('p1', 'person 1')"
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$CLUSTER_IDENTIFIER --secret-arn $secret --sql "insert into organizations(org_id, org_name) VALUES('o1', 'org1')"
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$CLUSTER_IDENTIFIER --secret-arn $secret --sql "insert into memberships(person_id, organization_id) VALUES('p1', 'o1')"
awslocal rds-data execute-statement --resource-arn arn:aws:rds:us-east-1:000000000000:cluster:$CLUSTER_IDENTIFIER --secret-arn $secret --sql 'CREATE TABLE IF NOT EXISTS hist_root(id varchar, name varchar, org_id varchar, org_name varchar, person_id varchar, organization_id varchar)'

echo Starting Glue job from PySpark script ...
awslocal glue create-job --name $JOB_NAME --role r1 \
--command '{"Name": "pythonshell", "ScriptLocation": "'$S3_URL'"}' \
--connections '{"Connections": ["$cluster_identifier"]}'
--connections '{"Connections": ["'$CLUSTER_IDENTIFIER'"]}'
run_id=$(awslocal glue start-job-run --job-name $JOB_NAME | jq -r .JobRunId)

state=$(awslocal glue get-job-run --job-name $JOB_NAME --run-id $run_id | jq -r .JobRun.JobRunState)
Expand Down