Add GIN support for pg_trgm. From Guillaume Smet <guillaume.smet@gmail.com>

with minor editorization by me.

contrib/pg_trgm/Makefile

-# $PostgreSQL: pgsql/contrib/pg_trgm/Makefile,v 1.6 2007/02/09 17:24:33 petere Exp $
+# $PostgreSQL: pgsql/contrib/pg_trgm/Makefile,v 1.7 2007/03/14 14:15:40 teodor Exp $
 
 MODULE_big = pg_trgm
-OBJS = trgm_op.o trgm_gist.o 
+OBJS = trgm_op.o trgm_gist.o trgm_gin.o
 
 DATA_built = pg_trgm.sql
 DATA = uninstall_pg_trgm.sql

contrib/pg_trgm/README.pg_trgm

@@ -113,6 +113,8 @@ Tsearch2 Integration
 	Next, create a trigram index on the word column:
 
 	CREATE INDEX words_idx ON words USING gist(word gist_trgm_ops);
+	or
+	CREATE INDEX words_idx ON words USING gin(word gist_trgm_ops);
 
 	Now, a SELECT query similar to the example above can be used to
 	suggest spellings for misspelled words in user search terms. A

contrib/pg_trgm/pg_trgm.sql.in

@@ -36,7 +36,7 @@ CREATE OPERATOR % (
         JOIN = contjoinsel
 );
 
---gist key
+-- gist key
 CREATE FUNCTION gtrgm_in(cstring)
 RETURNS gtrgm
 AS 'MODULE_PATHNAME'
@@ -53,7 +53,7 @@ CREATE TYPE gtrgm (
         OUTPUT = gtrgm_out
 );
 
--- support functions
+-- support functions for gist
 CREATE FUNCTION gtrgm_consistent(gtrgm,internal,int4)
 RETURNS bool
 AS 'MODULE_PATHNAME'
@@ -89,7 +89,7 @@ RETURNS internal
 AS 'MODULE_PATHNAME'
 LANGUAGE C;
 
--- create the operator class
+-- create the operator class for gist
 CREATE OPERATOR CLASS gist_trgm_ops
 FOR TYPE text USING gist
 AS
@@ -103,5 +103,31 @@ AS
         FUNCTION        7       gtrgm_same (gtrgm, gtrgm, internal),
         STORAGE         gtrgm;
 
+-- support functions for gin
+CREATE FUNCTION gin_extract_trgm(text, internal)
+RETURNS internal
+AS 'MODULE_PATHNAME'
+LANGUAGE C;
+
+CREATE FUNCTION gin_extract_trgm(text, internal, internal)
+RETURNS internal
+AS 'MODULE_PATHNAME'
+LANGUAGE C;
+
+CREATE FUNCTION gin_trgm_consistent(internal, internal, text)
+RETURNS internal
+AS 'MODULE_PATHNAME'
+LANGUAGE C;
+
+-- create the operator class for gin
+CREATE OPERATOR CLASS gin_trgm_ops
+FOR TYPE text USING gin
+AS
+        OPERATOR        1       % (text, text) RECHECK,
+        FUNCTION        1       btint4cmp (int4, int4),
+        FUNCTION        2       gin_extract_trgm (text, internal),
+        FUNCTION        3       gin_extract_trgm (text, internal, internal),
+        FUNCTION        4       gin_trgm_consistent (internal, internal, text),
+        STORAGE         int4;
 
 COMMIT;

contrib/pg_trgm/sql/pg_trgm.sql

@@ -28,3 +28,11 @@ select t,similarity(t,'qwertyu0988') as sml from test_trgm where t % 'qwertyu098
 select t,similarity(t,'gwertyu0988') as sml from test_trgm where t % 'gwertyu0988' order by sml desc, t;
 select t,similarity(t,'gwertyu1988') as sml from test_trgm where t % 'gwertyu1988' order by sml desc, t;
 
