X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=pod%2Fpod2man.PL;h=6821d84334e8ee76a2e030991755f8e3c0ee6ef2;hb=a9bc755754f0db5e848e65dfd2e63a96af50ffd4;hp=3a8c5db2a8242411297c7d74f4f539b57b6bed1a;hpb=4633a7c4bad06b471d9310620b7fe8ddd158cccd;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/pod/pod2man.PL b/pod/pod2man.PL
index 3a8c5db..6821d84 100644
--- a/pod/pod2man.PL
+++ b/pod/pod2man.PL
@@ -15,8 +15,7 @@ use File::Basename qw(&basename &dirname);
 chdir(dirname($0));
 ($file = basename($0)) =~ s/\.PL$//;
 $file =~ s/\.pl$//
-	if ($Config{'osname'} eq 'VMS' or
-	    $Config{'osname'} eq 'OS2');  # "case-forgiving"
+	if ($^O eq 'VMS' or $^O eq 'os2' or $^O eq 'amigaos');  # "case-forgiving"
 
 open OUT,">$file" or die "Can't create $file: $!";
 
@@ -26,43 +25,404 @@ print "Extracting $file (with variable substitutions)\n";
 # You can use $Config{...} to use Configure variables.
 
 print OUT <<"!GROK!THIS!";
-$Config{'startperl'}
-    eval 'exec perl -S \$0 "\$@"'
-	if 0;
+$Config{startperl}
+    eval 'exec $Config{perlpath} -S \$0 \${1+"\$@"}'
+	if \$running_under_some_shell;
 !GROK!THIS!
 
 # In the following, perl variables are not expanded during extraction.
 
 print OUT <<'!NO!SUBS!';
 
