postgresql

mirror of https://git.postgresql.org/git/postgresql.git synced 2024-12-09 08:10:09 +08:00

History

Tom Lane 234a02b2a8 Replace direct assignments to VARATT_SIZEP(x) with SET_VARSIZE(x, len). Get rid of VARATT_SIZE and VARATT_DATA, which were simply redundant with VARSIZE and VARDATA, and as a consequence almost no code was using the longer names. Rename the length fields of struct varlena and various derived structures to catch anyplace that was accessing them directly; and clean up various places so caught. In itself this patch doesn't change any behavior at all, but it is necessary infrastructure if we hope to play any games with the representation of varlena headers. Greg Stark and Tom Lane		2007-02-27 23:48:10 +00:00
..
dmetaphone.c	Replace direct assignments to VARATT_SIZEP(x) with SET_VARSIZE(x, len).	2007-02-27 23:48:10 +00:00
fuzzystrmatch.c	Update /contrib/fuzzystrmatch error message to mention bytes, not just	2007-02-13 18:00:35 +00:00
fuzzystrmatch.h	Update CVS HEAD for 2007 copyright. Back branches are typically not	2007-01-05 22:20:05 +00:00
fuzzystrmatch.sql.in	The attached patch implements the soundex difference function which	2005-01-26 08:04:04 +00:00
Makefile	Simplify contrib Makefiles by removing unnecessary SRCS macro,	2006-10-19 17:40:03 +00:00
README.fuzzystrmatch	Update CVS HEAD for 2007 copyright. Back branches are typically not	2007-01-05 22:20:05 +00:00
README.soundex	Clean up CREATE FUNCTION syntax usage in contrib and elsewhere, in	2006-02-27 16:09:50 +00:00
uninstall_fuzzystrmatch.sql	contrib uninstall scripts	2006-02-27 12:54:39 +00:00

README.soundex

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;