Give inet/cidr datatypes their own hash function that ignores the inet vs

cidr type bit, the same as network_eq does.  This is needed for hash joins
and hash aggregation to work correctly on these types.  Per bug report
from Michael Fuhr, 2004-04-13.
Also, improve hash function for int8 as suggested by Greg Stark.

Author: tglsfdc

src/backend/access/hash/hashfunc.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/hash/hashfunc.c,v 1.39 2003/11/29 19:51:40 pgsql Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/hash/hashfunc.c,v 1.40 2004/06/13 21:57:24 tgl Exp $
  *
  * NOTES
  *	  These functions are stored in pg_amproc.	For each operator class
@@ -44,8 +44,26 @@ hashint4(PG_FUNCTION_ARGS)
 Datum
 hashint8(PG_FUNCTION_ARGS)
 {
-	/* we just use the low 32 bits... */
+	/*
+	 * The idea here is to produce a hash value compatible with the values
+	 * produced by hashint4 and hashint2 for logically equivalent inputs;
+	 * this is necessary if we ever hope to support cross-type hash joins
+	 * across these input types.  Since all three types are signed, we can
+	 * xor the high half of the int8 value if the sign is positive, or the
+	 * complement of the high half when the sign is negative.
+	 */
+#ifndef INT64_IS_BUSTED
+	int64		val = PG_GETARG_INT64(0);
+	uint32		lohalf = (uint32) val;
+	uint32		hihalf = (uint32) (val >> 32);
+
+	lohalf ^= (val >= 0) ? hihalf : ~hihalf;
+
+	PG_RETURN_UINT32(~lohalf);
+#else
+	/* here if we can't count on "x >> 32" to work sanely */
 	PG_RETURN_UINT32(~((uint32) PG_GETARG_INT64(0)));
+#endif
 }
 
 Datum

src/backend/utils/adt/network.c

@@ -1,18 +1,18 @@
 /*
  *	PostgreSQL type definitions for the INET and CIDR types.
  *
- *	$PostgreSQL: pgsql/src/backend/utils/adt/network.c,v 1.51 2004/06/13 19:56:50 tgl Exp $
+ *	$PostgreSQL: pgsql/src/backend/utils/adt/network.c,v 1.52 2004/06/13 21:57:25 tgl Exp $
  *
  *	Jon Postel RIP 16 Oct 1998
  */
 
 #include "postgres.h"
 
-#include <errno.h>
 #include <sys/socket.h>
 #include <netinet/in.h>
 #include <arpa/inet.h>
 
+#include "access/hash.h"
 #include "catalog/pg_type.h"
 #include "libpq/ip.h"
 #include "libpq/libpq-be.h"
@@ -42,7 +42,7 @@ static int	ip_addrsize(inet *inetptr);
 	(((inet_struct *)VARDATA(inetptr))->type)
 
 #define ip_addr(inetptr) \
-	(((inet_struct *)VARDATA(inetptr))->ip_addr)
+	(((inet_struct *)VARDATA(inetptr))->ipaddr)
 
 #define ip_maxbits(inetptr) \
 	(ip_family(inetptr) == PGSQL_AF_INET ? 32 : 128)
@@ -60,7 +60,7 @@ ip_addrsize(inet *inetptr)
 		case PGSQL_AF_INET6:
 			return 16;
 		default:
-			return -1;
+			return 0;
 	}
 }
 
@@ -424,6 +424,27 @@ network_ne(PG_FUNCTION_ARGS)
 	PG_RETURN_BOOL(network_cmp_internal(a1, a2) != 0);
 }
 
+/*
+ * Support function for hash indexes on inet/cidr.
+ *
+ * Since network_cmp considers only ip_family, ip_bits, and ip_addr,
+ * only these fields may be used in the hash; in particular don't use type.
+ */
+Datum
+hashinet(PG_FUNCTION_ARGS)
+{
+	inet	   *addr = PG_GETARG_INET_P(0);
+	int			addrsize = ip_addrsize(addr);
+	unsigned char key[sizeof(inet_struct)];
+
+	Assert(addrsize + 2 <= sizeof(key));
+	key[0] = ip_family(addr);
+	key[1] = ip_bits(addr);
+	memcpy(key + 2, ip_addr(addr), addrsize);
+
+	return hash_any(key, addrsize + 2);
+}
+
 /*
  *	Boolean network-inclusion tests.
  */

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.234 2004/06/06 19:06:59 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.235 2004/06/13 21:57:25 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200406061
+#define CATALOG_VERSION_NO	200406131
 
