require Exporter;
use vars qw($VERSION @ISA @EXPORT @EXPORT_OK);
-$VERSION = 1.0503;
+$VERSION = 1.08;
@ISA = qw(Exporter);
@EXPORT = qw(pod2html htmlify);
@EXPORT_OK = qw(anchorify);
can automatically generate indexes and cross-references, and it keeps
a cache of things it knows how to cross-reference.
-=head1 ARGUMENTS
+=head1 FUNCTIONS
-Pod::Html takes the following arguments:
+=head2 pod2html
+
+ pod2html("pod2html",
+ "--podpath=lib:ext:pod:vms",
+ "--podroot=/usr/src/perl",
+ "--htmlroot=/perl/nmanual",
+ "--libpods=perlfunc:perlguts:perlvar:perlrun:perlop",
+ "--recurse",
+ "--infile=foo.pod",
+ "--outfile=/perl/nmanual/foo.html");
+
+pod2html takes the following arguments:
=over 4
=back
-=head1 EXAMPLE
+=head2 htmlify
- pod2html("pod2html",
- "--podpath=lib:ext:pod:vms",
- "--podroot=/usr/src/perl",
- "--htmlroot=/perl/nmanual",
- "--libpods=perlfunc:perlguts:perlvar:perlrun:perlop",
- "--recurse",
- "--infile=foo.pod",
- "--outfile=/perl/nmanual/foo.html");
+ htmlify($heading);
+
+Converts a pod section specification to a suitable section specification
+for HTML. Note that we keep spaces and special characters except
+C<", ?> (Netscape problem) and the hyphen (writer's problem...).
+
+=head2 anchorify
+
+ anchorify(@heading);
+
+Similar to C<htmlify()>, but turns non-alphanumerics into underscores. Note
+that C<anchorify()> is not exported by default.
=head1 ENVIRONMENT
=cut
-
my($Cachedir);
my($Dircache, $Itemcache);
my @Begin_Stack;
my %Local_Items;
my $Is83;
-my $PTQuote;
my $Curdir = File::Spec->curdir;
# to prevent the first <hr /> directive.
$Paragraph = ''; # which paragraph we're processing (used
# for error messages)
- $PTQuote = 0; # status of double-quote conversion
%Sections = (); # sections within this page
%Local_Items = ();
# still generate an index, but surround it with an html comment.
# that way some other program can extract it if desired.
$index =~ s/--+/-/g;
- print HTML "<p><a name=\"__index__\"></a></p>\n";
- print HTML "<!-- INDEX BEGIN -->\n";
- print HTML "<!--\n" unless $Doindex;
- print HTML $index;
- print HTML "-->\n" unless $Doindex;
- print HTML "<!-- INDEX END -->\n\n";
- print HTML "<hr />\n" if $Doindex and $index;
+
+ my $hr = ($Doindex and $index) ? qq(<hr name="index" />) : "";
+
+ unless ($Doindex)
+ {
+ $index = qq(<!--\n$index\n-->\n);
+ }
+
+ print HTML << "END_OF_INDEX";
+
+<!-- INDEX BEGIN -->
+<div name="index">
+<p><a name=\"__index__\"></a></p>
+$index
+$hr
+</div>
+<!-- INDEX END -->
+
+END_OF_INDEX
# now convert this file
my $after_item; # set to true after an =item
my $need_dd = 0;
warn "Converting input file $Podfile\n" if $Verbose;
foreach my $i (0..$#poddata){
- $PTQuote = 0; # status of quote conversion
-
$_ = $poddata[$i];
$Paragraph = $i+1;
if (/^(=.*)/s) { # is it a pod directive?
