586 lines
17 KiB
Perl
586 lines
17 KiB
Perl
#!./perl -Ilib -w
|
|
|
|
# This file should really be extracted from a .PL file
|
|
|
|
use strict;
|
|
use Config; # for config options in the makefile
|
|
use File::Path qw(remove_tree);
|
|
use File::Spec::Functions qw(rel2abs no_upwards);
|
|
use Getopt::Long; # for command-line parsing
|
|
use Cwd;
|
|
use Pod::Html 1.23 qw(anchorify relativize_url);
|
|
|
|
=head1 NAME
|
|
|
|
installhtml - converts a collection of POD pages to HTML format.
|
|
|
|
=head1 SYNOPSIS
|
|
|
|
installhtml [--help] [--podpath=<name>:...:<name>] [--podroot=<name>]
|
|
[--htmldir=<name>] [--htmlroot=<name>] [--norecurse] [--recurse]
|
|
[--splithead=<name>,...,<name>] [--splititem=<name>,...,<name>]
|
|
[--ignore=<name>,...,<name>] [--verbose]
|
|
|
|
=head1 DESCRIPTION
|
|
|
|
I<installhtml> converts a collection of POD pages to a corresponding
|
|
collection of HTML pages. This is used to convert the pod pages found in the
|
|
perl distribution. (It is not intended as a general-purpose
|
|
converter/installer of POD pages in HTML format. See L<Pod::Html>.)
|
|
|
|
=head1 OPTIONS
|
|
|
|
=over 4
|
|
|
|
=item B<--help> help
|
|
|
|
Displays the usage.
|
|
|
|
=item B<--podroot> POD search path base directory
|
|
|
|
The base directory to search for all .pod and .pm files to be converted.
|
|
Default is current directory.
|
|
|
|
=item B<--podpath> POD search path
|
|
|
|
The list of directories to search for .pod and .pm files to be converted.
|
|
Default is 'podroot/.'.
|
|
|
|
=item B<--recurse> recurse on subdirectories
|
|
|
|
Whether or not to convert all .pm and .pod files found in subdirectories
|
|
too. Default is to not recurse.
|
|
|
|
=item B<--htmldir> HTML destination directory
|
|
|
|
The base directory which all HTML files will be written to. This should
|
|
be a path relative to the filesystem, not the resulting URL.
|
|
|
|
=item B<--htmlroot> URL base directory
|
|
|
|
The base directory which all resulting HTML files will be visible at in
|
|
a URL. The default is '/'.
|
|
|
|
=item B<--splithead> POD files to split on =head directive
|
|
|
|
Comma-separated list of pod files to split by the =head directive. The
|
|
.pod suffix is optional. These files should have names specified
|
|
relative to podroot.
|
|
|
|
=item B<--splititem> POD files to split on =item directive
|
|
|
|
Comma-separated list of all pod files to split by the =item directive. The
|
|
.pod suffix is optional. I<installhtml> does not do the actual split, rather
|
|
it invokes I<splitpod>, a separate program in the Perl 5 core distribution,
|
|
to do the dirty work. As with --splithead, these files should have names
|
|
specified relative to podroot.
|
|
|
|
=item B<--splitpod> Directory containing the splitpod program
|
|
|
|
The directory containing the splitpod program. The default is 'podroot/pod'.
|
|
|
|
=item B<--ignore> files to be ignored
|
|
|
|
Comma-separated of files that shouldn't be installed, given relative
|
|
to podroot.
|
|
|
|
=item B<--verbose> verbose output
|
|
|
|
Self-explanatory.
|
|
|
|
=back
|
|
|
|
=head1 EXAMPLE
|
|
|
|
The following command-line is an example of the one we use to convert
|
|
perl documentation:
|
|
|
|
./installhtml --podpath=lib:ext:pod:vms \
|
|
--podroot=/usr/src/perl \
|
|
--htmldir=/perl/nmanual \
|
|
--htmlroot=/perl/nmanual \
|
|
--splithead=pod/perlipc \
|
|
--splititem=pod/perlfunc \
|
|
--recurse \
|
|
--verbose
|
|
|
|
=head1 AUTHOR
|
|
|
|
Chris Hall E<lt>hallc@cs.colorado.eduE<gt>
|
|
|
|
=cut
|
|
|
|
my $usage;
|
|
|
|
$usage =<<END_OF_USAGE;
|
|
Usage: $0 --help --podpath=<name>:...:<name> --podroot=<name>
|
|
--htmldir=<name> --htmlroot=<name> --norecurse --recurse
|
|
--splithead=<name>,...,<name> --splititem=<name>,...,<name>
|
|
--ignore=<name>,...,<name> --verbose
|
|
|
|
--help - this message
|
|
--podpath - colon-separated list of directories containing .pod and
|
|
.pm files to be converted (. by default).
|
|
--podroot - filesystem base directory from which all relative paths in
|
|
podpath stem (default is .).
|
|
--htmldir - directory to store resulting html files in relative
|
|
to the filesystem (\$podroot/html by default).
|
|
--htmlroot - http-server base directory from which all relative paths
|
|
in podpath stem (default is /).
|
|
--norecurse - don't recurse on those subdirectories listed in podpath.
|
|
(default behavior).
|
|
--recurse - recurse on those subdirectories listed in podpath
|
|
--splithead - comma-separated list of .pod or .pm files to split. will
|
|
split each file into several smaller files at every occurrence
|
|
of a pod =head[1-6] directive.
|
|
--splititem - comma-separated list of .pod or .pm files to split using
|
|
splitpod.
|
|
--splitpod - directory where the program splitpod can be found
|
|
(\$podroot/pod by default).
|
|
--ignore - comma-separated list of files that shouldn't be installed.
