html.pm

UNIX下perl实现代码

package Pod::Html;
use strict;
require Exporter;

use vars qw($VERSION @ISA @EXPORT);
$VERSION = 1.03;
@ISA = qw(Exporter);
@EXPORT = qw(pod2html htmlify);

use Carp;
use Config;
use Cwd;
use File::Spec::Unix;
use Getopt::Long;
use Pod::Functions;

use locale;	# make \w work right in non-ASCII lands

=head1 NAME

Pod::Html - module to convert pod files to HTML

=head1 SYNOPSIS

    use Pod::Html;
    pod2html([options]);

=head1 DESCRIPTION

Converts files from pod format (see L<perlpod>) to HTML format.  It
can automatically generate indexes and cross-references, and it keeps
a cache of things it knows how to cross-reference.

=head1 ARGUMENTS

Pod::Html takes the following arguments:

=over 4

=item backlink

    --backlink="Back to Top"

Adds "Back to Top" links in front of every HEAD1 heading (except for
the first).  By default, no backlink are being generated.

=item css

    --css=stylesheet

Specify the URL of a cascading style sheet.

=item flush

    --flush

Flushes the item and directory caches.

=item header

    --header
    --noheader

Creates header and footer blocks containing the text of the NAME
section.  By default, no headers are being generated.

=item help

    --help

Displays the usage message.

=item htmldir

    --htmldir=name

Sets the directory in which the resulting HTML file is placed.  This
is used to generate relative links to other files. Not passing this
causes all links to be absolute, since this is the value that tells
Pod::Html the root of the documentation tree.

=item htmlroot

    --htmlroot=name

Sets the base URL for the HTML files.  When cross-references are made,
the HTML root is prepended to the URL.

=item index

    --index
    --noindex

Generate an index at the top of the HTML file.  This is the default
behaviour.

=item infile

    --infile=name

Specify the pod file to convert.  Input is taken from STDIN if no
infile is specified.

=item libpods

    --libpods=name:...:name

List of page names (eg, "perlfunc") which contain linkable C<=item>s.

=item netscape

    --netscape
    --nonetscape

Use Netscape HTML directives when applicable.  By default, they will
B<not> be used.

=item outfile

    --outfile=name

Specify the HTML file to create.  Output goes to STDOUT if no outfile
is specified.

=item podpath

    --podpath=name:...:name

Specify which subdirectories of the podroot contain pod files whose
HTML converted forms can be linked-to in cross-references.

=item podroot

    --podroot=name

Specify the base directory for finding library pods.

=item quiet

    --quiet
    --noquiet

Don't display I<mostly harmless> warning messages.  These messages
will be displayed by default.  But this is not the same as C<verbose>
mode.

=item recurse

    --recurse
    --norecurse

Recurse into subdirectories specified in podpath (default behaviour).

=item title

    --title=title

Specify the title of the resulting HTML file.

=item verbose

    --verbose
    --noverbose

Display progress messages.  By default, they won't be displayed.

=back

=head1 EXAMPLE

    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");

=head1 ENVIRONMENT

Uses $Config{pod2html} to setup default options.

=head1 AUTHOR

Tom Christiansen, E<lt>[e-mail]<gt>.

=head1 SEE ALSO

L<perlpod>

=head1 COPYRIGHT

This program is distributed under the Artistic License.

=cut

my $cache_ext = $^O eq 'VMS' ? ".tmp" : ".x~~";
my $dircache = "pod2htmd$cache_ext";
my $itemcache = "pod2htmi$cache_ext";

my @begin_stack = ();		# begin/end stack

my @libpods = ();	    	# files to search for links from C<> directives
my $htmlroot = "/";	    	# http-server base directory from which all
				#   relative paths in $podpath stem.
my $htmldir = "";		# The directory to which the html pages
				# will (eventually) be written.
my $htmlfile = "";		# write to stdout by default
my $htmlfileurl = "" ;		# The url that other files would use to
				# refer to this file.  This is only used
				# to make relative urls that point to
				# other files.
my $podfile = "";		# read from stdin by default
my @podpath = ();		# list of directories containing library pods.
my $podroot = ".";		# filesystem base directory from which all
				#   relative paths in $podpath stem.
my $css = '';                   # Cascading style sheet
my $recurse = 1;		# recurse on subdirectories in $podpath.
my $quiet = 0;			# not quiet by default
my $verbose = 0;		# not verbose by default
my $doindex = 1;   	    	# non-zero if we should generate an index
my $backlink = '';              # text for "back to top" links
my $listlevel = 0;		# current list depth
my @listend = ();		# the text to use to end the list.
my $after_lpar = 0;             # set to true after a par in an =item
my $ignore = 1;			# whether or not to format text.  we don't
				#   format text until we hit our first pod
				#   directive.