sub emit_item_tag($$$){
my( $otext, $text, $compact ) = @_;
- my $item = fragment_id( $text );
+ my $item = fragment_id( $text , -generate);
$EmittedItem = $item;
### print STDERR "emit_item_tag=$item ($text)\n";
if ($Items_Named{$item}++) {
print HTML process_text( \$otext );
} else {
- my $name = 'item_' . $item;
+ my $name = $item;
$name = anchorify($name);
- print HTML qq{<a name="$name">}, process_text( \$otext ), '</a>';
+ print HTML qq{<a name="$name" class="item">}, process_text( \$otext ), '</a>';
}
print HTML "</strong>\n";
undef( $EmittedItem );
#
sub pure_text($){
my $text = shift();
- process_puretext( $text, \$PTQuote, 1 );
+ process_puretext( $text, 1 );
}
sub inIS_text($){
my $text = shift();
- process_puretext( $text, \$PTQuote, 0 );
+ process_puretext( $text, 0 );
}
#
# double-quotes and handling implicit C<> links.
#
sub process_puretext {
- my($text, $quote, $notinIS) = @_;
+ my($text, $notinIS) = @_;
## Guessing at func() or [\$\@%&]*var references in plain text is destined
## to produce some strange looking ref's. uncomment to disable:
my(@words, $lead, $trail);
- # convert double-quotes to single-quotes
- if( $$quote && $text =~ s/"/''/s ){
- $$quote = 0;
- }
- while ($text =~ s/"([^"]*)"/``$1''/sg) {};
- $$quote = 1 if $text =~ s/"/``/s;
-
# keep track of leading and trailing white-space
$lead = ($text =~ s/\A(\s+)//s ? $1 : "");
$trail = ($text =~ s/(\s+)\Z//s ? $1 : "");
return if $Ignore;
my( $tref ) = @_;
my $res = process_text1( 0, $tref );
+ $res =~ s/\s+$//s;
$$tref = $res;
}
+sub process_text_rfc_links {
+ my $text = shift;
+
+ # For every "RFCnnnn" or "RFC nnn", link it to the authoritative
+ # ource. Do not use the /i modifier here. Require "RFC" to be written in
+ # in capital letters.
+
+ $text =~ s{
+ (?<=[^<>[:alpha:]]) # Make sure this is not an URL already
+ (RFC\s*([0-9]{1,5}))(?![0-9]) # max 5 digits
+ }
+ {<a href="http://www.ietf.org/rfc/rfc$3.txt" class="rfc">$1</a>}gx;
+
+ $text;
+}
+
sub process_text1($$;$$){
my( $lev, $rstr, $func, $closing ) = @_;
my $res = '';
$res = "&$escape;";
} elsif( $func eq 'F' ){
- # F<filename> - italizice
- $res = '<em>' . process_text1( $lev, $rstr ) . '</em>';
+ # F<filename> - italicize
+ $res = '<em class="file">' . process_text1( $lev, $rstr ) . '</em>';
} elsif( $func eq 'I' ){
- # I<text> - italizice
+ # I<text> - italicize
$res = '<em>' . process_text1( $lev, $rstr ) . '</em>';
} elsif( $func eq 'L' ){
} else {
warn "$0: $Podfile: undelimited $func<> in paragraph $Paragraph.\n" unless $Quiet;
}
+ $res = process_text_rfc_links($res);
}
return $res;
}
$section = "#$section" if $section;
### print STDERR "...section=$section\n";
- # check if there is a .pod with the page name
- if ($Pages{$page} =~ /([^:]*)\.pod:/) {
- $link = "$Htmlroot/$1.html$section";
- } elsif ($Pages{$page} =~ /([^:]*)\.pm:/) {
+ # check if there is a .pod with the page name.
