Adjust the APIs for GIN opclass support functions to allow the extractQuery()

method to pass extra data to the consistent() and comparePartial() methods.
This is the core infrastructure needed to support the soon-to-appear
contrib/btree_gin module.  The APIs are still upward compatible with the
definitions used in 8.3 and before, although *not* with the previous 8.4devel
function definitions.

catversion bump for changes in pg_proc entries (although these are just
cosmetic, since GIN doesn't actually look at the function signature before
calling it...)

Teodor Sigaev and Oleg Bartunov

contrib/hstore/hstore.sql.in

-/* $PostgreSQL: pgsql/contrib/hstore/hstore.sql.in,v 1.9 2008/04/14 17:05:32 tgl Exp $ */
+/* $PostgreSQL: pgsql/contrib/hstore/hstore.sql.in,v 1.10 2009/03/25 22:19:01 tgl Exp $ */
 
 -- Adjust this setting to control where the objects get created.
 SET search_path = public;
@@ -244,12 +244,12 @@ RETURNS internal
 AS 'MODULE_PATHNAME'
 LANGUAGE C IMMUTABLE;
 
-CREATE OR REPLACE FUNCTION gin_extract_hstore_query(internal, internal, int2)
+CREATE OR REPLACE FUNCTION gin_extract_hstore_query(internal, internal, int2, internal, internal)
 RETURNS internal
 AS 'MODULE_PATHNAME'
 LANGUAGE C IMMUTABLE;
 
-CREATE OR REPLACE FUNCTION gin_consistent_hstore(internal, int2, internal, internal)
+CREATE OR REPLACE FUNCTION gin_consistent_hstore(internal, int2, internal, int4, internal, internal)
 RETURNS bool
 AS 'MODULE_PATHNAME'
 LANGUAGE C IMMUTABLE;
@@ -261,6 +261,6 @@ AS
 	OPERATOR        9       ?(hstore,text),
 	FUNCTION        1       bttextcmp(text,text),
 	FUNCTION        2       gin_extract_hstore(internal, internal),
-	FUNCTION        3       gin_extract_hstore_query(internal, internal, int2),
-	FUNCTION        4       gin_consistent_hstore(internal, int2, internal, internal),
+	FUNCTION        3       gin_extract_hstore_query(internal, internal, int2, internal, internal),
+	FUNCTION        4       gin_consistent_hstore(internal, int2, internal, int4, internal, internal),
 STORAGE         text;

contrib/hstore/hstore_gin.c

 /*
- * $PostgreSQL: pgsql/contrib/hstore/hstore_gin.c,v 1.4 2008/05/12 00:00:42 alvherre Exp $
+ * $PostgreSQL: pgsql/contrib/hstore/hstore_gin.c,v 1.5 2009/03/25 22:19:01 tgl Exp $
  */
 #include "postgres.h"
 
@@ -122,7 +122,9 @@ gin_consistent_hstore(PG_FUNCTION_ARGS)
 	bool	   *check = (bool *) PG_GETARG_POINTER(0);
 	StrategyNumber strategy = PG_GETARG_UINT16(1);
 	HStore	   *query = PG_GETARG_HS(2);
-	bool	   *recheck = (bool *) PG_GETARG_POINTER(3);
+	/* int32	nkeys = PG_GETARG_INT32(3); */
+	/* Pointer	   *extra_data = (Pointer *) PG_GETARG_POINTER(4); */
+	bool	   *recheck = (bool *) PG_GETARG_POINTER(5);
 	bool		res = true;
 
 	if (strategy == HStoreContainsStrategyNumber)

contrib/hstore/uninstall_hstore.sql

-/* $PostgreSQL: pgsql/contrib/hstore/uninstall_hstore.sql,v 1.7 2008/04/14 17:05:32 tgl Exp $ */
+/* $PostgreSQL: pgsql/contrib/hstore/uninstall_hstore.sql,v 1.8 2009/03/25 22:19:01 tgl Exp $ */
 
 -- Adjust this setting to control where the objects get dropped.
 SET search_path = public;
@@ -38,9 +38,9 @@ DROP FUNCTION ghstore_picksplit(internal, internal);
 DROP FUNCTION ghstore_union(internal, internal);
 DROP FUNCTION ghstore_same(internal, internal, internal);
 DROP FUNCTION ghstore_consistent(internal,internal,int,oid,internal);
-DROP FUNCTION gin_consistent_hstore(internal, int2, internal, internal);
+DROP FUNCTION gin_consistent_hstore(internal, int2, internal, int4, internal, internal);
 DROP FUNCTION gin_extract_hstore(internal, internal);
-DROP FUNCTION gin_extract_hstore_query(internal, internal, smallint);
+DROP FUNCTION gin_extract_hstore_query(internal, internal, smallint, internal, internal);
 
 DROP TYPE hstore CASCADE;
 DROP TYPE ghstore CASCADE;

contrib/intarray/_int.sql.in

-/* $PostgreSQL: pgsql/contrib/intarray/_int.sql.in,v 1.28 2008/04/14 17:05:32 tgl Exp $ */
+/* $PostgreSQL: pgsql/contrib/intarray/_int.sql.in,v 1.29 2009/03/25 22:19:01 tgl Exp $ */
 
 -- Adjust this setting to control where the objects get created.
 SET search_path = public;
@@ -458,13 +458,13 @@ AS
 
 --GIN
 
-CREATE OR REPLACE FUNCTION ginint4_queryextract(internal, internal, int2)
+CREATE OR REPLACE FUNCTION ginint4_queryextract(internal, internal, int2, internal, internal)
 RETURNS internal
 AS 'MODULE_PATHNAME'
 LANGUAGE C IMMUTABLE;
 
