Extend VacAttrStats to allow typanalyze functions to store statistic values

of different types than the underlying column. The capability isn't yet
used for anything, but will be required by upcoming patch to analyze
tsvector columns.

Jan Urbanski

src/backend/commands/analyze.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.122 2008/06/08 22:00:47 alvherre Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.123 2008/07/01 10:33:09 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -684,6 +684,7 @@ examine_attribute(Relation onerel, int attnum)
 	Form_pg_attribute attr = onerel->rd_att->attrs[attnum - 1];
 	HeapTuple	typtuple;
 	VacAttrStats *stats;
+	int			i;
 	bool		ok;
 
 	/* Never analyze dropped columns */
@@ -711,6 +712,20 @@ examine_attribute(Relation onerel, int attnum)
 	stats->anl_context = anl_context;
 	stats->tupattnum = attnum;
 
+	/*
+	 * The fields describing the stats->stavalues[n] element types default
+	 * to the type of the field being analyzed, but the type-specific
+	 * typanalyze function can change them if it wants to store something
+	 * else.
+	 */
+	for (i = 0; i < STATISTIC_NUM_SLOTS; i++)
+	{
+		stats->statypid[i] = stats->attr->atttypid;
+		stats->statyplen[i] = stats->attrtype->typlen;
+		stats->statypbyval[i] = stats->attrtype->typbyval;
+		stats->statypalign[i] = stats->attrtype->typalign;
+	}
+
 	/*
 	 * Call the type-specific typanalyze function.	If none is specified, use
 	 * std_typanalyze().
@@ -1322,10 +1337,10 @@ update_attstats(Oid relid, int natts, VacAttrStats **vacattrstats)
 
 				arry = construct_array(stats->stavalues[k],
 									   stats->numvalues[k],
-									   stats->attr->atttypid,
-									   stats->attrtype->typlen,
-									   stats->attrtype->typbyval,
-									   stats->attrtype->typalign);
+									   stats->statypid[k],
+									   stats->statyplen[k],
+									   stats->statypbyval[k],
+									   stats->statypalign[k]);
 				values[i++] = PointerGetDatum(arry);	/* stavaluesN */
 			}
 			else
@@ -1855,6 +1870,10 @@ compute_minimal_stats(VacAttrStatsP stats,
 			stats->numnumbers[0] = num_mcv;
 			stats->stavalues[0] = mcv_values;
 			stats->numvalues[0] = num_mcv;
+			/*
+			 * Accept the defaults for stats->statypid and others.
+			 * They have been set before we were called (see vacuum.h)
+			 */
 		}
 	}
 	else if (null_cnt > 0)
@@ -2198,6 +2217,10 @@ compute_scalar_stats(VacAttrStatsP stats,
 			stats->numnumbers[slot_idx] = num_mcv;
 			stats->stavalues[slot_idx] = mcv_values;
 			stats->numvalues[slot_idx] = num_mcv;
+			/*
+			 * Accept the defaults for stats->statypid and others.
+			 * They have been set before we were called (see vacuum.h)
+			 */
 			slot_idx++;
 		}
 
@@ -2282,6 +2305,10 @@ compute_scalar_stats(VacAttrStatsP stats,
 			stats->staop[slot_idx] = mystats->ltopr;
 			stats->stavalues[slot_idx] = hist_values;
 			stats->numvalues[slot_idx] = num_hist;
+			/*
+			 * Accept the defaults for stats->statypid and others.
+			 * They have been set before we were called (see vacuum.h)
+			 */
 			slot_idx++;
 		}
 

src/include/commands/vacuum.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/commands/vacuum.h,v 1.78 2008/06/19 00:46:06 alvherre Exp $
+ * $PostgreSQL: pgsql/src/include/commands/vacuum.h,v 1.79 2008/07/01 10:33:09 heikki Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -93,6 +93,18 @@ typedef struct VacAttrStats
 	int			numvalues[STATISTIC_NUM_SLOTS];
 	Datum	   *stavalues[STATISTIC_NUM_SLOTS];
 
+	/*
+	 * These fields describe the stavalues[n] element types. They will
+	 * be initialized to be the same as the column's that's underlying the
+	 * slot, but a custom typanalyze function might want to store an array of
+	 * something other than the analyzed column's elements. It should then
+	 * overwrite these fields.
+	 */
+	Oid			statypid[STATISTIC_NUM_SLOTS];
+	int2		statyplen[STATISTIC_NUM_SLOTS];
+	bool		statypbyval[STATISTIC_NUM_SLOTS];
+	char		statypalign[STATISTIC_NUM_SLOTS];
+
 	/*
 	 * These fields are private to the main ANALYZE code and should not be
 	 * looked at by type-specific functions.