[sql] SQL SELECT WHERE field contains words

I need a select which would return results like this:

SELECT * FROM MyTable WHERE Column1 CONTAINS 'word1 word2 word3'

And I need all results, i.e. this includes strings with 'word2 word3 word1' or 'word1 word3 word2' or any other combination of the three.

All words need to be in the result.

If you just want to find a match.

SELECT * FROM MyTable WHERE INSTR('word1 word2 word3',Column1)<>0

SQL Server :

CHARINDEX(Column1, 'word1 word2 word3', 1)<>0

To get exact match. Example (';a;ab;ac;',';b;') will not get a match.

SELECT * FROM MyTable WHERE INSTR(';word1;word2;word3;',';'||Column1||';')<>0

select * from table where name regexp '^word[1-3]$'

or

select * from table where name in ('word1','word2','word3')

This should ideally be done with the help of sql server full text search if using. However, if you can't get that working on your DB for some reason, here is a performance intensive solution :-

-- table to search in
CREATE TABLE dbo.myTable
    (
    myTableId int NOT NULL IDENTITY (1, 1),
    code varchar(200) NOT NULL, 
    description varchar(200) NOT NULL -- this column contains the values we are going to search in 
    )  ON [PRIMARY]
GO

-- function to split space separated search string into individual words
CREATE FUNCTION [dbo].[fnSplit] (@StringInput nvarchar(max),
@Delimiter nvarchar(1))
RETURNS @OutputTable TABLE (
  id nvarchar(1000)
)
AS
BEGIN
  DECLARE @String nvarchar(100);

  WHILE LEN(@StringInput) > 0
  BEGIN
    SET @String = LEFT(@StringInput, ISNULL(NULLIF(CHARINDEX(@Delimiter, @StringInput) - 1, -1),
    LEN(@StringInput)));
    SET @StringInput = SUBSTRING(@StringInput, ISNULL(NULLIF(CHARINDEX
    (
    @Delimiter, @StringInput
    ),
    0
    ), LEN
    (
    @StringInput)
    )
    + 1, LEN(@StringInput));

    INSERT INTO @OutputTable (id)
      VALUES (@String);
  END;

  RETURN;
END;
GO

-- this is the search script which can be optionally converted to a stored procedure /function


declare @search varchar(max) = 'infection upper acute genito'; -- enter your search string here
-- the searched string above should give rows containing the following
-- infection in upper side with acute genitointestinal tract
-- acute infection in upper teeth
-- acute genitointestinal pain

if (len(trim(@search)) = 0) -- if search string is empty, just return records ordered alphabetically
begin
 select 1 as Priority ,myTableid, code, Description from myTable order by Description 
 return;
end

declare @splitTable Table(
wordRank int Identity(1,1), -- individual words are assinged priority order (in order of occurence/position)
word varchar(200)
)
declare @nonWordTable Table( -- table to trim out auxiliary verbs, prepositions etc. from the search
id varchar(200)
)

insert into @nonWordTable values
('of'),
('with'),
('at'),
('in'),
('for'),
('on'),
('by'),
('like'),
('up'),
('off'),
('near'),
('is'),
('are'),
(','),
(':'),
(';')

insert into @splitTable
select id from dbo.fnSplit(@search,' '); -- this function gives you a table with rows containing all the space separated words of the search like in this e.g., the output will be -
--  id
-------------
-- infection
-- upper
-- acute
-- genito

delete s from @splitTable s join @nonWordTable n  on s.word = n.id; -- trimming out non-words here
declare @countOfSearchStrings int = (select count(word) from @splitTable);  -- count of space separated words for search
declare @highestPriority int = POWER(@countOfSearchStrings,3);

