Add hooks for type-specific calculation of ANALYZE statistics. Idea and

coding by Mark Cave-Ayland, some kibitzing by Tom Lane.  initdb forced
due to new column in pg_type.

doc/src/sgml/catalogs.sgml

 <!--
  Documentation of the system catalogs, directed toward PostgreSQL developers
- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.82 2004/01/06 23:55:18 tgl Exp $
+ $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.83 2004/02/12 23:41:00 tgl Exp $
  -->
 
 <chapter id="catalogs">
@@ -3524,6 +3524,13 @@
       <entry>Output conversion function (binary format), or 0 if none</entry>
      </row>
 
+     <row>
+      <entry><structfield>typanalyze</structfield></entry>
+      <entry><type>regproc</type></entry>
+      <entry><literal><link linkend="catalog-pg-proc"><structname>pg_proc</structname></link>.oid</literal></entry>
+      <entry>Custom ANALYZE function, or 0 to use the standard function</entry>
+     </row>
+
      <row>
       <entry><structfield>typalign</structfield></entry>
       <entry><type>char</type></entry>

doc/src/sgml/ref/create_type.sgml

 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/create_type.sgml,v 1.48 2003/11/29 19:51:38 pgsql Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/create_type.sgml,v 1.49 2004/02/12 23:41:02 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -28,6 +28,7 @@ CREATE TYPE <replaceable class="parameter">name</replaceable> (
     OUTPUT = <replaceable class="parameter">output_function</replaceable>
     [ , RECEIVE = <replaceable class="parameter">receive_function</replaceable> ]
     [ , SEND = <replaceable class="parameter">send_function</replaceable> ]
+    [ , ANALYZE = <replaceable class="parameter">analyze_function</replaceable> ]
     [ , INTERNALLENGTH = { <replaceable class="parameter">internallength</replaceable> | VARIABLE } ]
     [ , PASSEDBYVALUE ]
     [ , ALIGNMENT = <replaceable class="parameter">alignment</replaceable> ]
@@ -83,8 +84,9 @@ CREATE TYPE <replaceable class="parameter">name</replaceable> (
    <replaceable class="parameter">input_function</replaceable> and
    <replaceable class="parameter">output_function</replaceable>
    are required, while the functions
-   <replaceable class="parameter">receive_function</replaceable> and
-   <replaceable class="parameter">send_function</replaceable>
+   <replaceable class="parameter">receive_function</replaceable>,
+   <replaceable class="parameter">send_function</replaceable> and
+   <replaceable class="parameter">analyze_function</replaceable>
    are optional.  Generally these functions have to be coded in C
    or another low-level language.
   </para>
@@ -152,6 +154,19 @@ CREATE TYPE <replaceable class="parameter">name</replaceable> (
    shell entry with a complete type definition, and the new type can be used.
   </para>
 
+  <para>
+   The optional <replaceable class="parameter">analyze_function</replaceable>
+   performs type-specific statistics collection for columns of the data type.
+   By default, <command>ANALYZE</> will attempt to gather statistics using
+   the type's <quote>equals</> and <quote>less-than</> operators, if there
+   is a default b-tree operator class for the type.  For non-scalar types
+   this behavior is likely to be unsuitable, so it can be overridden by
+   specifying a custom analysis function.  The analysis function must be
+   declared to take a single argument of type <type>internal</>, and return
+   a <type>boolean</> result.  The detailed API for analysis functions appears
+   in <filename>src/include/commands/vacuum.h</>.
+  </para>
+
   <para>
    While the details of the new type's internal representation are only
    known to the I/O functions and other functions you create to work with
@@ -341,6 +356,16 @@ CREATE TYPE <replaceable class="parameter">name</replaceable> (
     </listitem>
    </varlistentry>
 
