Use symbolic references for pg_language OIDs in the bootstrap data.

This patch teaches genbki.pl to replace pg_language names by OIDs
in much the same way as it already does for pg_am names etc, and
converts pg_proc.dat to use such symbolic references in the prolang
column.

Aside from getting rid of a few more magic numbers in the initial
catalog data, this means that Gen_fmgrtab.pl no longer needs to read
pg_language.dat, since it doesn't have to know the OID of the "internal"
language; now it's just looking for the string "internal".

No need for a catversion bump, since the contents of postgres.bki
don't actually change at all.

John Naylor

Discussion: https://postgr.es/m/CAJVSVGWtUqxpfAaxS88vEGvi+jKzWZb2EStu5io-UPc4p9rSJg@mail.gmail.com

doc/src/sgml/bki.sgml

@@ -409,8 +409,9 @@
     that's error-prone and hard to understand, so for frequently-referenced
     catalogs, <filename>genbki.pl</filename> provides mechanisms to write
     symbolic references instead.  Currently this is possible for references
-    to access methods, functions, operators, opclasses, opfamilies, and
-    types.  The rules are as follows:
+    to access methods, functions, languages,
+    operators, opclasses, opfamilies, and types.
+    The rules are as follows:
    </para>
 
    <itemizedlist>
@@ -421,6 +422,7 @@
       by attaching <literal>BKI_LOOKUP(<replaceable>lookuprule</replaceable>)</literal>
       to the column's definition, where <replaceable>lookuprule</replaceable>
       is <literal>pg_am</literal>, <literal>pg_proc</literal>,
+      <literal>pg_language</literal>,
       <literal>pg_operator</literal>, <literal>pg_opclass</literal>,
       <literal>pg_opfamily</literal>, or <literal>pg_type</literal>.
       <literal>BKI_LOOKUP</literal> can be attached to columns of

src/backend/catalog/genbki.pl

@@ -178,13 +178,20 @@ my $PG_CATALOG_NAMESPACE =
 # Build lookup tables for OID macro substitutions and for pg_attribute
 # copies of pg_type values.
 
-# index access method OID lookup
+# access method OID lookup
 my %amoids;
 foreach my $row (@{ $catalog_data{pg_am} })
 {
 	$amoids{ $row->{amname} } = $row->{oid};
 }
 
+# language OID lookup
+my %langoids;
+foreach my $row (@{ $catalog_data{pg_language} })
+{
+	$langoids{ $row->{lanname} } = $row->{oid};
+}
+
 # opclass OID lookup
 my %opcoids;
 foreach my $row (@{ $catalog_data{pg_opclass} })
@@ -259,6 +266,7 @@ foreach my $row (@{ $catalog_data{pg_type} })
 # Map catalog name to OID lookup.
 my %lookup_kind = (
 	pg_am       => \%amoids,
+	pg_language => \%langoids,
 	pg_opclass  => \%opcoids,
 	pg_operator => \%operoids,
 	pg_opfamily => \%opfoids,

src/backend/utils/Gen_fmgrtab.pl

@@ -59,6 +59,8 @@ die "No include path; you must specify -I.\n" if !$include_path;
 # Note: We pass data file names as arguments and then look for matching
 # headers to parse the schema from. This is backwards from genbki.pl,
 # but the Makefile dependencies look more sensible this way.
+# We currently only need pg_proc, but retain the possibility of reading
+# more than one data file.
 my %catalogs;
 my %catalog_data;
 foreach my $datfile (@input_files)
@@ -82,9 +84,6 @@ foreach my $datfile (@input_files)
 my $FirstGenbkiObjectId =
   Catalog::FindDefinedSymbol('access/transam.h', $include_path,
 	'FirstGenbkiObjectId');
-my $INTERNALlanguageId =
-  Catalog::FindDefinedSymbolFromData($catalog_data{pg_language},
-	'INTERNALlanguageId');
 
 # Collect certain fields from pg_proc.dat.
 my @fmgr = ();
@@ -94,7 +93,7 @@ foreach my $row (@{ $catalog_data{pg_proc} })
 	my %bki_values = %$row;
 
 	# Select out just the rows for internal-language procedures.
-	next if $bki_values{prolang} ne $INTERNALlanguageId;
+	next if $bki_values{prolang} ne 'internal';
 
 	push @fmgr,
 	  {

src/backend/utils/Makefile

@@ -31,15 +31,11 @@ generated-header-symlinks: $(top_builddir)/src/include/utils/header-stamp $(top_
 
 $(SUBDIRS:%=%-recursive): fmgr-stamp errcodes.h
 
-FMGR_DATA := $(addprefix $(top_srcdir)/src/include/catalog/,\
-	pg_language.dat pg_proc.dat \
-	)
-
 # fmgr-stamp records the last time we ran Gen_fmgrtab.pl.  We don't rely on
 # the timestamps of the individual output files, because the Perl script
 # won't update them if they didn't change (to avoid unnecessary recompiles).
-fmgr-stamp: Gen_fmgrtab.pl $(catalogdir)/Catalog.pm $(FMGR_DATA) $(top_srcdir)/src/include/access/transam.h
-	$(PERL) -I $(catalogdir) $< -I $(top_srcdir)/src/include/ $(FMGR_DATA)
+fmgr-stamp: Gen_fmgrtab.pl $(catalogdir)/Catalog.pm $(top_srcdir)/src/include/catalog/pg_proc.dat $(top_srcdir)/src/include/access/transam.h
+	$(PERL) -I $(catalogdir) $< -I $(top_srcdir)/src/include/ $(top_srcdir)/src/include/catalog/pg_proc.dat
 	touch $@
 
 errcodes.h: $(top_srcdir)/src/backend/utils/errcodes.txt generate-errcodes.pl

src/include/catalog/pg_proc.h

@@ -42,7 +42,7 @@ CATALOG(pg_proc,1255,ProcedureRelationId) BKI_BOOTSTRAP BKI_ROWTYPE_OID(81,Proce
 	Oid			proowner BKI_DEFAULT(PGUID);
 
 	/* OID of pg_language entry */
-	Oid			prolang BKI_DEFAULT(12);
+	Oid			prolang BKI_DEFAULT(internal) BKI_LOOKUP(pg_language);
 
 	/* estimated execution cost */
 	float4		procost BKI_DEFAULT(1);

src/tools/msvc/Solution.pm

@@ -269,16 +269,14 @@ sub GenerateFiles
 		"LIBPGTYPES");
 
 	chdir('src/backend/utils');
-	my $pg_language_dat = '../../../src/include/catalog/pg_language.dat';
 	my $pg_proc_dat     = '../../../src/include/catalog/pg_proc.dat';
 	if (   IsNewer('fmgr-stamp', 'Gen_fmgrtab.pl')
 		|| IsNewer('fmgr-stamp', '../catalog/Catalog.pm')
-		|| IsNewer('fmgr-stamp', $pg_language_dat)
 		|| IsNewer('fmgr-stamp', $pg_proc_dat)
 		|| IsNewer('fmgr-stamp', '../../../src/include/access/transam.h'))
 	{
 		system(
-			"perl -I ../catalog Gen_fmgrtab.pl -I../../../src/include/ $pg_language_dat $pg_proc_dat"
+			"perl -I ../catalog Gen_fmgrtab.pl -I../../../src/include/ $pg_proc_dat"
 		);
 		open(my $f, '>', 'fmgr-stamp')
 		  || confess "Could not touch fmgr-stamp";