+=head1 NAME
+
+pod2man - translate embedded Perl pod directives into man pages
+
+=head1 SYNOPSIS
+
+B<pod2man>
+[ B<--section=>I<manext> ]
+[ B<--release=>I<relpatch> ]
+[ B<--center=>I<string> ]
+[ B<--date=>I<string> ]
+[ B<--fixed=>I<font> ]
+[ B<--official> ]
+I<inputfile>
+
+=head1 DESCRIPTION
+
+B<pod2man> converts its input file containing embedded pod directives (see
+L<perlpod>) into nroff source suitable for viewing with nroff(1) or
+troff(1) using the man(7) macro set.
+
+Besides the obvious pod conversions, B<pod2man> also takes care of
+func(), func(n), and simple variable references like $foo or @bar so
+you don't have to use code escapes for them; complex expressions like
+C<$fred{'stuff'}> will still need to be escaped, though.  Other nagging
+little roffish things that it catches include translating the minus in
+something like foo-bar, making a long dash--like this--into a real em
+dash, fixing up "paired quotes", putting a little space after the
+parens in something like func(), making C++ and PI look right, making
+double underbars have a little tiny space between them, making ALLCAPS
+a teeny bit smaller in troff(1), and escaping backslashes so you don't
+have to.
+
+=head1 OPTIONS
+
+=over 8
+
+=item center
+
+Set the centered header to a specific string.  The default is
+"User Contributed Perl Documentation", unless the C<--official> flag is
+given, in which case the default is "Perl Programmers Reference Guide".
+
+=item date
+
+Set the left-hand footer string to this value.  By default,
+the modification date of the input file will be used.
+
+=item fixed
+
+The fixed font to use for code refs.  Defaults to CW.
+
+=item official
+
+Set the default header to indicate that this page is of
+the standard release in case C<--center> is not given.
+
+=item release
+
+Set the centered footer.  By default, this is the current
+perl release.
+
+=item section
+
+Set the section for the C<.TH> macro.  The standard conventions on
+sections are to use 1 for user commands,  2 for system calls, 3 for
+functions, 4 for devices, 5 for file formats, 6 for games, 7 for
+miscellaneous information, and 8 for administrator commands.  This works
+best if you put your Perl man pages in a separate tree, like
+F</usr/local/perl/man/>.  By default, section 1 will be used
+unless the file ends in F<.pm> in which case section 3 will be selected.
+
+=back
+
+=head1 Anatomy of a Proper Man Page
+
+For those not sure of the proper layout of a man page, here's
+an example of the skeleton of a proper man page.  Head of the
+major headers should be setout as a C<=head1> directive, and
+are historically written in the rather startling ALL UPPER CASE
+format, although this is not mandatory.
+Minor headers may be included using C<=head2>, and are
+typically in mixed case.
+
+=over 10
+
+=item NAME
+
+Mandatory section; should be a comma-separated list of programs or
+functions documented by this podpage, such as:
+
+    foo, bar - programs to do something
+
+=item SYNOPSIS
+
+A short usage summary for programs and functions, which
+may someday be deemed mandatory.
+
+=item DESCRIPTION
+
+Long drawn out discussion of the program.  It's a good idea to break this
+up into subsections using the C<=head2> directives, like
+
+    =head2 A Sample Subection
+
+    =head2 Yet Another Sample Subection
+
+=item OPTIONS
+
+Some people make this separate from the description.
+
+=item RETURN VALUE
+
+What the program or function returns if successful.
+
+=item ERRORS
+
+Exceptions, return codes, exit stati, and errno settings.
+
+=item EXAMPLES
+
+Give some example uses of the program.
+
+=item ENVIRONMENT
+
+Envariables this program might care about.
+
+=item FILES
+
+All files used by the program.  You should probably use the FE<lt>E<gt>
+for these.
+
+=item SEE ALSO
+
+Other man pages to check out, like man(1), man(7), makewhatis(8), or catman(8).
+
+=item NOTES
+
+Miscellaneous commentary.
+
+=item CAVEATS
+
+Things to take special care with; sometimes called WARNINGS.
+
+=item DIAGNOSTICS
+
+All possible messages the program can print out--and
+what they mean.
+
+=item BUGS
+
+Things that are broken or just don't work quite right.
+
+=item RESTRICTIONS
+
+Bugs you don't plan to fix :-)
+
+=item AUTHOR
+
+Who wrote it (or AUTHORS if multiple).
+
+=item HISTORY
+
+Programs derived from other sources sometimes have this, or
+you might keep a modification log here.
+
+=back
+
+=head1 EXAMPLES
+
+    pod2man program > program.1
+    pod2man some_module.pm > /usr/perl/man/man3/some_module.3
+    pod2man --section=7 note.pod > note.7
+
+=head1 DIAGNOSTICS
+
+The following diagnostics are generated by B<pod2man>.  Items
+marked "(W)" are non-fatal, whereas the "(F)" errors will cause
+B<pod2man> to immediately exit with a non-zero status.
+
+=over 4
+
+=item bad option in paragraph %d of %s: ``%s'' should be [%s]<%s>
+
+(W) If you start include an option, you should set it off
+as bold, italic, or code.
+
+=item can't open %s: %s
+
+(F) The input file wasn't available for the given reason.
+
+=item Improper man page - no dash in NAME header in paragraph %d of %s
+
+(W) The NAME header did not have an isolated dash in it.  This is
+considered important.
+
+=item Invalid man page - no NAME line in %s
+
+(F) You did not include a NAME header, which is essential.
+
+=item roff font should be 1 or 2 chars, not `%s'  (F)
+
+(F) The font specified with the C<--fixed> option was not
+a one- or two-digit roff font.
+
+=item %s is missing required section: %s
+
+(W) Required sections include NAME, DESCRIPTION, and if you're
+using a section starting with a 3, also a SYNOPSIS.  Actually,
+not having a NAME is a fatal.
+
+=item Unknown escape: %s in %s
+
+(W) An unknown HTML entity (probably for an 8-bit character) was given via
+a C<EE<lt>E<gt>> directive.  Besides amp, lt, gt, and quot, recognized
+entities are Aacute, aacute, Acirc, acirc, AElig, aelig, Agrave, agrave,
+Aring, aring, Atilde, atilde, Auml, auml, Ccedil, ccedil, Eacute, eacute,
+Ecirc, ecirc, Egrave, egrave, ETH, eth, Euml, euml, Iacute, iacute, Icirc,
+icirc, Igrave, igrave, Iuml, iuml, Ntilde, ntilde, Oacute, oacute, Ocirc,
+ocirc, Ograve, ograve, Oslash, oslash, Otilde, otilde, Ouml, ouml, szlig,
+THORN, thorn, Uacute, uacute, Ucirc, ucirc, Ugrave, ugrave, Uuml, uuml,
+Yacute, yacute, and yuml.
+
+=item Unmatched =back
+
+(W) You have a C<=back> without a corresponding C<=over>.
+
+=item Unrecognized pod directive: %s
+
+(W) You specified a pod directive that isn't in the known list of
+C<=head1>, C<=head2>, C<=item>, C<=over>, C<=back>, or C<=cut>.
+
+
+=back
+
+=head1 NOTES
+
+If you would like to print out a lot of man page continuously, you
+probably want to set the C and D registers to set contiguous page
+numbering and even/odd paging, at least on some versions of man(7).
+Settting the F register will get you some additional experimental
+indexing:
+
+    troff -man -rC1 -rD1 -rF1 perl.1 perldata.1 perlsyn.1 ...
+
+The indexing merely outputs messages via C<.tm> for each
+major page, section, subsection, item, and any C<XE<lt>E<gt>>
+directives.
+
+
+=head1 RESTRICTIONS
+
+None at this time.
+
+=head1 BUGS
+
+The =over and =back directives don't really work right.  They
+take absolute positions instead of offsets, don't nest well, and
+making people count is suboptimal in any event.
+
+=head1 AUTHORS
+
+Original prototype by Larry Wall, but so massively hacked over by
+Tom Christiansen such that Larry probably doesn't recognize it anymore.
+
+=cut
+
 $/ = "";
 $cutting = 1;
 
