Code and docs review for pg_column_size() patch.

4 files changed, 130 insertions, 108 deletions

diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index ba372618ac8..7dc9a3b5978 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.275 2005/07/30 22:53:15 tgl Exp $
+$PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.276 2005/08/02 16:11:56 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -2207,14 +2207,6 @@ PostgreSQL documentation
       </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>
        <entry>Location of specified substring</entry>
@@ -9181,11 +9173,29 @@ SELECT set_config('log_statement_stats', 'off', false);
    </para>
 
    <para>
-    The functions shown in <xref
-    linkend="functions-admin-dbsize"> calculate the actual disk space
-    usage of database objects.
+    The functions shown in <xref linkend="functions-admin-dbsize"> calculate
+    the actual disk space usage of database objects.
    </para>
 
+   <indexterm zone="functions-admin">
+    <primary>pg_column_size</primary>
+   </indexterm>
+   <indexterm zone="functions-admin">
+    <primary>pg_tablespace_size</primary>
+   </indexterm>
+   <indexterm zone="functions-admin">
+    <primary>pg_database_size</primary>
+   </indexterm>
+   <indexterm zone="functions-admin">
+    <primary>pg_relation_size</primary>
+   </indexterm>
+   <indexterm zone="functions-admin">
+    <primary>pg_complete_relation_size</primary>
+   </indexterm>
+   <indexterm zone="functions-admin">
+    <primary>pg_size_pretty</primary>
+   </indexterm>
+
    <table id="functions-admin-dbsize">
     <title>Database Object Size Functions</title>
     <tgroup cols="3">
@@ -9196,96 +9206,107 @@ SELECT set_config('log_statement_stats', 'off', false);
 
      <tbody>
       <row>
+       <entry><function>pg_column_size</function>(<parameter>any</parameter>)</entry>
+       <entry><type>integer</type></entry>
+       <entry>Number of bytes used to store a particular value (possibly compressed)</entry>
+      </row>
+      <row>
        <entry>
         <literal><function>pg_tablespace_size</function>(<parameter>oid</parameter>)</literal>
         </entry>
-       <entry><type>int8</type></entry>
-       <entry>Calculates the total disk space used by the tablespace with the specified OID</entry>
+       <entry><type>bigint</type></entry>
+       <entry>Total disk space used by the tablespace with the specified OID</entry>
       </row>
       <row>
        <entry>
         <literal><function>pg_tablespace_size</function>(<parameter>name</parameter>)</literal>
         </entry>
-       <entry><type>int8</type></entry>
-       <entry>Calculates the total disk space used by the tablespace with the specified name</entry>
+       <entry><type>bigint</type></entry>
+       <entry>Total disk space used by the tablespace with the specified name</entry>
       </row>
       <row>
        <entry>
         <literal><function>pg_database_size</function>(<parameter>oid</parameter>)</literal>
         </entry>
-       <entry><type>int8</type></entry>
-       <entry>Calculates the total disk space used by the database with the specified OID</entry>
+       <entry><type>bigint</type></entry>
+       <entry>Total disk space used by the database with the specified OID</entry>
       </row>
       <row>
        <entry>
         <literal><function>pg_database_size</function>(<parameter>name</parameter>)</literal>
         </entry>
-       <entry><type>int8</type></entry>
-       <entry>Calculates the total disk space used by the database with the specified name</entry>
+       <entry><type>bigint</type></entry>
+       <entry>Total disk space used by the database with the specified name</entry>
       </row>
       <row>
        <entry>
         <literal><function>pg_relation_size</function>(<parameter>oid</parameter>)</literal>
         </entry>
-       <entry><type>int8</type></entry>
-       <entry>Calculates the disk space used by the table or index with the specified OID</entry>
+       <entry><type>bigint</type></entry>
+       <entry>Disk space used by the table or index with the specified OID</entry>
       </row>
       <row>
        <entry>
         <literal><function>pg_relation_size</function>(<parameter>text</parameter>)</literal>
         </entry>
-       <entry><type>int8</type></entry>
-       <entry>Calculates the disk space used by the index or table with the specified name. 
-       The name may be prefixed with a schema name if required</entry>
+       <entry><type>bigint</type></entry>
+       <entry>Disk space used by the table or index with the specified name.
+       The name may be qualified with a schema name</entry>
       </row>
       <row>
        <entry>
         <literal><function>pg_complete_relation_size</function>(<parameter>oid</parameter>)</literal>
         </entry>
-       <entry><type>int8</type></entry>
-       <entry>Calculates the total disk space used by the table with the specified OID, 
+       <entry><type>bigint</type></entry>
+       <entry>Total disk space used by the table with the specified OID, 
        including indexes and toasted data</entry>
       </row>
       <row>
        <entry>
         <literal><function>pg_complete_relation_size</function>(<parameter>text</parameter>)</literal>
         </entry>
-       <entry><type>int8</type></entry>
-       <entry>Calculates the total disk space used by the table with the specified name, 
-       including indexes and toasted data. The name may be prefixed with a schema name if 
-       required</entry>
+       <entry><type>bigint</type></entry>
+       <entry>Total disk space used by the table with the specified name, 
+       including indexes and toasted data.
+       The table name may be qualified with a schema name</entry>
       </row>
       <row>
        <entry>
-        <literal><function>pg_size_pretty</function>(<parameter>int8</parameter>)</literal>
+        <literal><function>pg_size_pretty</function>(<parameter>bigint</parameter>)</literal>
         </entry>
        <entry><type>text</type></entry>
-       <entry>Formats the size value (in bytes) into a human readable format with size units </entry>
+       <entry>Converts a size in bytes into a human-readable format with size units</entry>
       </row>
      </tbody>
     </tgroup>
    </table>
 