-CREATE OR REPLACE FUNCTION ginint4_consistent(internal, int2, internal, internal)
-RETURNS internal
+CREATE OR REPLACE FUNCTION ginint4_consistent(internal, int2, internal, int4, internal, internal)
+RETURNS bool
 AS 'MODULE_PATHNAME'
 LANGUAGE C IMMUTABLE;
 
@@ -480,6 +480,6 @@ AS
 	OPERATOR	20	@@ (_int4, query_int),
 	FUNCTION	1	btint4cmp (int4, int4),
 	FUNCTION	2	ginarrayextract (anyarray, internal),
-	FUNCTION	3	ginint4_queryextract (internal, internal, int2),
-	FUNCTION	4	ginint4_consistent (internal, int2, internal, internal),
+	FUNCTION	3	ginint4_queryextract (internal, internal, int2, internal, internal),
+	FUNCTION	4	ginint4_consistent (internal, int2, internal, int4, internal, internal),
 	STORAGE		int4;

contrib/intarray/_int_gin.c

 /*
- * $PostgreSQL: pgsql/contrib/intarray/_int_gin.c,v 1.8 2008/05/17 01:28:19 adunstan Exp $ 
+ * $PostgreSQL: pgsql/contrib/intarray/_int_gin.c,v 1.9 2009/03/25 22:19:01 tgl Exp $ 
  */
 #include "postgres.h"
 
@@ -90,7 +90,9 @@ ginint4_consistent(PG_FUNCTION_ARGS)
 {
 	bool	   *check = (bool *) PG_GETARG_POINTER(0);
 	StrategyNumber strategy = PG_GETARG_UINT16(1);
-	bool	   *recheck = (bool *) PG_GETARG_POINTER(3);
+	/* int32	nkeys = PG_GETARG_INT32(3); */
+	/* Pointer	   *extra_data = (Pointer *) PG_GETARG_POINTER(4); */
+	bool	   *recheck = (bool *) PG_GETARG_POINTER(5);
 	bool		res = FALSE;
 
 	/*

contrib/intarray/uninstall__int.sql

-/* $PostgreSQL: pgsql/contrib/intarray/uninstall__int.sql,v 1.9 2008/04/14 17:05:32 tgl Exp $ */
+/* $PostgreSQL: pgsql/contrib/intarray/uninstall__int.sql,v 1.10 2009/03/25 22:19:01 tgl Exp $ */
 
 -- Adjust this setting to control where the objects get created.
 SET search_path = public;
 
 DROP OPERATOR CLASS gin__int_ops USING gin;
 
-DROP FUNCTION ginint4_queryextract(internal, internal, int2);
+DROP FUNCTION ginint4_queryextract(internal, internal, int2, internal, internal);
 
-DROP FUNCTION ginint4_consistent(internal, int2, internal, internal);
+DROP FUNCTION ginint4_consistent(internal, int2, internal, int4, internal, internal);
 
 DROP OPERATOR CLASS gist__intbig_ops USING gist;
 

contrib/pg_trgm/pg_trgm.sql.in

-/* $PostgreSQL: pgsql/contrib/pg_trgm/pg_trgm.sql.in,v 1.8 2008/04/14 17:05:32 tgl Exp $ */
+/* $PostgreSQL: pgsql/contrib/pg_trgm/pg_trgm.sql.in,v 1.9 2009/03/25 22:19:01 tgl Exp $ */
 
 -- Adjust this setting to control where the objects get created.
 SET search_path = public;
@@ -110,13 +110,13 @@ RETURNS internal
 AS 'MODULE_PATHNAME'
 LANGUAGE C IMMUTABLE;
 
-CREATE OR REPLACE FUNCTION gin_extract_trgm(text, internal, internal)
+CREATE OR REPLACE FUNCTION gin_extract_trgm(text, internal, int2, internal, internal)
 RETURNS internal
 AS 'MODULE_PATHNAME'
 LANGUAGE C IMMUTABLE;
 
-CREATE OR REPLACE FUNCTION gin_trgm_consistent(internal, int2, text, internal)
-RETURNS internal
+CREATE OR REPLACE FUNCTION gin_trgm_consistent(internal, int2, text, int4, internal, internal)
+RETURNS bool
 AS 'MODULE_PATHNAME'
 LANGUAGE C IMMUTABLE;
 
@@ -127,6 +127,6 @@ AS
         OPERATOR        1       % (text, text),
         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, int2, text, internal),
+        FUNCTION        3       gin_extract_trgm (text, internal, int2, internal, internal),
+        FUNCTION        4       gin_trgm_consistent (internal, int2, text, int4, internal, internal),
         STORAGE         int4;

contrib/pg_trgm/trgm_gin.c

 /*
- * $PostgreSQL: pgsql/contrib/pg_trgm/trgm_gin.c,v 1.6 2008/11/12 13:43:54 teodor Exp $ 
+ * $PostgreSQL: pgsql/contrib/pg_trgm/trgm_gin.c,v 1.7 2009/03/25 22:19:01 tgl Exp $ 
  */
 #include "trgm.h"
 
@@ -47,53 +47,40 @@ gin_extract_trgm(PG_FUNCTION_ARGS)
 
 			ptr++;
 		}
+		if (PG_NARGS() > 4)
+		{
+			/*
+			 * Function called from query extracting
+			 */
+			Pointer      **extra_data = (Pointer **) PG_GETARG_POINTER(4);
+
+			*extra_data = (Pointer*) palloc0(sizeof(Pointer)*(*nentries));
+
+			*(int32*)(*extra_data) = trglen;
+		}
 	}
 
