A construct for AWS Glue DataBrew wtih CICD
npm install cdk-databrew-cicd| npm (JS/TS) | PyPI (Python) | Maven (Java) | Go | NuGet |
| --- | --- | --- | --- | --- |
| Link | Link | Link | Link | Link |
     
typescript
import { IamRole } from 'cdk-databrew-cicd';new IamRole(this, 'AccountIamRole', {
environment: 'preproduction', // or 'production'
accountID: 'ACCOUNT_ID',
// roleName: 'OPTIONAL'
});
` Example
Typescript
You could also refer to here.
`bash
$ cdk --init language typescript
$ yarn add cdk-databrew-cicd
`
`typescript
import * as cdk from '@aws-cdk/core';
import { DataBrewCodePipeline } from 'cdk-databrew-cicd';class TypescriptStack extends cdk.Stack {
constructor(scope: cdk.Construct, id: string, props?: cdk.StackProps) {
super(scope, id, props);
const preproductionAccountId = 'PREPRODUCTION_ACCOUNT_ID';
const productionAccountId = 'PRODUCTION_ACCOUNT_ID';
const dataBrewPipeline = new DataBrewCodePipeline(this, 'DataBrewCicdPipeline', {
preproductionIamRoleArn:
arn:${cdk.Aws.PARTITION}:iam::${preproductionAccountId}:role/preproduction-Databrew-Cicd-Role,
productionIamRoleArn: arn:${cdk.Aws.PARTITION}:iam::${productionAccountId}:role/production-Databrew-Cicd-Role,
// bucketName: 'OPTIONAL',
// repoName: 'OPTIONAL',
// branchName: 'OPTIONAL',
// pipelineName: 'OPTIONAL'
}); new cdk.CfnOutput(this, 'OPreproductionLambdaArn', { value: dataBrewPipeline.preproductionFunctionArn });
new cdk.CfnOutput(this, 'OProductionLambdaArn', { value: dataBrewPipeline.productionFunctionArn });
new cdk.CfnOutput(this, 'OCodeCommitRepoArn', { value: dataBrewPipeline.codeCommitRepoArn });
new cdk.CfnOutput(this, 'OCodePipelineArn', { value: dataBrewPipeline.codePipelineArn });
}
}
const app = new cdk.App();
new TypescriptStack(app, 'TypescriptStack', {
stackName: 'DataBrew-CICD'
});
`
Python
You could also refer to here.
bash
upgrading related Python packages
$ python -m ensurepip --upgrade
$ python -m pip install --upgrade pip
$ python -m pip install --upgrade virtualenv
initialize a CDK Python project
$ cdk init --language python
make packages installed locally instead of globally
$ source .venv/bin/activate
$ cat < requirements.txt
aws-cdk.core
cdk-databrew-cicd
EOL
$ python -m pip install -r requirements.txt
`
`python
from aws_cdk import core as cdk
from cdk_databrew_cicd import DataBrewCodePipelineclass PythonStack(cdk.Stack):
def __init__(self, scope: cdk.Construct, construct_id: str, **kwargs) -> None:
super().__init__(scope, construct_id, **kwargs)
preproduction_account_id = "PREPRODUCTION_ACCOUNT_ID"
production_account_id = "PRODUCTION_ACCOUNT_ID"
databrew_pipeline = DataBrewCodePipeline(self,
"DataBrewCicdPipeline",
preproduction_iam_role_arn=f"arn:{cdk.Aws.PARTITION}:iam::{preproduction_account_id}:role/preproduction-Databrew-Cicd-Role",
production_iam_role_arn=f"arn:{cdk.Aws.PARTITION}:iam::{production_account_id}:role/preproduction-Databrew-Cicd-Role",
# bucket_name="OPTIONAL",
# repo_name="OPTIONAL",
# repo_name="OPTIONAL",
# branch_namne="OPTIONAL",
# pipeline_name="OPTIONAL"
)
cdk.CfnOutput(self, 'OPreproductionLambdaArn', value=databrew_pipeline.preproduction_function_arn)
cdk.CfnOutput(self, 'OProductionLambdaArn', value=databrew_pipeline.production_function_arn)
cdk.CfnOutput(self, 'OCodeCommitRepoArn', value=databrew_pipeline.code_commit_repo_arn)
cdk.CfnOutput(self, 'OCodePipelineArn', value=databrew_pipeline.code_pipeline_arn)
`
bash
$ deactivate
`
Java
You could also refer to here.
bash
$ cdk init --language java
$ mvn package
`
xml
.
