We have 2 columns in one table in oracle SQL as
Col1= "there is book on the table"
Col2= "there are flowers on the chair"
Now I need the result as differed data in the column3 as new column col3.
The col3 result should be
"are flowers chair".
How to achieve this in oracle SQL??
You can use:
WITH words ( rid, col, name, id, word ) AS (
SELECT rid,
CASE INSTR(col, ' ')
WHEN 0
THEN NULL
ELSE SUBSTR(col, INSTR(col, ' ') + 1)
END,
name,
1,
CASE INSTR(col, ' ')
WHEN 0
THEN col
ELSE SUBSTR(col, 1, INSTR(col, ' ') - 1)
END
FROM ( SELECT ROWID AS rid, col1, col2 FROM table_name )
UNPIVOT ( col FOR name IN (col1, col2) )
UNION ALL
SELECT rid,
CASE INSTR(col, ' ')
WHEN 0
THEN NULL
ELSE SUBSTR(col, INSTR(col, ' ') + 1)
END,
name,
id + 1,
CASE INSTR(col, ' ')
WHEN 0
THEN col
ELSE SUBSTR(col, 1, INSTR(col, ' ') - 1)
END
FROM words
WHERE col IS NOT NULL
),
paired_words ( rid, id1, id2 ) AS (
SELECT c1.rid,
c1.id AS id1,
c2.id AS id2
FROM ( SELECT rid, id, word FROM words WHERE name = 'COL1' ) c1
INNER JOIN
( SELECT rid, id, word FROM words WHERE name = 'COL2' ) c2
ON (c1.rid = c2.rid AND c1.word = c2.word)
),
max_path ( rid, path ) AS (
SELECT rid,
path
FROM (
SELECT rid,
SYS_CONNECT_BY_PATH(id2, ',') || ',' AS path,
ROW_NUMBER() OVER (PARTITION BY rid ORDER BY LEVEL DESC) AS rn
FROM paired_words
CONNECT BY PRIOR rid = rid
AND PRIOR id1 < id1
AND PRIOR id2 < id2
)
WHERE rn = 1
)
SELECT LISTAGG(word, ' ') WITHIN GROUP (ORDER BY id) AS missing
FROM words w
WHERE NOT EXISTS (
SELECT 1
FROM max_path mp
WHERE w.rid = mp.rid
AND mp.path LIKE '%,' || w.id || ',%'
)
AND w.name = 'COL2'
GROUP BY rid;
Which, for the sample data:
CREATE TABLE table_name ( col1, col2 ) AS
SELECT 'there is book on the table', 'there are flowers on the chair' FROM DUAL UNION ALL
SELECT 'there is book on the table', 'there is a book on the table' FROM DUAL UNION ALL
SELECT 'there is book on the table', 'there is book there is book on the table on the table' FROM DUAL
Outputs:
MISSING
are flowers chair
a
there is book on the table
db<>fiddle here
Here's one option (which follows what you asked). Read comments within code.
SQL> with test (id, col1, col2) as
2 (select 1, 'there is book on the table',
3 'there are flowers on the chair'
4 from dual
5 ),
6 -- split sentences into words (each in its own line)
7 sent1 as
8 (select id,
9 column_value cv,
10 regexp_substr(col1, '[^ ]+', 1, column_value) word
11 from test cross join
12 table(cast(multiset(select level from dual
13 connect by level <= regexp_count(col1, ' ') + 1
14 ) as sys.odcinumberlist))
15 ),
16 sent2 as
17 (select id,
18 column_value cv,
19 regexp_substr(col2, '[^ ]+', 1, column_value) word
20 from test cross join
21 table(cast(multiset(select level from dual
22 connect by level <= regexp_count(col2, ' ') + 1
23 ) as sys.odcinumberlist))
24 )
25 -- final result
26 select a.id,
27 listagg(b.word, ' ') within group (order by a.cv) result
28 from sent2 b join sent1 a on a.id = b.id and a.cv = b.cv and a.word <> b.word
29 group by a.id;
ID RESULT
---------- ------------------------------
1 are flowers chair
SQL>
Column1 =A,B,C,D,E,F
Column2 =C,D,A,F,C,B (It can have duplicates)
I need to remove column2 values from column1 and get the missing value.
