duckdb going mad...

UNION Type

CREATE TABLE messages(u UNION(num INT, error VARCHAR));
INSERT INTO messages VALUES (42);
INSERT INTO messages VALUES ('oh my globs');

FROM-first

-- SELECT clause is optional, SELECT * is implied (if not included)
FROM tbl;

-- first 5 rows of the table
FROM tbl LIMIT 5;

-- SELECT can be used after the FROM
FROM tbl SELECT l_orderkey;

-- insert all data from tbl1 into tbl2
INSERT INTO tbl2 FROM tbl1;

BTW SQL standard already has special syntax for it:

TABLE tbl;

COLUMNS Expression

SELECT MIN(COLUMNS(*)), COUNT(*) from obs;
SELECT COLUMNS('val[0-9]+') from obs;

List comprehension support

SELECT [x + 1 for x in [1, 2, 3]] AS l;

оО
https://techcrunch.com/2022/11/15/motherduck-secures-investment-from-andreessen-horowitz-to-commercialize-duckdb/

Now in snowflake...

create table t (a int, b int, c int);
create view v as 
    select * exclude (a) rename (b as d, c as e) from t
;

... and in dwh.dev and parsers.dev!

Только сейчас заметила, что у ребят из IT Resume можно прямо на сайте пробовать решать sql задачки. Вот задача про когорты, например: https://itresume.ru/problems/sql-cohort

Где еще практиковать SQL бесплатно:
- sql-ex
- sqlbolt
- sql-academy
- stepik тренажер
- w3schools
- sqlzoo
- pgexercises

Smart-ass...

https://readyset.io

> can you write a new Radiohead song about data lineage?

Verse 1:
I’m tracing the data lineage
From its source to where it ends
Every table and column
Every join and every blend

Chorus:
I’m on the path of data lineage
Following the trail of bits and bytes
Through the labyrinth of technology
Where the truth of data lies

Verse 2:
I’m chasing the data lineage
From the past to the present tense
Every calculation and transformation
Every rule and every exception

Chorus:
I’m on the path of data lineage
Following the trail of bits and bytes
Through the labyrinth of technology
Where the truth of data lies

Bridge:
I see the patterns and the connections
I see the errors and the corrections
I see the beauty and the complexity
Of the data lineage

Outro:
I’m on the path of data lineage
Following the trail of bits and bytes
Through the labyrinth of technology
Where the truth of data lies.

{
    "data": "beeline meetup: data engineering tools",
    "details": {
        "date": "December, 20",
        "time": "17:00 GMT+3",
        "place": "online"
    }
}

We will discuss creating end-to-end logs, working with Apache NiFi and Apache Flink at the free meetup from beeline and JUG Ru Group.

Registration

> So increasing speed up to 4 times of both in-memory and on-disk sorts in version 15 is one of the main reasons to upgrade.

https://supabase.com/blog/new-in-postgres-15