.
UTF-8
2.87.0
2.0.196
5.7.1
.
.
software.amazon.awscdk
aws-cdk-lib
${cdk.version}
io.github.hsiehshujeng
cdk-databrew-cicd
${constrcut.verion}
.
.
.
`
java
package com.myorg;import software.amazon.awscdk.core.CfnOutput;
import software.amazon.awscdk.core.CfnOutputProps;
import software.amazon.awscdk.core.Construct;
import software.amazon.awscdk.core.Stack;
import software.amazon.awscdk.core.StackProps;
import io.github.hsiehshujeng.cdk.databrew.cicd.DataBrewCodePipeline;
import io.github.hsiehshujeng.cdk.databrew.cicd.DataBrewCodePipelineProps;
public class JavaStack extends Stack {
public JavaStack(final Construct scope, final String id) {
this(scope, id, null);
}
public JavaStack(final Construct scope, final String id, final StackProps props) {
super(scope, id, props);
String preproductionAccountId = "PREPRODUCTION_ACCOUNT_ID";
String productionAccountId = "PRODUCTION_ACCOUNT_ID";
DataBrewCodePipeline databrewPipeline = new DataBrewCodePipeline(this, "DataBrewCicdPipeline",
DataBrewCodePipelineProps.builder().preproductionIamRoleArn(preproductionAccountId)
.productionIamRoleArn(productionAccountId)
// .bucketName("OPTIONAL")
// .branchName("OPTIONAL")
// .pipelineName("OPTIONAL")
.build());
new CfnOutput(this, "OPreproductionLambdaArn",
CfnOutputProps.builder()
.value(databrewPipeline.getPreproductionFunctionArn())
.build());
new CfnOutput(this, "OProductionLambdaArn",
CfnOutputProps.builder()
.value(databrewPipeline.getProductionFunctionArn())
.build());
new CfnOutput(this, "OCodeCommitRepoArn",
CfnOutputProps.builder()
.value(databrewPipeline.getCodeCommitRepoArn())
.build());
new CfnOutput(this, "OCodePipelineArn",
CfnOutputProps.builder()
.value(databrewPipeline.getCodePipelineArn())
.build());
}
}
`
C#
You could also refer to here.
bash
$ cdk init --language csharp
$ dotnet add src/Csharp package Databrew.Cicd --version 2.0.196
`
cs
using Amazon.CDK;
using ScottHsieh.Cdk;namespace Csharp
{
public class CsharpStack : Stack
{
internal CsharpStack(Construct scope, string id, IStackProps props = null) : base(scope, id, props)
{
var preproductionAccountId = "PREPRODUCTION_ACCOUNT_ID";
var productionAccountId = "PRODUCTION_ACCOUNT_ID";
var dataBrewPipeline = new DataBrewCodePipeline(this, "DataBrewCicdPipeline", new DataBrewCodePipelineProps
{
PreproductionIamRoleArn = $"arn:{Aws.PARTITION}:iam::{preproductionAccountId}:role/preproduction-Databrew-Cicd-Role",
ProductionIamRoleArn = $"arn:{Aws.PARTITION}:iam::{productionAccountId}:role/preproduction-Databrew-Cicd-Role",
// BucketName = "OPTIONAL",
// RepoName = "OPTIONAL",
// BranchName = "OPTIONAL",
// PipelineName = "OPTIONAL"
});
new CfnOutput(this, "OPreproductionLambdaArn", new CfnOutputProps
{
Value = dataBrewPipeline.PreproductionFunctionArn
});
new CfnOutput(this, "OProductionLambdaArn", new CfnOutputProps
{
Value = dataBrewPipeline.ProductionFunctionArn
});
new CfnOutput(this, "OCodeCommitRepoArn", new CfnOutputProps
{
Value = dataBrewPipeline.CodeCommitRepoArn
});
new CfnOutput(this, "OCodePipelineArn", new CfnOutputProps
{
Value = dataBrewPipeline.CodeCommitRepoArn
});
}
}
}
`
Go
You could also refer to here.
bash
Initialize a new AWS CDK application in the current directory with the Go programming language
cdk init app -l go
Add this custom CDK construct to your project
go get github.com/HsiehShuJeng/cdk-databrew-cicd-go/cdkdatabrewcicd/v2@v2.0.196
Ensure all dependencies are properly listed in the go.mod file and remove any unused ones
go mod tidy
Upgrade all Go modules in your project to their latest minor or patch versions
go get -u ./...
