src/backend/catalog/Makefile     |  11 +++-
 src/backend/catalog/genbki.pl    | 109 +++++++++++++++++++++++++++++----------
 src/backend/utils/Gen_fmgrtab.pl |  32 +++++++-----
 src/backend/utils/Makefile       |   2 +-
 4 files changed, 112 insertions(+), 42 deletions(-)

diff --git a/src/backend/catalog/Makefile b/src/backend/catalog/Makefile
new file mode 100644
index 30ca509..23858b8
*** a/src/backend/catalog/Makefile
--- b/src/backend/catalog/Makefile
*************** POSTGRES_BKI_SRCS = $(addprefix $(top_sr
*** 49,54 ****
--- 49,63 ----
  	toasting.h indexing.h \
      )
  
+ POSTGRES_BKI_DATA = $(addprefix $(top_srcdir)/src/include/catalog/,\
+ 	pg_aggregate.dat pg_am.dat pg_amop.dat pg_amproc.dat pg_authid.dat \
+ 	pg_cast.dat pg_class.dat pg_collation.dat pg_database.dat pg_language.dat \
+ 	pg_namespace.dat pg_opclass.dat pg_operator.dat pg_opfamily.dat \
+ 	pg_pltemplate.dat pg_proc.dat pg_range.dat pg_tablespace.dat \
+ 	pg_ts_config.dat pg_ts_config_map.dat pg_ts_dict.dat pg_ts_parser.dat \
+ 	pg_ts_template.dat pg_type.dat \
+ 	)
+ 
  # location of Catalog.pm
  catalogdir = $(top_srcdir)/src/backend/catalog
  
*************** schemapg.h: postgres.bki ;
*** 67,73 ****
  # even in distribution tarballs.  So this is cheating a bit, but it
  # will achieve the goal of updating the version number when it
  # changes.
! postgres.bki: genbki.pl Catalog.pm $(POSTGRES_BKI_SRCS) $(top_srcdir)/configure $(top_srcdir)/src/include/catalog/duplicate_oids
  	cd $(top_srcdir)/src/include/catalog && $(PERL) ./duplicate_oids
  	$(PERL) -I $(catalogdir) $< $(pg_includes) --set-version=$(MAJORVERSION) $(POSTGRES_BKI_SRCS)
  
--- 76,82 ----
  # even in distribution tarballs.  So this is cheating a bit, but it
  # will achieve the goal of updating the version number when it
  # changes.
! postgres.bki: genbki.pl Catalog.pm $(POSTGRES_BKI_SRCS) $(POSTGRES_BKI_DATA) $(top_srcdir)/configure $(top_srcdir)/src/include/catalog/duplicate_oids
  	cd $(top_srcdir)/src/include/catalog && $(PERL) ./duplicate_oids
  	$(PERL) -I $(catalogdir) $< $(pg_includes) --set-version=$(MAJORVERSION) $(POSTGRES_BKI_SRCS)
  
diff --git a/src/backend/catalog/genbki.pl b/src/backend/catalog/genbki.pl
new file mode 100644
index 1876399..1b2a570
*** a/src/backend/catalog/genbki.pl
--- b/src/backend/catalog/genbki.pl
*************** my $PG_CATALOG_NAMESPACE =
*** 93,100 ****
    Catalog::FindDefinedSymbol('pg_namespace.h', \@include_path,
  							 'PG_CATALOG_NAMESPACE');
  
! # Read all the input header files into internal data structures
! my $catalogs = Catalog::Catalogs(@input_files);
  
  # Generate postgres.bki, postgres.description, and postgres.shdescription
  
--- 93,118 ----
    Catalog::FindDefinedSymbol('pg_namespace.h', \@include_path,
  							 'PG_CATALOG_NAMESPACE');
  
! # We pass .h file names as arguments and then look for matching
! # data files for the data.
! my @datfiles;
! foreach my $header (@input_files)
! {
! 	$header =~ /(.+)\.h$/;
! 	my $datfile = "$1.dat";
! 	if (-e $datfile)
! 	{
! 		push @datfiles, $datfile;
! 	}
! }
! 
! # Read all the files into internal data structures
! my $catalogs     = Catalog::ParseHeader(@input_files);
! my $catalog_data = Catalog::ParseData(@datfiles);
! 
! # Note: Since we have now loaded all the data, we can build lookup
! # tables here. However, if we need default values for a catalog, we
! # need to wait until the full tuples have been built.
  