+ # for L<Foo>, Foo.(pod|pm) is preferred to A/Foo.(pod|pm)
+ if ($Pages{$page} =~ /([^:]*)\.(?:pod|pm):/) {
$link = "$Htmlroot/$1.html$section";
} else {
$link = "";
$heading =~ s/\s+\Z//;
$heading =~ s/\A\s+//;
# The hyphen is a disgrace to the English language.
- $heading =~ s/[-"?]//g;
+ # $heading =~ s/[-"?]//g;
+ $heading =~ s/["?]//g;
$heading = lc( $heading );
return $heading;
}
return $res unless defined $$rstr;
if( ! defined( $func ) ){
# skip to next begin of an interior sequence
- while( $$rstr =~ s/\A(.*?)([BCEFILSXZ])<(<+[^\S\n]+)?// ){
+ while( $$rstr =~ s/\A(.*?)([BCEFILSXZ])<(<+[^\S\n]+)?//s ){
# recurse into its text
$res .= $1 . depod1( $rstr, $2, closing $3);
}
# all others: either recurse into new function or
# terminate at closing angle bracket
my $term = pattern $closing;
- while( $$rstr =~ s/\A(.*?)(([BCEFILSXZ])<(<+[^\S\n]+)?|$term)// ){
+ while( $$rstr =~ s/\A(.*?)(([BCEFILSXZ])<(<+[^\S\n]+)?|$term)//s ){
$res .= $1;
last unless $3;
$res .= depod1( $rstr, $3, closing $4 );
return $res;
}
+{
+ my %seen; # static fragment record hash
+
+sub fragment_id_readable {
+ my $text = shift;
+ my $generate = shift; # optional flag
+
+ my $orig = $text;
+
+ # leave the words for the fragment identifier,
+ # change everything else to underbars.
+ $text =~ s/[^A-Za-z0-9_]+/_/g; # do not use \W to avoid locale dependency.
+ $text =~ s/_{2,}/_/g;
+ $text =~ s/\A_//;
+ $text =~ s/_\Z//;
+
+ unless ($text)
+ {
+ # Nothing left after removing punctuation, so leave it as is
+ # E.g. if option is named: "=item -#"
+
+ $text = $orig;
+ }
+
+ if ($generate) {
+ if ( exists $seen{$text} ) {
+ # This already exists, make it unique
+ $seen{$text}++;
+ $text = $text . $seen{$text};
+ } else {
+ $seen{$text} = 1; # first time seen this fragment
+ }
+ }
+
+ $text;
+}}
+
+my @HC;
+sub fragment_id_obfuscated { # This was the old "_2d_2d__"
+ my $text = shift;
+ my $generate = shift; # optional flag
+
+ # text? Normalize by obfuscating the fragment id to make it unique
+ $text =~ s/\s+/_/sg;
+
+ $text =~ s{(\W)}{
+ defined( $HC[ord($1)] ) ? $HC[ord($1)]
+ : ( $HC[ord($1)] = sprintf( "%%%02X", ord($1) ) ) }gxe;
+ $text = substr( $text, 0, 50 );
+
+ $text;
+}
+
#
# fragment_id - construct a fragment identifier from:
# a) =item text
# b) contents of C<...>
#
-my @HC;
+
sub fragment_id {
- my $text = shift();
+ my $text = shift;
+ my $generate = shift; # optional flag
+
$text =~ s/\s+\Z//s;
if( $text ){
# a method or function?
# honour the perlfunc manpage: func [PAR[,[ ]PAR]...]
# and some funnies with ... Module ...
- return $1 if $text =~ m{^([a-z\d_]+)(\s+[A-Z\d,/& ]+)?$};
+ return $1 if $text =~ m{^([a-z\d_]+)(\s+[A-Z,/& ][A-Z\d,/& ]*)?$};
return $1 if $text =~ m{^([a-z\d]+)\s+Module(\s+[A-Z\d,/& ]+)?$};
- # text? normalize!
- $text =~ s/\s+/_/sg;
- $text =~ s{(\W)}{
- defined( $HC[ord($1)] ) ? $HC[ord($1)]
- : ( $HC[ord($1)] = sprintf( "%%%02X", ord($1) ) ) }gxe;
- $text = substr( $text, 0, 50 );
+ return fragment_id_readable($text, $generate);
} else {
- return undef();
+ return;
}
}