Move your data from Amazon S3 to Google BigQuery, continuously

CREATE TABLE orders_rw (
    order_id INTEGER PRIMARY KEY,
    customer_id INTEGER,
    order_status VARCHAR,
    total_amount DECIMAL,
    last_updated TIMESTAMP)
INCLUDE file as file_name
INCLUDE offset -- default column name is `_rw_s3_offset`
WITH (
    connector = 's3',
    match_pattern = '%Ring%*.ndjson',
    s3.region_name = 'ap-southeast-2',
    s3.bucket_name = 's3-source',
    s3.credentials.access = 'credentials_access',
    s3.credentials.secret = 'credentials_secret',
    s3.endpoint_url = 'https://s3.us-east-1.amazonaws.com'
) FORMAT PLAIN ENCODE JSON;

CREATE SINK big_query_sink_local AS
SELECT
    order_status,
    COUNT(*) as order_count,
    SUM(total_amount) as total_revenue,
    AVG(total_amount) as avg_order_value,
    MIN(last_updated) as first_order_time,
    MAX(last_updated) as last_order_time
FROM orders_rw
WITH (
    connector = 'bigquery',
    type = 'append-only',
    bigquery.local.path = '/path/to/my/service-account.json',
    bigquery.project = 'my_project_id',
    bigquery.dataset = 'my_dataset',
    bigquery.table = 'my_table',
    force_append_only = 'true'
);