Perl's chop / chomp considered bad, use a regexp instead

Once upon a time, there was chop, which somply chopped off the last
character of $_ or a given variable, and it was used to take off the
EOL character (\n) of strings.

... but then, you had to check for the presence of such character.

So came chomp, the better chop which checks for \n before chopping it
off.  And this worked well, as long as Perl made internally sure that
all EOLs were converted to \n.

These days, though, there seems to be a mixture of perls, so lines
from files in the "wrong" environment might have \r\n as EOL, or just
\r (Mac OS, unless I'm misinformed).

So it's time we went for the more generic variant and use s|\R$||, the
better chomp which recognises all kinds of known EOLs and chops them
off.

A few chops were left alone, as they are use as surgical tools to
remove one last slash or one last comma.

NOTE: \R came with perl 5.10.0.  It means that from now on, our
scripts will fail with any older version.

Reviewed-by: Rich Salz <rsalz@openssl.org>

VMS/VMSify-conf.pl

@@ -7,7 +7,7 @@ my @directory_vars = ( "dir", "certs", "crl_dir", "new_certs_dir" );
 my @file_vars = ( "database", "certificate", "serial", "crlnumber",
 		  "crl", "private_key", "RANDFILE" );
 while(<STDIN>) {
-    chomp;
+    s|\R$||;
     foreach my $d (@directory_vars) {
 	if (/^(\s*\#?\s*${d}\s*=\s*)\.\/([^\s\#]*)([\s\#].*)$/) {
 	    $_ = "$1sys\\\$disk:\[.$2$3";

VMS/translatesyms.pl

@@ -28,7 +28,7 @@ my %translations = ();
 open DEMANGLER_DATA, $ARGV[0]
     or die "Couldn't open $ARGV[0]: $!\n";
 while(<DEMANGLER_DATA>) {
-    chomp;
+    s|\R$||;
     (my $translated, my $original) = split /\$/;
     $translations{$original} = $translated.'$';
 }

apps/CA.pl.in

@@ -121,7 +121,7 @@ if ($WHAT eq '-newcert' ) {
     # ask user for existing CA certificate
     print "CA certificate filename (or enter to create)\n";
     $FILE = <STDIN>;
-    chop $FILE if $FILE;
+    $FILE = s|\R$|| if $FILE;
     if ($FILE) {
         copy_pemfile($FILE,"${CATOP}/private/$CAKEY", "PRIVATE");
         copy_pemfile($FILE,"${CATOP}/$CACERT", "CERTIFICATE");

crypto/lhash/num.pl

@@ -5,7 +5,7 @@
 while (<>)
 	{
 	next unless /^node/;
-	chop;
+	s|\R$||;                # Better chomp
 	@a=split;
 	$num{$a[3]}++;
 	}

crypto/objects/obj_dat.pl

@@ -257,7 +257,7 @@ foreach (@out)
 				}
 			$out=$t;
 			}
-		chop $out;
+		chop $out;      # Get rid of the last comma
 		print OUT "$out";
 		}
 	else

crypto/objects/objects.pl

@@ -5,7 +5,7 @@ $max_nid=0;
 $o=0;
 while(<NUMIN>)
 	{
-	chop;
+	s|\R$||;
 	$o++;
 	s/#.*$//;
 	next if /^\s*$/;
@@ -28,7 +28,7 @@ $Cname="";
 $o=0;
 while (<IN>)
 	{
-	chop;
+	s|\R$||;
 	$o++;
         if (/^!module\s+(.*)$/)
 		{

crypto/objects/objxref.pl

@@ -13,7 +13,7 @@ open(IN, $mac_file) || die "Can't open $mac_file, $!\n";
 
 while (<IN>)
 	{
-	chomp;
+	s|\R$||;                # Better chomp
 	my ($name, $num) = /^(\S+)\s+(\S+)$/;
 	$oid_tbl{$name} = $num;
 	}
@@ -25,7 +25,7 @@ my $ln = 1;
 