 	PG_RETURN_POINTER(entries);
 }
 
-/*
- * Per call strage for consistent functions to
- * cache computed value from query
- */
-typedef struct PerCallConsistentStorage {
-	int		trglen;
-	text	data[1]; /* query */
-} PerCallConsistentStorage;
-#define PCCSHDR_SZ  offsetof(PerCallConsistentStorage, data)
-
 Datum
 gin_trgm_consistent(PG_FUNCTION_ARGS)
 {
 	bool	   *check = (bool *) PG_GETARG_POINTER(0);
 	/* StrategyNumber strategy = PG_GETARG_UINT16(1); */
-	text	   *query = PG_GETARG_TEXT_P(2);
-	bool	   *recheck = (bool *) PG_GETARG_POINTER(3);
+	/* text	   *query = PG_GETARG_TEXT_P(2); */
+	/* int32	nkeys = PG_GETARG_INT32(3); */
+	Pointer    *extra_data = (Pointer *) PG_GETARG_POINTER(4);
+	bool	   *recheck = (bool *) PG_GETARG_POINTER(5);
 	bool		res = FALSE;
 	int4		i,
 				trglen,
 				ntrue = 0;
-	PerCallConsistentStorage  *pccs = (PerCallConsistentStorage*) fcinfo->flinfo->fn_extra;
 
 	/* All cases served by this function are inexact */
 	*recheck = true;
 
-	if ( pccs == NULL || VARSIZE(pccs->data) != VARSIZE(query) || memcmp( pccs->data, query, VARSIZE(query) ) !=0  )
-	{
-		TRGM	   *trg = generate_trgm(VARDATA(query), VARSIZE(query) - VARHDRSZ);
-
-		if ( pccs )
-			pfree(pccs);
-
-		fcinfo->flinfo->fn_extra = MemoryContextAlloc(fcinfo->flinfo->fn_mcxt, 
-									VARSIZE(query) + PCCSHDR_SZ);
-		pccs = (PerCallConsistentStorage*) fcinfo->flinfo->fn_extra;
-
-		pccs->trglen = ARRNELEM(trg);
-		memcpy( pccs->data, query, VARSIZE(query) );
-	}
-
-	trglen = pccs->trglen;
+	trglen = *(int32*)extra_data;
 
 	for (i = 0; i < trglen; i++)
 		if (check[i])

contrib/pg_trgm/uninstall_pg_trgm.sql

-/* $PostgreSQL: pgsql/contrib/pg_trgm/uninstall_pg_trgm.sql,v 1.6 2008/04/14 17:05:32 tgl Exp $ */
+/* $PostgreSQL: pgsql/contrib/pg_trgm/uninstall_pg_trgm.sql,v 1.7 2009/03/25 22:19:01 tgl Exp $ */
 
 -- Adjust this setting to control where the objects get dropped.
 SET search_path = public;
@@ -25,9 +25,9 @@ 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_extract_trgm(text, internal, int2, internal, internal);
 
-DROP FUNCTION gin_trgm_consistent(internal, int2, text, internal);
+DROP FUNCTION gin_trgm_consistent(internal, int2, text, int4, internal, internal);
 
 DROP OPERATOR % (text, text);
 

contrib/tsearch2/tsearch2.sql.in

-/* $PostgreSQL: pgsql/contrib/tsearch2/tsearch2.sql.in,v 1.6 2008/05/16 17:26:07 tgl Exp $ */
+/* $PostgreSQL: pgsql/contrib/tsearch2/tsearch2.sql.in,v 1.7 2009/03/25 22:19:01 tgl Exp $ */
 
 -- Adjust this setting to control where the objects get created.
 SET search_path = public;
@@ -552,8 +552,9 @@ AS
         OPERATOR        2       @@@ (tsvector, tsquery),
         FUNCTION        1       bttextcmp(text, text),
         FUNCTION        2       gin_extract_tsvector(tsvector,internal),
-        FUNCTION        3       gin_extract_tsquery(tsquery,internal,smallint,internal),
-        FUNCTION        4       gin_tsquery_consistent(internal,smallint,tsquery,internal),
+        FUNCTION        3       gin_extract_tsquery(tsquery,internal,smallint,internal,internal),
+        FUNCTION        4       gin_tsquery_consistent(internal,smallint,tsquery,int,internal,internal),
+        FUNCTION        5       gin_cmp_prefix(text,text,smallint,internal),
         STORAGE         text;
 
 CREATE OPERATOR CLASS tsvector_ops

doc/src/sgml/gin.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/gin.sgml,v 2.17 2009/03/24 20:17:07 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/gin.sgml,v 2.18 2009/03/25 22:19:01 tgl Exp $ -->
 
