Instead of storing pg_statistic stavalues entries as text strings, store

them as arrays of the internal datatype.  This requires treating the
stavalues columns as 'anyarray' rather than 'text[]', which is not 100%
kosher but seems to work fine for the purposes we need for pg_statistic.
Perhaps in the future 'anyarray' will be allowed more generally.

doc/src/sgml/catalogs.sgml

 <!--
  Documentation of the system catalogs, directed toward PostgreSQL developers
- $Header: /cvsroot/pgsql/doc/src/sgml/catalogs.sgml,v 2.66 2003/02/22 00:45:03 tgl Exp $
+ $Header: /cvsroot/pgsql/doc/src/sgml/catalogs.sgml,v 2.67 2003/03/23 05:14:36 tgl Exp $
  -->
 
 <chapter id="catalogs">
@@ -3050,12 +3050,14 @@
 
      <row>
       <entry>stavaluesN</entry>
-      <entry><type>text[]</type></entry>
+      <entry><type>anyarray</type></entry>
       <entry></entry>
       <entry>Column data values of the appropriate kind for the Nth
-      <quote>slot</quote>, or NULL if the slot kind does not store any data values.
-      For data-type independence, all column data values are converted
-      to external textual form and stored as TEXT datums.
+      <quote>slot</quote>, or NULL if the slot kind does not store any data
+      values.
+      Each array's element values are actually of the specific column's
+      datatype, so there is no way to define these columns' type more
+      specifically than <quote>anyarray</>.
       </entry>
      </row>
     </tbody>

src/backend/catalog/heap.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/catalog/heap.c,v 1.240 2003/03/20 03:34:55 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/catalog/heap.c,v 1.241 2003/03/23 05:14:36 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -421,8 +421,12 @@ CheckAttributeType(const char *attname, Oid atttypid)
 			 "\n\tProceeding with relation creation anyway",
 			 attname);
 	else if (att_typtype == 'p')
-		elog(ERROR, "Attribute \"%s\" has pseudo-type %s",
-			 attname, format_type_be(atttypid));
+	{
+		/* Special hack for pg_statistic: allow ANYARRAY during initdb */
+		if (atttypid != ANYARRAYOID || IsUnderPostmaster)
+			elog(ERROR, "Attribute \"%s\" has pseudo-type %s",
+				 attname, format_type_be(atttypid));
+	}
 	else if (att_typtype == 'c')
 	{
 		Oid		typrelid = get_typ_typrelid(atttypid);

src/backend/commands/analyze.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/commands/analyze.c,v 1.51 2002/11/29 21:39:10 tgl Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/commands/analyze.c,v 1.52 2003/03/23 05:14:36 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1694,7 +1694,6 @@ update_attstats(Oid relid, int natts, VacAttrStats **vacattrstats)
 	for (attno = 0; attno < natts; attno++)
 	{
 		VacAttrStats *stats = vacattrstats[attno];
-		FmgrInfo	out_function;
 		HeapTuple	stup,
 					oldtup;
 		int			i,
@@ -1708,8 +1707,6 @@ update_attstats(Oid relid, int natts, VacAttrStats **vacattrstats)
 		if (!stats->stats_valid)
 			continue;
 
-		fmgr_info(stats->attrtype->typoutput, &out_function);
-
 		/*
 		 * Construct a new pg_statistic tuple
 		 */
@@ -1758,33 +1755,16 @@ update_attstats(Oid relid, int natts, VacAttrStats **vacattrstats)
 		}
 		for (k = 0; k < STATISTIC_NUM_SLOTS; k++)
 		{
-			int			ntxt = stats->numvalues[k];
-
-			if (ntxt > 0)
+			if (stats->numvalues[k] > 0)
 			{
-				Datum	   *txtdatums = (Datum *) palloc(ntxt * sizeof(Datum));
 				ArrayType  *arry;
 
-				for (n = 0; n < ntxt; n++)
-				{
-					/*
-					 * Convert data values to a text string to be inserted
-					 * into the text array.
-					 */
-					Datum		stringdatum;
-
-					stringdatum =
-						FunctionCall3(&out_function,
-									  stats->stavalues[k][n],
-							  ObjectIdGetDatum(stats->attrtype->typelem),
-								  Int32GetDatum(stats->attr->atttypmod));
-					txtdatums[n] = DirectFunctionCall1(textin, stringdatum);
-					pfree(DatumGetPointer(stringdatum));
-				}
-				/* XXX knows more than it should about type text: */
-				arry = construct_array(txtdatums, ntxt,
-									   TEXTOID,
-									   -1, false, 'i');
+				arry = construct_array(stats->stavalues[k],
+									   stats->numvalues[k],
+									   stats->attr->atttypid,
+									   stats->attrtype->typlen,
+									   stats->attrtype->typbyval,
+									   stats->attrtype->typalign);
 				values[i++] = PointerGetDatum(arry);	/* stavaluesN */
 			}
 			else

src/backend/utils/adt/selfuncs.c

@@ -15,7 +15,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/utils/adt/selfuncs.c,v 1.133 2003/03/23 01:49:02 tgl Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/utils/adt/selfuncs.c,v 1.134 2003/03/23 05:14:36 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1826,16 +1826,11 @@ mergejoinscansel(Query *root, Node *clause,
 	/*
 	 * Now skip any binary-compatible relabeling; there can only be one level
 	 * since constant-expression folder eliminates adjacent RelabelTypes.
-	 *
-	 * XXX can't enable this quite yet, it exposes regproc uncertainty problems
-	 * in regression tests.  FIXME soon.
 	 */
-#if 0
 	if (IsA(left, RelabelType))
 		left = (Var *) ((RelabelType *) left)->arg;
 	if (IsA(right, RelabelType))
 		right = (Var *) ((RelabelType *) right)->arg;
-#endif
 
