cemeyer/man2html.pl

## man2html.pl
#!/usr/bin/env perl

# Extracted from 2-clause BSDL https://www.freebsd.org/cgi/man.cgi/source
#
# Usage example:
#   $ man 3 tree | path/to/man2html.pl > tree.3.html

# encode unknown text data for using as HTML,
# treats ^H as overstrike ala nroff.
sub encode_data {
        local ($_) = @_;
        local ($str);

        # Escape &, < and >
        s,\010[><&],,g;
        s/\&/\&amp\;/g;
        s/\</\&lt\;/g;
        s/\>/\&gt\;/g;

        s,((_\010[^_])+),($str = $1) =~ s/.\010//g; "<i>$str</i>";,ge;
        s,((.\010.)+),($str = $1) =~ s/.\010//g; "<b>$str</b>";,ge;

        #s,((_\010.)+),($str = $1) =~ s/.\010//g; "<i>$str</i>";,ge;
        #s,(.\010)+,$1,g;
        #if (!s,((.\010.)+\s+(.\010.)+),($str = $1) =~ s/.\010//g; "<b>$str</b>";,ge) {
        # s,(([^_]\010.)+),($str = $1) =~ s/[^_]\010//g; "<b>$str</b>";,ge;
        # s,(([_]\010.)+),($str = $1) =~ s/[_]\010//g; "<i>$str</i>";,ge;
        #}
        # Escape binary data except for ^H which we process below
        # \375 gets turned into the & for the entity reference
        #s/([^\010\012\015\032-\176])/sprintf('\375#%03d;',ord($1))/eg;
        # Process ^H sequences, we use \376 and \377 (already escaped
        # above) to stand in for < and > until those characters can
        # be properly escaped below.
        #s,\376[IB]\377_\376/[IB]\377,,g;
        #s/.[\b]//g;                    # just do an erase for anything else
        # Now convert our magic chars into our tag markers
        #s/\375/\&/g; s/\376/</g; s/\377/>/g;

        # cleanup all the rest
        s,.\010,,g;

        $_;
}

sub encode_url {
        local ($_) = @_;

        # rfc1738 says that ";"|"/"|"?"|":"|"@"|"&"|"=" may be reserved.
        # And % is the escape character so we escape it along with
        # single-quote('), double-quote("), grave accent(`), less than(<),
        # greater than(>), and non-US-ASCII characters (binary data),
        # and white space.  Whew.
        s/([\000-\032\;\/\?\:\@\&\=\%\'\"\`\<\>\177-\377 ])/sprintf('%%%02x',ord($1))/eg;
        s/%20/+/g;
        $_;
}


sub mlnk {
        local ($matched) = @_;
        local ( $link, $section );
        ( $link = $matched ) =~ s/[\s]+//g;
        $link =~ s/<\/?[IB]>//ig;
        ( $link, $section ) = ( $link =~ m/^([^\(]*)\((.*)\)/ );
        $link    = &encode_url($link);
        $section = &encode_url($section);
        local ($manpath) = &encode_url($manpath);
        return qq{<a href="$BASE?query=$link}
        . qq{&amp;sektion=$section&amp;apropos=0&amp;manpath=$manpath">$matched</a>};
}

local ($space) = 1;
local (@sect);
local ( $i, $j );

print "<html>\n<body>\n";
print "<pre>\n";
while (<>) {
        # remove tailing white space
        if (/^\s+$/) {
                next if $space;
                $space = 1;
        }
        else {
                $space = 0;
        }

        $_ = &encode_data($_);

        /^\s/ &&    # skip headers
        s,((<[IB]>)?[\w\_\.\-]+\s*(</[IB]>)?\s*\(([1-9ln][a-zA-Z]*)\)),&mlnk($1),oige;

        # detect E-Mail Addreses in manpages
        if ( $enable_mailto_links && /\@/ ) {
                s/([a-z0-9_\-\.]+\@[a-z0-9\-\.]+\.[a-z]+)/<a href="mailto:$1">$1<\/A>/gi;
        }

        # detect URLs in manpages
        if (m%tp://%) {
                s,((ftp|http)://[^\s<>\)]+),<a href="$1">$1</a>,gi;
        }

        if (s%^(<b>.*?</b>)+\n?$% ($str = $1) =~ s,(<b>|</b>),,g; $str%ge) {
                $i = $_;
                $j = &encode_url($i);
                $j =~ s/\+/_/g;
                $_ = qq{<a name="$j" href="#end"><b>$i</b></a>\n};
                push( @sect, $i );
        }
        print;
}
print "</pre>\n</body>\n</html>\n";
	#!/usr/bin/env perl