+drop index trgm_idx;
+create index trgm_idx on test_trgm using gin (t gin_trgm_ops);
+set enable_seqscan=off;
+
+select t,similarity(t,'qwertyu0988') as sml from test_trgm where t % 'qwertyu0988' order by sml desc, t;
+select t,similarity(t,'gwertyu0988') as sml from test_trgm where t % 'gwertyu0988' order by sml desc, t;
+select t,similarity(t,'gwertyu1988') as sml from test_trgm where t % 'gwertyu1988' order by sml desc, t;
+

contrib/pg_trgm/trgm.h

@@ -28,6 +28,7 @@ typedef char trgm[3];
 	*(((char*)(a))+2) = *(((char*)(b))+2);	\
 } while(0);
 
+#define TRGMINT(a) ( (*(((char*)(a))+2)<<16)+(*(((char*)(a))+1)<<8)+*(((char*)(a))+0) )
 
 typedef struct
 {

contrib/pg_trgm/trgm_gin.c

+#include "trgm.h"
+
+#include "access/gin.h"
+#include "access/itup.h"
+#include "access/tuptoaster.h"
+#include "storage/bufpage.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+
+PG_FUNCTION_INFO_V1(gin_extract_trgm);
+Datum		gin_extract_trgm(PG_FUNCTION_ARGS);
+
+PG_FUNCTION_INFO_V1(gin_trgm_consistent);
+Datum		gin_trgm_consistent(PG_FUNCTION_ARGS);
+
+Datum
+gin_extract_trgm(PG_FUNCTION_ARGS)
+{
+	text		*val = (text *) PG_GETARG_TEXT_P(0);
+	int32		*nentries = (int32 *) PG_GETARG_POINTER(1);
+	Datum		*entries = NULL;
+	TRGM		*trg;
+	int4		trglen;
+	
+	*nentries = 0;
+	
+	trg = generate_trgm(VARDATA(val), VARSIZE(val) - VARHDRSZ);
+	trglen = ARRNELEM(trg);
+	
+	if (trglen > 0)
+	{
+		trgm	*ptr;
+		int4	i = 0,
+				item;
+		
+		*nentries = (int32) trglen;
+		entries = (Datum *) palloc(sizeof(Datum) * trglen);
+
+		ptr = GETARR(trg);
+		while (ptr - GETARR(trg) < ARRNELEM(trg))
+		{
+			item = TRGMINT(ptr);
+			entries[i++] = Int32GetDatum(item);
+			
+			ptr++;
+		}
+	}
+
+	PG_RETURN_POINTER(entries);
+}
+
+Datum
+gin_trgm_consistent(PG_FUNCTION_ARGS)
+{
+	bool		*check = (bool *) PG_GETARG_POINTER(0);
+	text		*query = (text *) PG_GETARG_TEXT_P(2);
+	bool		res = FALSE;
+	TRGM		*trg;
+	int4		i,
+				trglen,
+				ntrue = 0;
+	
+	trg = generate_trgm(VARDATA(query), VARSIZE(query) - VARHDRSZ);
+	trglen = ARRNELEM(trg);
+	
+	for (i = 0; i < trglen; i++)
+		if (check[i])
+			ntrue ++;
+
+#ifdef DIVUNION
+	res = (trglen == ntrue) ? true : ((((((float4) ntrue) / ((float4) (trglen - ntrue)))) >= trgm_limit) ? true : false);
+#else
+	res = (trglen == 0) ? false : ((((((float4) ntrue) / ((float4) trglen))) >= trgm_limit) ? true : false);
+#endif
+
+	PG_RETURN_BOOL(res);
+}

contrib/pg_trgm/uninstall_pg_trgm.sql

@@ -20,6 +20,14 @@ DROP FUNCTION gtrgm_consistent(gtrgm,internal,int4);
 
 DROP TYPE gtrgm CASCADE;
 
+DROP OPERATOR CLASS gin_trgm_ops USING gin;
+
+DROP FUNCTION gin_extract_trgm(text, internal);
+
+DROP FUNCTION gin_extract_trgm(text, internal, internal);
+
+DROP FUNCTION gin_trgm_consistent(internal, internal, text);
+
 DROP OPERATOR % (text, text);
 
 DROP FUNCTION similarity_op(text,text);