aws-cdk-aws-s3tables-alpha

import os from aws_cdk import App, Stack, Environment, aws_s3 as s3 from aws_cdk.aws_s3 import Bucket, RemovalPolicy from aws_cdk_aws_s3tables_alpha import S3Table, TableOptions, DataFormat, Column class MyS3TableStack(Stack): def __init__(self, scope: App, id: str, **kwargs) -> None: super().__init__(scope, id, **kwargs) # Define an S3 Bucket to store the table data # In production, use RemovalPolicy.RETAIN and consider bucket versioning data_bucket = Bucket(self, "MyDataLakeBucket", versioned=True, removal_policy=RemovalPolicy.DESTROY # CAUTION: Deletes bucket and contents on stack delete ) # Define the S3 Table construct, creating a Glue Table s3_glue_table = S3Table(self, "MyProductSalesS3Table", bucket=data_bucket, table_name="product_sales", database_name="sales_data_db", # The AWS Glue database name table_options=TableOptions( data_format=DataFormat.PARQUET, # Common for data lakes columns=[ Column(name="product_id", type="string"), Column(name="sale_date", type="date"), Column(name="amount", type="double"), Column(name="region", type="string") ], ), # Example: Partition by year and month for efficient querying # partition_keys=[ # Column(name="year", type="string"), # Column(name="month", type="string") # ] ) # You can access properties like table_name or database_name # CfnOutput(self, "S3BucketName", value=data_bucket.bucket_name) # CfnOutput(self, "GlueTableName", value=s3_glue_table.table_name) # Standard CDK application entry point app = App() MyS3TableStack(app, "MyS3TableStack", env=Environment( account=os.environ.get("CDK_DEFAULT_ACCOUNT"), region=os.environ.get("CDK_DEFAULT_REGION") ) ) app.synth()