require Exporter;
use vars qw($VERSION @ISA @EXPORT @EXPORT_OK);
-$VERSION = 1.0502;
+$VERSION = 1.08;
@ISA = qw(Exporter);
@EXPORT = qw(pod2html htmlify);
@EXPORT_OK = qw(anchorify);
can automatically generate indexes and cross-references, and it keeps
a cache of things it knows how to cross-reference.
-=head1 ARGUMENTS
+=head1 FUNCTIONS
-Pod::Html takes the following arguments:
+=head2 pod2html
+
+ pod2html("pod2html",
+ "--podpath=lib:ext:pod:vms",
+ "--podroot=/usr/src/perl",
+ "--htmlroot=/perl/nmanual",
+ "--libpods=perlfunc:perlguts:perlvar:perlrun:perlop",
+ "--recurse",
+ "--infile=foo.pod",
+ "--outfile=/perl/nmanual/foo.html");
+
+pod2html takes the following arguments:
=over 4
=back
-=head1 EXAMPLE
+=head2 htmlify
- pod2html("pod2html",
- "--podpath=lib:ext:pod:vms",
- "--podroot=/usr/src/perl",
- "--htmlroot=/perl/nmanual",
- "--libpods=perlfunc:perlguts:perlvar:perlrun:perlop",
- "--recurse",
- "--infile=foo.pod",
- "--outfile=/perl/nmanual/foo.html");
+ htmlify($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)
- $PTQuote = 0; # status of double-quote conversion
%Sections = (); # sections within this page
%Local_Items = ();
END_OF_BLOCK
print HTML <<END_OF_HEAD;
+<?xml version="1.0" ?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<title>$Title</title>$csslink
+<meta http-equiv="content-type" content="text/html; charset=utf-8" />
<link rev="made" href="mailto:$Config{perladmin}" />
</head>
# 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 = $i+1;
if (/^(=.*)/s) { # is it a pod directive?
} elsif (/^=over\s*(.*)/) { # =over N
process_over();
} elsif (/^=back/) { # =back
- process_back();
+ process_back($need_dd);
} elsif (/^=for\s+(\S+)\s*(.*)/si) {# =for
process_for($1,$2);
} else {
/^=(\S*)\s*/;
warn "$0: $Podfile: unknown pod directive '$1' in "
- . "paragraph $Paragraph. ignoring.\n";
+ . "paragraph $Paragraph. ignoring.\n" unless $Quiet;
}
}
$Top = 0;
## end of experimental
if( $after_item ){
- print HTML "$text\n";
$After_Lpar = 1;
- } else {
- print HTML "<p>$text</p>\n";
}
+ print HTML "<p>$text</p>\n";
}
print HTML "</dd>\n" if $need_dd;
$after_item = 0;
pods (empty by default).
--podroot - filesystem base directory from which all relative paths
in podpath stem (default is .).
- --[no]quiet - supress some benign warning messages (default is off).
+ --[no]quiet - suppress some benign warning messages (default is off).
--[no]recurse - recurse on those subdirectories listed in podpath
(default behaviour).
--title - title that will appear in resulting html file.
scan_items( \%Items, "$pod", @poddata);
} else {
- warn "$0: shouldn't be here (line ".__LINE__."\n";
+ warn "$0: shouldn't be here (line ".__LINE__."\n" unless $Quiet;
}
}
@poddata = (); # clean-up a bit
$Pages{$_} = "" unless defined $Pages{$_};
$Pages{$_} .= "$dir/$_.pm:";
push(@pods, "$dir/$_.pm");
+ } elsif (-T "$dir/$_") { # script(?)