+   <varlistentry>
+    <term><replaceable class="parameter">analyze_function</replaceable></term>
+    <listitem>
+     <para>
+      The name of a function that performs statistical analysis for the
+      data type.
+     </para>
+    </listitem>
+   </varlistentry>
+
    <varlistentry>
     <term><replaceable class="parameter">internallength</replaceable></term>
     <listitem>

src/backend/catalog/heap.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/catalog/heap.c,v 1.258 2004/02/10 01:55:24 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/catalog/heap.c,v 1.259 2004/02/12 23:41:02 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -689,6 +689,7 @@ AddNewRelationType(const char *typeName,
 			   F_RECORD_OUT,	/* output procedure */
 			   F_RECORD_RECV,	/* receive procedure */
 			   F_RECORD_SEND,	/* send procedure */
+			   InvalidOid,		/* analyze procedure - default */
 			   InvalidOid,		/* array element type - irrelevant */
 			   InvalidOid,		/* domain base type - irrelevant */
 			   NULL,			/* default type value - none */

src/backend/catalog/pg_type.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/catalog/pg_type.c,v 1.92 2004/01/07 18:56:25 neilc Exp $
+ *	  $PostgreSQL: pgsql/src/backend/catalog/pg_type.c,v 1.93 2004/02/12 23:41:02 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -86,6 +86,7 @@ TypeShellMake(const char *typeName, Oid typeNamespace)
 	values[i++] = ObjectIdGetDatum(InvalidOid); /* typoutput */
 	values[i++] = ObjectIdGetDatum(InvalidOid); /* typreceive */
 	values[i++] = ObjectIdGetDatum(InvalidOid); /* typsend */
+	values[i++] = ObjectIdGetDatum(InvalidOid); /* typanalyze */
 	values[i++] = CharGetDatum('i');	/* typalign */
 	values[i++] = CharGetDatum('p');	/* typstorage */
 	values[i++] = BoolGetDatum(false);	/* typnotnull */
@@ -121,6 +122,7 @@ TypeShellMake(const char *typeName, Oid typeNamespace)
 								 InvalidOid,
 								 InvalidOid,
 								 InvalidOid,
+								 InvalidOid,
 								 NULL,
 								 false);
 
@@ -157,6 +159,7 @@ TypeCreate(const char *typeName,
 		   Oid outputProcedure,
 		   Oid receiveProcedure,
 		   Oid sendProcedure,
+		   Oid analyzeProcedure,
 		   Oid elementType,
 		   Oid baseType,
 		   const char *defaultTypeValue,		/* human readable rep */
@@ -236,6 +239,7 @@ TypeCreate(const char *typeName,
 	values[i++] = ObjectIdGetDatum(outputProcedure);	/* typoutput */
 	values[i++] = ObjectIdGetDatum(receiveProcedure);	/* typreceive */
 	values[i++] = ObjectIdGetDatum(sendProcedure);		/* typsend */
+	values[i++] = ObjectIdGetDatum(analyzeProcedure);	/* typanalyze */
 	values[i++] = CharGetDatum(alignment);		/* typalign */
 	values[i++] = CharGetDatum(storage);		/* typstorage */
 	values[i++] = BoolGetDatum(typeNotNull);	/* typnotnull */
@@ -332,6 +336,7 @@ TypeCreate(const char *typeName,
 								 outputProcedure,
 								 receiveProcedure,
 								 sendProcedure,
+								 analyzeProcedure,
 								 elementType,
 								 baseType,
 								 (defaultTypeBin ?
@@ -366,6 +371,7 @@ GenerateTypeDependencies(Oid typeNamespace,
 						 Oid outputProcedure,
 						 Oid receiveProcedure,
 						 Oid sendProcedure,
+						 Oid analyzeProcedure,
 						 Oid elementType,
 						 Oid baseType,
 						 Node *defaultExpr,
@@ -425,6 +431,14 @@ GenerateTypeDependencies(Oid typeNamespace,
 		recordDependencyOn(&myself, &referenced, DEPENDENCY_NORMAL);
 	}
 
+	if (OidIsValid(analyzeProcedure))
+	{
+		referenced.classId = RelOid_pg_proc;
+		referenced.objectId = analyzeProcedure;
+		referenced.objectSubId = 0;
+		recordDependencyOn(&myself, &referenced, DEPENDENCY_NORMAL);
+	}
+
 	/*
 	 * If the type is a rowtype for a relation, mark it as internally
 	 * dependent on the relation, *unless* it is a stand-alone composite