-$CFont = 'CW';
-if ($ARGV[0] =~ s/-fc(.*)//) {
-    shift;
-    $CFont = $1 || shift;
+# We try first to get the version number from a local binary, in case we're
+# running an installed version of Perl to produce documentation from an
+# uninstalled newer version's pod files.
+if ($^O ne 'plan9') {
+  ($version,$patch) =
+    `\PATH=.:..:\$PATH; perl -v` =~ /version (\d\.\d{3})(?:_(\d{2}))?/;
+}
+# No luck; we'll just go with the running Perl's version
+($version,$patch) = $] =~ /^(.{5})(\d{2})?/ unless $version;
+$DEF_RELEASE  = "perl $version";
+$DEF_RELEASE .= ", patch $patch" if $patch;
+
+
+sub makedate {
+    my $secs = shift;
+    my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime($secs);
+    my $mname = (qw{Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec})[$mon];
+    return "$mday/$mname/$year";
+}
+
+use Getopt::Long;
+
+$DEF_SECTION = 1;
+$DEF_CENTER = "User Contributed Perl Documentation";
+$STD_CENTER = "Perl Programmers Reference Guide";
+$DEF_FIXED = 'CW';
+
+sub usage {
+    warn "$0: @_\n" if @_;
+    die <<EOF;
+usage: $0 [options] podpage
+Options are:
+	--section=manext      (default "$DEF_SECTION")
+	--release=relpatch    (default "$DEF_RELEASE")
+	--center=string       (default "$DEF_CENTER")
+	--date=string         (default "$DEF_DATE")
+	--fixed=font	      (default "$DEF_FIXED")
+	--official	      (default NOT)
+EOF
 }
 