+ local *F;
+ if (open(F, "$dir/$_")) {
+ my $line;
+ while (defined($line = <F>)) {
+ if ($line =~ /^=(?:pod|head1)/) {
+ $Pages{$_} = "" unless defined $Pages{$_};
+ $Pages{$_} .= "$dir/$_.pod:";
+ last;
+ }
+ }
+ close(F);
+ }
}
}
closedir(DIR);
my $level = $1;
if( $Listlevel ){
- warn "$0: $Podfile: unterminated list at =head in paragraph $Paragraph. ignoring.\n";
+ warn "$0: $Podfile: unterminated list at =head in paragraph $Paragraph. ignoring.\n" unless $Quiet;
while( $Listlevel ){
process_back();
}
sub emit_item_tag($$$){
my( $otext, $text, $compact ) = @_;
- my $item = fragment_id( $text );
-
+ my $item = fragment_id( depod($text) , -generate);
+ Carp::confess("Undefined fragment '$text' (".depod($text).") from fragment_id() in emit_item_tag() in $Podfile")
+ if !defined $item;
$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><br />\n";
+ print HTML "</strong>\n";
undef( $EmittedItem );
}
# bad! but, the proper thing to do seems to be to just assume
# they did do an =over. so warn them once and then continue.
if( $Listlevel == 0 ){
- warn "$0: $Podfile: unexpected =item directive in paragraph $Paragraph. ignoring.\n";
+ warn "$0: $Podfile: unexpected =item directive in paragraph $Paragraph. ignoring.\n" unless $Quiet;
process_over();
}
# formatting: insert a paragraph if preceding item has >1 paragraph
if( $After_Lpar ){
- print HTML "<p></p>\n";
+ print HTML $need_dd ? "</dd>\n" : "</li>\n" if $After_Lpar;
$After_Lpar = 0;
}
# all the list variants:
if( $text =~ /\A\*/ ){ # bullet
$emitted = emit_li( 'ul' );
- if ($text =~ /\A\*\s+(.+)\Z/s ) { # with additional text
+ if ($text =~ /\A\*\s+(\S.*)\Z/s ) { # with additional text
my $tag = $1;
$otext =~ s/\A\*\s+//;
emit_item_tag( $otext, $tag, 1 );
} elsif( $text =~ /\A\d+/ ){ # numbered list
$emitted = emit_li( 'ol' );
- if ($text =~ /\A(?>\d+\.?)\s*(.+)\Z/s ) { # with additional text
+ if ($text =~ /\A(?>\d+\.?)\s*(\S.*)\Z/s ) { # with additional text
my $tag = $1;
$otext =~ s/\A\d+\.?\s*//;
emit_item_tag( $otext, $tag, 1 );
}
$need_dd = 1;
}
- print HTML "</$emitted>" if $emitted;
print HTML "\n";
return $need_dd;
}
# process_back - process a pod back tag and convert it to HTML format.
#
sub process_back {
+ my $need_dd = shift;
if( $Listlevel == 0 ){
- warn "$0: $Podfile: unexpected =back directive in paragraph $Paragraph. ignoring.\n";
+ warn "$0: $Podfile: unexpected =back directive in paragraph $Paragraph. ignoring.\n" unless $Quiet;
return;
}
# $Listend[$Listlevel] may have never been initialized.
$Listlevel--;
if( defined $Listend[$Listlevel] ){
- print HTML '<p></p>' if $After_Lpar;
+ print HTML $need_dd ? "</dd>\n" : "</li>\n" if $After_Lpar;
print HTML $Listend[$Listlevel];
print HTML "\n";
pop( @Listend );
sub process_end {
my($whom, $text) = @_;
$whom = lc($whom);
- if ($Begin_Stack[-1] ne $whom ) {
- die "Unmatched begin/end at chunk $Paragraph\n"
+ if (!defined $Begin_Stack[-1] or $Begin_Stack[-1] ne $whom ) {
+ Carp::confess("Unmatched begin/end at chunk $Paragraph in pod $Podfile\n")
}
pop( @Begin_Stack );
}
#
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
+ ## Guessing at func() or [\$\@%&]*var references in plain text is destined
## to produce some strange looking ref's. uncomment to disable:
## $notinIS = 0;
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 : "");
foreach my $word (@words) {
# skip space runs
next if $word =~ /^\s*$/;
- # see if we can infer a link
- if( $notinIS && $word =~ /^(\w+)\((.*)\)$/ ) {
+ # see if we can infer a link or a function call
+ #
+ # NOTE: This is a word based search, it won't automatically
+ # mark "substr($var, 1, 2)" because the 1st word would be "substr($var"
+ # User has to enclose those with proper C<>
+
+ if( $notinIS && $word =~
+ m/
+ ^([a-z_]{2,}) # The function name
+ \(
+ ([0-9][a-z]* # Manual page(1) or page(1M)
+ |[^)]*[\$\@\%][^)]+ # ($foo), (1, @foo), (%hash)
+ | # ()
+ )
+ \)
