Foneticalize (https://github.com/vyper/fonetica-sql)

buscaBR.java

import org.apache.commons.lang3.StringUtils;

final public class BuscaBr {
	
	final static String vogais = "aaaaaeeeeiiiiooooouuuu";
	final static String vogaisAcentuadas = "áâàãäéêèëíîìïóõòôöúùûü";
	
	final static String[] lista01 = 		{"y","br","bl","ph","gr","gl","mg","ng","rg","ge","gi","rj","mj","nj","q","ca","co","cu","ck","c","lh","n","rm","gm","md","sm"};
	final static String[] lista01Troca = 	{"i","b","b","f","g","g","g","g","g","j","j","j","j","j","k","k","k","k","k","k","l","m","m","m","m","m"};
	
	final static String[] lista02 = 		{"nh","pr","ç","ce","ci","ch","x","ts","cs","c","z","rs","lt","tr","ct","rt","st","w","l"};
	final static String[] lista02Troca = 	{"n","p","s","s","s","s","s","s","s","s","s","s","t","t","t","t","t","v","r"};
	
	final static String[] lista03 = 	 {"h","aa","bb","cc","dd","ee","ff","gg","hh","ii","jj","kk","ll","mm","nn","oo","pp","qq","rr","ss","tt","uu","vv","ww","xx","yy","zz"};
	final static String[] lista03Troca = {"","a","","","","e","","","","i","","","l","m","n","","p","","r","s","t","","","","","",""};
	//lista03Troca original
	//final static String[] lista03Troca = {"","","","","","","","","","","","","","","","","","","","","","","","","","",""};
	
	final static String[] lista04 = 	{"a","e","i","o","u"};
	final static String[] lista04Troca = 	{"","","","",""};

	public static String buscaBr(String entrada){
		entrada = entrada.toLowerCase();
		entrada = entrada.trim();
		String textoBuilder = entrada;
		StringBuilder stringFinal = new StringBuilder();
		
		
		String[] frase = StringUtils.split(textoBuilder); 
		
		for (int i = 0; i < frase.length; i++) {
			textoBuilder = frase[i].trim();
			textoBuilder = StringUtils.replaceChars(textoBuilder, vogaisAcentuadas, vogais);
			textoBuilder = StringUtils.replaceEach(textoBuilder, lista01, lista01Troca);
			textoBuilder = StringUtils.replaceEach(textoBuilder, lista02, lista02Troca);
			
			if (StringUtils.substring(textoBuilder, -1).equals("s")) 
				textoBuilder = StringUtils.substring(textoBuilder, 0, -1);
			
			if (StringUtils.substring(textoBuilder, -1).equals("z")) 
				textoBuilder = StringUtils.substring(textoBuilder, 0, -1);
			
			if (StringUtils.substring(textoBuilder, -1).equals("r")) 
				textoBuilder = StringUtils.substring(textoBuilder, 0, -1);
			
			if (StringUtils.substring(textoBuilder, -1).equals("m")) 
				textoBuilder = StringUtils.substring(textoBuilder, 0, -1);
			
			if (StringUtils.substring(textoBuilder, -1).equals("n")) 
				textoBuilder = StringUtils.substring(textoBuilder, 0, -1);
			
			if (StringUtils.substring(textoBuilder, -2).equals("ao")) 
				textoBuilder = StringUtils.substring(textoBuilder, 0, -2);
			
			if (StringUtils.substring(textoBuilder, -1).equals("l")) 
				textoBuilder = StringUtils.substring(textoBuilder, 0, -1);
			
			
			textoBuilder = StringUtils.replaceEach(textoBuilder, lista03, lista03Troca);
		  //Neste ponto é possivel retirar todas as vogais, simplinficando ainda mais o codigo fonético.
		  textoBuilder = StringUtils.replaceEach(textoBuilder, lista04, lista04Troca);
			
			stringFinal.append(textoBuilder+" ");
			