Desired output
(Column1)-(Column2) = E
Split columns' contents into rows, use MINUS set operator. Sample data in lines #1 - 3; query begins at line #4.
SQL> with test (col1, col2) as
2 (select 'A,B,C,D,E,F', 'C,D,A,F,C,B' from dual
3 )
4 select regexp_substr(col1, '[^,]+', 1, level) val
5 from test
6 connect by level <= regexp_count(col1, ',') + 1
7 minus
8 select regexp_substr(col2, '[^,]+', 1, level) val
9 from test
10 connect by level <= regexp_count(col2, ',') + 1
11 /
VAL
--------------------------------------------
E
SQL>
If you're comparing columns in a multi-row table, the above approach won't work OK as it'll retrieve duplicates and will be slow. In that case, rewrite it to
SQL> with test (id, col1, col2) as
2 (select 1, 'A,B,C,D,E,F', 'C,D,A,F,C,B' from dual union all
3 select 2, 'A,B,C,D,E,F', 'A,B,B,B' from dual
4 )
5 select id, listagg(val, ',') within group (order by val) missing_letters
6 from
7 (
8 select id,
9 regexp_substr(col1, '[^,]+', 1, column_value) val
10 from test cross join
11 table(cast(multiset(select level from dual
12 connect by level <= regexp_count(col1, ',') + 1
13 ) as sys.odcinumberlist))
14 minus
15 select id,
16 regexp_substr(col2, '[^,]+', 1, column_value) val
17 from test cross join
18 table(cast(multiset(select level from dual
19 connect by level <= regexp_count(col2, ',') + 1
20 ) as sys.odcinumberlist))
21 )
22 group by id;
ID MISSING_LETTERS
---------- --------------------
1 E
2 C,D,E,F
SQL>
You may use translate function with additional cleanup logic to remove all remaining commas. This will work only for single character replacement (one character between commas), but doesn't require to split string into tokens and uses simple string functions.
with a(col1, col2) as (
select 'A,B,C,D,E,F', 'C,D,A,F,C,B' from dual
)
select
/*Then remove leading and trailing commas*/
trim(',' from
/*Then condense all intermediate commas and spaces*/
regexp_replace(
/*Do actual replacement*/
translate(col1, replace(col2, ','), ' '),
'[, ]+', ','
)
) as res
from a
| RES |
| :-- |
| E |
db<>fiddle here
You do not need to split the string.
If your delimited values do not have any characters with special meaning in regular expressions then you can double-up the delimiters in col1 and then convert col2 to a regular expression and replace matches with an empty string and then remove the excess delimiters:
SELECT col1,
col2,
TRIM(
BOTH ',' FROM
REPLACE(
REGEXP_REPLACE(
',' || REPLACE(col1, ',', ',,') || ',',
',(' || REPLACE(col2, ',', '|') || '),'
),
',,',
','
)
) AS missing
FROM table_name;
Which, for the sample data:
CREATE TABLE table_name ( col1, col2 ) AS
SELECT 'A,B,C,D,E,F', 'C,D,A,F,C,B' FROM DUAL UNION ALL
SELECT 'A,AB,BA,B,', 'A,B' FROM DUAL;
Outputs:
COL1
COL2
MISSING
A,B,C,D,E,F
C,D,A,F,C,B
E
A,AB,BA,B,
A,B
AB,BA
If you do have characters with special meaning then you can do a similar replacement using a recursive sub-query:
WITH replacements ( col1, col2 ) AS (
SELECT ',' || REPLACE( col1, ',', ',,') || ',',
col2 || ','
FROM table_name
UNION ALL
SELECT REPLACE(col1, ',' || SUBSTR(col2, 1, INSTR(col2, ','))),
SUBSTR(col2, INSTR(col2, ',') + 1)
FROM replacements
WHERE col2 IS NOT NULL
)
SELECT TRIM(BOTH ',' FROM REPLACE(col1, ',,', ',')) AS missing
FROM replacements
WHERE col2 IS NULL
Which outputs:
MISSING
AB,BA
E
Note: both of these queries only require a single table scan.
