Is it possible to group string within a string in Teradata? - sql

Question

The original table (exactly the one that I am using .. with all commas brackets etc)
id attributes
1 123(red), 139(red), 123(white), 123(black), 139(white),
2 123(black), 139(white), 123(green),
32 223(blue), 223(red), 553(white), 123(black),
4 323(white), 139(red),
23 523(red),
I need to group the attribute numbers so that my table looks like
id attributes
1 123(red, white, black); 139(red, white);
2 123(black, green); 139(white);
32 223(blue, red); 553(white); 123(black);
4 323(white); 139(red);
23 523(red);
How can I do this?
Unfortunately i do not have access to stored procedures and functions like oreplace .. translate. I used to deal with Oracle previously and this is an easy task given one has access to stored procedures ... here i have no idea what to do

Answer 1

SQL is definitely not the right language to do string processing like that :-)
I used existing code to split/create comma-delimited strings, but in TD14 it would be much easier (there's strtok_split_to_table and udfConcat).
CREATE VOLATILE TABLE vt (id INT, attrib VARCHAR(100)) ON COMMIT PRESERVE ROWS;
INSERT INTO vt(1 ,'123(red), 139(red), 123(white), 123(black), 139(white),');
INSERT INTO vt(2 ,'123(black), 139(white), 123(green),');
INSERT INTO vt(32 ,'223(blue), 223(red), 553(white), 123(black),');
INSERT INTO vt(4 ,'323(white), 139(red), ');
INSERT INTO vt(23 ,'523(red),');
WITH RECURSIVE cte
(id,
len,
remaining,
word,
pos
) AS (
SELECT
id,
POSITION(',' IN attrib || ',') - 1 AS len,
SUBSTRING(attrib || ',' FROM len + 2) AS remaining,
TRIM(SUBSTRING(attrib FROM 1 FOR len)) AS word,
1
FROM vt
UNION ALL
SELECT
id,
POSITION(',' IN remaining)- 1 AS len_new,
SUBSTRING(remaining FROM len_new + 2),
TRIM(SUBSTRING(remaining FROM 1 FOR len_new)),
pos + 1
FROM cte
WHERE remaining <> ''
)
SELECT
id,
MAX(CASE WHEN newpos = 1 THEN newgrp ELSE '' END) ||
MAX(CASE WHEN newpos = 2 THEN newgrp ELSE '' END) ||
MAX(CASE WHEN newpos = 3 THEN newgrp ELSE '' END) ||
MAX(CASE WHEN newpos = 4 THEN newgrp ELSE '' END) ||
MAX(CASE WHEN newpos = 5 THEN newgrp ELSE '' END) ||
MAX(CASE WHEN newpos = 6 THEN newgrp ELSE '' END)
-- add as many CASEs as needed
FROM
(
SELECT
id,
ROW_NUMBER()
OVER (PARTITION BY id
ORDER BY newgrp) AS newpos,
a ||
MAX(CASE WHEN pos = 1 THEN '(' || b ELSE '' END) ||
MAX(CASE WHEN pos = 2 THEN ', ' || b ELSE '' END) ||
MAX(CASE WHEN pos = 3 THEN ', ' || b ELSE '' END) ||
MAX(CASE WHEN pos = 4 THEN ', ' || b ELSE '' END) ||
MAX(CASE WHEN pos = 5 THEN ', ' || b ELSE '' END) ||
MAX(CASE WHEN pos = 6 THEN ', ' || b ELSE '' END)
-- add as many CASEs as needed
|| '); ' AS newgrp
FROM
(
SELECT
id,
ROW_NUMBER()
OVER (PARTITION BY id, a
ORDER BY pos) AS pos,
SUBSTRING(word FROM 1 FOR POSITION('(' IN word) - 1) AS a,
TRIM(TRAILING ')' FROM SUBSTRING(word FROM POSITION('(' IN word) + 1)) AS b
FROM cte
WHERE word <> ''
) AS dt
GROUP BY id, a
) AS dt
GROUP BY id;