Make assorted quality-of-life improvements in gen_node_support.pl.

Fix incorrect reporting of the location of errors (such as bogus
node attributes).  Add header comments to the generated files,
containing copyright notices and reminders that they are generated
files, as we do in other file-generating scripts.  Arrange to not
leave a clutter of temporary files when the script detects an error.

Discussion: https://postgr.es/m/3843645.1657385930@sss.pgh.pa.us

Author: tglsfdc

src/backend/nodes/gen_node_support.pl

@@ -34,6 +34,8 @@ sub elem
 	return grep { $_ eq $x } @_;
 }
 
+# output file names
+my @output_files;
 
 # collect node names
 my @node_types = qw(Node);
@@ -124,19 +126,31 @@ sub elem
 	my $supertype_field;
 
 	my $node_attrs = '';
+	my $node_attrs_lineno;
 	my @my_fields;
 	my %my_field_types;
 	my %my_field_attrs;
 
 	open my $ifh, '<', $infile or die "could not open \"$infile\": $!";
 
-	my $file_content = do { local $/; <$ifh> };
+	my $raw_file_content = do { local $/; <$ifh> };
 
-	# strip C comments
-	$file_content =~ s{/\*.*?\*/}{}gs;
+	# strip C comments, preserving newlines so we can count lines correctly
+	my $file_content = '';
+	while ($raw_file_content =~ m{^(.*?)(/\*.*?\*/)(.*)$}s)
+	{
+		$file_content .= $1;
+		my $comment = $2;
+		$raw_file_content = $3;
+		$comment =~ tr/\n//cd;
+		$file_content .= $comment;
+	}
+	$file_content .= $raw_file_content;
 
+	my $lineno = 0;
 	foreach my $line (split /\n/, $file_content)
 	{
+		$lineno++;
 		chomp $line;
 		$line =~ s/\s*$//;
 		next if $line eq '';
@@ -153,13 +167,14 @@ sub elem
 				$is_node_struct = 0;
 				$supertype      = undef;
 				next if $line eq '{';
-				die "$infile:$.: expected opening brace\n";
+				die "$infile:$lineno: expected opening brace\n";
 			}
 			# second line could be node attributes
 			elsif ($subline == 2
 				&& $line =~ /^\s*pg_node_attr\(([\w(), ]*)\)$/)
 			{
-				$node_attrs = $1;
+				$node_attrs        = $1;
+				$node_attrs_lineno = $lineno;
 				# hack: don't count the line
 				$subline--;
 				next;
@@ -236,7 +251,7 @@ sub elem
 						else
 						{
 							die
-							  "$infile:$.: unrecognized attribute \"$attr\"\n";
+							  "$infile:$node_attrs_lineno: unrecognized attribute \"$attr\"\n";
 						}
 					}
 
@@ -330,7 +345,9 @@ sub elem
 					# strip space between type and "*" (pointer) */
 					$type =~ s/\s+\*$/*/;
 
-					die if $type eq '';
+					die
+					  "$infile:$lineno: cannot parse data type in \"$line\"\n"
+					  if $type eq '';
 
 					my @attrs;
 					if ($attrs)
@@ -347,7 +364,7 @@ sub elem
 							  )
 							{
 								die
-								  "$infile:$.: unrecognized attribute \"$attr\"\n";
+								  "$infile:$lineno: unrecognized attribute \"$attr\"\n";
 							}
 						}
 					}
@@ -362,7 +379,7 @@ sub elem
 			{
 				if ($is_node_struct)
 				{
-					#warn "$infile:$.: could not parse \"$line\"\n";
+					#warn "$infile:$lineno: could not parse \"$line\"\n";
 				}
 			}
 		}
@@ -411,10 +428,35 @@ sub elem
 
 my $tmpext = ".tmp$$";
 
+# opening boilerplate for output files
+my $header_comment =
+  '/*-------------------------------------------------------------------------
+ *
+ * %s
+ *    Generated node infrastructure code
+ *
+ * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * NOTES
+ *  ******************************
+ *  *** DO NOT EDIT THIS FILE! ***
+ *  ******************************
+ *
+ *  It has been GENERATED by src/backend/nodes/gen_node_support.pl
+ *
+ *-------------------------------------------------------------------------
+ */
+';
+
+
 # nodetags.h
 
+push @output_files, 'nodetags.h';
 open my $nt, '>', 'nodetags.h' . $tmpext or die $!;
 
+printf $nt $header_comment, 'nodetags.h';
+
 my $i = 1;
 foreach my $n (@node_types, @extra_tags)
 {
@@ -437,11 +479,20 @@ sub elem
 