my %items_named = ();		# for the multiples of the same item in perlfunc
my @items_seen = ();
my $netscape = 0;		# whether or not to use netscape directives.
my $title;			# title to give the pod(s)
my $header = 0;			# produce block header/footer
my $top = 1;			# true if we are at the top of the doc.  used
				#   to prevent the first <HR> directive.
my $paragraph;			# which paragraph we're processing (used
				#   for error messages)
my $ptQuote = 0;                # status of double-quote conversion
my %pages = ();			# associative array used to find the location
				#   of pages referenced by L<> links.
my %sections = ();		# sections within this page
my %items = ();			# associative array used to find the location
				#   of =item directives referenced by C<> links
my %local_items = ();           # local items - avoid destruction of %items
my $Is83;                       # is dos with short filenames (8.3)

sub init_globals {
$dircache = "pod2htmd$cache_ext";
$itemcache = "pod2htmi$cache_ext";

@begin_stack = ();		# begin/end stack

@libpods = ();	    	# files to search for links from C<> directives
$htmlroot = "/";	    	# http-server base directory from which all
				#   relative paths in $podpath stem.
$htmldir = "";	    	# The directory to which the html pages
				# will (eventually) be written.
$htmlfile = "";		# write to stdout by default
$podfile = "";		# read from stdin by default
@podpath = ();		# list of directories containing library pods.
$podroot = ".";		# filesystem base directory from which all
				#   relative paths in $podpath stem.
$css = '';                   # Cascading style sheet
$recurse = 1;		# recurse on subdirectories in $podpath.
$quiet = 0;		# not quiet by default
$verbose = 0;		# not verbose by default
$doindex = 1;   	    	# non-zero if we should generate an index
$backlink = '';		# text for "back to top" links
$listlevel = 0;		# current list depth
@listend = ();		# the text to use to end the list.
$after_lpar = 0;        # set to true after a par in an =item
$ignore = 1;			# whether or not to format text.  we don't
				#   format text until we hit our first pod
				#   directive.

@items_seen = ();
%items_named = ();
$netscape = 0;		# whether or not to use netscape directives.
$header = 0;			# produce block header/footer
$title = '';			# title to give the pod(s)
$top = 1;			# true if we are at the top of the doc.  used
				#   to prevent the first <HR> directive.
$paragraph = '';			# which paragraph we're processing (used
				#   for error messages)
%sections = ();		# sections within this page

# These are not reinitialised here but are kept as a cache.
# See get_cache and related cache management code.
#%pages = ();			# associative array used to find the location
				#   of pages referenced by L<> links.
#%items = ();			# associative array used to find the location
				#   of =item directives referenced by C<> links
%local_items = ();
$Is83=$^O eq 'dos';
}

#
# clean_data: global clean-up of pod data
#
sub clean_data($){
    my( $dataref ) = @_;
    my $i;
    for( $i = 0; $i <= $#$dataref; $i++ ){
	${$dataref}[$i] =~ s/\s+\Z//;

        # have a look for all-space lines
	if( ${$dataref}[$i] =~ /^\s+$/m ){
	    my @chunks = split( /^\s+$/m, ${$dataref}[$i] );
	    splice( @$dataref, $i, 1, @chunks );
	}
    }
}


sub pod2html {
    local(@ARGV) = @_;
    local($/);
    local $_;

    init_globals();

    $Is83 = 0 if (defined (&Dos::UseLFN) && Dos::UseLFN());

    # cache of %pages and %items from last time we ran pod2html

    #undef $opt_help if defined $opt_help;

    # parse the command-line parameters
    parse_command_line();

    # set some variables to their default values if necessary
    local *POD;
    unless (@ARGV && $ARGV[0]) { 
	$podfile  = "-" unless $podfile;	# stdin
	open(POD, "<$podfile")
		|| die "$0: cannot open $podfile file for input: $!\n";
    } else {
	$podfile = $ARGV[0];  # XXX: might be more filenames
	*POD = *ARGV;
    } 
    $htmlfile = "-" unless $htmlfile;	# stdout
    $htmlroot = "" if $htmlroot eq "/";	# so we don't get a //
    $htmldir =~ s#/\z## ;               # so we don't get a //
    if (  $htmlroot eq ''
       && defined( $htmldir ) 
       && $htmldir ne ''
       && substr( $htmlfile, 0, length( $htmldir ) ) eq $htmldir 
       ) 
    {
	# Set the 'base' url for this file, so that we can use it
	# as the location from which to calculate relative links 
	# to other files. If this is '', then absolute links will
	# be used throughout.
        $htmlfileurl= "$htmldir/" . substr( $htmlfile, length( $htmldir ) + 1);
    }