		}	
		return stringFinal.toString().trim();
	}
	
	
}

buscaBR.scala

import java.text.Normalizer

object BuscaBR {
  def buscaBR(string:String) :String = {
    Normalizer.normalize(string, Normalizer.Form.NFD)
      .replaceAll("[^\\p{ASCII}]", "")
      .toLowerCase()
      .replaceAll("[^a-z ]","")
      .replaceAll("[ ]+"," ")
      .replaceAll("^ ","")
      .replaceAll(" $","")
      .replaceAll("y","i")
      .replaceAll("w","v")
      .replaceAll("[szprmnl] "," ")
      .replaceAll("[szprmnl]$","")
      .replaceAll("que","ke")
      .replaceAll("qui","ki")
      .replaceAll("q","k")
      .replaceAll("ge", "je")
      .replaceAll("gi", "ji")
      .replaceAll("gue", "ge")
      .replaceAll("gui", "gi")
      .replaceAll("ce", "se")
      .replaceAll("ci", "si")
      .replaceAll("ck", "k")
      .replaceAll("ca", "ka")
      .replaceAll("co", "ko")
      .replaceAll("cu", "ku")
      .replaceAll("pr", "p")
      .replaceAll("pl", "p")
      .replaceAll("br", "b")
      .replaceAll("bl", "b")
      .replaceAll("lh", "l")
      .replaceAll("nh", "n")
      .replaceAll("ch", "s")
      .replaceAll("ct", "t")
      .replaceAll("pt", "t")
      .replaceAll("st", "t")
      .replaceAll("rt", "p")
      .replaceAll("lt", "t")
      .replaceAll("tr", "t")
      .replaceAll("tl", "t")
      .replaceAll("mg", "g")
      .replaceAll("ng", "g")
      .replaceAll("rg", "g")
      .replaceAll("lg", "g")
      .replaceAll("gr", "g")
      .replaceAll("gl", "g")
      .replaceAll("md", "d")
      .replaceAll("nd", "d")
      .replaceAll("rd", "d")
      .replaceAll("ld", "d")
      .replaceAll("dr", "d")
      .replaceAll("dl", "d")
      .replaceAll("mc", "k")
      .replaceAll("nc", "k")
      .replaceAll("rc", "k")
      .replaceAll("lc", "k")
      .replaceAll("cr", "k")
      .replaceAll("cl", "k")
      .replaceAll("rj", "j")
      .replaceAll("lj", "j")
      .replaceAll("mj", "j")
      .replaceAll("nj", "j")
      .replaceAll("rm", "m")
      .replaceAll("lm", "m")
      .replaceAll("gm", "m")
      .replaceAll("sm", "m")
      .replaceAll("rn", "n")
      .replaceAll("ln", "n")
      .replaceAll("gn", "n")
      .replaceAll("sn", "n")
      .replaceAll("ph", "f")
      .replaceAll("fr", "f")
      .replaceAll("fl", "f")
      .replaceAll("rl", "l")
      .replaceAll("sl", "l")
      .replaceAll("rs", "s")
      .replaceAll("ts", "s")
      .replaceAll("[xzc]", "s")
      .replaceAll("[aeiou]","")
      .replaceAll("^h","")
      .replaceAll(" ","")
  }
}

mssql-function-foneticalize.sql

create function dbo.foneticalize(@word varchar(255))
    returns varchar(255) as
BEGIN
    DECLARE @i             int
    DECLARE @foneticalized varchar(255)
    DECLARE @letter        char(1)
    DECLARE @specials      varchar(38)
    DECLARE @non_specials  varchar(38)

    set @i = 1
    set @foneticalized = ''
    set @letter = ''
    set @specials = 'ÁÀÃÂÉÈÊÍÌÎÓÒÔÕÚÙÛÜÇáàãâéèêíìîóòôõúùûüç'
    set @non_specials = 'AAAAEEEIIIOOOOUUUUSAAAAEEEIIIOOOOUUUUS'