db<>fiddle here
Using ora:tokenize you could do something like this (including a few test cases in the with clause; you should remove it, and use your actual table and column names in the main query):
with
inputs (col1, col2) as (
select 'A,B,C,D,E,F', 'C,D,A,F,C,B' from dual union all
select 'D,,F' , 'F,A' from dual union all
select 'A,B,E,F' , 'E' from dual union all
select 'ABC' , 'A,B,ABC' from dual
)
-- END OF TEST DATA; QUERY BEGINS **BELOW THIS LINE**
select i.col1, i.col2, l.diff
from inputs i cross join lateral
( select listagg(token, ',') within group (order by null) as diff
from xmltable('ora:tokenize(.,",")' passing i.col1 || ','
columns token varchar2(10) path '.')
where not ',' || col2 || ',' like '%,' || token || ',%' ) l
;
COL1 COL2 DIFF
----------- ----------- --------------------
A,B,C,D,E,F C,D,A,F,C,B E
D,,F F,A D
A,B,E,F E A,B,F
ABC A,B,ABC
I have a 'MASTER' table as shown below:
Entity Cat1 Cat2
A Mary;Steve Jacob
B Alex;John Sally;Andrew
Another table 'PERSON' has associations of person's name (this could be InfoID as well) with emails.
Name Email InfoID
Mary maryD#gmail.com mryD
Steve steveR#gmail.com stvR
Jacob jacobB#gmail.com jacbb
Sally sallyD#gmail.com sallD
Alex AlexT#gmail.com alexT
John JohnP#gmail.com johP
Andrew AndrewV#gmail.com andV
I want to join the person table with master such as:
Entity Cat1 EmailCat1 Cat2 EmailCat2
A Mary;Steve maryD#gmail.com;steveR#gmail.com Jacob jacobB#gmail.com
B Alex;John AlexT#gmail.com;JohnP#gmail.com Sally;Andrew sallyD#gmail.com;AndrewV#gmail.com
any insights on how to go about it?
Honestly, your master table design needs to be normalized. But, in the meantime you could try this query below :
with
needed_rows_for_cat1_tab (lvl) as (
select level from dual
connect by level <= (select max(regexp_count(Cat1, ';')) from Your_bad_master_tab) + 1
)
, needed_rows_for_cat2_tab (lvl) as (
select level from dual
connect by level <= (select max(regexp_count(Cat2, ';')) from Your_bad_master_tab) + 1
)
, split_cat1_val_tab as (
select Entity, Cat1
, substr(Cat1||';'
, lag(pos, 1, 0)over(partition by Entity order by lvl) + 1
, pos - lag(pos, 1, 0)over(partition by Entity order by lvl) - 1
) val
, lvl
, pos
, 1 cat
from (
select Entity, Cat1, instr(Cat1||';', ';', 1, r1.lvl)pos, r1.lvl
from Your_bad_master_tab c1
join needed_rows_for_cat1_tab r1 on r1.lvl <= regexp_count(Cat1, ';') + 1
)
)
, split_cat2_val_tab as (
select Entity, Cat2
, substr(Cat2||';'
, lag(pos, 1, 0)over(partition by Entity order by lvl) + 1
, pos - lag(pos, 1, 0)over(partition by Entity order by lvl) - 1
) val
, lvl
, pos
, 2 cat
from (
select Entity, Cat2, instr(Cat2||';', ';', 1, r2.lvl)pos, r2.lvl
from Your_bad_master_tab c1
join needed_rows_for_cat2_tab r2 on r2.lvl <= regexp_count(Cat2, ';') + 1
)
)
select ENTITY
, max(decode(cat, 1, CAT1, null)) CAT1
, listagg(decode(cat, 1, EMAIL, null), ';')within group (order by lvl) EmailCat1
, max(decode(cat, 2, CAT1, null)) CAT2
, listagg(decode(cat, 2, EMAIL, null), ';')within group (order by lvl) EmailCat2
from (
select c.*, p.Email
from split_cat1_val_tab c join Your_person_tab p on (c.val = p.name)
union all
select c.*, p.Email
from split_cat2_val_tab c join Your_person_tab p on (c.val = p.name)
)
group by ENTITY
;
Here are your sample data
--drop table Your_bad_master_tab purge;
create table Your_bad_master_tab (Entity, Cat1, Cat2) as
select 'A', 'Mary;Steve', 'Jacob' from dual union all
select 'B', 'Alex;John', 'Sally;Andrew' from dual
;
--drop table Your_person_tab purge;
create table Your_person_tab (Name, Email, InfoID) as
select 'Mary', 'maryD#gmail.com' ,'mryD' from dual union all
select 'Steve', 'steveR#gmail.com' ,'stvR' from dual union all
select 'Jacob', 'jacobB#gmail.com' ,'jacbb' from dual union all
select 'Sally', 'sallyD#gmail.com' ,'sallD' from dual union all
select 'Alex', 'AlexT#gmail.com' ,'alexT' from dual union all
select 'John', 'JohnP#gmail.com' ,'johP' from dual union all
select 'Andrew', 'AndrewV#gmail.com' ,'andV' from dual
;
DB<>fiddle
i'm trying to get total count by using UNION operator but it gives wrong count.