src/backend/commands/typecmds.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/typecmds.c,v 1.52 2004/01/10 23:28:44 neilc Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/typecmds.c,v 1.53 2004/02/12 23:41:02 tgl Exp $
  *
  * DESCRIPTION
  *	  The "DefineFoo" routines take the parse tree and pick out the
@@ -77,6 +77,7 @@ static Oid	findTypeInputFunction(List *procname, Oid typeOid);
 static Oid	findTypeOutputFunction(List *procname, Oid typeOid);
 static Oid	findTypeReceiveFunction(List *procname, Oid typeOid);
 static Oid	findTypeSendFunction(List *procname, Oid typeOid);
+static Oid	findTypeAnalyzeFunction(List *procname, Oid typeOid);
 static List *get_rels_with_domain(Oid domainOid, LOCKMODE lockmode);
 static void domainOwnerCheck(HeapTuple tup, TypeName *typename);
 static char *domainAddConstraint(Oid domainOid, Oid domainNamespace,
@@ -101,6 +102,7 @@ DefineType(List *names, List *parameters)
 	List	   *outputName = NIL;
 	List	   *receiveName = NIL;
 	List	   *sendName = NIL;
+	List	   *analyzeName = NIL;
 	char	   *defaultValue = NULL;
 	bool		byValue = false;
 	char		delimiter = DEFAULT_TYPDELIM;
@@ -110,6 +112,7 @@ DefineType(List *names, List *parameters)
 	Oid			outputOid;
 	Oid			receiveOid = InvalidOid;
 	Oid			sendOid = InvalidOid;
+	Oid			analyzeOid = InvalidOid;
 	char	   *shadow_type;
 	List	   *pl;
 	Oid			typoid;
@@ -151,6 +154,9 @@ DefineType(List *names, List *parameters)
 			receiveName = defGetQualifiedName(defel);
 		else if (strcasecmp(defel->defname, "send") == 0)
 			sendName = defGetQualifiedName(defel);
+		else if (strcasecmp(defel->defname, "analyze") == 0 ||
+				 strcasecmp(defel->defname, "analyse") == 0)
+			analyzeName = defGetQualifiedName(defel);
 		else if (strcasecmp(defel->defname, "delimiter") == 0)
 		{
 			char	   *p = defGetString(defel);
@@ -318,6 +324,13 @@ DefineType(List *names, List *parameters)
 							NameListToString(sendName))));
 	}
 
+	/*
+	 * Convert analysis function proc name to an OID. If no analysis function
+	 * is specified, we'll use zero to select the built-in default algorithm.
+	 */
+	if (analyzeName)
+		analyzeOid = findTypeAnalyzeFunction(analyzeName, typoid);
+
 	/*
 	 * now have TypeCreate do all the real work.
 	 */
@@ -334,6 +347,7 @@ DefineType(List *names, List *parameters)
 				   outputOid,	/* output procedure */
 				   receiveOid,	/* receive procedure */
 				   sendOid,		/* send procedure */
+				   analyzeOid,	/* analyze procedure */
 				   elemType,	/* element type ID */
 				   InvalidOid,	/* base type ID (only for domains) */
 				   defaultValue,	/* default type value */
@@ -366,6 +380,7 @@ DefineType(List *names, List *parameters)
 			   F_ARRAY_OUT,		/* output procedure */
 			   F_ARRAY_RECV,	/* receive procedure */
 			   F_ARRAY_SEND,	/* send procedure */
+			   InvalidOid,		/* analyze procedure - default */
 			   typoid,			/* element type ID */
 			   InvalidOid,		/* base type ID */
 			   NULL,			/* never a default type value */
@@ -473,6 +488,7 @@ DefineDomain(CreateDomainStmt *stmt)
 	Oid			outputProcedure;
 	Oid			receiveProcedure;
 	Oid			sendProcedure;
+	Oid			analyzeProcedure;
 	bool		byValue;
 	char		delimiter;
 	char		alignment;
@@ -562,6 +578,9 @@ DefineDomain(CreateDomainStmt *stmt)
 	receiveProcedure = baseType->typreceive;
 	sendProcedure = baseType->typsend;
 
+	/* Analysis function */
+	analyzeProcedure = baseType->typanalyze;
+
 	/* Inherited default value */
 	datum = SysCacheGetAttr(TYPEOID, typeTup,
 							Anum_pg_type_typdefault, &isnull);
@@ -714,6 +733,7 @@ DefineDomain(CreateDomainStmt *stmt)
 				   outputProcedure,		/* output procedure */
 				   receiveProcedure,	/* receive procedure */
 				   sendProcedure,		/* send procedure */
+				   analyzeProcedure,	/* analyze procedure */
 				   basetypelem, /* element type ID */
 				   basetypeoid, /* base type ID */
 				   defaultValue,	/* default type value (text) */
@@ -1033,6 +1053,35 @@ findTypeSendFunction(List *procname, Oid typeOid)
 	return InvalidOid;			/* keep compiler quiet */
 }
 