+$uok = GetOptions( qw(
+	section=s
+	release=s
+	center=s
+	date=s
+	fixed=s
+	official
+	help));
+
+$DEF_DATE = makedate((stat($ARGV[0]))[9] || time());
+
+usage("Usage error!") unless $uok;
+usage() if $opt_help;
+usage("Need one and only one podpage argument") unless @ARGV == 1;
+
+$section = $opt_section || ($ARGV[0] =~ /\.pm$/ ? 3 : $DEF_SECTION);
+$RP = $opt_release || $DEF_RELEASE;
+$center = $opt_center || ($opt_official ? $STD_CENTER : $DEF_CENTER);
+
+$CFont = $opt_fixed || $DEF_FIXED;
+
 if (length($CFont) == 2) {
     $CFont_embed = "\\f($CFont";
-} 
+}
 elsif (length($CFont) == 1) {
     $CFont_embed = "\\f$CFont";
-} 
+}
 else {
-    die "Roff font should be 1 or 2 chars, not `$CFont_embed'";
-} 
+    die "roff font should be 1 or 2 chars, not `$CFont_embed'";
+}
+
+$section = $opt_section || $DEF_SECTION;
+$date = $opt_date || $DEF_DATE;
+
+for (qw{NAME DESCRIPTION}) {
+# for (qw{NAME DESCRIPTION AUTHOR}) {
+    $wanna_see{$_}++;
+}
+$wanna_see{SYNOPSIS}++ if $section =~ /^3/;
 
-$name = @ARGV ? $ARGV[0] : "something";
-$name =~ s/\..*//;
+
+$name = @ARGV ? $ARGV[0] : "<STDIN>";
+$Filename = $name;
+if ($section =~ /^1/) {
+    require File::Basename;
+    $name = uc File::Basename::basename($name);
+}
+$name =~ s/\.(pod|p[lm])$//i;
+$name =~ s(/)(::)g; # translate Getopt/Long to Getopt::Long, etc.
+
+if ($name ne 'something') {
+    FCHECK: {
+	open(F, "< $ARGV[0]") || die "can't open $ARGV[0]: $!";
+	while (<F>) {
+	    next unless /^=\b/;
+	    if (/^=head1\s+NAME\s*$/) {  # an /m would forgive mistakes
+		$_ = <F>;
+		unless (/\s*-+\s+/) {
+		    $oops++;
+		    warn "$0: Improper man page - no dash in NAME header in paragraph $. of $ARGV[0]\n"
+		}
+		%namedesc = split /\s+-+\s+/;
+		last FCHECK;
+	    }
+	    next if /^=cut\b/;	# DB_File and Net::Ping have =cut before NAME
+	    die "$0: Invalid man page - 1st pod line is not NAME in $ARGV[0]\n";
+	}
+	die "$0: Invalid man page - no documentation in $ARGV[0]\n";
+    }
+    close F;
+}
 
 print <<"END";
 .rn '' }`
 ''' \$RCSfile\$\$Revision\$\$Date\$
-''' 
+'''
 ''' \$Log\$
-''' 
+'''
 .de Sh
 .br
 .if t .Sp
@@ -100,6 +460,7 @@ print <<"END";
 .tr \\(*W-|\\(bv\\*(Tr
 .ie n \\{\\
 .ds -- \\(*W-
+.ds PI pi
 .if (\\n(.H=4u)&(1m=24u) .ds -- \\(*W\\h'-12u'\\(*W\\h'-12u'-\\" diablo 10 pitch
 .if (\\n(.H=4u)&(1m=20u) .ds -- \\(*W\\h'-12u'\\(*W\\h'-8u'-\\" diablo 12 pitch
 .ds L" ""
@@ -114,15 +475,42 @@ print <<"END";
 .ds R" ''
 .ds L' `
 .ds R' '
-.if t .ds PI \\(*p
-.if n .ds PI PI
+.ds PI \\(*p
 'br\\}
-.TH \U$name\E 1 "\\*(RP"
+END
+
+print <<'END';
+.\"	If the F register is turned on, we'll generate
+.\"	index entries out stderr for the following things:
+.\"		TH	Title 
+.\"		SH	Header
+.\"		Sh	Subsection 
+.\"		Ip	Item
+.\"		X<>	Xref  (embedded
+.\"	Of course, you have to process the output yourself
+.\"	in some meaninful fashion.
+.if \nF \{
+.de IX
+.tm Index:\\$1\t\\n%\t"\\$2"
+..
+.nr % 0
+.rr F
+.\}
+END
+
+print <<"END";
+.TH $name $section "$RP" "$date" "$center"
+.IX Title "$name $section"
 .UC
 END
 