 <chapter id="GIN">
 <title>GIN Indexes</title>
@@ -88,7 +88,7 @@
 
     <varlistentry>
      <term>Datum *extractQuery(Datum query, int32 *nkeys,
-        StrategyNumber n, bool **pmatch)</term>
+        StrategyNumber n, bool **pmatch, Pointer **extra_data)</term>
      <listitem>
       <para>
        Returns an array of keys given a value to be queried; that is,
@@ -104,7 +104,7 @@
        should store 0 or -1 into <literal>*nkeys</>, depending on the
        semantics of the operator.  0 means that every
        value matches the <literal>query</> and a sequential scan should be
-       produced.  -1 means nothing can match the <literal>query</>.
+       performed.  -1 means nothing can match the <literal>query</>.
        <literal>pmatch</> is an output argument for use when partial match
        is supported.  To use it, <function>extractQuery</> must allocate
        an array of <literal>*nkeys</> booleans and store its address at
@@ -114,25 +114,40 @@
        is not required.  The variable is initialized to NULL before call,
        so this argument can simply be ignored by operator classes that do
        not support partial match.
+       <literal>extra_data</> is an output argument that allows
+       <function>extractQuery</> to pass additional data to the
+       <function>consistent</> and <function>comparePartial</> methods.
+       To use it, <function>extractQuery</> must allocate
+       an array of <literal>*nkeys</> Pointers and store its address at
+       <literal>*extra_data</>, then store whatever it wants to into the
+       individual pointers.  The variable is initialized to NULL before
+       call, so this argument can simply be ignored by operator classes that
+       do not require extra data.  If <literal>*extra_data</> is set, the
+       whole array is passed to the <function>consistent</> method, and
+       the appropriate element to the <function>comparePartial</> method.
       </para>
 
      </listitem>
     </varlistentry>
 
     <varlistentry>
-     <term>bool consistent(bool check[], StrategyNumber n, Datum query, bool *recheck)</term>
+     <term>bool consistent(bool check[], StrategyNumber n, Datum query,
+                           int32 nkeys, Pointer extra_data[], bool *recheck)</term>
      <listitem>
       <para>
        Returns TRUE if the indexed value satisfies the query operator with
        strategy number <literal>n</> (or might satisfy, if the recheck
-       indication is returned).  The <literal>check</> array has
-       the same length as the number of keys previously returned by
-       <function>extractQuery</> for this query.  Each element of the
+       indication is returned).  The <literal>check</> array has length
+       <literal>nkeys</>, which is the same as the number of keys previously
+       returned by <function>extractQuery</> for this <literal>query</> datum.
+       Each element of the
        <literal>check</> array is TRUE if the indexed value contains the
        corresponding query key, ie, if (check[i] == TRUE) the i-th key of the
        <function>extractQuery</> result array is present in the indexed value.
        The original <literal>query</> datum (not the extracted key array!) is
        passed in case the <function>consistent</> method needs to consult it.
+       <literal>extra_data</> is the extra-data array returned by
+       <function>extractQuery</>, or NULL if none.
        On success, <literal>*recheck</> should be set to TRUE if the heap
        tuple needs to be rechecked against the query operator, or FALSE if
        the index test is exact.
@@ -150,7 +165,8 @@
   <variablelist>
 
     <varlistentry>
-     <term>int comparePartial(Datum partial_key, Datum key, StrategyNumber n)</term>
+     <term>int comparePartial(Datum partial_key, Datum key, StrategyNumber n,
+                              Pointer extra_data)</term>
      <listitem>
       <para>
        Compare a partial-match query to an index key.  Returns an integer
@@ -160,7 +176,9 @@
        indicates that the index scan should stop because no more matches
        are possible.  The strategy number <literal>n</> of the operator
        that generated the partial match query is provided, in case its
-       semantics are needed to determine when to end the scan.
+       semantics are needed to determine when to end the scan.  Also,
+       <literal>extra_data</> is the corresponding element of the extra-data
+       array made by <function>extractQuery</>, or NULL if none.
       </para>
      </listitem>
     </varlistentry>
@@ -383,6 +401,13 @@
  </para>
 
  <variablelist>
+  <varlistentry>
+   <term>btree-gin</term>
+   <listitem>
+    <para>B-Tree equivalent functionality for several data types</para>
+   </listitem>
+  </varlistentry>
+
   <varlistentry>
    <term>hstore</term>
    <listitem>

src/backend/access/gin/ginarrayproc.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/gin/ginarrayproc.c,v 1.14 2009/01/01 17:23:34 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/gin/ginarrayproc.c,v 1.15 2009/03/25 22:19:01 tgl Exp $
  *-------------------------------------------------------------------------
  */
 #include "postgres.h"
@@ -95,7 +95,9 @@ ginarrayconsistent(PG_FUNCTION_ARGS)
 	bool	   *check = (bool *) PG_GETARG_POINTER(0);
 	StrategyNumber strategy = PG_GETARG_UINT16(1);
 	ArrayType  *query = PG_GETARG_ARRAYTYPE_P(2);
-	bool	   *recheck = (bool *) PG_GETARG_POINTER(3);
+	/* int32	nkeys = PG_GETARG_INT32(3); */
+	/* Pointer	   *extra_data = (Pointer *) PG_GETARG_POINTER(4); */
+	bool	   *recheck = (bool *) PG_GETARG_POINTER(5);
 	bool		res;
 	int			i,
 				nentries;

src/backend/access/gin/ginget.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *			$PostgreSQL: pgsql/src/backend/access/gin/ginget.c,v 1.23 2009/03/24 20:17:10 tgl Exp $
+ *			$PostgreSQL: pgsql/src/backend/access/gin/ginget.c,v 1.24 2009/03/25 22:19:01 tgl Exp $
  *-------------------------------------------------------------------------
  */
 
@@ -178,10 +178,11 @@ computePartialMatchList( GinBtreeData *btree, GinBtreeStack *stack, GinScanEntry
 		 * case cmp < 0 => not match and continue scan
 		 *----------
 		 */
-    	cmp = DatumGetInt32(FunctionCall3(&btree->ginstate->comparePartialFn[scanEntry->attnum-1],
+    	cmp = DatumGetInt32(FunctionCall4(&btree->ginstate->comparePartialFn[scanEntry->attnum-1],
 										  scanEntry->entry,
 										  idatum,
-										  UInt16GetDatum(scanEntry->strategy)));
+										  UInt16GetDatum(scanEntry->strategy),
+										  PointerGetDatum(scanEntry->extra_data)));
 
 		if ( cmp > 0 )
 			return true;
@@ -695,16 +696,18 @@ keyGetItem(Relation index, GinState *ginstate, MemoryContext tempCtx,
 