    -- removing especial chars
    set @i = 1
    while @i <= len(@specials)
    begin
      set @word = replace(@word, substring(@specials, @i, 2), substring(@non_specials, @i / 2, 1))

      set @i = @i + 2
    end

    -- uppering word
    set @word = upper(@word)

    -- replace chars
    set @word = replace(@word, 'BL',  'B')
    set @word = replace(@word, 'BR',  'B')
    set @word = replace(@word, 'PH',  'F')
    set @word = replace(@word, 'GL',  'G')
    set @word = replace(@word, 'GR',  'G')
    set @word = replace(@word, 'MG',  'G')
    set @word = replace(@word, 'NG',  'G')
    set @word = replace(@word, 'RG',  'G')

    set @word = replace(@word, 'Y',   'I')

    set @word = replace(@word, 'GE',  'J')
    set @word = replace(@word, 'GI',  'J')
    set @word = replace(@word, 'RJ',  'J')
    set @word = replace(@word, 'MJ',  'J')

    set @word = replace(@word, 'CA',  'K')
    set @word = replace(@word, 'CO',  'K')
    set @word = replace(@word, 'CU',  'K')
    set @word = replace(@word, 'CK',  'K')
    set @word = replace(@word, 'Q',   'K')

    set @word = replace(@word, 'N',   'M')

    set @word = replace(@word, 'AO',  'M')
    set @word = replace(@word, 'AUM', 'M')
    set @word = replace(@word, 'GM',  'M')
    set @word = replace(@word, 'MD',  'M')
    set @word = replace(@word, 'OM',  'M')
    set @word = replace(@word, 'ON',  'M')

    set @word = replace(@word, 'PR',  'P')

    set @word = replace(@word, 'L',   'R')

    set @word = replace(@word, 'CE',  'S')
    set @word = replace(@word, 'CI',  'S')
    set @word = replace(@word, 'CH',  'S')
    set @word = replace(@word, 'CS',  'S')
    set @word = replace(@word, 'RS',  'S')
    set @word = replace(@word, 'TS',  'S')
    set @word = replace(@word, 'X',   'S')
    set @word = replace(@word, 'Z',   'S')

    set @word = replace(@word, 'TR',  'T')
    set @word = replace(@word, 'TL',  'T')

    set @word = replace(@word, 'CT',  'T')
    set @word = replace(@word, 'RT',  'T')
    set @word = replace(@word, 'ST',  'T')
    set @word = replace(@word, 'PT',  'T')
    set @word = replace(@word, 'RM', 'SM')
    set @word = replace(@word, 'A',    '')
    set @word = replace(@word, 'E',    '')
    set @word = replace(@word, 'I',    '')
    set @word = replace(@word, 'O',    '')
    set @word = replace(@word, 'U',    '')
    set @word = replace(@word, 'H',    '')

    -- replacing chars with regular expression: "\b[UW]" e "[MRS]\b"
    set @i = 1
    while @i <= len(@word)
    begin
      set @letter = substring(@word, @i, 1)

      if @letter = ' '
        set @foneticalized = @foneticalized + ' '
      else if (@i = 1 or substring(@word, @i-1, 1) = ' ') and (@letter = 'W' or @letter = 'U')
        set @foneticalized = @foneticalized + 'V'
      else if (@i = len(@word) or substring(@word, @i+1, 1) = ' ') and (@letter = 'M' or @letter = 'R' or @letter = 'S')
        set @foneticalized = @foneticalized + ''
      else
        set @foneticalized = @foneticalized + @letter

      set @i = @i + 1
    end

    -- removing repeated letters
    set @i = 1;
    set @word = @foneticalized;
    set @foneticalized = '';
    while @i <= len(@word)
    begin
      set @letter = substring(@word, @i, 1)

      if @letter = ' '
        set @foneticalized = @foneticalized + ' '
      else if @i > 1 and @letter <> substring(@word, @i-1, 1)
        set @foneticalized = @foneticalized + @letter
      else if @i = 1
        set @foneticalized = @foneticalized + @letter

      set @i = @i + 1
    end

    return @foneticalized
END

mysql-function-foneticalize.sql

DROP FUNCTION IF EXISTS foneticalize;