    # read the pod a paragraph at a time
    warn "Scanning for sections in input file(s)\n" if $verbose;
    $/ = "";
    my @poddata  = <POD>;
    close(POD);
    clean_data( \@poddata );

    # scan the pod for =head[1-6] directives and build an index
    my $index = scan_headings(\%sections, @poddata);

    unless($index) {
	warn "No headings in $podfile\n" if $verbose;
    }

    # open the output file
    open(HTML, ">$htmlfile")
	    || die "$0: cannot open $htmlfile file for output: $!\n";

    # put a title in the HTML file if one wasn't specified
    if ($title eq '') {
	TITLE_SEARCH: {
	    for (my $i = 0; $i < @poddata; $i++) { 
		if ($poddata[$i] =~ /^=head1\s*NAME\b/m) {
		    for my $para ( @poddata[$i, $i+1] ) { 
			last TITLE_SEARCH
			    if ($title) = $para =~ /(\S+\s+-+.*\S)/s;
		    }
		} 

	    } 
	}
    }
    if (!$title and $podfile =~ /\.pod\z/) {
	# probably a split pod so take first =head[12] as title
	for (my $i = 0; $i < @poddata; $i++) { 
	    last if ($title) = $poddata[$i] =~ /^=head[12]\s*(.*)/;
	} 
	warn "adopted '$title' as title for $podfile\n"
	    if $verbose and $title;
    } 
    if ($title) {
	$title =~ s/\s*\(.*\)//;
    } else {
	warn "$0: no title for $podfile" unless $quiet;
	$podfile =~ /^(.*)(\.[^.\/]+)?\z/s;
	$title = ($podfile eq "-" ? 'No Title' : $1);
	warn "using $title" if $verbose;
    }
    my $csslink = $css ? qq(\n<LINK REL="stylesheet" HREF="$css" TYPE="text/css">) : '';
    $csslink =~ s,\\,/,g;
    $csslink =~ s,(/.):,$1|,;

    my $block = $header ? <<END_OF_BLOCK : '';
<TABLE BORDER=0 CELLPADDING=0 CELLSPACING=0 WIDTH=100%>
<TR><TD CLASS=block VALIGN=MIDDLE WIDTH=100% BGCOLOR="#cccccc">
<FONT SIZE=+1><STRONG><P CLASS=block>&nbsp;$title</P></STRONG></FONT>
</TD></TR>
</TABLE>
END_OF_BLOCK

    print HTML <<END_OF_HEAD;
<HTML>
<HEAD>
<TITLE>$title</TITLE>$csslink
<LINK REV="made" HREF="mailto:$Config{perladmin}">
</HEAD>

<BODY>
$block
END_OF_HEAD

    # load/reload/validate/cache %pages and %items
    get_cache($dircache, $itemcache, \@podpath, $podroot, $recurse);

    # scan the pod for =item directives
    scan_items( \%local_items, "", @poddata);

    # put an index at the top of the file.  note, if $doindex is 0 we
    # 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 "<A NAME=\"__index__\"></A>\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;

    # now convert this file
    my $after_item;             # set to true after an =item
    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?
	    $ignore = 0;
	    $after_item = 0;
	    $_ = $1;
	    if (/^=begin\s+(\S+)\s*(.*)/si) {# =begin
		process_begin($1, $2);
	    } elsif (/^=end\s+(\S+)\s*(.*)/si) {# =end
		process_end($1, $2);
	    } elsif (/^=cut/) {			# =cut
		process_cut();
	    } elsif (/^=pod/) {			# =pod
		process_pod();
	    } else {
		next if @begin_stack && $begin_stack[-1] ne 'html';

		if (/^=(head[1-6])\s+(.*\S)/s) {	# =head[1-6] heading
		    process_head( $1, $2, $doindex && $index );
		} elsif (/^=item\s*(.*\S)?/sm) {	# =item text
		    warn "$0: $podfile: =item without bullet, number or text"
		       . " in paragraph $paragraph.\n" if !defined($1) or $1 eq '';
		    process_item( $1 );
		    $after_item = 1;
		} elsif (/^=over\s*(.*)/) {		# =over N
		    process_over();
		} elsif (/^=back/) {		# =back
		    process_back();
		} 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";
		}
	    }
	    $top = 0;
	}
	else {
	    next if $ignore;
	    next if @begin_stack && $begin_stack[-1] ne 'html';
	    my $text = $_;
	    if( $text =~ /\A\s+/ ){
		process_pre( \$text );
	        print HTML "<PRE>\n$text</PRE>\n";

	    } else {
		process_text( \$text );

		# experimental: check for a paragraph where all lines
		# have some ...\t...\t...\n pattern
		if( $text =~ /\t/ ){
		    my @lines = split( "\n", $text );
		    if( @lines > 1 ){