Repeating values in a column

Question

I have the following values in a column which are separated by comma.

BHOP23,BHOP23,BHOP24

I would like to know whether values are repeating in a column.

How can I do this?

Answer 1

A PL/SQL function which only relies on simple string functions (SUBSTR, INSTR and LENGTH) to remove duplicates from a string list:

SQL Fiddle

Oracle 11g R2 Schema Setup:

CREATE TABLE your_table ( your_list_column ) AS
  SELECT 'a,a,b,c,d' FROM DUAL UNION ALL -- duplicates both at head
  SELECT 'a,b,a,c,d' FROM DUAL UNION ALL -- duplicates at head and middle
  SELECT 'a,b,c,d,a' FROM DUAL UNION ALL -- duplicates at head and tail
  SELECT 'a,b,b,c,d' FROM DUAL UNION ALL -- duplicates at middle and next item
  SELECT 'a,b,c,b,d' FROM DUAL UNION ALL -- duplicates at middle and middle
  SELECT 'a,b,c,d,b' FROM DUAL UNION ALL -- duplicates at middle and tail
  SELECT 'a,b,c,d,d' FROM DUAL UNION ALL -- duplicates both at tail
  SELECT 'a,b,a,c,b' FROM DUAL UNION ALL -- two pairs of duplicates
  SELECT 'a,b,c,d,e' FROM DUAL           -- no duplicates
/

CREATE OR REPLACE FUNCTION remove_Duplicates_From_List(
  i_str    IN  VARCHAR2,
  i_delim  IN  VARCHAR2 DEFAULT ','
) RETURN VARCHAR2 DETERMINISTIC
AS
  p_result       VARCHAR2(4000) := i_delim;
  p_temp         VARCHAR2(4000);
  p_start        NUMBER(5) := 1;
  p_end          NUMBER(5);
  c_len CONSTANT NUMBER(5) := LENGTH( i_str );
  c_ld  CONSTANT NUMBER(5) := LENGTH( i_delim );
BEGIN
  IF c_len > 0 THEN
    p_end := INSTR( i_str, i_delim, p_start );
    WHILE p_end > 0 LOOP
      p_temp := SUBSTR( i_str, p_start, p_end + c_ld - p_start );
      IF INSTR( p_result, i_delim || p_temp ) = 0 THEN
        p_result := p_result || p_temp;
      END IF;
      p_start := p_end + c_ld;
      p_end := INSTR( i_str, i_delim, p_start );
    END LOOP;
    IF p_start <= c_len + 1 THEN
      p_temp := SUBSTR( i_str, p_start, c_len - p_start + 1 ) || i_delim;
      IF INSTR( p_result, i_delim || p_temp ) = 0 THEN
        p_result := p_result || p_temp;
      END IF;
    END IF;
  END IF;
  RETURN SUBSTR( p_result, c_ld + 1, LENGTH( p_result ) - 2 * c_ld );
END;
/

Query 1:

SELECT your_list_column,
       remove_Duplicates_From_List( your_list_column ) AS uniq
FROM   your_table

Results:

| YOUR_LIST_COLUMN |      UNIQ |
|------------------|-----------|
|        a,a,b,c,d |   a,b,c,d |
|        a,b,a,c,d |   a,b,c,d |
|        a,b,c,d,a |   a,b,c,d |
|        a,b,b,c,d |   a,b,c,d |
|        a,b,c,b,d |   a,b,c,d |
|        a,b,c,d,b |   a,b,c,d |
|        a,b,c,d,d |   a,b,c,d |
|        a,b,a,c,b |     a,b,c |
|        a,b,c,d,e | a,b,c,d,e |

Answer 2

Oracle Setup:

CREATE TABLE your_table ( your_list_column ) AS
  SELECT 'a,a,b,c,d' FROM DUAL UNION ALL -- duplicates both at head
  SELECT 'a,b,a,c,d' FROM DUAL UNION ALL -- duplicates at head and middle
  SELECT 'a,b,c,d,a' FROM DUAL UNION ALL -- duplicates at head and tail
  SELECT 'a,b,b,c,d' FROM DUAL UNION ALL -- duplicates at middle and next item
  SELECT 'a,b,c,b,d' FROM DUAL UNION ALL -- duplicates at middle and middle
  SELECT 'a,b,c,d,b' FROM DUAL UNION ALL -- duplicates at middle and tail
  SELECT 'a,b,c,d,d' FROM DUAL UNION ALL -- duplicates both at tail
  SELECT 'a,b,a,c,b' FROM DUAL UNION ALL -- two pairs of duplicates
  SELECT 'a,b,c,d,e' FROM DUAL;          -- no duplicates

To get the lists which have repeated values, you can use a back-reference in a regular expression:

SELECT *
FROM   your_table
WHERE  REGEXP_LIKE( ',' || your_list_column || ',', ',([^,]+),(.+,)?\1,' )

Output:

YOUR_LIST_COLUMN
----------------
a,a,b,c,d
a,b,a,c,d
a,b,c,d,a
a,b,b,c,d
a,b,c,b,d
a,b,c,d,b
a,b,c,d,d
a,b,a,c,b

To get the first repeated value you can extract the first sub-group of the above regular expression:

SELECT your_list_column,
       REGEXP_SUBSTR( ',' || your_list_column || ',', ',([^,]+),(.+,)?\1,', 1, 1, NULL, 1 )
         AS duplicate_value
FROM   your_table
WHERE  REGEXP_LIKE( ',' || your_list_column || ',', ',([^,]+),(.+,)?\1,' )

Output:

YOUR_LIST_COLUMN DUPLICATE VALUE
---------------- ---------------
a,a,b,c,d        a
a,b,a,c,d        a
a,b,c,d,a        a
a,b,b,c,d        b
a,b,c,b,d        b
a,b,c,d,b        b
a,b,c,d,d        d
a,b,a,c,b        a

To get the unique values then, use the split_string() function as defined here (but using a user-defined type rather than a pre-defined VARRAY):

CREATE OR REPLACE TYPE stringlist IS TABLE OF VARCHAR2(4000);
/

CREATE OR REPLACE FUNCTION split_String(
  i_str    IN  VARCHAR2,
  i_delim  IN  VARCHAR2 DEFAULT ','
) RETURN stringlist DETERMINISTIC
AS
  p_result       stringlist := stringlist();
  p_start        NUMBER(5) := 1;
  p_end          NUMBER(5);
  c_len CONSTANT NUMBER(5) := LENGTH( i_str );
  c_ld  CONSTANT NUMBER(5) := LENGTH( i_delim );
BEGIN
  IF c_len > 0 THEN
    p_end := INSTR( i_str, i_delim, p_start );
    WHILE p_end > 0 LOOP
      p_result.EXTEND;
      p_result( p_result.COUNT ) := SUBSTR( i_str, p_start, p_end - p_start );
      p_start := p_end + c_ld;
      p_end := INSTR( i_str, i_delim, p_start );
    END LOOP;
    IF p_start <= c_len + 1 THEN
      p_result.EXTEND;
      p_result( p_result.COUNT ) := SUBSTR( i_str, p_start, c_len - p_start + 1 );
    END IF;
  END IF;
  RETURN p_result;
END;
/

Then you can use it in conjunction with the SET() collection function:

SELECT t.*,
       (
         SELECT LISTAGG( COLUMN_VALUE, ',' ) WITHIN GROUP ( ORDER BY ROWNUM )
         FROM   TABLE( SET( split_string( t.your_list_column ) ) )
       ) AS unique_list
FROM   your_table t

Output:

YOUR_LIST_COLUMN UNIQUE_LIST
---------------- ---------------
a,a,b,c,d        a,b,c,d
a,b,a,c,d        a,b,c,d
a,b,c,d,a        a,b,c,d
a,b,b,c,d        a,b,c,d
a,b,c,b,d        a,b,c,d
a,b,c,d,b        a,b,c,d
a,b,c,d,d        a,b,c,d
a,b,a,c,b        a,b,c
a,b,c,d,e        a,b,c,d,e