DELIMITER //

CREATE FUNCTION foneticalize(word VARCHAR(255) charset utf8)
  RETURNS VARCHAR(255)
  DETERMINISTIC
  BEGIN
    DECLARE i             int          default 1;
    DECLARE foneticalized varchar(255) default '';
    DECLARE letter        char(1)      default '';
    DECLARE specials      varchar(76) default 'ÁÀÃÂÉÈÊÍÌÎÓÒÔÕÚÙÛÜÇáàãâéèêíìîóòôõúùûüç';
    DECLARE non_specials  varchar(38) default 'AAAAEEEIIIOOOOUUUUSAAAAEEEIIIOOOOUUUUS';
    
    -- removing especial chars
    set i = 1;
    while i <= length(specials) do
      set word = replace(word, substring(specials, i, 2), substring(non_specials, i / 2, 1));
      
      set i = i + 2;
    end while;

    -- uppering word
    set word = upper(word);

    -- replace chars
    set word = replace(word, 'BL',  'B');
    set word = replace(word, 'BR',  'B');
    set word = replace(word, 'PH',  'F');
    set word = replace(word, 'GL',  'G');
    set word = replace(word, 'GR',  'G');
    set word = replace(word, 'MG',  'G');
    set word = replace(word, 'NG',  'G');
    set word = replace(word, 'RG',  'G');

    set word = replace(word, 'Y',   'I');

    set word = replace(word, 'GE',  'J');
    set word = replace(word, 'GI',  'J');
    set word = replace(word, 'RJ',  'J');
    set word = replace(word, 'MJ',  'J');

    set word = replace(word, 'CA',  'K');
    set word = replace(word, 'CO',  'K');
    set word = replace(word, 'CU',  'K');
    set word = replace(word, 'CK',  'K');
    set word = replace(word, 'Q',   'K');

    set word = replace(word, 'N',   'M');

    set word = replace(word, 'AO',  'M');
    set word = replace(word, 'AUM', 'M');
    set word = replace(word, 'GM',  'M');
    set word = replace(word, 'MD',  'M');
    set word = replace(word, 'OM',  'M');
    set word = replace(word, 'ON',  'M');

    set word = replace(word, 'PR',  'P');

    set word = replace(word, 'L',   'R');

    set word = replace(word, 'CE',  'S');
    set word = replace(word, 'CI',  'S');
    set word = replace(word, 'CH',  'S');
    set word = replace(word, 'CS',  'S');
    set word = replace(word, 'RS',  'S');
    set word = replace(word, 'TS',  'S');
    set word = replace(word, 'X',   'S');
    set word = replace(word, 'Z',   'S');

    set word = replace(word, 'TR',  'T');
    set word = replace(word, 'TL',  'T');

    set word = replace(word, 'CT',  'T');
    set word = replace(word, 'RT',  'T');
    set word = replace(word, 'ST',  'T');
    set word = replace(word, 'PT',  'T');
    set word = replace(word, 'RM', 'SM');
    set word = replace(word, 'A',    '');
    set word = replace(word, 'E',    '');
    set word = replace(word, 'I',    '');
    set word = replace(word, 'O',    '');
    set word = replace(word, 'U',    '');
    set word = replace(word, 'H',    '');

    -- replacing chars with regular expression: "\b[UW]" e "[MRS]\b"
    set i = 1;
    while i <= length(word) do
      set letter = substring(word, i, 1);

      if letter = ' ' then
        set foneticalized = concat(foneticalized, ' ');
      elseif (i = 1 or substring(word, i-1, 1) = " ") and (letter = 'W' or letter = 'U') then
        set foneticalized = concat(foneticalized, 'V');
      elseif (i = length(word) or substring(word, i+1, 1) = " ") and (letter = 'M' or letter = 'R' or letter = 'S') then
        set foneticalized = concat(foneticalized, '');
      else
        set foneticalized = concat(foneticalized, letter);
      end if;

      set i = i + 1;
    end while;