+ ([.,;]?)$ # a possible punctuation follows
+ /xi
+ ) {
# has parenthesis so should have been a C<> ref
## try for a pagename (perlXXX(1))?
- my( $func, $args ) = ( $1, $2 );
+ my( $func, $args, $rest ) = ( $1, $2, $3 || '' );
if( $args =~ /^\d+$/ ){
my $url = page_sect( $word, '' );
if( defined $url ){
- $word = "<a href=\"$url\">the $word manpage</a>";
+ $word = qq(<a href="$url" class="man">the $word manpage</a>$rest);
next;
}
}
## try function name for a link, append tt'ed argument list
- $word = emit_C( $func, '', "($args)");
+ $word = emit_C( $func, '', "($args)") . $rest;
#### disabled. either all (including $\W, $\w+{.*} etc.) or nothing.
## } elsif( $notinIS && $word =~ /^[\$\@%&*]+\w+$/) {
#
sub process_text1($$;$$);
-sub pattern ($) { $_[0] ? '[^\S\n]+'.('>' x ($_[0] + 1)) : '>' }
-sub closing ($) { local($_) = shift; (defined && s/\s+$//) ? length : 0 }
+sub pattern ($) { $_[0] ? '\s+'.('>' x ($_[0] + 1)) : '>' }
+sub closing ($) { local($_) = shift; (defined && s/\s+\z//) ? length : 0 }
sub process_text {
return if $Ignore;
my( $tref ) = @_;
my $res = process_text1( 0, $tref );
+ $res =~ s/\s+$//s;
$$tref = $res;
}
+sub process_text_rfc_links {
+ my $text = shift;
+
+ # For every "RFCnnnn" or "RFC nnn", link it to the authoritative
+ # ource. Do not use the /i modifier here. Require "RFC" to be written in
+ # in capital letters.
+
+ $text =~ s{
+ (?<=[^<>[:alpha:]]) # Make sure this is not an URL already
+ (RFC\s*([0-9]{1,5}))(?![0-9]) # max 5 digits
+ }
+ {<a href="http://www.ietf.org/rfc/rfc$2.txt" class="rfc">$1</a>}gx;
+
+ $text;
+}
+
sub process_text1($$;$$){
my( $lev, $rstr, $func, $closing ) = @_;
my $res = '';
$res = "&$escape;";
} elsif( $func eq 'F' ){
- # F<filename> - italizice
- $res = '<em>' . process_text1( $lev, $rstr ) . '</em>';
+ # F<filename> - italicize
+ $res = '<em class="file">' . process_text1( $lev, $rstr ) . '</em>';
} elsif( $func eq 'I' ){
- # I<text> - italizice
+ # I<text> - italicize
$res = '<em>' . process_text1( $lev, $rstr ) . '</em>';
} elsif( $func eq 'L' ){
# check for link patterns
if( $par =~ m{^([^/]+?)/(?!")(.*?)$} ){ # name/ident
# we've got a name/ident (no quotes)
- ( $page, $ident ) = ( $1, $2 );
+ if (length $2) {
+ ( $page, $ident ) = ( $1, $2 );
+ } else {
+ ( $page, $section ) = ( $1, $2 );
+ }
### print STDERR "--> L<$par> to page $page, ident $ident\n";
} elsif( $par =~ m{^(.*?)/"?(.*?)"?$} ){ # [name]/"section"