 		/*
 		 * If one of the entry's scans returns lossy result, return it without
-		 * checking - we can't suggest anything helpful to consistentFn.
+		 * further checking - we can't call consistentFn for lack of data.
 		 */
 		if (ItemPointerIsLossyPage(&key->curItem))
 			return FALSE;
 
 		oldCtx = MemoryContextSwitchTo(tempCtx);
-		res = DatumGetBool(FunctionCall4(&ginstate->consistentFn[key->attnum-1],
+		res = DatumGetBool(FunctionCall6(&ginstate->consistentFn[key->attnum-1],
 										 PointerGetDatum(key->entryRes),
 										 UInt16GetDatum(key->strategy),
 										 key->query,
+										 UInt32GetDatum(key->nentries),
+										 PointerGetDatum(key->extra_data),
 										 PointerGetDatum(keyrecheck)));
 		MemoryContextSwitchTo(oldCtx);
 		MemoryContextReset(tempCtx);
@@ -796,10 +799,11 @@ matchPartialInPendingList(GinState *ginstate, Page page,
 						  OffsetNumber off, OffsetNumber maxoff,
 						  Datum value, OffsetNumber attrnum,
 						  Datum	*datum, bool *datumExtracted,
-						  StrategyNumber strategy)
+						  StrategyNumber strategy,
+						  Pointer extra_data)
 {
 	IndexTuple  		itup;
-	int 				res;
+	int32 				cmp;
 
 	while ( off < maxoff )
 	{
@@ -813,13 +817,14 @@ matchPartialInPendingList(GinState *ginstate, Page page,
 			datumExtracted[  off-1 ] = true;
 		}
 
-		res = DatumGetInt32(FunctionCall3(&ginstate->comparePartialFn[attrnum],
-						  value,
-						  datum[ off-1 ],
-						  UInt16GetDatum(strategy)));
-		if ( res == 0 )
+		cmp = DatumGetInt32(FunctionCall4(&ginstate->comparePartialFn[attrnum],
+										  value,
+										  datum[off-1],
+										  UInt16GetDatum(strategy),
+										  PointerGetDatum(extra_data)));
+		if (cmp == 0)
 			return true;
-		else if (res>0)
+		else if (cmp > 0)
 			return false;
 	}
 
@@ -912,7 +917,8 @@ collectDatumForItem(IndexScanDesc scan, pendingPosition *pos)
 															  entry->attnum,
 															  datum,
 															  datumExtracted,
-															  entry->strategy);
+															  entry->strategy,
+															  entry->extra_data);
 							else
 								key->entryRes[j] = true;
 							break;
@@ -933,7 +939,8 @@ collectDatumForItem(IndexScanDesc scan, pendingPosition *pos)
 												  entry->attnum,
 												  datum,
 												  datumExtracted,
-												  entry->strategy);
+												  entry->strategy,
+												  entry->extra_data);
 
 				hasMatch |= key->entryRes[j];
 			}
@@ -1015,19 +1022,22 @@ scanPendingInsert(IndexScanDesc scan, TIDBitmap *tbm, int64 *ntids)
 		recheck = false;
 		match = true;
 
-		for (i = 0; match && i < so->nkeys; i++)
+		for (i = 0; i < so->nkeys; i++)
 		{
 			GinScanKey  	key = so->keys + i;
 
 			keyrecheck = true;
 
-			if ( DatumGetBool(FunctionCall4(&so->ginstate.consistentFn[ key->attnum-1 ],
-									 PointerGetDatum(key->entryRes),
-									 UInt16GetDatum(key->strategy),
-									 key->query,
-									 PointerGetDatum(&keyrecheck))) == false )
+			if (!DatumGetBool(FunctionCall6(&so->ginstate.consistentFn[key->attnum-1],
+											PointerGetDatum(key->entryRes),
+											UInt16GetDatum(key->strategy),
+											key->query,
+											UInt32GetDatum(key->nentries),
+											PointerGetDatum(key->extra_data),
+											PointerGetDatum(&keyrecheck))))
 			{
 				match = false;
+				break;
 			}
 
 			recheck |= keyrecheck;

src/backend/access/gin/ginscan.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *			$PostgreSQL: pgsql/src/backend/access/gin/ginscan.c,v 1.21 2009/01/10 21:08:36 tgl Exp $
+ *			$PostgreSQL: pgsql/src/backend/access/gin/ginscan.c,v 1.22 2009/03/25 22:19:01 tgl Exp $
  *-------------------------------------------------------------------------
  */
 