+while (($name, $desc) = each %namedesc) {
+    for ($name, $desc) { s/^\s+//; s/\s+$//; }
+    print qq(.IX Name "$name - $desc"\n);
+}
+
 print <<'END';
-.if n .hy 0 
+.if n .hy 0
 .if n .na
 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
 .de CQ          \" put $1 in typewriter font
@@ -138,7 +526,7 @@ print <<'END';
 ..
 .\" @(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2
 .	\" AM - accent mark definitions
-.bd S B 3
+.bd B 3
 .	\" fudge factors for nroff and troff
 .if n \{\
 .	ds #H 0
@@ -163,8 +551,8 @@ print <<'END';
 .	ds ~ ~
 .	ds ? ?
 .	ds ! !
-.	ds / 
-.	ds q 
+.	ds /
+.	ds q
 .\}
 .if t \{\
 .	ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
@@ -220,11 +608,22 @@ END
 
 $indent = 0;
 
+$begun = "";
+
 while (<>) {
     if ($cutting) {
 	next unless /^=/;
 	$cutting = 0;
     }
+    if ($begun) {
+	if (/^=end\s+$begun/) {
+            $begun = "";
+	}
+	elsif ($begun =~ /^(roff|man)$/) {
+	    print STDOUT $_;
+        }
+	next;
+    }
     chomp;
 
     # Translate verbatim paragraph
@@ -249,6 +648,22 @@ while (<>) {
 
     $verbatim = 0;
 
+    if (/^=for\s+(\S+)\s*/s) {
+	if ($1 eq "man" or $1 eq "roff") {
+	    print STDOUT $',"\n\n";
+	} else {
+	    # ignore unknown for
+	}
+	next;
+    }
+    elsif (/^=begin\s+(\S+)\s*/s) {
+	$begun = $1;
+	if ($1 eq "man" or $1 eq "roff") {
+	    print STDOUT $'."\n\n";
+	}
+	next;
+    }
+
     # check for things that'll hosed our noremap scheme; affects $_
     init_noremap();
 
@@ -257,7 +672,7 @@ while (<>) {
 	# trofficate backslashes; must do it before what happens below
 	s/\\/noremap('\\e')/ge;
 
-	# first hide the escapes in case we need to 
+	# first hide the escapes in case we need to
 	# intuit something and get it wrong due to fmting
 
 	s/([A-Z]<[^<>]*>)/noremap($1)/ge;
@@ -291,14 +706,16 @@ while (<>) {
 			[^\051]*?
 		    \)
 		)
-	    }x && $` !~ /([LCI]<[^<>]*|-)$/ && !/^=\w/) 
+	    }x && $` !~ /([LCI]<[^<>]*|-)$/ && !/^=\w/)
 	{
-	    warn "``$1'' should be a [LCI]<$1> ref";
-	} 
+	    warn "$0: bad option in paragraph $. of $ARGV: ``$1'' should be [LCI]<$1>\n";
+	    $oops++;
+	}
 
 	while (/(-[a-zA-Z])\b/g && $` !~ /[\w\-]$/) {
-	    warn "``$1'' should be [CB]<$1> ref";
-	} 
+	    warn "$0: bad option in paragraph $. of $ARGV: ``$1'' should be [CB]<$1>\n";
+	    $oops++;
+	}
 
 	# put it back so we get the <> processed again;
 	clear_noremap(0); # 0 means leave the E's
@@ -307,7 +724,7 @@ while (<>) {
 	# trofficate backslashes
 	s/\\/noremap('\\e')/ge;
 