    <para>
-    <function>pg_tablespace_size</> and <function>pg_database_size</> accept an 
-    oid or name of a tablespace or database, and return the disk space usage of the specified object. 
+    <function>pg_column_size</> shows the space used to store any individual
+    data value.
    </para>
 
-   <indexterm zone="functions-admin">
-    <primary>pg_relation_size</primary>
-   </indexterm>
    <para>
-    <function>pg_relation_size</> accepts the oid or name of a table, index or
+    <function>pg_tablespace_size</> and <function>pg_database_size</> accept
+    the OID or name of a tablespace or database, and return the total disk
+    space used therein.
+   </para>
+
+   <para>
+    <function>pg_relation_size</> accepts the OID or name of a table, index or
     toast table, and returns the size in bytes.
    </para>
+
    <para>
-    <function>pg_complete_relation_size</> accepts the oid or name of a table or
-    toast table, and returns the size in bytes of the data and all associated
-    indexes and toast tables.
+    <function>pg_complete_relation_size</> accepts the OID or name of a table
+    or toast table, and returns the size in bytes of the data and all
+    associated indexes and toast tables.
    </para>
+
    <para>
-    <function>pg_size_pretty</> can be used to format the size of the
-    database objects in a human readable way, using kB, MB, GB or TB as appropriate.
+    <function>pg_size_pretty</> can be used to format the result of one of
+    the other functions in a human-readable way, using kB, MB, GB or TB as
+    appropriate.
    </para>
 
   </sect1>
diff --git a/src/backend/access/heap/tuptoaster.c b/src/backend/access/heap/tuptoaster.c
index 77caf79dd19..5359f24fce2 100644
--- a/src/backend/access/heap/tuptoaster.c
+++ b/src/backend/access/heap/tuptoaster.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/heap/tuptoaster.c,v 1.50 2005/07/06 19:02:52 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/heap/tuptoaster.c,v 1.51 2005/08/02 16:11:57 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -268,6 +268,38 @@ toast_raw_datum_size(Datum value)
 	return result;
 }
 