  # Generate postgres.bki, postgres.description, and postgres.shdescription
  
*************** my @tables_needing_macros;
*** 107,113 ****
  my %regprocoids;
  my @types;
  
! # produce output, one catalog at a time
  foreach my $catname (@{ $catalogs->{names} })
  {
  
--- 125,131 ----
  my %regprocoids;
  my @types;
  
! # Produce output, one catalog at a time.
  foreach my $catname (@{ $catalogs->{names} })
  {
  
*************** foreach my $catname (@{ $catalogs->{name
*** 156,172 ****
  		print $bki "open $catname\n";
  	}
  
! 	if (defined $catalog->{data})
  	{
  
! 		# Ordinary catalog with DATA line(s)
! 		foreach my $row (@{ $catalog->{data} })
  		{
! 
! 			# Split line into tokens without interpreting their meaning.
! 			my %bki_values;
! 			@bki_values{@attnames} =
! 			  Catalog::SplitDataLine($row->{bki_values});
  
  			# Perform required substitutions on fields
  			foreach my $column (@$schema)
--- 174,187 ----
  		print $bki "open $catname\n";
  	}
  
! 	if (defined $catalog_data->{$catname})
  	{
  
! 		# Ordinary catalog with a data file
! 		foreach my $row (@{ $catalog_data->{$catname} })
  		{
! 			my %bki_values = %$row;
! 			Catalog::AddDefaultValues(\%bki_values, $schema, $catname);
  
  			# Perform required substitutions on fields
  			foreach my $column (@$schema)
*************** foreach my $catname (@{ $catalogs->{name
*** 200,206 ****
  				}
  				else
  				{
! 					$regprocoids{ $bki_values{proname} } = $row->{oid};
  				}
  			}
  
--- 215,221 ----
  				}
  				else
  				{
! 					$regprocoids{ $bki_values{proname} } = $bki_values{oid};
  				}
  			}
  
*************** foreach my $catname (@{ $catalogs->{name
*** 208,240 ****
  			if ($catname eq 'pg_type')
  			{
  				my %type = %bki_values;
- 				$type{oid} = $row->{oid};
  				push @types, \%type;
  			}
  
  			# Write to postgres.bki
! 			my $oid = $row->{oid} ? "OID = $row->{oid} " : '';
! 			printf $bki "insert %s( %s )\n", $oid,
! 			  join(' ', @bki_values{@attnames});
  
  			# Write comments to postgres.description and
  			# postgres.shdescription
! 			if (defined $row->{descr})
  			{
! 				printf $descr "%s\t%s\t0\t%s\n", $row->{oid}, $catname,
! 				  $row->{descr};
  			}
! 			if (defined $row->{shdescr})
  			{
! 				printf $shdescr "%s\t%s\t%s\n", $row->{oid}, $catname,
! 				  $row->{shdescr};
  			}
  		}
  	}
  	if ($catname eq 'pg_attribute')
  	{
  
! 		# For pg_attribute.h, we generate DATA entries ourselves.
  		# NB: pg_type.h must come before pg_attribute.h in the input list
  		# of catalog names, since we use info from pg_type.h here.
  		foreach my $table_name (@{ $catalogs->{names} })
--- 223,255 ----
  			if ($catname eq 'pg_type')
  			{
  				my %type = %bki_values;
  				push @types, \%type;
  			}
  
+ 			# Add quotes where necessary.
+ 			format_bki_row(\%bki_values, $schema);
+ 
  			# Write to postgres.bki
! 			bki_insert(\%bki_values, @attnames);
  
  			# Write comments to postgres.description and
  			# postgres.shdescription
! 			if (defined $bki_values{descr})
  			{
! 				printf $descr "%s\t%s\t0\t%s\n", $bki_values{oid}, $catname,
! 				  $bki_values{descr};
  			}
! 			if (defined $bki_values{shdescr})
  			{
! 				printf $shdescr "%s\t%s\t%s\n", $bki_values{oid}, $catname,
! 				  $bki_values{shdescr};
  			}
  		}
  	}
  	if ($catname eq 'pg_attribute')
  	{
  
! 		# For pg_attribute.h, we generate data entries ourselves.
  		# NB: pg_type.h must come before pg_attribute.h in the input list
  		# of catalog names, since we use info from pg_type.h here.
  		foreach my $table_name (@{ $catalogs->{names} })
*************** foreach my $catname (@{ $catalogs->{name
*** 317,328 ****
  # (i.e., not contained in a header with a CATALOG() statement) comes here
  
  # Write out declare toast/index statements
! foreach my $declaration (@{ $catalogs->{toasting}->{data} })
  {
  	print $bki $declaration;
  }
  
