5 התכונות המרכזיות של Apache Iceberg עבור אגמי נתונים מודרניים

-- time travel to October 5th, 1978 at 07:00:00

SELECT * FROM prod.retail.cusotmers TIMESTAMP AS OF '1978-10-05 07:00:00';

​

-- time travel using a specific snapshot ID:

SELECT * FROM prod.retail.customers VERSON AS OF 949530903748831869;

-- add a new column to the table

ALTER TABLE prod.retail.customers ADD COLUMNS (email_address STRING);

​

-- remove an existing column from the table 

ALTER TABLE prod.retail.customers DROP COLUMN num_of_years;

​

-- rename an existing column

ALTER TABLE prod.retail.customers RENAME COLUMN email_address TO email;

​

-- iceberg allows updating column types from int to bigint, float to double 

ALTER TABLE prod.retail.customers ALTER COLUMN customer_id TYPE bigint;

-- create customers table partitioned by month of the create_date initially

CREATE TABLE local.retail.customer (

    id BIGINT,

    name STRING,

    street STRING,

    city STRING,

    state STRING,

    create_date DATE

USING iceberg

PARTITIONED BY (month(create_date));

​

-- insert some data into the table

INSERT INTO local.retail.customer VALUES

    (1, 'Alice', '123 Maple St', 'Springfield', 'IL', DATE('2024-01-10')),

    (2, 'Bob', '456 Oak St', 'Salem', 'OR', DATE('2024-02-15')),

    (3, 'Charlie', '789 Pine St', 'Austin', 'TX', DATE('2024-02-20'));

​

-- change the partition scheme from month to date

ALTER TABLE local.retail.customer

REPLACE PARTITION FIELD month(create_date) WITH days(create_date);

​

-- insert couple more records

INSERT INTO local.retail.customer VALUES

    (4, 'David', '987 Elm St', 'Portland', 'ME', DATE('2024-03-01')),

    (5, 'Eve', '654 Birch St', 'Miami', 'FL', DATE('2024-03-02'));

​

-- select all columns from the table 

SELECT * FROM local.retail.customer

WHERE create_date BETWEEN DATE('2024-01-01') AND DATE('2024-03-31');

-- output

1 Alice 123 Maple St Springfield IL 2024-01-10

5 Eve 654 Birch St Miami FL 2024-03-02

4 David 987 Elm St Portland ME 2024-03-01

2 Bob 456 Oak St Salem OR 2024-02-15

3 Charlie 789 Pine St Austin TX 2024-02-20

​

-- View parition details

SELECT partition, file_path, record_count

FROM local.retail.customer.files;

-- output

{"create_date_month":null,"create_date_day":2024-03-02} /Users/rellaturi/warehouse/retail/customer/data/create_date_day=2024-03-02/00000-6-ae2fdf0d-5567-4c77-9bd1-a5d9f6c83dfe-0-00002.parquet 1

{"create_date_month":null,"create_date_day":2024-03-01} /Users/rvellaturi/warehouse/retail/customer/data/create_date_day=2024-03-01/00000-6-ae2fdf0d-5567-4c77-9bd1-a5d9f6c83dfe-0-00001.parquet 1

{"create_date_month":648,"create_date_day":null} /Users/rvellaturi/warehouse/retail/customer/data/create_date_month=2024-01/00000-3-64c8b711-f757-45b4-828f-553ae9779d14-0-00001.parquet 1

{"create_date_month":649,"create_date_day":null} /Users/rvellaturi/warehouse/retail/customer/data/create_date_month=2024-02/00000-3-64c8b711-f757-45b4-828f-553ae9779d14-0-00002.parquet 2

-- Start a transaction

START TRANSACTION;

​

-- Insert new records

INSERT INTO customers VALUES (1, 'John'), (2, 'Mike');

​

-- Update existing records

UPDATE customers SET column1 = 'Josh' WHERE id = 1;

​

-- Delete records

DELETE FROM customers WHERE id = 2;

​

-- Commit the transaction

COMMIT;

-- Atomic update across multiple tables

START TRANSACTION;

​

UPDATE orders SET status = 'processed' WHERE order_id = 100;

INSERT INTO orders_processed SELECT * FROM orders WHERE order_id = 100;

​

COMMIT;