+static Oid
+findTypeAnalyzeFunction(List *procname, Oid typeOid)
+{
+	Oid			argList[FUNC_MAX_ARGS];
+	Oid			procOid;
+
+	/*
+	 * Analyze functions always take one INTERNAL argument and return bool.
+	 */
+	MemSet(argList, 0, FUNC_MAX_ARGS * sizeof(Oid));
+
+	argList[0] = INTERNALOID;
+
+	procOid = LookupFuncName(procname, 1, argList, true);
+	if (!OidIsValid(procOid))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_FUNCTION),
+				 errmsg("function %s does not exist",
+						func_signature_string(procname, 1, argList))));
+
+	if (get_func_rettype(procOid) != BOOLOID)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
+				 errmsg("type analyze function %s must return type \"boolean\"",
+						NameListToString(procname))));
+
+	return procOid;
+}
+
 
 /*-------------------------------------------------------------------
  * DefineCompositeType
@@ -1192,6 +1241,7 @@ AlterDomainDefault(List *names, Node *defaultRaw)
 							 typTup->typoutput,
 							 typTup->typreceive,
 							 typTup->typsend,
+							 typTup->typanalyze,
 							 typTup->typelem,
 							 typTup->typbasetype,
 							 defaultExpr,

src/bin/pg_dump/pg_dump.c

@@ -12,7 +12,7 @@
  *	by PostgreSQL
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.c,v 1.363 2004/01/22 19:09:32 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.c,v 1.364 2004/02/12 23:41:03 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1648,9 +1648,9 @@ getTypes(int *numTypes)
 
 		/*
 		 * Make sure there are dependencies from the type to its input and
-		 * output functions.  (We don't worry about typsend/typreceive since
-		 * those are only valid in 7.4 and later, wherein the standard
-		 * dependency mechanism will pick them up.)
+		 * output functions.  (We don't worry about typsend, typreceive, or
+		 * typanalyze since those are only valid in 7.4 and later, wherein
+		 * the standard dependency mechanism will pick them up.)
 		 */
 		funcInfo = findFuncByOid(tinfo[i].typinput);
 		if (funcInfo)
@@ -4148,10 +4148,12 @@ dumpBaseType(Archive *fout, TypeInfo *tinfo)
 	char	   *typoutput;
 	char	   *typreceive;
 	char	   *typsend;
+	char	   *typanalyze;
 	Oid			typinputoid;
 	Oid			typoutputoid;
 	Oid			typreceiveoid;
 	Oid			typsendoid;
+	Oid			typanalyzeoid;
 	char	   *typdelim;
 	char	   *typdefault;
 	char	   *typbyval;
@@ -4162,14 +4164,32 @@ dumpBaseType(Archive *fout, TypeInfo *tinfo)
 	selectSourceSchema(tinfo->typnamespace->nspname);
 