! foreach my $declaration (@{ $catalogs->{indexing}->{data} })
  {
  	print $bki $declaration;
  }
--- 332,343 ----
  # (i.e., not contained in a header with a CATALOG() statement) comes here
  
  # Write out declare toast/index statements
! foreach my $declaration (@{ $catalogs->{toasting} })
  {
  	print $bki $declaration;
  }
  
! foreach my $declaration (@{ $catalogs->{indexing} })
  {
  	print $bki $declaration;
  }
*************** exit 0;
*** 380,385 ****
--- 395,442 ----
  
  #################### Subroutines ########################
  
+ # Supply quoting for a normal bki row.
+ # This allows us to keep most double quotes
+ # out of the catalog data files for readability.
+ sub format_bki_row
+ {
+ 	my $row    = shift;
+ 	my $schema = shift;
+ 
+ 	foreach my $column (@$schema)
+ 	{
+ 		my $attname = $column->{name};
+ 		my $atttype = $column->{type};
+ 
+ 		if
+ 		(
+ 			length($row->{$attname}) == 0
+ 
+ 			# Whitespace
+ 			or $row->{$attname} =~ /\s/
+ 
+ 			# Quote strings that have special characters
+ 			# except for certain cases. See bootscanner.l
+ 			or (    $row->{$attname} =~ /\W/
+ 				and $row->{$attname} !~ /^\\\d{3}$/  # octal
+ 				and $row->{$attname} !~ /^-\d*$/)    # '-' or '-1'
+ 
+ 			# XXX Not needed, but keeps the .bki diff down to a reasonable
+ 			# size during review
+ 			or $attname eq 'oprname'    # Operator names
+ 			or $atttype eq 'oidvector'  # Arrays etc.
+ 			or $atttype eq 'int2vector'
+ 			or $atttype =~ /\[\]$/
+ 		)
+ 		{
+ 			if ($row->{$attname} ne '_null_' and $row->{$attname} !~ /^"([^"])*"$/)
+ 			{
+ 				$row->{$attname} = q|"| . $row->{$attname} . q|"|;
+ 			}
+ 		}
+ 	}
+ }
+ 
  
  # Given the schema of pg_attribute, generate an entry for it using information
  # about the attribute it describes.  Any value that is not handled here
*************** sub emit_pgattr_row
*** 447,453 ****
  	Catalog::AddDefaultValues($row, $pgattr_schema, 'pg_attribute');
  }
  
! # Write a pg_attribute entry to postgres.bki
  sub bki_insert
  {
  	my $row        = shift;
--- 504,510 ----
  	Catalog::AddDefaultValues($row, $pgattr_schema, 'pg_attribute');
  }
  
! # Write an entry to postgres.bki
  sub bki_insert
  {
  	my $row        = shift;
diff --git a/src/backend/utils/Gen_fmgrtab.pl b/src/backend/utils/Gen_fmgrtab.pl
new file mode 100644
index a51a755..2d13470
*** a/src/backend/utils/Gen_fmgrtab.pl
--- b/src/backend/utils/Gen_fmgrtab.pl
***************
*** 3,9 ****
  #
  # Gen_fmgrtab.pl
  #    Perl script that generates fmgroids.h, fmgrprotos.h, and fmgrtab.c
! #    from pg_proc.h
  #
  # Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
  # Portions Copyright (c) 1994, Regents of the University of California
--- 3,9 ----
  #
  # Gen_fmgrtab.pl
  #    Perl script that generates fmgroids.h, fmgrprotos.h, and fmgrtab.c
! #    from pg_proc.h and pg_proc.dat
  #
  # Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
  # Portions Copyright (c) 1994, Regents of the University of California
*************** if ($output_path ne '' && substr($output
*** 55,89 ****
  die "No input files.\n"                                     if !$infile;
  die "No include path; you must specify -I at least once.\n" if !@include_path;
  
  my $FirstBootstrapObjectId =
  	Catalog::FindDefinedSymbol('access/transam.h', \@include_path, 'FirstBootstrapObjectId');
  my $INTERNALlanguageId =
  	Catalog::FindDefinedSymbol('catalog/pg_language.h', \@include_path, 'INTERNALlanguageId');
  
! # Read all the data from the include/catalog files.
! my $catalogs = Catalog::Catalogs($infile);
  
  # Collect the raw data from pg_proc.h.
  my @fmgr = ();
- my @attnames;
- foreach my $column (@{ $catalogs->{pg_proc}->{columns} })
- {
- 	push @attnames, $column->{name};
- }
  