# warning; show some text.
$linktext = $opar unless defined $linktext;
- warn "$0: $Podfile: cannot resolve L<$opar> in paragraph $Paragraph.\n";
+ warn "$0: $Podfile: cannot resolve L<$opar> in paragraph $Paragraph.\n" unless $Quiet;
}
# now we have a URL or just plain code
} elsif( $func eq 'X' ){
# X<> - ignore
- $$rstr =~ s/^[^>]*>//;
-
+ warn "$0: $Podfile: invalid X<> in paragraph $Paragraph.\n"
+ unless $$rstr =~ s/^[^>]*>// or $Quiet;
} elsif( $func eq 'Z' ){
# Z<> - empty
- warn "$0: $Podfile: invalid X<> in paragraph $Paragraph.\n"
- unless $$rstr =~ s/^>//;
+ warn "$0: $Podfile: invalid Z<> in paragraph $Paragraph.\n"
+ unless $$rstr =~ s/^>// or $Quiet;
} else {
my $term = pattern $closing;
}
if( $lev == 1 ){
$res .= pure_text( $$rstr );
- } else {
- warn "$0: $Podfile: undelimited $func<> in paragraph $Paragraph.\n";
+ } elsif( ! $Quiet ) {
+ my $snippet = substr($$rstr,0,60);
+ warn "$0: $Podfile: undelimited $func<> in paragraph $Paragraph: '$snippet'.\n"
+
}
+ $res = process_text_rfc_links($res);
}
return $res;
}
my $res = '';
my @closing = ($closing);
while( $$rstr =~
- s/\A(.*?)(([BCEFILSXZ])<(<+[^\S\n]+)?|@{[pattern $closing[0]]})//s ){
+ s/\A(.*?)(([BCEFILSXZ])<(<+\s+)?|@{[pattern $closing[0]]})//s ){
$res .= $1;
unless( $3 ){
shift @closing;
}
$res .= $2;
}
- warn "$0: $Podfile: undelimited $func<> in paragraph $Paragraph.\n";
+ unless ($Quiet) {
+ my $snippet = substr($$rstr,0,60);
+ warn "$0: $Podfile: undelimited $func<> in paragraph $Paragraph (go_ahead): '$snippet'.\n"
+ }
return $res;
}
$section = "#$section" if $section;
### print STDERR "...section=$section\n";
- # check if there is a .pod with the page name
- if ($Pages{$page} =~ /([^:]*)\.pod:/) {
- $link = "$Htmlroot/$1.html$section";
- } elsif ($Pages{$page} =~ /([^:]*)\.pm:/) {
+ # check if there is a .pod with the page name.
+ # for L<Foo>, Foo.(pod|pm) is preferred to A/Foo.(pod|pm)
+ if ($Pages{$page} =~ /([^:]*)\.(?:pod|pm):/) {
$link = "$Htmlroot/$1.html$section";
} else {
$link = "";
my( $url );
my $fid = fragment_id( $item );
- if( defined( $page ) ){
+
+ if( defined( $page ) && $page ne "" ){
# we have been given a $page...
$page =~ s{::}{/}g;
+ Carp::confess("Undefined fragment '$item' from fragment_id() in coderef() in $Podfile")
+ if !defined $fid;
# Do we take it? Item could be a section!
my $base = $Items{$fid} || "";
$base =~ s{[^/]*/}{};
$heading =~ s/\s+\Z//;
$heading =~ s/\A\s+//;
# The hyphen is a disgrace to the English language.
- $heading =~ s/[-"?]//g;
+ # $heading =~ s/[-"?]//g;
+ $heading =~ s/["?]//g;
$heading = lc( $heading );
return $heading;
}
return $res unless defined $$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?
return $1 if $text =~ /->\s*(\w+)\s*\(?/;
# a variable name?
- return $1 if $text =~ /^([$@%*]\S+)/;
+ return $1 if $text =~ /^([\$\@%*]\S+)/;
# some pattern matching operator?
return $1 if $text =~ m|^(\w+/).*/\w*$|;
# 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;
}
}
projects / p5sagit/p5-mst-13.2.git / blobdiff