 while (<IN>)
 	{
-	chomp;
+	s|\R$||;                # Better chomp
 	s/#.*$//;
 	next if (/^\S*$/);
 	my ($xr, $p1, $p2) = /^(\S+)\s+(\S+)\s+(\S+)/;
@@ -112,6 +112,6 @@ sub check_oid
 	my ($chk) = @_;
 	if (!exists $oid_tbl{$chk})
 		{
-		die "Can't find \"$chk\", $!\n";
+		die "Can't find \"$chk\"\n";
 		}
 	}

crypto/perlasm/x86_64-xlate.pl

@@ -80,7 +80,7 @@ my $nasm=0;
 
 if    ($flavour eq "mingw64")	{ $gas=1; $elf=0; $win64=1;
 				  $prefix=`echo __USER_LABEL_PREFIX__ | $ENV{CC} -E -P -`;
-				  chomp($prefix);
+				  $prefix =~ s|\R$||; # Better chomp
 				}
 elsif ($flavour eq "macosx")	{ $gas=1; $elf=0; $prefix="_"; $decor="L\$"; }
 elsif ($flavour eq "masm")	{ $gas=0; $elf=0; $masm=$masmref; $win64=1; $decor="\$L\$"; }
@@ -852,7 +852,7 @@ ___
 }
 while($line=<>) {
 
-    chomp($line);
+    $line =~ s|\R$||;           # Better chomp
 
     $line =~ s|[#!].*$||;	# get rid of asm-style comments...
     $line =~ s|/\*.*\*/||;	# ... and C-style comments...

util/check-buildinfo.pl

@@ -7,7 +7,7 @@ my $reldir = "";
 my $searchterm = "";
 my $goal = "";
 while (<$minfo>) {
-    chomp;
+    s|\R$||;
 
     if (/^RELATIVE_DIRECTORY=(.*)$/) {
         $reldir=$1;

util/extract-names.pl

@@ -2,7 +2,7 @@
 
 $/ = "";			# Eat a paragraph at once.
 while(<STDIN>) {
-    chop;
+    s|\R$||;
     s/\n/ /gm;
     if (/^=head1 /) {
 	$name = 0;

util/files.pl

@@ -13,7 +13,7 @@ while ($ARGV[0] =~ /^([^\s=]+)\s*=\s*(.*)$/)
 $s="";
 while (<>)
 	{
-	chop;
+	s|\R$||;
 	s/#.*//;
 	if (/^([^\s=]+)\s*=\s*(.*)$/)
 		{
@@ -23,10 +23,10 @@ while (<>)
 			{
 			if ($b =~ /\\$/)
 				{
-				chop($b);
+				$b=$`; # Keep what is before the backslash
 				$o.=$b." ";
 				$b=<>;
-				chop($b);
+				$b =~ s|\R$||; # Better chomp
 				}
 			else
 				{
@@ -43,7 +43,7 @@ while (<>)
 		}
 	}
 
-$pwd=`pwd`; chop($pwd);
+$pwd=`pwd`; $pwd =~ s|\R$||;
 
 if ($sym{'TOP'} eq ".")
 	{
@@ -55,7 +55,7 @@ else	{
 	@_=split(/\//,$pwd);
 	$z=$#_-$n+1;
 	foreach $i ($z .. $#_) { $dir.=$_[$i]."/"; }
-	chop($dir);
+	chop($dir);             # Remove the last slash
 	}
 
 print "RELATIVE_DIRECTORY=$dir\n";

util/fipslink.pl

@@ -59,7 +59,7 @@ open my $sha1_res, '<', $fips_target.".sha1" or die "Get hash failure";
 $fips_hash=<$sha1_res>;
 close $sha1_res;
 unlink $fips_target.".sha1";
-chomp $fips_hash;
+$fips_hash =~ s|\R$||;          # Better chomp
 die "Get hash failure" if $? != 0;
 