-    } 
+    }
 
     # need to hide E<> first; they're processed in clear_noremap
     s/(E<[^<>]+>)/noremap($1)/ge;
@@ -325,7 +742,7 @@ while (<>) {
 	# no break -- usually we want C<> for this
 	s/S<([^<>]*)>/nobreak($1)/eg;
 
-	# LREF: a manpage(3f) 
+	# LREF: a manpage(3f)
 	s:L<([a-zA-Z][^\s\/]+)(\([^\)]+\))?>:the I<$1>$2 manpage:g;
 
 	# LREF: an =item on another manpage
@@ -359,7 +776,7 @@ while (<>) {
 	s{
 	    L<
 		(?:
-		    ([a-zA-Z]\S+?) / 
+		    ([a-zA-Z]\S+?) /
 		)?
 		"?(.*?)"?
 	    >
@@ -368,8 +785,8 @@ while (<>) {
 		$1 	# if no $1, assume it means on this page.
 		    ?  "the section on I<$2> in the I<$1> manpage"
 		    :  "the section on I<$2>"
-	    } 
-	}gex;
+	    }
+	}gesx; # s in case it goes over multiple lines, so . matches \n
 
 	s/Z<>/\\&/g;
 
@@ -395,26 +812,34 @@ while (<>) {
 	    $cutting = 1;
 	}
 	elsif ($Cmd eq 'head1') {
-	    print qq{.SH "$_"\n}
+	    s/\s+$//;
+	    delete $wanna_see{$_} if exists $wanna_see{$_};
+	    print qq{.SH "$_"\n};
+	    print qq{.IX Header "$_"\n};
 	}
 	elsif ($Cmd eq 'head2') {
-	    print qq{.Sh "$_"\n}
+	    print qq{.Sh "$_"\n};
+	    print qq{.IX Subsection "$_"\n};
 	}
 	elsif ($Cmd eq 'over') {
 	    push(@indent,$indent);
-	    $indent = $_ + 0;
+	    $indent += ($_ + 0) || 5;
 	}
 	elsif ($Cmd eq 'back') {
 	    $indent = pop(@indent);
-	    warn "Unmatched =back\n" unless defined $indent;
+	    warn "$0: Unmatched =back in paragraph $. of $ARGV\n" unless defined $indent;
 	    $needspace = 1;
 	}
 	elsif ($Cmd eq 'item') {
 	    s/^\*( |$)/\\(bu$1/g;
 	    print STDOUT qq{.Ip "$_" $indent\n};
+	    print qq{.IX Item "$_"\n};
 	}
+	elsif ($Cmd eq 'pod') {
+	    # this is just a comment
+	} 
 	else {
-	    warn "Unrecognized directive: $Cmd\n";
+	    warn "$0: Unrecognized pod directive in paragraph $. of $ARGV: $Cmd\n";
 	}
     }
     else {
@@ -433,6 +858,17 @@ print <<"END";
 .rn }` ''
 END
 
+if (%wanna_see) {
+    @missing = keys %wanna_see;
+    warn "$0: $Filename is missing required section"
+	.  (@missing > 1 && "s")
+	.  ": @missing\n";
+    $oops++;
+}
+
+exit;
+#exit ($oops != 0);
+
 #########################################################################
 
 sub nobreak {
@@ -443,6 +879,8 @@ sub nobreak {
 
 sub escapes {
 
+    s/X<(.*?)>/mkindex($1)/ge;
+
     # translate the minus in foo-bar into foo\-bar for roff
     s/([^0-9a-z-])-([^-])/$1\\-$2/g;
 
@@ -459,7 +897,7 @@ sub escapes {
 
     #s/(?!")(?:.)--(?!")(?:.)/\\*(--/g;
     #s/(?:(?!")(?:.)--(?:"))|(?:(?:")--(?!")(?:.))/\\*(--/g;
-    
+
 