select count(*) as companyRatings from (
select count(*) hrs from (
select distinct hrs from companyA
)
union
select count(*) financehrs from (
select distinct finance_hrs from companyB
)
union
select count(*) hrids from (
select regexp_substr(hr_id,'[^/]+',1,3) hrid from companyZ
)
union
select count(*) cities from (
select regexp_substr(city,'[^/]+',1,3) city from companyY
)
);
individual query's working fine but total count not matching.
individual results here: 12 19 3 6
present total count: 31
Actual total count:40.
so there is any alternate solution without UNION operator?
To add values you'd use +. UNION is to add data sets.
select
(select count(distinct hrs) from companyA)
+
(select count(distinct finance_hrs) from companyB)
+
(select count(regexp_substr(hr_id,'[^/]+',1,3)) from companyZ)
+
(select count(regexp_substr(city,'[^/]+',1,3)) from companyY)
as total
from dual;
But I agree with juergen d; you should not have separate tables per company in the first place.
Edit. Updated query using Sum
select sum(cnt) as companyRatings from
(
select count(*) as cnt from (select distinct hrs from companyA)
union all
select count(*) as cnt from (select distinct finance_hrs from companyB)
union all
select count(*) as cnt from (select regexp_substr(hr_id,'[^/]+',1,3) hrid from companyZ)
union all
select count(*) as cnt from (select regexp_substr(city,'[^/]+',1,3) city from companyY)
)
Previous answer:
Try this
SELECT (
SELECT count(*) hrs
FROM (
SELECT DISTINCT hrs
FROM companyA
)
)
+
(
SELECT count(*) financehrs
FROM (
SELECT DISTINCT finance_hrs
FROM companyB
)
)
+
(
SELECT count(*) hrids
FROM (
SELECT regexp_substr(hr_id, '[^/]+', 1, 3) hrid
FROM companyZ
)
)
+
(
SELECT count(*) cities
FROM (
SELECT regexp_substr(city, '[^/]+', 1, 3) city
FROM companyY
)
)
AS total_count
FROM dual
How to get the following result ?
Input : -
t1
--------------
col1 col2 col3
--------------
101, abc, 100
101, xyz, 200
101, rst, 300
-------------
Output : -
101 abc 100 xyz 200 rst 300
Please try:
SELECT col1, replace(wm_concat(col2||col3),',', '') FROM t1 GROUP BY col1;
or
SELECT col1, (SELECT XMLAGG(xmlelement(X, X1.col2||col3)order by X1.col2).extract('//text()')
FROM t1 X1 WHERE X1.col1=X.col1)
FROM t1 X
This works with 11g and maintains the order of items.
select LISTAGG (code, ' ') WITHIN GROUP (ORDER BY rn, coln)
from(
select code, min(rn) as rn, min(coln) as coln
from(
select col1 as code, rownum rn, 1 as coln from t order by col1, col3
union all
select col2 as code, rownum rn, 2 as coln from t order by col1, col3
union all
select col3 as code, rownum rn, 3 as coln from t order by col1, col3
)
group by code
)
Try with
select col1 || ' ' || listagg( col2 || ' ' || col3, ' ' ) within group ( order by COL3 )
from t1
group by col1;