`
go
package mainimport (
"fmt"
"github.com/aws/aws-cdk-go/awscdk/v2"
// "github.com/aws/aws-cdk-go/awscdk/v2/awssqs"
"github.com/HsiehShuJeng/cdk-databrew-cicd-go/cdkdatabrewcicd/v2"
"github.com/aws/constructs-go/constructs/v10"
"github.com/aws/jsii-runtime-go"
)
type GoLangStackProps struct {
awscdk.StackProps
}
func NewGoLangStack(scope constructs.Construct, id string, props *GoLangStackProps) awscdk.Stack {
var sprops awscdk.StackProps
if props != nil {
sprops = props.StackProps
}
stack := awscdk.NewStack(scope, &id, &sprops)
preproductionAccountId := "PREPRODUCTION_ACCOUNT_ID"
productionAccountId := "PRODUCTION_ACCOUNT_ID"
dataBrewPipeline := cdkdatabrewcicd.NewDataBrewCodePipeline(stack, jsii.String("DataBrewCicdPipeline"), &cdkdatabrewcicd.DataBrewCodePipelineProps{
PreproductionIamRoleArn: jsii.String(fmt.Sprintf("arn:%s:iam::%s:role/preproduction-Databrew-Cicd-Role", *awscdk.Aws_PARTITION(), preproductionAccountId)),
ProductionIamRoleArn: jsii.String(fmt.Sprintf("arn:%s:iam::%s:role/production-Databrew-Cicd-Role", *awscdk.Aws_PARTITION(), productionAccountId)),
// BucketName: jsii.String("OPTIONAL"),
// RepoName: jsii.String("OPTIONAL"),
// BranchName: jsii.String("OPTIONAL"),
// PipelineName: jsii.String("OPTIONAL"),
})
awscdk.NewCfnOutput(stack, jsii.String("OPreproductionLambdaArn"), &awscdk.CfnOutputProps{Value: dataBrewPipeline.PreproductionFunctionArn()})
awscdk.NewCfnOutput(stack, jsii.String("OProductionLambdaArn"), &awscdk.CfnOutputProps{Value: dataBrewPipeline.ProductionFunctionArn()})
awscdk.NewCfnOutput(stack, jsii.String("OCodeCommitRepoArn"), &awscdk.CfnOutputProps{Value: dataBrewPipeline.CodeCommitRepoArn()})
awscdk.NewCfnOutput(stack, jsii.String("OCodePipelineArn"), &awscdk.CfnOutputProps{Value: dataBrewPipeline.CodePipelineArn()})
return stack
}
func main() {
defer jsii.Close()
app := awscdk.NewApp(nil)
NewGoLangStack(app, "GoLangStack", &GoLangStackProps{
awscdk.StackProps{
Env: env(),
},
})
app.Synth(nil)
}
func env() *awscdk.Environment {
return nil
}
`Some Efforts after Stack Creation
CodeCommit
1. Create HTTPS Git credentials for AWS CodeCommit with an IAM user that you're going to use.
!image
2. Run through the steps noted on the README.md of the CodeCommit repository after finishing establishing the stack via CDK. The returned message with success should be looked like the following (assume you have installed ):
`bash
$ git clone codecommit://scott.codecommit@DataBrew-Recipes-Repo
Cloning into 'DataBrew-Recipes-Repo'...
remote: Counting objects: 6, done.
Unpacking objects: 100% (6/6), 2.03 KiB | 138.00 KiB/s, done.
`
3. Add a DataBrew recipe into the local repositroy (directory) and commit the change. (either directly on the main branch or merging another branch into the main branch) Glue DataBrew
1. Download any recipe either generated out by following Getting started with AWS Glue DataBrew or made by yourself as JSON file.
!image
2. Move the recipe from the download directory to the local directory for the CodeCommit repository.
`bash
$ mv ${DOWNLOAD_DIRECTORY}/chess-project-recipe.json ${CODECOMMIT_LOCAL_DIRECTORY}/
`
3. Commit the change to a branch with a name you prefer.
bash
$ cd ${{CODECOMMIT_LOCAL_DIRECTORY}}
$ git checkout -b add-recipe main
$ git add .
$ git commit -m "first recipe"
$ git push --set-upstream origin add-recipe
``