Add a hash function for "numeric". Mark the equality operator for

numerics as "oprcanhash", and make the corresponding system catalog
updates. As a result, hash indexes, hashed aggregation, and hash
joins can now be used with the numeric type. Bump the catversion.

The only tricky aspect to doing this is writing a correct hash
function: it's possible for two Numerics to be equal according to
their equality operator, but have different in-memory bit patterns.
To cope with this, the hash function doesn't consider the Numeric's
"scale" or "sign", and explictly skips any leading or trailing
zeros in the Numeric's digit buffer (the current implementation
should suppress any such zeros, but it seems unwise to rely upon
this). See discussion on pgsql-patches for more details.

src/backend/utils/adt/numeric.c

@@ -14,7 +14,7 @@
  * Copyright (c) 1998-2007, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/numeric.c,v 1.101 2007/02/27 23:48:08 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/numeric.c,v 1.102 2007/05/08 18:56:47 neilc Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -26,6 +26,7 @@
 #include <limits.h>
 #include <math.h>
 
+#include "access/hash.h"
 #include "catalog/pg_type.h"
 #include "libpq/pqformat.h"
 #include "utils/array.h"
@@ -1149,6 +1150,81 @@ cmp_numerics(Numeric num1, Numeric num2)
 	return result;
 }
 
+Datum
+hash_numeric(PG_FUNCTION_ARGS)
+{
+	Numeric 	key = PG_GETARG_NUMERIC(0);
+	Datum 		digit_hash;
+	Datum 		result;
+	int 		weight;
+	int 		start_offset;
+	int 		end_offset;
+	int 		i;
+	int 		hash_len;
+
+	/* If it's NaN, don't try to hash the rest of the fields */
+	if (NUMERIC_IS_NAN(key))
+		PG_RETURN_UINT32(0);
+
+	weight 		 = key->n_weight;
+	start_offset = 0;
+	end_offset 	 = 0;
+
+	/*
+	 * Omit any leading or trailing zeros from the input to the
+	 * hash. The numeric implementation *should* guarantee that
+	 * leading and trailing zeros are suppressed, but we're
+	 * paranoid. Note that we measure the starting and ending offsets
+	 * in units of NumericDigits, not bytes.
+	 */
+	for (i = 0; i < NUMERIC_NDIGITS(key); i++)
+	{
+		if (NUMERIC_DIGITS(key)[i] != (NumericDigit) 0)
+			break;
+
+		start_offset++;
+		/*
+		 * The weight is effectively the # of digits before the
+		 * decimal point, so decrement it for each leading zero we
+		 * skip.
+		 */
+		weight--;
+	}
+
+	/*
+	 * If there are no non-zero digits, then the value of the number
+	 * is zero, regardless of any other fields.
+	 */
+	if (NUMERIC_NDIGITS(key) == start_offset)
+		PG_RETURN_UINT32(-1);
+
+	for (i = NUMERIC_NDIGITS(key) - 1; i >= 0; i--)
+	{
+		if (NUMERIC_DIGITS(key)[i] != (NumericDigit) 0)
+			break;
+
+		end_offset++;
+	}
+
+	/* If we get here, there should be at least one non-zero digit */
+	Assert(start_offset + end_offset < NUMERIC_NDIGITS(key));
+
+	/*
+	 * Note that we don't hash on the Numeric's scale, since two
+	 * numerics can compare equal but have different scales. We also
+	 * don't hash on the sign, although we could: since a sign
+	 * difference implies inequality, this shouldn't affect correctness.
+	 */
+	hash_len = NUMERIC_NDIGITS(key) - start_offset - end_offset;
+	digit_hash = hash_any((unsigned char *) (NUMERIC_DIGITS(key) + start_offset),
+                          hash_len * sizeof(NumericDigit));
+
+	/* Mix in the weight, via XOR */
+	result = digit_hash ^ weight;
+
+	PG_RETURN_DATUM(result);
+}
+
 
 /* ----------------------------------------------------------------------
  *

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.404 2007/04/15 10:56:27 ishii Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.405 2007/05/08 18:56:47 neilc Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200704151
+#define CATALOG_VERSION_NO	200705081
 
 #endif

src/include/catalog/pg_amop.h

@@ -29,7 +29,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_amop.h,v 1.80 2007/04/02 03:49:40 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_amop.h,v 1.81 2007/05/08 18:56:47 neilc Exp $
  *
  * NOTES
  *	 the genbki.sh script reads this file and generates .bki
@@ -568,6 +568,8 @@ DATA(insert (	2232   19 19 1 f 2334	405 ));
 DATA(insert (	2235   1033 1033 1 f  974	405 ));
 /* uuid_ops */ 
 DATA(insert (	2969   2950 2950 1 f 2972 405 ));
+/* numeric_ops */
+DATA(insert (	1998   1700 1700 1 f 1752 405 ));
 
