Add pg_column_size() to return storage size of a column, including

possible compression.

Mark Kirkwood

doc/src/sgml/func.sgml

 <!--
-$PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.262 2005/06/29 01:52:56 momjian Exp $
+$PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.263 2005/07/06 19:02:52 momjian Exp $
 PostgreSQL documentation
 -->
 
@@ -2186,6 +2186,14 @@ PostgreSQL documentation
        <entry><literal>5</literal></entry>
       </row>
 
+      <row>
+       <entry><literal><function>pg_column_size</function>(<parameter>string</parameter>)</literal></entry>
+       <entry><type>integer</type></entry>
+       <entry>Number of bytes required to store the value, which might be compressed</entry>
+       <entry><literal>pg_column_size('jo\\000se'::bytea)</literal></entry>
+       <entry><literal>5</literal></entry>
+      </row>
+
       <row>
        <entry><literal><function>position</function>(<parameter>substring</parameter> in <parameter>string</parameter>)</literal></entry>
        <entry><type>integer</type></entry>

src/backend/access/heap/tuptoaster.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/heap/tuptoaster.c,v 1.49 2005/03/21 01:23:58 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/heap/tuptoaster.c,v 1.50 2005/07/06 19:02:52 momjian Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -1436,3 +1436,45 @@ toast_fetch_datum_slice(varattrib *attr, int32 sliceoffset, int32 length)
 
 	return result;
 }
+
+/* ----------
+ * toast_datum_size
+ *
+ *	Show the (possibly compressed) size of a datum
+ * ----------
+ */
+Size 
+toast_datum_size(Datum value)
+{
+
+	varattrib	*attr = (varattrib *) DatumGetPointer(value);
+	Size		result;
+
+	if (VARATT_IS_EXTERNAL(attr))
+	{
+		/*
+		 * Attribute is stored externally - If it is compressed too, 
+		 * then we need to get the external datum and calculate its size,
+		 * otherwise we just use the external rawsize.
+		 */
+		if (VARATT_IS_COMPRESSED(attr))
+		{
+			varattrib		*attrext = toast_fetch_datum(attr);
+			result = VARSIZE(attrext);
+			pfree(attrext);
+		}
+		else
+			result = attr->va_content.va_external.va_rawsize;
+	}
+	else
+	{
+		/*
+		 * Attribute is stored inline either compressed or not, just
+		 * calculate the size of the datum in either case.
+		 */
+		result = VARSIZE(attr);
+	}
+
+	return result;
+	
+}

src/backend/utils/adt/varlena.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.124 2005/07/04 18:56:44 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.125 2005/07/06 19:02:52 momjian Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -28,6 +28,7 @@
 #include "utils/builtins.h"
 #include "utils/lsyscache.h"
 #include "utils/pg_locale.h"
+#include "utils/syscache.h"
 
 
 typedef struct varlena unknown;
@@ -2348,3 +2349,47 @@ md5_bytea(PG_FUNCTION_ARGS)
 	result_text = PG_STR_GET_TEXT(hexsum);
 	PG_RETURN_TEXT_P(result_text);
 }
+
+/* 
+ * Return the length of a datum, possibly compressed
+ */
+Datum
+pg_column_size(PG_FUNCTION_ARGS)
+{
+	Datum			value = PG_GETARG_DATUM(0);
+	int				result;
+
+	/*	fn_extra stores the fixed column length, or -1 for varlena. */
+	if (fcinfo->flinfo->fn_extra == NULL)	/* first call? */
+	{
+		/* On the first call lookup the datatype of the supplied argument */
+		Oid				argtypeid = get_fn_expr_argtype(fcinfo->flinfo, 0);
+		HeapTuple		tp;
+		int				typlen;
+
+		tp = SearchSysCache(TYPEOID,
+							ObjectIdGetDatum(argtypeid),
+							0, 0, 0);
+		if (!HeapTupleIsValid(tp))
+		{
+			/* Oid not in pg_type, should never happen. */
+			ereport(ERROR,
+					(errcode(ERRCODE_INTERNAL_ERROR),
+					 errmsg("invalid typid: %u", argtypeid)));
+		}
+		
+		typlen = ((Form_pg_type)GETSTRUCT(tp))->typlen;
+		ReleaseSysCache(tp);
+		fcinfo->flinfo->fn_extra = MemoryContextAlloc(fcinfo->flinfo->fn_mcxt,
+													  sizeof(int));
+		*(int *)fcinfo->flinfo->fn_extra = typlen;
+	}
+
+	if (*(int *)fcinfo->flinfo->fn_extra != -1)
+		PG_RETURN_INT32(*(int *)fcinfo->flinfo->fn_extra);
+	else
+	{
+		result = toast_datum_size(value) - VARHDRSZ;
+		PG_RETURN_INT32(result);
+	}
+}

src/include/access/tuptoaster.h

@@ -6,7 +6,7 @@
  *
  * Copyright (c) 2000-2005, PostgreSQL Global Development Group
  *
- * $PostgreSQL: pgsql/src/include/access/tuptoaster.h,v 1.22 2005/03/21 01:24:04 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/access/tuptoaster.h,v 1.23 2005/07/06 19:02:53 momjian Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -138,4 +138,12 @@ extern Datum toast_compress_datum(Datum value);
  */
 extern Size toast_raw_datum_size(Datum value);
 
+/* ----------
+ * toast_datum_size -
+ *
+ *	Return the storage size of a varlena datum
+ * ----------
+ */
+extern Size toast_datum_size(Datum value);
+
 #endif   /* TUPTOASTER_H */

src/include/catalog/pg_proc.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.373 2005/07/01 19:19:03 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.374 2005/07/06 19:02:53 momjian Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -3658,6 +3658,10 @@ DESCR("current value from last used sequence");
 DATA(insert OID = 2560 (  pg_postmaster_start_time PGNSP PGUID 12 f f t f s 0 1184 "" _null_ _null_ _null_ pgsql_postmaster_start_time - _null_ ));
 DESCR("postmaster start time");
 
+/* Column storage size */
+DATA(insert OID = 1269 (  pg_column_size	   PGNSP PGUID 12 f f t f i 1 23 "2276" _null_ _null_ _null_  pg_column_size - _null_ ));
+DESCR("bytes required to store the value, perhaps with compression");
+
 /* new functions for Y-direction rtree opclasses */
 DATA(insert OID = 2562 (  box_below		   PGNSP PGUID 12 f f t f i 2 16 "603 603" _null_ _null_ _null_	box_below - _null_ ));
 DESCR("is below");

src/include/utils/builtins.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/builtins.h,v 1.258 2005/06/17 22:32:50 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/utils/builtins.h,v 1.259 2005/07/06 19:02:54 momjian Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -601,6 +601,7 @@ extern Datum byteacat(PG_FUNCTION_ARGS);
 extern Datum byteapos(PG_FUNCTION_ARGS);
 extern Datum bytea_substr(PG_FUNCTION_ARGS);
 extern Datum bytea_substr_no_len(PG_FUNCTION_ARGS);
+extern Datum pg_column_size(PG_FUNCTION_ARGS);
 
 /* version.c */
 extern Datum pgsql_version(PG_FUNCTION_ARGS);