 # copyfuncs.c, equalfuncs.c
 
-open my $cff, '>', 'copyfuncs.funcs.c' . $tmpext   or die $!;
-open my $eff, '>', 'equalfuncs.funcs.c' . $tmpext  or die $!;
-open my $cfs, '>', 'copyfuncs.switch.c' . $tmpext  or die $!;
+push @output_files, 'copyfuncs.funcs.c';
+open my $cff, '>', 'copyfuncs.funcs.c' . $tmpext or die $!;
+push @output_files, 'equalfuncs.funcs.c';
+open my $eff, '>', 'equalfuncs.funcs.c' . $tmpext or die $!;
+push @output_files, 'copyfuncs.switch.c';
+open my $cfs, '>', 'copyfuncs.switch.c' . $tmpext or die $!;
+push @output_files, 'equalfuncs.switch.c';
 open my $efs, '>', 'equalfuncs.switch.c' . $tmpext or die $!;
 
+printf $cff $header_comment, 'copyfuncs.funcs.c';
+printf $eff $header_comment, 'equalfuncs.funcs.c';
+printf $cfs $header_comment, 'copyfuncs.switch.c';
+printf $efs $header_comment, 'equalfuncs.switch.c';
+
 # add required #include lines to each file set
 print $cff $node_includes;
 print $eff $node_includes;
@@ -552,7 +603,7 @@ sub elem
 			my $tt = $1;
 			if (!defined $array_size_field)
 			{
-				die "no array size defined for $n.$f of type $t";
+				die "no array size defined for $n.$f of type $t\n";
 			}
 			if ($node_type_info{$n}->{field_types}{$array_size_field} eq
 				'List*')
@@ -597,7 +648,8 @@ sub elem
 		}
 		else
 		{
-			die "could not handle type \"$t\" in struct \"$n\" field \"$f\"";
+			die
+			  "could not handle type \"$t\" in struct \"$n\" field \"$f\"\n";
 		}
 	}
 
@@ -619,11 +671,20 @@ sub elem
 
 # outfuncs.c, readfuncs.c
 
-open my $off, '>', 'outfuncs.funcs.c' . $tmpext   or die $!;
-open my $rff, '>', 'readfuncs.funcs.c' . $tmpext  or die $!;
-open my $ofs, '>', 'outfuncs.switch.c' . $tmpext  or die $!;
+push @output_files, 'outfuncs.funcs.c';
+open my $off, '>', 'outfuncs.funcs.c' . $tmpext or die $!;
+push @output_files, 'readfuncs.funcs.c';
+open my $rff, '>', 'readfuncs.funcs.c' . $tmpext or die $!;
+push @output_files, 'outfuncs.switch.c';
+open my $ofs, '>', 'outfuncs.switch.c' . $tmpext or die $!;
+push @output_files, 'readfuncs.switch.c';
 open my $rfs, '>', 'readfuncs.switch.c' . $tmpext or die $!;
 
+printf $off $header_comment, 'outfuncs.funcs.c';
+printf $rff $header_comment, 'readfuncs.funcs.c';
+printf $ofs $header_comment, 'outfuncs.switch.c';
+printf $rfs $header_comment, 'readfuncs.switch.c';
+
 print $off $node_includes;
 print $rff $node_includes;
 
@@ -814,7 +875,7 @@ sub elem
 			}
 			if (!defined $array_size_field)
 			{
-				die "no array size defined for $n.$f of type $t";
+				die "no array size defined for $n.$f of type $t\n";
 			}
 			if ($node_type_info{$n}->{field_types}{$array_size_field} eq
 				'List*')
@@ -886,7 +947,8 @@ sub elem
 		}
 		else
 		{
-			die "could not handle type \"$t\" in struct \"$n\" field \"$f\"";
+			die
+			  "could not handle type \"$t\" in struct \"$n\" field \"$f\"\n";
 		}
 
 		# for read_as() without read_write_ignore, we have to read the value
@@ -911,10 +973,26 @@ sub elem
 close $rfs;
 
 
-# now rename the temporary files to their final name
-foreach my $file (
-	qw(nodetags.h copyfuncs.funcs.c copyfuncs.switch.c equalfuncs.funcs.c equalfuncs.switch.c outfuncs.funcs.c outfuncs.switch.c readfuncs.funcs.c readfuncs.switch.c)
-  )
+# now rename the temporary files to their final names
+foreach my $file (@output_files)
 {
 	Catalog::RenameTempFile($file, $tmpext);
 }
+
+
+# Automatically clean up any temp files if the script fails.
+END
+{
+	# take care not to change the script's exit value
+	my $exit_code = $?;
+
+	if ($exit_code != 0)
+	{
+		foreach my $file (@output_files)
+		{
+			unlink($file . $tmpext);
+		}
+	}
+
+	$? = $exit_code;
+}