+/* ----------
+ * toast_datum_size
+ *
+ *	Return the physical storage size (possibly compressed) of a varlena datum
+ * ----------
+ */
+Size 
+toast_datum_size(Datum value)
+{
+	varattrib	*attr = (varattrib *) DatumGetPointer(value);
+	Size		result;
+
+	if (VARATT_IS_EXTERNAL(attr))
+	{
+		/*
+		 * Attribute is stored externally - return the extsize whether
+		 * compressed or not.  We do not count the size of the toast
+		 * pointer ... should we?
+		 */
+		result = attr->va_content.va_external.va_extsize;
+	}
+	else
+	{
+		/*
+		 * Attribute is stored inline either compressed or not, just
+		 * calculate the size of the datum in either case.
+		 */
+		result = VARSIZE(attr);
+	}
+	return result;
+}
+
 
 /* ----------
  * toast_delete -
@@ -1436,45 +1468,3 @@ 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;
-	
-}
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index 9ea8a17b025..399da666130 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.130 2005/07/29 03:17:55 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.131 2005/08/02 16:11:57 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -2574,38 +2574,49 @@ md5_bytea(PG_FUNCTION_ARGS)
 }
 
 /* 
- * Return the length of a datum, possibly compressed
+ * Return the size of a datum, possibly compressed
+ *
+ * Works on any data type
  */
 Datum
 pg_column_size(PG_FUNCTION_ARGS)
 {
-	Datum			value = PG_GETARG_DATUM(0);
-	int				result;
+	Datum		value = PG_GETARG_DATUM(0);
+	int32		result;
+	int			typlen;
 
-	/*	fn_extra stores the fixed column length, or -1 for varlena. */
-	if (fcinfo->flinfo->fn_extra == NULL)	/* first call? */
+	/* On first call, get the input type's typlen, and save at *fn_extra */
+	if (fcinfo->flinfo->fn_extra == NULL)
 	{
-		/* On the first call lookup the datatype of the supplied argument */
-		Oid				argtypeid = get_fn_expr_argtype(fcinfo->flinfo, 0);
-		int				typlen    = get_typlen(argtypeid);
+		/* Lookup the datatype of the supplied argument */
+		Oid		argtypeid = get_fn_expr_argtype(fcinfo->flinfo, 0);
 
-		
-		if (typlen == 0)
-		{
-			/* Oid not in pg_type, should never happen. */
+		typlen = get_typlen(argtypeid);
+		if (typlen == 0)		/* should not happen */
 			elog(ERROR, "cache lookup failed for type %u", argtypeid);
-		}
 
 		fcinfo->flinfo->fn_extra = MemoryContextAlloc(fcinfo->flinfo->fn_mcxt,
 													  sizeof(int));
-		*(int *)fcinfo->flinfo->fn_extra = typlen;
+		*((int *) fcinfo->flinfo->fn_extra) = typlen;
 	}
+	else
+		typlen = *((int *) fcinfo->flinfo->fn_extra);
 
-	if (*(int *)fcinfo->flinfo->fn_extra != -1)
-		PG_RETURN_INT32(*(int *)fcinfo->flinfo->fn_extra);
+	if (typlen == -1)
+	{
+		/* varlena type, possibly toasted */
+		result = toast_datum_size(value);
+	}
+	else if (typlen == -2)
+	{
+		/* cstring */
+		result = strlen(DatumGetCString(value)) + 1;
+	}
 	else
 	{
-		result = toast_datum_size(value) - VARHDRSZ;
-		PG_RETURN_INT32(result);
+		/* ordinary fixed-width type */
+		result = typlen;
 	}
+
+	PG_RETURN_INT32(result);
 }
diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index 72e23c3f0b5..71f51172dc5 100644
--- a/src/include/catalog/pg_proc.h
+++ b/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 1.379 2005/07/29 14:47:01 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_proc.h,v 1.380 2005/08/02 16:11:57 tgl Exp $
  *
  * NOTES
  *	  The script catalog/genbki.sh reads this file and generates .bki
@@ -3701,7 +3701,7 @@ DATA(insert OID = 2560 (  pg_postmaster_start_time PGNSP PGUID 12 f f t f s 0 11
 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_ ));
+DATA(insert OID = 1269 (  pg_column_size	   PGNSP PGUID 12 f f t f s 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 */