 	/* Can't do anything if inputs are not Vars */
 	if (!IsA(left, Var) ||

src/backend/utils/cache/lsyscache.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/utils/cache/lsyscache.c,v 1.90 2003/02/03 21:15:44 tgl Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/utils/cache/lsyscache.c,v 1.91 2003/03/23 05:14:36 tgl Exp $
  *
  * NOTES
  *	  Eventually, the index information should go through here, too.
@@ -28,6 +28,7 @@
 #include "nodes/makefuncs.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
+#include "utils/datum.h"
 #include "utils/lsyscache.h"
 #include "utils/syscache.h"
 
@@ -1387,8 +1388,7 @@ get_attstatsslot(HeapTuple statstuple,
 	ArrayType  *statarray;
 	int			narrayelem;
 	HeapTuple	typeTuple;
-	FmgrInfo	inputproc;
-	Oid			typelem;
+	Form_pg_type typeForm;
 
 	for (i = 0; i < STATISTIC_NUM_SLOTS; i++)
 	{
@@ -1408,48 +1408,40 @@ get_attstatsslot(HeapTuple statstuple,
 			elog(ERROR, "get_attstatsslot: stavalues is null");
 		statarray = DatumGetArrayTypeP(val);
 
-		/*
-		 * Do initial examination of the array.  This produces a list of
-		 * text Datums --- ie, pointers into the text array value.
-		 */
-		deconstruct_array(statarray,
-						  TEXTOID, -1, false, 'i',
-						  values, nvalues);
-		narrayelem = *nvalues;
-
-		/*
-		 * We now need to replace each text Datum by its internal
-		 * equivalent.
-		 *
-		 * Get the type input proc and typelem for the column datatype.
-		 */
+		/* Need to get info about the array element type */
 		typeTuple = SearchSysCache(TYPEOID,
 								   ObjectIdGetDatum(atttype),
 								   0, 0, 0);
 		if (!HeapTupleIsValid(typeTuple))
 			elog(ERROR, "get_attstatsslot: Cache lookup failed for type %u",
 				 atttype);
-		fmgr_info(((Form_pg_type) GETSTRUCT(typeTuple))->typinput, &inputproc);
-		typelem = ((Form_pg_type) GETSTRUCT(typeTuple))->typelem;
-		ReleaseSysCache(typeTuple);
+		typeForm = (Form_pg_type) GETSTRUCT(typeTuple);
+
+		/* Deconstruct array into Datum elements */
+		deconstruct_array(statarray,
+						  atttype,
+						  typeForm->typlen,
+						  typeForm->typbyval,
+						  typeForm->typalign,
+						  values, nvalues);
 
 		/*
-		 * Do the conversions.	The palloc'd array of Datums is reused in
-		 * place.
+		 * If the element type is pass-by-reference, we now have a bunch
+		 * of Datums that are pointers into the syscache value.  Copy them
+		 * to avoid problems if syscache decides to drop the entry.
 		 */
-		for (j = 0; j < narrayelem; j++)
+		if (!typeForm->typbyval)
 		{
-			char	   *strval;
-
-			strval = DatumGetCString(DirectFunctionCall1(textout,
-														 (*values)[j]));
-			(*values)[j] = FunctionCall3(&inputproc,
-										 CStringGetDatum(strval),
-										 ObjectIdGetDatum(typelem),
-										 Int32GetDatum(atttypmod));
-			pfree(strval);
+			for (j = 0; j < *nvalues; j++)
+			{
+				(*values)[j] = datumCopy((*values)[j],
+										 typeForm->typbyval,
+										 typeForm->typlen);
+			}
 		}
 
+		ReleaseSysCache(typeTuple);
+
 		/*
 		 * Free statarray if it's a detoasted copy.
 		 */

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: catversion.h,v 1.182 2003/03/21 01:58:04 tgl Exp $
+ * $Id: catversion.h,v 1.183 2003/03/23 05:14:37 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200303201
+#define CATALOG_VERSION_NO	200303221
 
 #endif

src/include/catalog/pg_statistic.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: pg_statistic.h,v 1.19 2003/03/10 22:28:21 tgl Exp $
+ * $Id: pg_statistic.h,v 1.20 2003/03/23 05:14:37 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -26,6 +26,12 @@
  * ----------------
  */
 
+/*
+ * Keep C compiler happy with anyarray, below.  This will need to go elsewhere
+ * if we ever use anyarray for more than pg_statistic.
+ */
+typedef struct varlena anyarray;
+
 /* ----------------
  *		pg_statistic definition.  cpp turns this into
  *		typedef struct FormData_pg_statistic
@@ -109,14 +115,14 @@ CATALOG(pg_statistic) BKI_WITHOUT_OIDS
 	float4		stanumbers4[1];
 
 	/*
-	 * Values in these text arrays are external representations of values
-	 * of the column's data type.  To re-create the actual Datum, do
-	 * datatypein(textout(arrayelement)).
+	 * Values in these arrays are values of the column's data type.  We
+	 * presently have to cheat quite a bit to allow polymorphic arrays
+	 * of this kind, but perhaps someday it'll be a less bogus facility.
 	 */
-	text		stavalues1[1];
-	text		stavalues2[1];
-	text		stavalues3[1];
-	text		stavalues4[1];
+	anyarray	stavalues1;
+	anyarray	stavalues2;
+	anyarray	stavalues3;
+	anyarray	stavalues4;
 } FormData_pg_statistic;
 
 #define STATISTIC_NUM_SLOTS  4