	# Extracted from 2-clause BSDL https://www.freebsd.org/cgi/man.cgi/source
	#
	# Usage example:
	# $ man 3 tree \| path/to/man2html.pl > tree.3.html

	# encode unknown text data for using as HTML,
	# treats ^H as overstrike ala nroff.
	sub encode_data {
	local ($_) = @_;
	local ($str);

	# Escape &, < and >
	s,\010[><&],,g;
	s/\&/\&amp\;/g;
	s/\</\&lt\;/g;
	s/\>/\&gt\;/g;

	s,((_\010[^_])+),($str = $1) =~ s/.\010//g; "<i>$str</i>";,ge;
	s,((.\010.)+),($str = $1) =~ s/.\010//g; "<b>$str</b>";,ge;

	#s,((_\010.)+),($str = $1) =~ s/.\010//g; "<i>$str</i>";,ge;
	#s,(.\010)+,$1,g;
	#if (!s,((.\010.)+\s+(.\010.)+),($str = $1) =~ s/.\010//g; "<b>$str</b>";,ge) {
	# s,(([^_]\010.)+),($str = $1) =~ s/[^_]\010//g; "<b>$str</b>";,ge;
	# s,(([_]\010.)+),($str = $1) =~ s/[_]\010//g; "<i>$str</i>";,ge;
	#}
	# Escape binary data except for ^H which we process below
	# \375 gets turned into the & for the entity reference
	#s/([^\010\012\015\032-\176])/sprintf('\375#%03d;',ord($1))/eg;
	# Process ^H sequences, we use \376 and \377 (already escaped
	# above) to stand in for < and > until those characters can
	# be properly escaped below.
	#s,\376[IB]\377_\376/[IB]\377,,g;
	#s/.[\b]//g; # just do an erase for anything else
	# Now convert our magic chars into our tag markers
	#s/\375/\&/g; s/\376/</g; s/\377/>/g;

	# cleanup all the rest
	s,.\010,,g;

	$_;
	}

	sub encode_url {
	local ($_) = @_;

	# rfc1738 says that ";"\|"/"\|"?"\|":"\|"@"\|"&"\|"=" may be reserved.
	# And % is the escape character so we escape it along with
	# single-quote('), double-quote("), grave accent(`), less than(<),
	# greater than(>), and non-US-ASCII characters (binary data),
	# and white space. Whew.
	s/([\000-\032\;\/\?\:\@\&\=\%\'\"\`\<\>\177-\377 ])/sprintf('%%%02x',ord($1))/eg;
	s/%20/+/g;
	$_;
	}


	sub mlnk {
	local ($matched) = @_;
	local ( $link, $section );
	( $link = $matched ) =~ s/[\s]+//g;
	$link =~ s/<\/?[IB]>//ig;
	( $link, $section ) = ( $link =~ m/^([^\(])\((.)\)/ );
	$link = &encode_url($link);
	$section = &encode_url($section);
	local ($manpath) = &encode_url($manpath);
	return qq{<a href="$BASE?query=$link}
	. qq{&sektion=$section&apropos=0&manpath=$manpath">$matched</a>};
	}

	local ($space) = 1;
	local (@sect);
	local ( $i, $j );

	print "<html>\n<body>\n";
	print "<pre>\n";
	while (<>) {
	# remove tailing white space
	if (/^\s+$/) {
	next if $space;
	$space = 1;
	}
	else {
	$space = 0;
	}

	$_ = &encode_data($_);

	/^\s/ && # skip headers
	s,((<[IB]>)?[\w\_\.\-]+\s(</[IB]>)?\s\(([1-9ln][a-zA-Z]*)\)),&mlnk($1),oige;

	# detect E-Mail Addreses in manpages
	if ( $enable_mailto_links && /\@/ ) {
	s/([a-z0-9_\-\.]+\@[a-z0-9\-\.]+\.[a-z]+)/<a href="mailto:$1">$1<\/A>/gi;
	}

	# detect URLs in manpages
	if (m%tp://%) {
	s,((ftp\|http)://[^\s<>\)]+),<a href="$1">$1</a>,gi;
	}

	if (s%^(<b>.*?</b>)+\n?$% ($str = $1) =~ s,(<b>\|</b>),,g; $str%ge) {
	$i = $_;
	$j = &encode_url($i);
	$j =~ s/\+/_/g;
	$_ = qq{<a name="$j" href="#end"><b>$i</b></a>\n};
	push( @sect, $i );
	}
	print;
	}
	print "</pre>\n</body>\n</html>\n";