 	/* Fetch type-specific details */
-	if (fout->remoteVersion >= 70400)
+	if (fout->remoteVersion >= 70500)
 	{
 		appendPQExpBuffer(query, "SELECT typlen, "
 						  "typinput, typoutput, typreceive, typsend, "
+						  "typanalyze, "
 						  "typinput::pg_catalog.oid as typinputoid, "
 						  "typoutput::pg_catalog.oid as typoutputoid, "
 						  "typreceive::pg_catalog.oid as typreceiveoid, "
 						  "typsend::pg_catalog.oid as typsendoid, "
+						  "typanalyze::pg_catalog.oid as typanalyzeoid, "
+						  "typdelim, typdefault, typbyval, typalign, "
+						  "typstorage "
+						  "FROM pg_catalog.pg_type "
+						  "WHERE oid = '%u'::pg_catalog.oid",
+						  tinfo->dobj.catId.oid);
+	}
+	else if (fout->remoteVersion >= 70400)
+	{
+		appendPQExpBuffer(query, "SELECT typlen, "
+						  "typinput, typoutput, typreceive, typsend, "
+						  "'-' as typanalyze, "
+						  "typinput::pg_catalog.oid as typinputoid, "
+						  "typoutput::pg_catalog.oid as typoutputoid, "
+						  "typreceive::pg_catalog.oid as typreceiveoid, "
+						  "typsend::pg_catalog.oid as typsendoid, "
+						  "0 as typanalyzeoid, "
 						  "typdelim, typdefault, typbyval, typalign, "
 						  "typstorage "
 						  "FROM pg_catalog.pg_type "
@@ -4181,9 +4201,11 @@ dumpBaseType(Archive *fout, TypeInfo *tinfo)
 		appendPQExpBuffer(query, "SELECT typlen, "
 						  "typinput, typoutput, "
 						  "'-' as typreceive, '-' as typsend, "
+						  "'-' as typanalyze, "
 						  "typinput::pg_catalog.oid as typinputoid, "
 						  "typoutput::pg_catalog.oid as typoutputoid, "
 						  "0 as typreceiveoid, 0 as typsendoid, "
+						  "0 as typanalyzeoid, "
 						  "typdelim, typdefault, typbyval, typalign, "
 						  "typstorage "
 						  "FROM pg_catalog.pg_type "
@@ -4199,9 +4221,11 @@ dumpBaseType(Archive *fout, TypeInfo *tinfo)
 		appendPQExpBuffer(query, "SELECT typlen, "
 						  "typinput, typoutput, "
 						  "'-' as typreceive, '-' as typsend, "
+						  "'-' as typanalyze, "
 						  "typinput::oid as typinputoid, "
 						  "typoutput::oid as typoutputoid, "
 						  "0 as typreceiveoid, 0 as typsendoid, "
+						  "0 as typanalyzeoid, "
 						  "typdelim, typdefault, typbyval, typalign, "
 						  "typstorage "
 						  "FROM pg_type "
@@ -4213,9 +4237,11 @@ dumpBaseType(Archive *fout, TypeInfo *tinfo)
 		appendPQExpBuffer(query, "SELECT typlen, "
 						  "typinput, typoutput, "
 						  "'-' as typreceive, '-' as typsend, "
+						  "'-' as typanalyze, "
 						  "typinput::oid as typinputoid, "
 						  "typoutput::oid as typoutputoid, "
 						  "0 as typreceiveoid, 0 as typsendoid, "
+						  "0 as typanalyzeoid, "
 						  "typdelim, typdefault, typbyval, typalign, "
 						  "'p'::char as typstorage "
 						  "FROM pg_type "
@@ -4240,10 +4266,12 @@ dumpBaseType(Archive *fout, TypeInfo *tinfo)
 	typoutput = PQgetvalue(res, 0, PQfnumber(res, "typoutput"));
 	typreceive = PQgetvalue(res, 0, PQfnumber(res, "typreceive"));
 	typsend = PQgetvalue(res, 0, PQfnumber(res, "typsend"));
+	typanalyze = PQgetvalue(res, 0, PQfnumber(res, "typanalyze"));
 	typinputoid = atooid(PQgetvalue(res, 0, PQfnumber(res, "typinputoid")));
 	typoutputoid = atooid(PQgetvalue(res, 0, PQfnumber(res, "typoutputoid")));
 	typreceiveoid = atooid(PQgetvalue(res, 0, PQfnumber(res, "typreceiveoid")));
 	typsendoid = atooid(PQgetvalue(res, 0, PQfnumber(res, "typsendoid")));
+	typanalyzeoid = atooid(PQgetvalue(res, 0, PQfnumber(res, "typanalyzeoid")));
 	typdelim = PQgetvalue(res, 0, PQfnumber(res, "typdelim"));
 	if (PQgetisnull(res, 0, PQfnumber(res, "typdefault")))
 		typdefault = NULL;
@@ -4270,13 +4298,15 @@ dumpBaseType(Archive *fout, TypeInfo *tinfo)
 