with plainMatches as
(
select myTableid, @highestPriority as Priority from myTable where Description like @search  -- exact matches have highest priority
union                                      
select myTableid, @highestPriority-1 as Priority from myTable where Description like  @search + '%'  -- then with something at the end
union                                      
select myTableid, @highestPriority-2 as Priority from myTable where Description like '%' + @search -- then with something at the beginning
union                                      
select myTableid, @highestPriority-3 as Priority from myTable where Description like '%' + @search + '%' -- then if the word falls somewhere in between
),
splitWordMatches as( -- give each searched word a rank based on its position in the searched string
                     -- and calculate its char index in the field to search
select myTable.myTableid, (@countOfSearchStrings - s.wordRank) as Priority, s.word,
wordIndex = CHARINDEX(s.word, myTable.Description)  from myTable join @splitTable s on myTable.Description like '%'+ s.word + '%'
-- and not exists(select myTableid from plainMatches p where p.myTableId = myTable.myTableId) -- need not look into myTables that have already been found in plainmatches as they are highest ranked
                                                                              -- this one takes a long time though, so commenting it, will have no impact on the result
),
matchingRowsWithAllWords as (
 select myTableid, count(myTableid) as myTableCount from splitWordMatches group by(myTableid) having count(myTableid) = @countOfSearchStrings
)
, -- trim off the CTE here if you don't care about the ordering of words to be considered for priority
wordIndexRatings as( -- reverse the char indexes retrived above so that words occuring earlier have higher weightage
                     -- and then normalize them to sequential values
select s.myTableid, Priority, word, ROW_NUMBER() over (partition by s.myTableid order by wordindex desc) as comparativeWordIndex 
from splitWordMatches s join matchingRowsWithAllWords m on s.myTableId = m.myTableId
)
,
wordIndexSequenceRatings as ( -- need to do this to ensure that if the same set of words from search string is found in two rows,
                              -- their sequence in the field value is taken into account for higher priority
    select w.myTableid, w.word, (w.Priority + w.comparativeWordIndex + coalesce(sequncedPriority ,0)) as Priority
    from wordIndexRatings w left join 
    (
     select w1.myTableid, w1.priority, w1.word, w1.comparativeWordIndex, count(w1.myTableid) as sequncedPriority
     from wordIndexRatings w1 join wordIndexRatings w2 on w1.myTableId = w2.myTableId and w1.Priority > w2.Priority and w1.comparativeWordIndex>w2.comparativeWordIndex
     group by w1.myTableid, w1.priority,w1.word, w1.comparativeWordIndex
    ) 
    sequencedPriority on w.myTableId = sequencedPriority.myTableId and w.Priority = sequencedPriority.Priority
),
prioritizedSplitWordMatches as ( -- this calculates the cumulative priority for a field value
select  w1.myTableId, sum(w1.Priority) as OverallPriority from wordIndexSequenceRatings w1 join wordIndexSequenceRatings w2 on w1.myTableId =  w2.myTableId 
where w1.word <> w2.word group by w1.myTableid 
),
completeSet as (
select myTableid, priority from plainMatches -- get plain matches which should be highest ranked
union
select myTableid, OverallPriority as priority from prioritizedSplitWordMatches -- get ranked split word matches (which are ordered based on word rank in search string and sequence)
),
maximizedCompleteSet as( -- set the priority of a field value = maximum priority for that field value
select myTableid, max(priority) as Priority  from completeSet group by myTableId
)
select priority, myTable.myTableid , code, Description from maximizedCompleteSet m join myTable  on m.myTableId = myTable.myTableId 
order by Priority desc, Description -- order by priority desc to get highest rated items on top
--offset 0 rows fetch next 50 rows only -- optional paging

try to use the "tesarus search" in full text index in MS SQL Server. This is much better than using "%" in search if you have millions of records. tesarus have a small amount of memory consumption than the others. try to search this functions :)

Note that if you use LIKE to determine if a string is a substring of another string, you must escape the pattern matching characters in your search string.

If your SQL dialect supports CHARINDEX, it's a lot easier to use it instead:

SELECT * FROM MyTable
WHERE CHARINDEX('word1', Column1) > 0
  AND CHARINDEX('word2', Column1) > 0
  AND CHARINDEX('word3', Column1) > 0

Also, please keep in mind that this and the method in the accepted answer only cover substring matching rather than word matching. So, for example, the string 'word1word2word3' would still match.

SELECT * FROM MyTable WHERE Column1 Like "*word*"

This will display all the records where column1 has a partial value contains word.

If you are using Oracle Database then you can achieve this using contains query. Contains querys are faster than like query.

If you need all of the words

SELECT * FROM MyTable WHERE CONTAINS(Column1,'word1 and word2 and word3', 1) > 0

If you need any of the words

SELECT * FROM MyTable WHERE CONTAINS(Column1,'word1 or word2 or word3', 1) > 0

Contains need index of type CONTEXT on your column.

CREATE INDEX SEARCH_IDX ON MyTable(Column) INDEXTYPE IS CTXSYS.CONTEXT

One of the easiest ways to achiever what is mentioned in the question is by using CONTAINS with NEAR or '~'. For example the following queries would give us all the columns that specifically include word1, word2 and word3.

SELECT * FROM MyTable WHERE CONTAINS(Column1, 'word1 NEAR word2 NEAR word3')

SELECT * FROM MyTable WHERE CONTAINS(Column1, 'word1 ~ word2 ~ word3')

In addition, CONTAINSTABLE returns a rank for each document based on the proximity of "word1", "word2" and "word3". For example, if a document contains the sentence, "The word1 is word2 and word3," its ranking would be high because the terms are closer to one another than in other documents.

One other thing that I would like to add is that we can also use proximity_term to find columns where the words are inside a specific distance between them inside the column phrase.