     # make sure that func() keeps a bit a space tween the parens
     ### s/\b\(\)/\\|()/g;
@@ -471,7 +909,7 @@ sub escapes {
     # make double underbars have a little tiny space between them
     s/__/_\\|_/g;
 
-    # PI goes to \*(-- (defined above)
+    # PI goes to \*(PI (defined above)
     s/\bPI\b/noremap('\\*(PI')/ge;
 
     # make all caps a teeny bit smaller, but don't muck with embedded code literals
@@ -494,7 +932,7 @@ sub escapes {
 	    (
 		\b[A-Z]{2,}[\/A-Z+:\-\d_\$]*\b
 	    )
-	} { 
+	} {
 	    $1 . noremap( '\\s-1' .  $2 . '\\s0' )
 	}egmox;
 
@@ -510,9 +948,9 @@ sub ccvt {
  	# what about $" ?
      } else {
  	noremap(qq{${CFont_embed}$_\\fR});
-     } 
+     }
     noremap(qq{.CQ "$_" \n\\&});
-} 
+}
 
 sub makespace {
     if ($indent) {
@@ -523,22 +961,32 @@ sub makespace {
     }
 }
 
+sub mkindex {
+    my ($entry) = @_;
+    my @entries = split m:\s*/\s*:, $entry;
+    print ".IX Xref ";
+    for $entry (@entries) {
+	print qq("$entry" );
+    }
+    print "\n";
+    return '';
+}
+
 sub font {
     local($font) = shift;
     return '\\f' . noremap($font);
-} 
+}
 
 sub noremap {
     local($thing_to_hide) = shift;
     $thing_to_hide =~ tr/\000-\177/\200-\377/;
     return $thing_to_hide;
-} 
+}
 
 sub init_noremap {
-    if ( /[\200-\377]/ ) {
-	warn "hit bit char in input stream";
-    } 
-} 
+	# escape high bit characters in input stream
+	s/([\200-\377])/"E<".ord($1).">"/ge;
+}
 
 sub clear_noremap {
     my $ready_to_print = $_[0];
@@ -552,20 +1000,26 @@ sub clear_noremap {
     # otherwise the interative \w<> processing would have
     # been hosed by the E<gt>
     s {
-	    E<	
-	    ( [A-Za-z]+ )	
+	    E<
+	    (
+	        ( \d + ) 
+	        | ( [A-Za-z]+ )	
+	    )
 	    >	
-    } { 
-	 do {	
-	     exists $HTML_Escapes{$1}
-		? do { $HTML_Escapes{$1} }
+    } {
+	 do {
+	     defined $2
+		? chr($2)
+		:	
+	     exists $HTML_Escapes{$3}
+		? do { $HTML_Escapes{$3} }
 		: do {
-		    warn "Unknown escape: $& in $_";
+		    warn "$0: Unknown escape in paragraph $. of $ARGV: ``$&''\n";
 		    "E<$1>";
-		} 
-	 } 
+		}
+	 }
     }egx if $ready_to_print;
-} 
+}
 
 sub internal_lrefs {
     local($_) = shift;
@@ -578,14 +1032,14 @@ sub internal_lrefs {
 	$retstr .= "C<$items[$i]>";
 	$retstr .= ", " if @items > 2 && $i != $#items;
 	$retstr .= " and " if $i+2 == @items;
-    } 
+    }
 
     $retstr .= " entr" . ( @items > 1  ? "ies" : "y" )
-	    .  " elsewhere in this document";
+	    .  " elsewhere in this document "; # terminal space to avoid words running together (pattern used strips terminal spaces)
 
     return $retstr;
 
-} 
+}
 
 BEGIN {
 %HTML_Escapes = (
@@ -658,6 +1112,7 @@ BEGIN {
     "yuml"	=>	"y\\*:",	#   small y, dieresis or umlaut mark
 );
 }
+
 !NO!SUBS!
 
 close OUT or die "Can't close $file: $!";