 	if (fout->remoteVersion >= 70300)
 	{
-		/* regproc result is correctly quoted in 7.3 */
+		/* regproc result is correctly quoted as of 7.3 */
 		appendPQExpBuffer(q, ",\n    INPUT = %s", typinput);
 		appendPQExpBuffer(q, ",\n    OUTPUT = %s", typoutput);
 		if (OidIsValid(typreceiveoid))
 			appendPQExpBuffer(q, ",\n    RECEIVE = %s", typreceive);
 		if (OidIsValid(typsendoid))
 			appendPQExpBuffer(q, ",\n    SEND = %s", typsend);
+		if (OidIsValid(typanalyzeoid))
+			appendPQExpBuffer(q, ",\n    ANALYZE = %s", typanalyze);
 	}
 	else
 	{
@@ -4284,7 +4314,7 @@ dumpBaseType(Archive *fout, TypeInfo *tinfo)
 		/* cannot combine these because fmtId uses static result area */
 		appendPQExpBuffer(q, ",\n    INPUT = %s", fmtId(typinput));
 		appendPQExpBuffer(q, ",\n    OUTPUT = %s", fmtId(typoutput));
-		/* no chance that receive/send need be printed */
+		/* no chance that receive/send/analyze need be printed */
 	}
 
 	if (typdefault != NULL)

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.217 2004/02/03 08:29:56 joe Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.218 2004/02/12 23:41:03 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200402021
+#define CATALOG_VERSION_NO	200402121
 
 #endif

src/include/catalog/pg_attribute.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_attribute.h,v 1.107 2004/01/06 23:55:19 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_attribute.h,v 1.108 2004/02/12 23:41:04 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -240,14 +240,15 @@ typedef FormData_pg_attribute *Form_pg_attribute;
 { 1247, {"typoutput"},	   24, -1,	4, 12, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
 { 1247, {"typreceive"},    24, -1,	4, 13, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
 { 1247, {"typsend"},	   24, -1,	4, 14, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
-{ 1247, {"typalign"},	   18, -1,	1, 15, 0, -1, -1, true, 'p', false, 'c', true, false, false, true, 0 }, \
-{ 1247, {"typstorage"},    18, -1,	1, 16, 0, -1, -1, true, 'p', false, 'c', true, false, false, true, 0 }, \
-{ 1247, {"typnotnull"},    16, -1,	1, 17, 0, -1, -1, true, 'p', false, 'c', true, false, false, true, 0 }, \
-{ 1247, {"typbasetype"},   26, -1,	4, 18, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
-{ 1247, {"typtypmod"},	   23, -1,	4, 19, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
-{ 1247, {"typndims"},	   23, -1,	4, 20, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
-{ 1247, {"typdefaultbin"}, 25, -1, -1, 21, 0, -1, -1, false, 'x', false, 'i', false, false, false, true, 0 }, \
-{ 1247, {"typdefault"},    25, -1, -1, 22, 0, -1, -1, false, 'x', false, 'i', false, false, false, true, 0 }
+{ 1247, {"typanalyze"},	   24, -1,	4, 15, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
+{ 1247, {"typalign"},	   18, -1,	1, 16, 0, -1, -1, true, 'p', false, 'c', true, false, false, true, 0 }, \
+{ 1247, {"typstorage"},    18, -1,	1, 17, 0, -1, -1, true, 'p', false, 'c', true, false, false, true, 0 }, \
+{ 1247, {"typnotnull"},    16, -1,	1, 18, 0, -1, -1, true, 'p', false, 'c', true, false, false, true, 0 }, \
+{ 1247, {"typbasetype"},   26, -1,	4, 19, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
+{ 1247, {"typtypmod"},	   23, -1,	4, 20, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
+{ 1247, {"typndims"},	   23, -1,	4, 21, 0, -1, -1, true, 'p', false, 'i', true, false, false, true, 0 }, \
+{ 1247, {"typdefaultbin"}, 25, -1, -1, 22, 0, -1, -1, false, 'x', false, 'i', false, false, false, true, 0 }, \
+{ 1247, {"typdefault"},    25, -1, -1, 23, 0, -1, -1, false, 'x', false, 'i', false, false, false, true, 0 }
 
