Ctas Patterns

CREATE TABLE "s3tablescatalog/my-bucket"."my_namespace"."customers"
WITH (format = 'PARQUET') AS
SELECT * FROM "awsdatacatalog"."legacy_db"."customers"

-- Source has explicit year/month/day columns from Hive partitioning
-- Target uses Iceberg day() transform on the timestamp column
CREATE TABLE "s3tablescatalog/my-bucket"."analytics"."events"
WITH (
    format = 'PARQUET',
    partitioning = ARRAY['day(event_timestamp)']
) AS
SELECT
    event_id,
    user_id,
    event_type,
    event_timestamp,
    payload
FROM "awsdatacatalog"."raw_db"."events_hive"

-- Batch 1: 2023 data
CREATE TABLE "s3tablescatalog/my-bucket"."ns"."orders"
WITH (format = 'PARQUET', partitioning = ARRAY['month(order_date)']) AS
SELECT * FROM "awsdatacatalog"."sales"."orders"
WHERE order_date >= DATE '2023-01-01' AND order_date < DATE '2024-01-01'

-- Batch 2+: INSERT INTO for subsequent years
INSERT INTO "s3tablescatalog/my-bucket"."ns"."orders"
SELECT * FROM "awsdatacatalog"."sales"."orders"
WHERE order_date >= DATE '2024-01-01' AND order_date < DATE '2025-01-01'

CREATE TABLE "s3tablescatalog/my-bucket"."clean"."users"
WITH (format = 'PARQUET') AS
SELECT
    user_id,
    LOWER(email) AS email,
    COALESCE(display_name, username) AS name,
    CAST(created_at AS timestamp) AS created_at,
    CASE WHEN status = 'A' THEN 'active' ELSE 'inactive' END AS status
FROM "awsdatacatalog"."legacy"."users_raw"

CREATE TABLE "s3tablescatalog/my-bucket"."analytics"."transactions"
WITH (
    format = 'PARQUET',
    partitioning = ARRAY['day(transaction_date)']
) AS
SELECT * FROM "awsdatacatalog"."iceberg_db"."transactions_selfmanaged"