@@ -38,7 +38,7 @@ ginbeginscan(PG_FUNCTION_ARGS)
 static void
 fillScanKey(GinState *ginstate, GinScanKey key, OffsetNumber attnum, Datum query,
 			Datum *entryValues, bool *partial_matches, uint32 nEntryValues, 
-			StrategyNumber strategy)
+			StrategyNumber strategy, Pointer *extra_data)
 {
 	uint32		i,
 				j;
@@ -48,6 +48,7 @@ fillScanKey(GinState *ginstate, GinScanKey key, OffsetNumber attnum, Datum query
 	key->scanEntry = (GinScanEntry) palloc(sizeof(GinScanEntryData) * nEntryValues);
 	key->strategy = strategy;
 	key->attnum = attnum;
+	key->extra_data = extra_data;
 	key->query = query;
 	key->firstCall = TRUE;
 	ItemPointerSet(&(key->curItem), InvalidBlockNumber, InvalidOffsetNumber);
@@ -57,6 +58,7 @@ fillScanKey(GinState *ginstate, GinScanKey key, OffsetNumber attnum, Datum query
 		key->scanEntry[i].pval = key->entryRes + i;
 		key->scanEntry[i].entry = entryValues[i];
 		key->scanEntry[i].attnum = attnum;
+		key->scanEntry[i].extra_data = (extra_data) ? extra_data[i] : NULL;
 		ItemPointerSet(&(key->scanEntry[i].curItem), InvalidBlockNumber, InvalidOffsetNumber);
 		key->scanEntry[i].offset = InvalidOffsetNumber;
 		key->scanEntry[i].buffer = InvalidBuffer;
@@ -156,60 +158,72 @@ newScanKey(IndexScanDesc scan)
 	int			i;
 	uint32		nkeys = 0;
 
-	so->keys = (GinScanKey) palloc(scan->numberOfKeys * sizeof(GinScanKeyData));
-
 	if (scan->numberOfKeys < 1)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 				 errmsg("GIN indexes do not support whole-index scans")));
 
+	so->keys = (GinScanKey) palloc(scan->numberOfKeys * sizeof(GinScanKeyData));
+
 	so->isVoidRes = false;
 
 	for (i = 0; i < scan->numberOfKeys; i++)
 	{
+		ScanKey		skey = &scankey[i];
 		Datum	   *entryValues;
-		int32		nEntryValues;
+		int32		nEntryValues = 0;
 		bool		*partial_matches = NULL;
+		Pointer		*extra_data = NULL;
 
 		/* XXX can't we treat nulls by just setting isVoidRes? */
 		/* This would amount to assuming that all GIN operators are strict */
-		if (scankey[i].sk_flags & SK_ISNULL)
-			elog(ERROR, "GIN doesn't support NULL as scan key");
-
-		entryValues = (Datum *) DatumGetPointer(FunctionCall4(
-												&so->ginstate.extractQueryFn[scankey[i].sk_attno - 1],
-												scankey[i].sk_argument,
-												PointerGetDatum(&nEntryValues),
-												UInt16GetDatum(scankey[i].sk_strategy),
-												PointerGetDatum(&partial_matches)));
+		if (skey->sk_flags & SK_ISNULL)
+			ereport(ERROR,
+					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+					 errmsg("GIN indexes do not support NULL scan keys")));
+
+		entryValues = (Datum *)
+			DatumGetPointer(FunctionCall5(&so->ginstate.extractQueryFn[skey->sk_attno - 1],
+										  skey->sk_argument,
+										  PointerGetDatum(&nEntryValues),
+										  UInt16GetDatum(skey->sk_strategy),
+										  PointerGetDatum(&partial_matches),
+										  PointerGetDatum(&extra_data)));
+
 		if (nEntryValues < 0)
 		{
 			/*
-			 * extractQueryFn signals that nothing will be found, so we can
-			 * just set isVoidRes flag...
+			 * extractQueryFn signals that nothing can match, so we can
+			 * just set isVoidRes flag.  No need to examine any more keys.
 			 */
 			so->isVoidRes = true;
 			break;
 		}
 
-		/*
-		 * extractQueryFn signals that everything matches
-		 */
 		if (entryValues == NULL || nEntryValues == 0)
-			/* full scan... */
+		{
+			/*
+			 * extractQueryFn signals that everything matches.  This would
+			 * require a full scan, which we can't do, but perhaps there
+			 * is another scankey that provides a restriction to use.  So
+			 * we keep going and check only at the end.
+			 */
 			continue;
+		}
 
-		fillScanKey(&so->ginstate, &(so->keys[nkeys]), scankey[i].sk_attno, scankey[i].sk_argument,
-					entryValues, partial_matches, nEntryValues, scankey[i].sk_strategy);
+		fillScanKey(&so->ginstate, &(so->keys[nkeys]),
+					skey->sk_attno, skey->sk_argument,
+					entryValues, partial_matches, nEntryValues,
+					skey->sk_strategy, extra_data);
 		nkeys++;
 	}
 
-	so->nkeys = nkeys;
-
-	if (so->nkeys == 0 && !so->isVoidRes)
+	if (nkeys == 0 && !so->isVoidRes)
 		ereport(ERROR,
 				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-			   errmsg("GIN index does not support search with void query")));
+				 errmsg("GIN indexes do not support whole-index scans")));
+
+	so->nkeys = nkeys;
 
 	pgstat_count_index_scan(scan->indexRelation);
 }

src/backend/utils/adt/tsginidx.c

@@ -7,7 +7,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/tsginidx.c,v 1.14 2009/01/01 17:23:50 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/tsginidx.c,v 1.15 2009/03/25 22:19:01 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -43,8 +43,9 @@ gin_cmp_prefix(PG_FUNCTION_ARGS)
 	text    *b = PG_GETARG_TEXT_PP(1);
 #ifdef NOT_USED
 	StrategyNumber strategy = PG_GETARG_UINT16(2);
+	Pointer  extra_data = PG_GETARG_POINTER(3);
 #endif
-	int     cmp;
+	int		cmp;
 
 	cmp = tsCompareString(
 					VARDATA_ANY(a), VARSIZE_ANY_EXHDR(a),
@@ -96,6 +97,7 @@ gin_extract_tsquery(PG_FUNCTION_ARGS)
 	int32	   *nentries = (int32 *) PG_GETARG_POINTER(1);
 	/* StrategyNumber strategy = PG_GETARG_UINT16(2); */
 	bool      **ptr_partialmatch = (bool**) PG_GETARG_POINTER(3);
+	Pointer	  **extra_data = (Pointer **) PG_GETARG_POINTER(4);
 	Datum	   *entries = NULL;
 	bool       *partialmatch;
 