 
 DATA(insert ( 1247 typname			19 -1 NAMEDATALEN	1 0 -1 -1 f p f i t f f t 0));
@@ -264,14 +265,15 @@ DATA(insert ( 1247 typinput			24 -1 4  11 0 -1 -1 t p f i t f f t 0));
 DATA(insert ( 1247 typoutput		24 -1 4  12 0 -1 -1 t p f i t f f t 0));
 DATA(insert ( 1247 typreceive		24 -1 4  13 0 -1 -1 t p f i t f f t 0));
 DATA(insert ( 1247 typsend			24 -1 4  14 0 -1 -1 t p f i t f f t 0));
-DATA(insert ( 1247 typalign			18 -1 1  15 0 -1 -1 t p f c t f f t 0));
-DATA(insert ( 1247 typstorage		18 -1 1  16 0 -1 -1 t p f c t f f t 0));
-DATA(insert ( 1247 typnotnull		16 -1 1  17 0 -1 -1 t p f c t f f t 0));
-DATA(insert ( 1247 typbasetype		26 -1 4  18 0 -1 -1 t p f i t f f t 0));
-DATA(insert ( 1247 typtypmod		23 -1 4  19 0 -1 -1 t p f i t f f t 0));
-DATA(insert ( 1247 typndims			23 -1 4  20 0 -1 -1 t p f i t f f t 0));
-DATA(insert ( 1247 typdefaultbin	25 -1 -1 21 0 -1 -1 f x f i f f f t 0));
-DATA(insert ( 1247 typdefault		25 -1 -1 22 0 -1 -1 f x f i f f f t 0));
+DATA(insert ( 1247 typanalyze		24 -1 4  15 0 -1 -1 t p f i t f f t 0));
+DATA(insert ( 1247 typalign			18 -1 1  16 0 -1 -1 t p f c t f f t 0));
+DATA(insert ( 1247 typstorage		18 -1 1  17 0 -1 -1 t p f c t f f t 0));
+DATA(insert ( 1247 typnotnull		16 -1 1  18 0 -1 -1 t p f c t f f t 0));
+DATA(insert ( 1247 typbasetype		26 -1 4  19 0 -1 -1 t p f i t f f t 0));
+DATA(insert ( 1247 typtypmod		23 -1 4  20 0 -1 -1 t p f i t f f t 0));
+DATA(insert ( 1247 typndims			23 -1 4  21 0 -1 -1 t p f i t f f t 0));
+DATA(insert ( 1247 typdefaultbin	25 -1 -1 22 0 -1 -1 f x f i f f f t 0));
+DATA(insert ( 1247 typdefault		25 -1 -1 23 0 -1 -1 f x f i f f f t 0));
 DATA(insert ( 1247 ctid				27 0  6  -1 0 -1 -1 f p f i t f f t 0));
 DATA(insert ( 1247 oid				26 0  4  -2 0 -1 -1 t p f i t f f t 0));
 DATA(insert ( 1247 xmin				28 0  4  -3 0 -1 -1 t p f i t f f t 0));

src/include/catalog/pg_class.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_class.h,v 1.79 2004/01/06 23:55:19 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_class.h,v 1.80 2004/02/12 23:41:04 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -134,7 +134,7 @@ typedef FormData_pg_class *Form_pg_class;
  * ----------------
  */
 
-DATA(insert OID = 1247 (  pg_type		PGNSP 71 PGUID 0 1247 0 0 0 0 f f r 22 0 0 0 0 0 t f f f _null_ ));
+DATA(insert OID = 1247 (  pg_type		PGNSP 71 PGUID 0 1247 0 0 0 0 f f r 23 0 0 0 0 0 t f f f _null_ ));
 DESCR("");
 DATA(insert OID = 1249 (  pg_attribute	PGNSP 75 PGUID 0 1249 0 0 0 0 f f r 18 0 0 0 0 0 f f f f _null_ ));
 DESCR("");

src/include/catalog/pg_statistic.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_statistic.h,v 1.23 2003/11/29 22:40:58 pgsql Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_statistic.h,v 1.24 2004/02/12 23:41:04 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -164,11 +164,30 @@ typedef FormData_pg_statistic *Form_pg_statistic;
 /*
  * Currently, three statistical slot "kinds" are defined: most common values,
  * histogram, and correlation.	Additional "kinds" will probably appear in
- * future to help cope with non-scalar datatypes.
+ * future to help cope with non-scalar datatypes.  Also, custom data types
+ * can define their own "kind" codes by mutual agreement between a custom
+ * typanalyze routine and the selectivity estimation functions of the type's
+ * operators.
  *
  * Code reading the pg_statistic relation should not assume that a particular
  * data "kind" will appear in any particular slot.	Instead, search the
- * stakind fields to see if the desired data is available.
+ * stakind fields to see if the desired data is available.  (The standard
+ * function get_attstatsslot() may be used for this.)
+ */
+
+/*
+ * The present allocation of "kind" codes is:
+ *
+ *	1-99:		reserved for assignment by the core PostgreSQL project
+ *				(values in this range will be documented in this file)
+ *	100-199:	reserved for assignment by the PostGIS project
+ *				(values to be documented in PostGIS documentation)
+ *	200-9999:	reserved for future public assignments
+ *
+ * For private use you may choose a "kind" code at random in the range
+ * 10000-30000.  However, for code that is to be widely disseminated it is
+ * better to obtain a publicly defined "kind" code by request from the
+ * PostgreSQL Global Development Group.
  */
 