 #endif

src/include/catalog/pg_amproc.h

@@ -19,7 +19,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_amproc.h,v 1.48 2004/03/22 01:38:17 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_amproc.h,v 1.49 2004/06/13 21:57:25 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -136,11 +136,11 @@ DATA(insert (	2234    0 1  381 ));
 /* hash */
 DATA(insert (	 427    0 1 1080 ));
 DATA(insert (	 431    0 1	454 ));
-DATA(insert (	 433    0 1	456 ));
+DATA(insert (	 433    0 1	422 ));
 DATA(insert (	 435    0 1	450 ));
 DATA(insert (	1971    0 1	451 ));
 DATA(insert (	1973    0 1	452 ));
-DATA(insert (	1975    0 1	456 ));
+DATA(insert (	1975    0 1	422 ));
 DATA(insert (	1977    0 1	449 ));
 DATA(insert (	1979    0 1	450 ));
 DATA(insert (	1981    0 1	949 ));

src/include/catalog/pg_proc.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.336 2004/06/13 19:56:51 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.337 2004/06/13 21:57:26 tgl Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -851,6 +851,8 @@ DATA(insert OID = 398 (  hashint2vector    PGNSP PGUID 12 f f t f i 1 23 "22" _n
 DESCR("hash");
 DATA(insert OID = 399 (  hashmacaddr	   PGNSP PGUID 12 f f t f i 1 23 "829" _null_	hashmacaddr - _null_ ));
 DESCR("hash");
+DATA(insert OID = 422 (  hashinet		   PGNSP PGUID 12 f f t f i 1 23 "869" _null_	hashinet - _null_ ));
+DESCR("hash");
 DATA(insert OID = 458 (  text_larger	   PGNSP PGUID 12 f f t f i 2 25 "25 25" _null_	text_larger - _null_ ));
 DESCR("larger of two");
 DATA(insert OID = 459 (  text_smaller	   PGNSP PGUID 12 f f t f i 2 25 "25 25" _null_	text_smaller - _null_ ));

src/include/utils/builtins.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/builtins.h,v 1.242 2004/06/13 19:56:52 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/utils/builtins.h,v 1.243 2004/06/13 21:57:26 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -664,6 +664,7 @@ extern Datum network_eq(PG_FUNCTION_ARGS);
 extern Datum network_ge(PG_FUNCTION_ARGS);
 extern Datum network_gt(PG_FUNCTION_ARGS);
 extern Datum network_ne(PG_FUNCTION_ARGS);
+extern Datum hashinet(PG_FUNCTION_ARGS);
 extern Datum network_sub(PG_FUNCTION_ARGS);
 extern Datum network_subeq(PG_FUNCTION_ARGS);
 extern Datum network_sup(PG_FUNCTION_ARGS);

src/include/utils/inet.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/inet.h,v 1.17 2003/11/29 22:41:15 pgsql Exp $
+ * $PostgreSQL: pgsql/src/include/utils/inet.h,v 1.18 2004/06/13 21:57:26 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -20,10 +20,10 @@
  */
 typedef struct
 {
-	unsigned char family;
-	unsigned char bits;
-	unsigned char type;
-	unsigned char ip_addr[16];	/* 128 bits of address */
+	unsigned char family;		/* PGSQL_AF_INET or PGSQL_AF_INET6 */
+	unsigned char bits;			/* number of bits in netmask */
+	unsigned char type;			/* 0 = inet, 1 = cidr */
+	unsigned char ipaddr[16];	/* up to 128 bits of address */
 } inet_struct;
 
 /*

src/test/regress/expected/opr_sanity.out

@@ -487,6 +487,16 @@ WHERE p1.oprcanhash AND NOT EXISTS
 -----+---------
 (0 rows)
 
+-- And the converse.
+SELECT p1.oid, p1.oprname, op.opcname
+FROM pg_operator AS p1, pg_opclass op, pg_amop p
+WHERE amopopr = p1.oid AND amopclaid = op.oid
+  AND opcamid = (SELECT oid FROM pg_am WHERE amname = 'hash')
+  AND NOT p1.oprcanhash;
+ oid | oprname | opcname 
+-----+---------+---------
+(0 rows)
+
 -- Check that each operator defined in pg_operator matches its oprcode entry
 -- in pg_proc.  Easiest to do this separately for each oprkind.
 SELECT p1.oid, p1.oprname, p2.oid, p2.proname

src/test/regress/sql/opr_sanity.sql

@@ -409,6 +409,13 @@ WHERE p1.oprcanhash AND NOT EXISTS
    WHERE opcamid = (SELECT oid FROM pg_am WHERE amname = 'hash') AND
          amopopr = p1.oid);
 
+-- And the converse.
+
+SELECT p1.oid, p1.oprname, op.opcname
+FROM pg_operator AS p1, pg_opclass op, pg_amop p
+WHERE amopopr = p1.oid AND amopclaid = op.oid
+  AND opcamid = (SELECT oid FROM pg_am WHERE amname = 'hash')
+  AND NOT p1.oprcanhash;
 
 -- Check that each operator defined in pg_operator matches its oprcode entry
 -- in pg_proc.  Easiest to do this separately for each oprkind.