@@ -108,6 +110,7 @@ gin_extract_tsquery(PG_FUNCTION_ARGS)
 					len;
 		QueryItem  *item;
 		bool		use_fullscan=false;
+		int		   *map_item_operand;
 
 		item = clean_NOT(GETQUERY(query), &len);
 		if (!item)
@@ -125,6 +128,15 @@ gin_extract_tsquery(PG_FUNCTION_ARGS)
 		entries = (Datum *) palloc(sizeof(Datum) * (*nentries));
 		partialmatch = *ptr_partialmatch = (bool*) palloc(sizeof(bool) * (*nentries));
 
+		/*
+		 * Make map to convert item's number to corresponding
+		 * operand's (the same, entry's) number. Entry's number
+		 * is used in check array in consistent method. We use
+		 * the same map for each entry.
+		 */
+		*extra_data = (Pointer*) palloc0(sizeof(Pointer)*(*nentries));
+		map_item_operand = palloc0(sizeof(int) * (query->size + 1));
+
 		for (i = 0; i < query->size; i++)
 			if (item[i].type == QI_VAL)
 			{
@@ -133,12 +145,18 @@ gin_extract_tsquery(PG_FUNCTION_ARGS)
 
 				txt = cstring_to_text_with_len(GETOPERAND(query) + val->distance,
 											   val->length);
+				(*extra_data)[j] = (Pointer)map_item_operand;
+				map_item_operand[i] = j;
 				partialmatch[j] = val->prefix;
 				entries[j++] = PointerGetDatum(txt);
 			}
 
 		if ( use_fullscan )
+		{
+			(*extra_data)[j] = (Pointer)map_item_operand;
+			map_item_operand[i] = j;
 			entries[j++] = PointerGetDatum(cstring_to_text_with_len("", 0));
+		}
 	}
 	else
 		*nentries = -1;			/* nothing can be found */
@@ -150,8 +168,9 @@ gin_extract_tsquery(PG_FUNCTION_ARGS)
 
 typedef struct
 {
-	QueryItem  *frst;
-	bool	   *mapped_check;
+	QueryItem  *first_item;
+	bool	   *check;
+	int		   *map_item_operand;
 	bool	   *need_recheck;
 } GinChkVal;
 
@@ -159,12 +178,17 @@ static bool
 checkcondition_gin(void *checkval, QueryOperand *val)
 {
 	GinChkVal  *gcv = (GinChkVal *) checkval;
+	int			j;
 
 	/* if any val requiring a weight is used, set recheck flag */
 	if (val->weight != 0)
 		*(gcv->need_recheck) = true;
 
-	return gcv->mapped_check[((QueryItem *) val) - gcv->frst];
+	/* convert item's number to corresponding entry's (operand's) number */
+	j = gcv->map_item_operand[ ((QueryItem *) val) - gcv->first_item ];
+
+	/* return presence of current entry in indexed value */
+	return gcv->check[j];
 }
 
 Datum
@@ -173,7 +197,9 @@ gin_tsquery_consistent(PG_FUNCTION_ARGS)
 	bool	   *check = (bool *) PG_GETARG_POINTER(0);
 	/* StrategyNumber strategy = PG_GETARG_UINT16(1); */
 	TSQuery		query = PG_GETARG_TSQUERY(2);
-	bool	   *recheck = (bool *) PG_GETARG_POINTER(3);
+	/* int32	nkeys = PG_GETARG_INT32(3); */
+	Pointer	   *extra_data = (Pointer *) PG_GETARG_POINTER(4);
+	bool	   *recheck = (bool *) PG_GETARG_POINTER(5);
 	bool		res = FALSE;
 
 	/* The query requires recheck only if it involves weights */
@@ -181,27 +207,18 @@ gin_tsquery_consistent(PG_FUNCTION_ARGS)
 
 	if (query->size > 0)
 	{
-		int			i,
-					j = 0;
 		QueryItem  *item;
 		GinChkVal	gcv;
 
 		/*
 		 * check-parameter array has one entry for each value (operand) in the
-		 * query. We expand that array into mapped_check, so that there's one
-		 * entry in mapped_check for every node in the query, including
-		 * operators, to allow quick lookups in checkcondition_gin. Only the
-		 * entries corresponding operands are actually used.
+		 * query.
 		 */
-
-		gcv.frst = item = GETQUERY(query);
-		gcv.mapped_check = (bool *) palloc(sizeof(bool) * query->size);
+		gcv.first_item = item = GETQUERY(query);
+		gcv.check = check;
+		gcv.map_item_operand = (int*)(extra_data[0]);
 		gcv.need_recheck = recheck;
 