Function

 CREATE FUNCTION [dbo].[fnSplit] ( @sep CHAR(1), @str VARCHAR(512) )
 RETURNS TABLE AS
 RETURN (
           WITH Pieces(pn, start, stop) AS (
           SELECT 1, 1, CHARINDEX(@sep, @str)
           UNION ALL
           SELECT pn + 1, stop + 1, CHARINDEX(@sep, @str, stop + 1)
           FROM Pieces
           WHERE stop > 0
      )

      SELECT
           pn AS Id,
           SUBSTRING(@str, start, CASE WHEN stop > 0 THEN stop - start ELSE 512 END) AS Data
      FROM
           Pieces
 )

Query

 DECLARE @FilterTable TABLE (Data VARCHAR(512))

 INSERT INTO @FilterTable (Data)
 SELECT DISTINCT S.Data
 FROM fnSplit(' ', 'word1 word2 word3') S -- Contains words

 SELECT DISTINCT
      T.*
 FROM
      MyTable T
      INNER JOIN @FilterTable F1 ON T.Column1 LIKE '%' + F1.Data + '%'
      LEFT JOIN @FilterTable F2 ON T.Column1 NOT LIKE '%' + F2.Data + '%'
 WHERE
      F2.Data IS NULL

best way is making full-text index on a column in table and use contain instead of LIKE

SELECT * FROM MyTable WHERE 
contains(Column1 , N'word1' )
AND contains(Column1 , N'word2' )
AND contains(Column1 , N'word3' )

why not use "in" instead?

Select *
from table
where columnname in (word1, word2, word3)

Instead of SELECT * FROM MyTable WHERE Column1 CONTAINS 'word1 word2 word3', add And in between those words like:

SELECT * FROM MyTable WHERE Column1 CONTAINS 'word1 And word2 And word3'

for details, see here https://msdn.microsoft.com/en-us/library/ms187787.aspx

UPDATE

For selecting phrases, use double quotes like:

SELECT * FROM MyTable WHERE Column1 CONTAINS '"Phrase one" And word2 And "Phrase Two"'

p.s. you have to first enable Full Text Search on the table before using contains keyword. for more details, See here https://docs.microsoft.com/en-us/sql/relational-databases/search/get-started-with-full-text-search

DECLARE @SearchStr nvarchar(100)
SET @SearchStr = ' '



CREATE TABLE #Results (ColumnName nvarchar(370), ColumnValue nvarchar(3630))

SET NOCOUNT ON

DECLARE @TableName nvarchar(256), @ColumnName nvarchar(128), @SearchStr2 nvarchar(110)
SET  @TableName = ''
SET @SearchStr2 = QUOTENAME('%' + @SearchStr + '%','''')

WHILE @TableName IS NOT NULL

BEGIN
    SET @ColumnName = ''
    SET @TableName = 
    (
        SELECT MIN(QUOTENAME(TABLE_SCHEMA) + '.' + QUOTENAME(TABLE_NAME))
        FROM     INFORMATION_SCHEMA.TABLES
        WHERE         TABLE_TYPE = 'BASE TABLE'
            AND    QUOTENAME(TABLE_SCHEMA) + '.' + QUOTENAME(TABLE_NAME) > @TableName
            AND    OBJECTPROPERTY(
                    OBJECT_ID(
                        QUOTENAME(TABLE_SCHEMA) + '.' + QUOTENAME(TABLE_NAME)
                         ), 'IsMSShipped'
                           ) = 0
    )

    WHILE (@TableName IS NOT NULL) AND (@ColumnName IS NOT NULL)

    BEGIN
        SET @ColumnName =
        (
            SELECT MIN(QUOTENAME(COLUMN_NAME))
            FROM     INFORMATION_SCHEMA.COLUMNS
            WHERE         TABLE_SCHEMA    = PARSENAME(@TableName, 2)
                AND    TABLE_NAME    = PARSENAME(@TableName, 1)
                AND    DATA_TYPE IN ('char', 'varchar', 'nchar', 'nvarchar', 'int', 'decimal')
                AND    QUOTENAME(COLUMN_NAME) > @ColumnName
        )

        IF @ColumnName IS NOT NULL

        BEGIN
            INSERT INTO #Results
            EXEC
            (
                'SELECT ''' + @TableName + '.' + @ColumnName + ''', LEFT(' + @ColumnName + ', 3630) FROM ' + @TableName + ' (NOLOCK) ' +
                ' WHERE ' + @ColumnName + ' LIKE ' + @SearchStr2
            )
        END
    END   
END

SELECT ColumnName, ColumnValue FROM #Results

DROP TABLE #Results

SELECT * FROM MyTable WHERE 
Column1 LIKE '%word1%'
AND Column1 LIKE '%word2%'
AND Column1 LIKE  '%word3%'

Changed OR to AND based on edit to question.