! my $data = $catalogs->{pg_proc}->{data};
  foreach my $row (@$data)
  {
! 
! 	# Split line into tokens without interpreting their meaning.
! 	my %bki_values;
! 	@bki_values{@attnames} = Catalog::SplitDataLine($row->{bki_values});
  
  	# Select out just the rows for internal-language procedures.
  	next if $bki_values{prolang} ne $INTERNALlanguageId;
  
  	push @fmgr,
! 	  { oid    => $row->{oid},
  		strict => $bki_values{proisstrict},
  		retset => $bki_values{proretset},
  		nargs  => $bki_values{pronargs},
--- 55,90 ----
  die "No input files.\n"                                     if !$infile;
  die "No include path; you must specify -I at least once.\n" if !@include_path;
  
+ # We pass the pg_proc.h path as an argument and then look for a matching
+ # data file.
+ $infile =~ /(.+)\.h$/;
+ my $datfile = "$1.dat";
+ die "No data files.\n" if ! -e $datfile;
+ 
  my $FirstBootstrapObjectId =
  	Catalog::FindDefinedSymbol('access/transam.h', \@include_path, 'FirstBootstrapObjectId');
  my $INTERNALlanguageId =
  	Catalog::FindDefinedSymbol('catalog/pg_language.h', \@include_path, 'INTERNALlanguageId');
  
! # Read all the files into internal data structures
! my $catalogs     = Catalog::ParseHeader($infile);
! my $catalog_data = Catalog::ParseData($datfile);
  
  # Collect the raw data from pg_proc.h.
  my @fmgr = ();
  
! my $schema  = $catalogs->{pg_proc}->{columns};
! my $data    = $catalog_data->{pg_proc};
  foreach my $row (@$data)
  {
! 	my %bki_values = %$row;
! 	Catalog::AddDefaultValues(\%bki_values, $schema, 'pg_proc');
  
  	# Select out just the rows for internal-language procedures.
  	next if $bki_values{prolang} ne $INTERNALlanguageId;
  
  	push @fmgr,
! 	  { oid    => $bki_values{oid},
  		strict => $bki_values{proisstrict},
  		retset => $bki_values{proretset},
  		nargs  => $bki_values{pronargs},
*************** qq|/*-----------------------------------
*** 122,127 ****
--- 123,129 ----
   *
   *	It has been GENERATED by $0
   *	from $infile
+  *	and  $datfile
   *
   *-------------------------------------------------------------------------
   */
*************** qq|/*-----------------------------------
*** 157,162 ****
--- 159,165 ----
   *
   *	It has been GENERATED by $0
   *	from $infile
+  *	and  $datfile
   *
   *-------------------------------------------------------------------------
   */
*************** qq|/*-----------------------------------
*** 185,190 ****
--- 188,194 ----
   *
   *	It has been GENERATED by $0
   *	from $infile
+  *	and  $datfile
   *
   *-------------------------------------------------------------------------
   */
diff --git a/src/backend/utils/Makefile b/src/backend/utils/Makefile
new file mode 100644
index efb8b53..8ccfc3b
*** a/src/backend/utils/Makefile
--- b/src/backend/utils/Makefile
*************** $(SUBDIRS:%=%-recursive): fmgroids.h fmg
*** 24,30 ****
  fmgrprotos.h: fmgroids.h ;
  fmgroids.h: fmgrtab.c ;
  
! fmgrtab.c: Gen_fmgrtab.pl $(catalogdir)/Catalog.pm $(top_srcdir)/src/include/catalog/pg_proc.h
  	$(PERL) -I $(catalogdir) $< -I $(top_srcdir)/src/include/ $(top_srcdir)/src/include/catalog/pg_proc.h
  
  errcodes.h: $(top_srcdir)/src/backend/utils/errcodes.txt generate-errcodes.pl
--- 24,30 ----
  fmgrprotos.h: fmgroids.h ;
  fmgroids.h: fmgrtab.c ;
  
! fmgrtab.c: Gen_fmgrtab.pl $(catalogdir)/Catalog.pm $(top_srcdir)/src/include/catalog/pg_proc.h $(top_srcdir)/src/include/catalog/pg_proc.dat
  	$(PERL) -I $(catalogdir) $< -I $(top_srcdir)/src/include/ $(top_srcdir)/src/include/catalog/pg_proc.h
  
  errcodes.h: $(top_srcdir)/src/backend/utils/errcodes.txt generate-errcodes.pl