-		for (i = 0; i < query->size; i++)
-			if (item[i].type == QI_VAL)
-				gcv.mapped_check[i] = check[j++];
-
 		res = TS_execute(
 						 GETQUERY(query),
 						 &gcv,

src/include/access/gin.h

@@ -4,7 +4,7 @@
  *
  *	Copyright (c) 2006-2009, PostgreSQL Global Development Group
  *
- *	$PostgreSQL: pgsql/src/include/access/gin.h,v 1.30 2009/03/24 22:06:03 tgl Exp $
+ *	$PostgreSQL: pgsql/src/include/access/gin.h,v 1.31 2009/03/25 22:19:01 tgl Exp $
  *--------------------------------------------------------------------------
  */
 #ifndef GIN_H
@@ -481,6 +481,7 @@ typedef struct GinScanEntryData
 	/* entry, got from extractQueryFn */
 	Datum		entry;
 	OffsetNumber	attnum;
+	Pointer			extra_data;
 
 	/* Current page in posting tree */
 	Buffer		buffer;
@@ -515,6 +516,7 @@ typedef struct GinScanKeyData
 
 	/* array of scans per entry */
 	GinScanEntry scanEntry;
+	Pointer		 *extra_data;
 
 	/* for calling consistentFn(GinScanKey->entryRes, strategy, query) */
 	StrategyNumber strategy;

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.525 2009/03/24 20:17:15 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.526 2009/03/25 22:19:02 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200903241
+#define CATALOG_VERSION_NO	200903251
 
 #endif

src/include/catalog/pg_proc.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.538 2009/03/24 20:17:15 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.539 2009/03/25 22:19:02 tgl Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -4212,9 +4212,9 @@ DESCR("gin(internal)");
 /* GIN array support */
 DATA(insert OID = 2743 (  ginarrayextract	 PGNSP PGUID 12 1 0 0 f f f t f i 2 0 2281 "2277 2281" _null_ _null_ _null_ _null_	ginarrayextract _null_ _null_ _null_ ));
 DESCR("GIN array support");
-DATA(insert OID = 2774 (  ginqueryarrayextract	PGNSP PGUID 12 1 0 0 f f f t f i 4 0 2281 "2277 2281 21 2281" _null_ _null_ _null_ _null_ ginqueryarrayextract _null_ _null_ _null_ ));
+DATA(insert OID = 2774 (  ginqueryarrayextract	PGNSP PGUID 12 1 0 0 f f f t f i 5 0 2281 "2277 2281 21 2281 2281" _null_ _null_ _null_ _null_ ginqueryarrayextract _null_ _null_ _null_ ));
 DESCR("GIN array support");
-DATA(insert OID = 2744 (  ginarrayconsistent PGNSP PGUID 12 1 0 0 f f f t f i 4 0 16 "2281 21 2281 2281" _null_ _null_ _null_ _null_	ginarrayconsistent _null_ _null_ _null_ ));
+DATA(insert OID = 2744 (  ginarrayconsistent	PGNSP PGUID 12 1 0 0 f f f t f i 6 0 16 "2281 21 2277 23 2281 2281" _null_ _null_ _null_ _null_ ginarrayconsistent _null_ _null_ _null_ ));
 DESCR("GIN array support");
 
 /* overlap/contains/contained */
@@ -4453,13 +4453,13 @@ DESCR("GiST tsvector support");
 
 DATA(insert OID = 3656 (  gin_extract_tsvector	PGNSP PGUID 12 1 0 0 f f f t f i 2 0 2281 "3614 2281" _null_ _null_ _null_ _null_	gin_extract_tsvector _null_ _null_ _null_ ));
 DESCR("GIN tsvector support");
-DATA(insert OID = 3657 (  gin_extract_tsquery	PGNSP PGUID 12 1 0 0 f f f t f i 4 0 2281 "3615 2281 21 2281" _null_ _null_ _null_ _null_ gin_extract_tsquery _null_ _null_ _null_ ));
+DATA(insert OID = 3657 (  gin_extract_tsquery	PGNSP PGUID 12 1 0 0 f f f t f i 5 0 2281 "3615 2281 21 2281 2281" _null_ _null_ _null_ _null_ gin_extract_tsquery _null_ _null_ _null_ ));
 DESCR("GIN tsvector support");
-DATA(insert OID = 3658 (  gin_tsquery_consistent PGNSP PGUID 12 1 0 0 f f f t f i 4 0 16 "2281 21 3615 2281" _null_ _null_ _null_ _null_	gin_tsquery_consistent _null_ _null_ _null_ ));
+DATA(insert OID = 3658 (  gin_tsquery_consistent PGNSP PGUID 12 1 0 0 f f f t f i 6 0 16 "2281 21 3615 23 2281 2281" _null_ _null_ _null_ _null_	gin_tsquery_consistent _null_ _null_ _null_ ));
 DESCR("GIN tsvector support");
 DATA(insert OID = 3724 (  gin_cmp_tslexeme      PGNSP PGUID 12 1 0 0 f f f t f i 2 0 23 "25 25" _null_ _null_ _null_ _null_ gin_cmp_tslexeme _null_ _null_ _null_ ));
 DESCR("GIN tsvector support");
-DATA(insert OID = 2700 (  gin_cmp_prefix        PGNSP PGUID 12 1 0 0 f f f t f i 3 0 23 "25 25 21" _null_ _null_ _null_ _null_ gin_cmp_prefix _null_ _null_ _null_ ));
+DATA(insert OID = 2700 (  gin_cmp_prefix        PGNSP PGUID 12 1 0 0 f f f t f i 4 0 23 "25 25 21 2281" _null_ _null_ _null_ _null_ gin_cmp_prefix _null_ _null_ _null_ ));
 DESCR("GIN tsvector support");
 
 DATA(insert OID = 3662 (  tsquery_lt			PGNSP PGUID 12 1 0 0 f f f t f i 2 0 16 "3615 3615" _null_ _null_ _null_ _null_ tsquery_lt _null_ _null_ _null_ ));