    -- removing repeated letters
    set i = 1;
    set word = foneticalized;
    set foneticalized = '';
    while i <= length(word) do
      set letter = substring(word, i, 1);

      if letter = ' ' then
        set foneticalized = concat(foneticalized, ' ');
      elseif i > 1 and letter <> substring(word, i-1, 1) then
        set foneticalized = concat(foneticalized, letter);
      elseif i = 1 then
        set foneticalized = concat(foneticalized, letter);
      end if;

      set i = i + 1;
    end while;

    RETURN foneticalized;
  END
//

DELIMITER ;

oracle-function-foneticalize.sql

CREATE OR REPLACE FUNCTION foneticalize(v_word IN VARCHAR2)
    RETURN VARCHAR AS
    i INTEGER;
    foneticalized VARCHAR2(255);
    letter CHAR;
    specials VARCHAR2(38);
    non_specials VARCHAR2(38);
    word VARCHAR2(255);
BEGIN
    -- Converting letter to uppercase
    word := UPPER(v_word);

    i := 1;
    foneticalized := '';
    letter := '';
    specials := 'ÁÀÃÂÉÈÊÍÌÎÓÒÔÕÚÙÛÜÇ';
    non_specials := 'AAAAEEEIIIOOOOUUUUS';

    -- Removing especial chars
    WHILE i < LENGTH(specials) LOOP
      word := REPLACE(word, SUBSTR(specials, i, 1), SUBSTR(non_specials, i, 1));
		
      i := i + 1;
    END LOOP;

    -- Replace chars
    word := REPLACE(word, 'Y',   'I');
    
    word := REPLACE(word, 'BL',  'B');
    word := REPLACE(word, 'BR',  'B');
    
    word := REPLACE(word, 'PH',  'F');
    
    word := REPLACE(word, 'GL',  'G');
    word := REPLACE(word, 'GR',  'G');
    word := REPLACE(word, 'MG',  'G');
    word := REPLACE(word, 'NG',  'G');
    word := REPLACE(word, 'RG',  'G');
	
    word := REPLACE(word, 'GE',  'J');
    word := REPLACE(word, 'GI',  'J');
    word := REPLACE(word, 'RJ',  'J');
    word := REPLACE(word, 'MJ',  'J');
    word := REPLACE(word, 'NJ',  'J');
	
    word := REPLACE(word, 'Q',   'K');
    word := REPLACE(word, 'C',  'K');
    word := REPLACE(word, 'CA',  'K');
    word := REPLACE(word, 'CO',  'K');
    word := REPLACE(word, 'CU',  'K');
    
    word := REPLACE(word, 'LH',  'L');
	
    word := REPLACE(word, 'N',   'M');
    word := REPLACE(word, 'RM',   'M');
    word := REPLACE(word, 'GM',  'M');
    word := REPLACE(word, 'MD',  'M');
    word := REPLACE(word, 'SM',  'M');
 
    word := REPLACE(word, 'NH',  'N');
    
    word := REPLACE(word, 'PR',  'P');
    
    word := REPLACE(word, 'Ç',  'S');
    word := REPLACE(word, 'X',  'S');
    word := REPLACE(word, 'TS',  'S');
    word := REPLACE(word, 'C',  'S');
    word := REPLACE(word, 'Z',  'S');
    word := REPLACE(word, 'RS',  'S');
    
    word := REPLACE(word, 'LT',  'T');
    word := REPLACE(word, 'TR',  'T');
    word := REPLACE(word, 'CT',  'T');
    word := REPLACE(word, 'RT',  'T');
    word := REPLACE(word, 'ST',  'T');
    
    word := REPLACE(word, 'W',  'V');