 /*

src/include/commands/vacuum.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/commands/vacuum.h,v 1.48 2004/02/10 03:42:45 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/commands/vacuum.h,v 1.49 2004/02/12 23:41:04 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -23,10 +23,86 @@
 #include "rusagestub.h"
 #endif
 
+#include "access/htup.h"
+#include "catalog/pg_attribute.h"
+#include "catalog/pg_statistic.h"
+#include "catalog/pg_type.h"
 #include "nodes/parsenodes.h"
 #include "utils/rel.h"
 
 
+/*----------
+ * ANALYZE builds one of these structs for each attribute (column) that is
+ * to be analyzed.  The struct and subsidiary data are in anl_context,
+ * so they live until the end of the ANALYZE operation.
+ *
+ * The type-specific typanalyze function is passed a pointer to this struct
+ * and must return TRUE to continue analysis, FALSE to skip analysis of this
+ * column.  In the TRUE case it must set the compute_stats and minrows fields,
+ * and can optionally set extra_data to pass additional info to compute_stats.
+ *
+ * The compute_stats routine will be called after sample rows have been
+ * gathered.  Aside from this struct, it is passed:
+ *		attnum: attribute number within the supplied tuples
+ *		tupDesc: tuple descriptor for the supplied tuples
+ *		totalrows: estimated total number of rows in relation
+ *		rows: an array of the sample tuples
+ *		numrows: the number of sample tuples
+ * Note that the passed attnum and tupDesc could possibly be different from
+ * what one would expect by looking at the pg_attribute row.  It is important
+ * to use these values for extracting attribute values from the given rows
+ * (and not for any other purpose).
+ *
+ * compute_stats should set stats_valid TRUE if it is able to compute
+ * any useful statistics.  If it does, the remainder of the struct holds
+ * the information to be stored in a pg_statistic row for the column.  Be
+ * careful to allocate any pointed-to data in anl_context, which will NOT
+ * be CurrentMemoryContext when compute_stats is called.
+ *----------
+ */
+typedef struct VacAttrStats
+{
+	/*
+	 * These fields are set up by the main ANALYZE code before invoking
+	 * the type-specific typanalyze function.
+	 */
+	Form_pg_attribute attr;		/* copy of pg_attribute row for column */
+	Form_pg_type attrtype;		/* copy of pg_type row for column */
+	MemoryContext anl_context;	/* where to save long-lived data */
+
+	/*
+	 * These fields must be filled in by the typanalyze routine,
+	 * unless it returns FALSE.
+	 */
+	void (*compute_stats) (struct VacAttrStats *stats, int attnum,
+						   TupleDesc tupDesc, double totalrows,
+						   HeapTuple *rows, int numrows);
+	int			minrows;		/* Minimum # of rows wanted for stats */
+	void	   *extra_data;		/* for extra type-specific data */
+
+	/*
+	 * These fields are to be filled in by the compute_stats routine.
+	 * (They are initialized to zero when the struct is created.)
+	 */
+	bool		stats_valid;
+	float4		stanullfrac;	/* fraction of entries that are NULL */
+	int4		stawidth;		/* average width of column values */
+	float4		stadistinct;	/* # distinct values */
+	int2		stakind[STATISTIC_NUM_SLOTS];
+	Oid			staop[STATISTIC_NUM_SLOTS];
+	int			numnumbers[STATISTIC_NUM_SLOTS];
+	float4	   *stanumbers[STATISTIC_NUM_SLOTS];
+	int			numvalues[STATISTIC_NUM_SLOTS];
+	Datum	   *stavalues[STATISTIC_NUM_SLOTS];
+
+	/*
+	 * These fields are private to the main ANALYZE code and should not
+	 * be looked at by type-specific functions.
+	 */
+	int			tupattnum;		/* attribute number within tuples */
+} VacAttrStats;
+
+
 /* State structure for vac_init_rusage/vac_show_rusage */
 typedef struct VacRUsage
 {