 
@@ -97,8 +97,8 @@ sub check_hash
 	$hashfile = <IN>;
 	close IN;
 	$hashval = `$sha1_exe ${fips_libdir}/$filename`;
-	chomp $hashfile;
-	chomp $hashval;
+	$hashfile =~ s|\R$||;    # Better chomp
+	$hashval =~ s|\R$||;     # Better chomp
 	$hashfile =~ s/^.*=\s+//;
 	$hashval =~ s/^.*=\s+//;
 	die "Invalid hash syntax in file" if (length($hashfile) != 40);

util/mk1mf.pl

@@ -553,7 +553,7 @@ if ($fips)
 			{
 			open (IN, "util/fipslib_path.txt") || fipslib_error();
 			$fipslibdir = <IN>;
-			chomp $fipslibdir;
+			$fipslibdir =~ s|\R$||;
 			close IN;
 			}
 		fips_check_files($fipslibdir,
@@ -1159,7 +1159,7 @@ sub do_defs
 		elsif ($var eq "SSLOBJ")
 			{ $ret.="\$(OBJ_D)\\\$(SSL).res "; }
 		}
-	chomp($ret);
+	chomp($ret);            # Does this actually do something? /RL
 	$ret.="\n\n";
 	return($ret);
 	}

util/mkdef.pl

@@ -459,7 +459,7 @@ sub do_defs
 			if($parens > 0) {
 				#Inside a DEPRECATEDIN
 				$stored_multiline .= $_;
-				chomp $stored_multiline;
+				$stored_multiline =~ s|\R$||; # Better chomp
 				print STDERR "DEBUG: Continuing multiline DEPRECATEDIN: $stored_multiline\n" if $debug;
 				$parens = count_parens($stored_multiline);
 				if ($parens == 0) {
@@ -480,9 +480,7 @@ sub do_defs
 			}
 
 			if (/\\$/) {
-				chomp; # remove eol
-				chop; # remove ending backslash
-				$line = $_;
+				$line = $`; # keep what was before the backslash
 				next;
 			}
 
@@ -867,7 +865,7 @@ sub do_defs
 							\@current_algorithms);
 					} else {
 						$stored_multiline = $_;
-						chomp $stored_multiline;
+						$stored_multiline =~ s|\R$||;
 						print STDERR "DEBUG: Found multiline DEPRECATEDIN starting with: $stored_multiline\n" if $debug;
 						next;
 					}
@@ -1365,7 +1363,7 @@ sub load_numbers
 
 	open(IN,"<$name") || die "unable to open $name:$!\n";
 	while (<IN>) {
-		chop;
+		s|\R$||;        # Better chomp
 		s/#.*$//;
 		next if /^\s*$/;
 		@a=split;

util/mkerr.pl

@@ -556,7 +556,7 @@ EOF
 	if (open(IN,"<$cfile")) {
 		my $line = "";
 		while (<IN>) {
-			chomp;
+			s|\R$||; # Better chomp
 			$_ = $line . $_;
 			$line = "";
 			if (/{ERR_(FUNC|REASON)\(/) {

util/mkfiles.pl

@@ -95,7 +95,7 @@ my $s="";
 
 while (<IN>)
 	{
-	chop;
+	s|\R$||;
 	s/#.*//;
 	if (/^([^\s=]+)\s*=\s*(.*)$/)
 		{
@@ -105,10 +105,10 @@ while (<IN>)
 			{
 			if ($b =~ /\\$/)
 				{
-				chop($b);
+				$b=$`;
 				$o.=$b." ";
 				$b=<IN>;
-				chop($b);
+				$b =~ s|\R$||;
 				}
 			else
 				{

util/selftest.pl

@@ -54,7 +54,7 @@ $cversion=`$cc -V |head -1` if $cversion =~ "Error";
 $cversion=`$cc --version` if $cversion eq "";
 $cversion =~ s/Reading specs.*\n//;
 $cversion =~ s/usage.*\n//;
-chomp $cversion;
+$cversion =~ s|\R$||;
 
 if (open(IN,"<CHANGES")) {
     while(<IN>) {

util/sp-diff.pl

@@ -54,7 +54,7 @@ sub loadfile
 		$header=0 if /^[dr]sa/;
 		if (/^type/) { $header=0; next; }
 		next if $header;
-		chop;
+		s|\R$||;
 		@a=split;
 		if ($a[0] =~ /^[dr]sa$/)
 			{