    -- Remove ending chars
    i := LENGTH(word) - 1;
    
    letter := SUBSTR(word, i, 1);
    
    IF (letter = 'S' OR letter = 'Z' OR letter = 'R' OR letter = 'M' OR letter = 'N' OR letter = 'L') THEN
      word := substr(word, 0, i);
    ELSIF substr(word, (i - 1), 2) = 'AO' THEN
      word := substr(word, 0, (i - 1));
    END IF;
    
    word := REPLACE(word, 'R',  'L');
    
    word := REPLACE(word, 'A',  '');
    word := REPLACE(word, 'E',  '');
    word := REPLACE(word, 'I',  '');
    word := REPLACE(word, 'O',  '');
    word := REPLACE(word, 'U',  '');
    word := REPLACE(word, 'H',  '');
    
    -- Removing repeated letters
    i := 1;
	
    WHILE i < LENGTH(word) LOOP
      letter := SUBSTR(word, i, 1);

      IF letter = ' ' THEN
        foneticalized := foneticalized || ' ';
      ELSIF i > 1 AND letter <> SUBSTR(word, i - 1, 1) THEN
        foneticalized := foneticalized || letter;
      ELSIF i = 1 THEN
        foneticalized := foneticalized || letter;
      END IF;

      i := i + 1;
    END LOOP;

    RETURN foneticalized;
    
    EXCEPTION
      WHEN OTHERS THEN
        RETURN '';
END;

pgsql-function-foneticalize.sql

CREATE OR REPLACE FUNCTION foneticalize(word VARCHAR(255))
  RETURNS VARCHAR(255) AS $$
  DECLARE 
    i             int          default 1;
    foneticalized varchar(255) default '';
    letter        char(1)      default '';
    specials      varchar(76) default 'ÁÀÃÂÉÈÊÍÌÎÓÒÔÕÚÙÛÜÇáàãâéèêíìîóòôõúùûüç';
    non_specials  varchar(38) default 'AAAAEEEIIIOOOOUUUUSAAAAEEEIIIOOOOUUUUS';
  BEGIN
    -- removing especial chars
    word := translate(word, specials, non_specials);

    -- uppering word
    word := upper(word);
    
    -- replace chars
    word := regexp_replace(word, e'BL|BR', 'B', 'g');
    word := replace(word, 'PH', 'F');
    word := regexp_replace(word, e'GL|GR|MG|NG|RG', 'G', 'g');
    word := replace(word, 'Y', 'I');
    word := regexp_replace(word, e'GE|GI|RJ|MJ', 'J', 'g');
    word := regexp_replace(word, e'CA|CO|CU|CK|Q', 'K', 'g');
    word := replace(word, 'N', 'M');
    word := regexp_replace(word, e'AO|AUM|GM|MD|OM|ON', 'M', 'g');
    word := replace(word, 'PR', 'P');
    word := replace(word, 'L', 'R');
    word := regexp_replace(word, e'CE|CI|CH|CS|RS|TS|X|Z', 'S', 'g');
    word := regexp_replace(word, e'TR|TL', 'T', 'g');
    word := regexp_replace(word, e'CT|RT|ST|PT', 'T', 'g');
    word := regexp_replace(word, e'\\y[UW]', 'V', 'g');
    word := replace(word, 'RM', 'SM');
    word := regexp_replace(word, e'[MRS]\\y', '', 'g');
    word := regexp_replace(word, e'[AEIOU]', '', 'g');

    -- removing repeated letters
    i := 1;
    while i <= length(word) loop
      letter := substring(word, i, 1);

      if letter = ' ' then
        foneticalized := concat(foneticalized, ' ');
      elseif i > 1 and letter <> substring(word, i-1, 1) then
        foneticalized := concat(foneticalized, letter);
      elseif i = 1 then
        foneticalized := concat(foneticalized, letter);
      end if;

      i := i + 1;
    end loop;

    RETURN foneticalized;
  END;
$$ LANGUAGE plpgsql;