NOTE: Modified August 07, 2001 by Joe Conway. Updated for accuracy
after combining soundex code into the fuzzystrmatch contrib
---------------------------------------------------------------------
The Soundex system is a method of matching similar sounding names
(or any words) to the same code. It was initially used by the
United States Census in 1880, 1900, and 1910, but it has little use
beyond English names (or the English pronunciation of names), and
it is not a linguistic tool.
When comparing two soundex values to determine similarity, the
difference function reports how close the match is on a scale
from zero to four, with zero being no match and four being an
exact match.
The following are some usage examples:
SELECT soundex('hello world!');
SELECT soundex('Anne'), soundex('Ann'), difference('Anne', 'Ann');
SELECT soundex('Anne'), soundex('Andrew'), difference('Anne', 'Andrew');
SELECT soundex('Anne'), soundex('Margaret'), difference('Anne', 'Margaret');
CREATE TABLE s (nm text);
INSERT INTO s VALUES ('john');
INSERT INTO s VALUES ('joan');
INSERT INTO s VALUES ('wobbly');
INSERT INTO s VALUES ('jack');
SELECT * FROM s WHERE soundex(nm) = soundex('john');
SELECT a.nm, b.nm FROM s a, s b WHERE soundex(a.nm) = soundex(b.nm) AND a.oid <> b.oid;
CREATE FUNCTION text_sx_eq(text, text) RETURNS boolean AS
'select soundex($1) = soundex($2)'
LANGUAGE SQL;
CREATE FUNCTION text_sx_lt(text, text) RETURNS boolean AS
'select soundex($1) < soundex($2)'
LANGUAGE SQL;
CREATE FUNCTION text_sx_gt(text, text) RETURNS boolean AS
'select soundex($1) > soundex($2)'
LANGUAGE SQL;
CREATE FUNCTION text_sx_le(text, text) RETURNS boolean AS
'select soundex($1) <= soundex($2)'
LANGUAGE SQL;
CREATE FUNCTION text_sx_ge(text, text) RETURNS boolean AS
'select soundex($1) >= soundex($2)'
LANGUAGE SQL;
CREATE FUNCTION text_sx_ne(text, text) RETURNS boolean AS
'select soundex($1) <> soundex($2)'
LANGUAGE SQL;
DROP OPERATOR #= (text, text);
CREATE OPERATOR #= (leftarg=text, rightarg=text, procedure=text_sx_eq, commutator = #=);
SELECT * FROM s WHERE text_sx_eq(nm, 'john');
SELECT * FROM s WHERE s.nm #= 'john';
SELECT * FROM s WHERE difference(s.nm, 'john') > 2;