 
 /*

src/include/catalog/pg_amproc.h

@@ -22,7 +22,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_amproc.h,v 1.64 2007/04/02 03:49:40 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_amproc.h,v 1.65 2007/05/08 18:56:47 neilc Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -148,6 +148,7 @@ DATA(insert (	1990   26 26 1 453 ));
 DATA(insert (	1992   30 30 1 457 ));
 DATA(insert (	1995   25 25 1 400 ));
 DATA(insert (	1997   1083 1083 1 452 ));
+DATA(insert (	1998   1700 1700 1 432 ));
 DATA(insert (	1999   1184 1184 1 452 ));
 DATA(insert (	2001   1266 1266 1 1696 ));
 DATA(insert (	2040   1114 1114 1 452 ));

src/include/catalog/pg_opclass.h

@@ -28,7 +28,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_opclass.h,v 1.75 2007/04/02 03:49:40 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_opclass.h,v 1.76 2007/05/08 18:56:47 neilc Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -129,6 +129,7 @@ DATA(insert (	405		macaddr_ops			PGNSP PGUID 1985  829 t 0 ));
 DATA(insert (	403		name_ops			PGNSP PGUID 1986   19 t 0 ));
 DATA(insert (	405		name_ops			PGNSP PGUID 1987   19 t 0 ));
 DATA(insert (	403		numeric_ops			PGNSP PGUID 1988 1700 t 0 ));
+DATA(insert (	405		numeric_ops			PGNSP PGUID 1998 1700 t 0 ));
 DATA(insert OID = 1981 ( 403	oid_ops		PGNSP PGUID 1989   26 t 0 ));
 #define OID_BTREE_OPS_OID 1981
 DATA(insert (	405		oid_ops				PGNSP PGUID 1990   26 t 0 ));

src/include/catalog/pg_operator.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_operator.h,v 1.151 2007/04/02 03:49:40 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_operator.h,v 1.152 2007/05/08 18:56:47 neilc Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -675,7 +675,7 @@ DATA(insert OID = 1630 (  "!~~*"  PGNSP PGUID b f f  1042 25	16 0 1629 bpcharicn
 
 /* NUMERIC type - OID's 1700-1799 */
 DATA(insert OID = 1751 (  "-"	   PGNSP PGUID l f f	0 1700 1700    0	0 numeric_uminus - - ));
-DATA(insert OID = 1752 (  "="	   PGNSP PGUID b t f 1700 1700	 16 1752 1753 numeric_eq eqsel eqjoinsel ));
+DATA(insert OID = 1752 (  "="	   PGNSP PGUID b t t 1700 1700	 16 1752 1753 numeric_eq eqsel eqjoinsel ));
 DATA(insert OID = 1753 (  "<>"	   PGNSP PGUID b f f 1700 1700	 16 1753 1752 numeric_ne neqsel neqjoinsel ));
 DATA(insert OID = 1754 (  "<"	   PGNSP PGUID b f f 1700 1700	 16 1756 1757 numeric_lt scalarltsel scalarltjoinsel ));
 DATA(insert OID = 1755 (  "<="	   PGNSP PGUID b f f 1700 1700	 16 1757 1756 numeric_le scalarltsel scalarltjoinsel ));

src/include/catalog/pg_opfamily.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_opfamily.h,v 1.4 2007/04/02 03:49:40 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_opfamily.h,v 1.5 2007/05/08 18:56:47 neilc Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -93,6 +93,7 @@ DATA(insert OID = 1986 (	403		name_ops		PGNSP PGUID ));
 #define NAME_BTREE_FAM_OID 1986
 DATA(insert OID = 1987 (	405		name_ops		PGNSP PGUID ));
 DATA(insert OID = 1988 (	403		numeric_ops		PGNSP PGUID ));
+DATA(insert OID = 1998 (	405		numeric_ops		PGNSP PGUID ));
 DATA(insert OID = 1989 (	403		oid_ops			PGNSP PGUID ));
 #define OID_BTREE_FAM_OID 1989
 DATA(insert OID = 1990 (	405		oid_ops			PGNSP PGUID ));

src/include/catalog/pg_proc.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.454 2007/04/02 03:49:40 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.455 2007/05/08 18:56:48 neilc Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -838,6 +838,8 @@ DATA(insert OID = 399 (  hashmacaddr	   PGNSP PGUID 12 1 0 f f t f i 1 23 "829"
 DESCR("hash");
 DATA(insert OID = 422 (  hashinet		   PGNSP PGUID 12 1 0 f f t f i 1 23 "869" _null_ _null_ _null_ hashinet - _null_ ));
 DESCR("hash");
+DATA(insert OID = 432 (  hash_numeric	   PGNSP PGUID 12 1 0 f f t f i 1 23 "1700" _null_ _null_ _null_ hash_numeric - _null_ ));
+DESCR("hash");
 DATA(insert OID = 458 (  text_larger	   PGNSP PGUID 12 1 0 f f t f i 2 25 "25 25" _null_ _null_ _null_ text_larger - _null_ ));
 DESCR("larger of two");
 DATA(insert OID = 459 (  text_smaller	   PGNSP PGUID 12 1 0 f f t f i 2 25 "25 25" _null_ _null_ _null_ text_smaller - _null_ ));

src/include/utils/builtins.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/builtins.h,v 1.291 2007/04/02 03:49:41 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/utils/builtins.h,v 1.292 2007/05/08 18:56:48 neilc Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -883,6 +883,7 @@ extern Datum int2_avg_accum(PG_FUNCTION_ARGS);
 extern Datum int4_avg_accum(PG_FUNCTION_ARGS);
 extern Datum int8_avg(PG_FUNCTION_ARGS);
 extern Datum width_bucket_numeric(PG_FUNCTION_ARGS);
+extern Datum hash_numeric(PG_FUNCTION_ARGS);
 
 /* ri_triggers.c */
 extern Datum RI_FKey_check_ins(PG_FUNCTION_ARGS);