|
|
--verbose - self-explanatory.
|
|
|
|
END_OF_USAGE
|
|
|
|
my (@podpath, $podroot, $htmldir, $htmlroot, $recurse, @splithead,
|
|
@splititem, $splitpod, $verbose, $pod2html, @ignore);
|
|
|
|
@podpath = ( "." ); # colon-separated list of directories containing .pod
|
|
# and .pm files to be converted.
|
|
$podroot = "."; # assume the pods we want are here
|
|
$htmldir = ""; # nothing for now...
|
|
$htmlroot = "/"; # default value
|
|
$recurse = 0; # default behavior
|
|
@splithead = (); # don't split any files by default
|
|
@splititem = (); # don't split any files by default
|
|
$splitpod = ""; # nothing for now.
|
|
|
|
$verbose = 0; # whether or not to print debugging info
|
|
|
|
$pod2html = "pod/pod2html";
|
|
|
|
usage("") unless @ARGV;
|
|
|
|
# Overcome shell's p1,..,p8 limitation.
|
|
# See vms/descrip_mms.template -> descrip.mms for invocation.
|
|
if ( $^O eq 'VMS' ) { @ARGV = split(/\s+/,$ARGV[0]); }
|
|
|
|
our %Options;
|
|
|
|
# parse the command-line
|
|
my $result = GetOptions( \%Options, qw(
|
|
help
|
|
podpath=s
|
|
podroot=s
|
|
htmldir=s
|
|
htmlroot=s
|
|
ignore=s
|
|
recurse!
|
|
splithead=s
|
|
splititem=s
|
|
splitpod=s
|
|
verbose
|
|
));
|
|
usage("invalid parameters") unless $result;
|
|
parse_command_line();
|
|
|
|
|
|
# set these variables to appropriate values if the user didn't specify
|
|
# values for them.
|
|
$htmldir = "$htmlroot/html" unless $htmldir;
|
|
$splitpod = "$podroot/pod" unless $splitpod;
|
|
|
|
|
|
# make sure that the destination directory exists
|
|
(mkdir($htmldir, 0755) ||
|
|
die "$0: cannot make directory $htmldir: $!\n") if ! -d $htmldir;
|
|
|
|
|
|
# the following array will eventually contain files that are to be
|
|
# ignored in the conversion process. these are files that have been
|
|
# process by splititem or splithead and should not be converted as a
|
|
# result.
|
|
my @splitdirs;
|
|
|
|
# split pods. It's important to do this before convert ANY pods because
|
|
# it may affect some of the links
|
|
@splitdirs = (); # files in these directories won't get an index
|
|
split_on_head($podroot, $htmldir, \@splitdirs, \@ignore, @splithead);
|
|
split_on_item($podroot, \@splitdirs, \@ignore, @splititem);
|
|
|
|
|
|
# convert the pod pages found in @poddirs
|
|
#warn "converting files\n" if $verbose;
|
|
#warn "\@ignore\t= @ignore\n" if $verbose;
|
|
foreach my $dir (@podpath) {
|
|
installdir($dir, $recurse, $podroot, \@splitdirs, \@ignore);
|
|
}
|
|
|
|
|
|
# now go through and create master indices for each pod we split
|
|
foreach my $dir (@splititem) {
|
|
print "creating index $htmldir/$dir.html\n" if $verbose;
|
|
create_index("$htmldir/$dir.html", "$htmldir/$dir");
|
|
}
|
|
|
|
foreach my $dir (@splithead) {
|
|
(my $pod = $dir) =~ s,^.*/,,;
|
|
$dir .= ".pod" unless $dir =~ /(\.pod|\.pm)$/;
|
|
# let pod2html create the file
|
|
runpod2html($dir, 1);
|
|
|
|
# now go through and truncate after the index
|
|
$dir =~ /^(.*?)(\.pod|\.pm)?$/sm;
|
|
my $file = "$htmldir/$1";
|
|
print "creating index $file.html\n" if $verbose;
|
|
|
|
# read in everything until what would have been the first =head
|
|
# directive, patching the index as we go.
|
|
open(H, '<', "$file.html") ||
|
|
die "$0: error opening $file.html for input: $!\n";
|
|
$/ = "";
|
|
my @data = ();
|
|
while (<H>) {
|
|
last if m!<h1 id="NAME">NAME</h1>!;
|
|
$_ =~ s{href="#(.*)">}{
|
|
my $url = "$file/@{[anchorify(qq($1))]}.html" ;
|
|
$url = relativize_url( $url, "$file.html" )
|
|
if ( ! defined $Options{htmlroot} || $Options{htmlroot} eq '' );
|
|
"href=\"$url\">" ;
|
|
}egi;
|
|
push @data, $_;
|
|
}
|
|
close(H);
|
|
|
|
# now rewrite the file
|
|
open(H, '>', "$file.html") ||
|
|
die "$0: error opening $file.html for output: $!\n";
|
|
print H @data, "</body>\n\n</html>\n\n\n";
|
|
close(H);
|
|
}
|
|
|
|
remove_tree(@splitdirs, {safe=>1});
|
|
|
|
##############################################################################
|
|
|
|
|
|
sub usage {
|
|
warn "$0: @_\n" if @_;
|
|
die $usage;
|
|
}
|
|
|
|
|
|
sub parse_command_line {
|
|
usage() if defined $Options{help};
|
|
$Options{help} = ""; # make -w shut up
|
|
|
|
# list of directories
|
|
@podpath = split(":", $Options{podpath}) if defined $Options{podpath};
|
|
|
|
# lists of files
|
|
@splithead = split(",", $Options{splithead}) if defined $Options{splithead};
|
|
@splititem = split(",", $Options{splititem}) if defined $Options{splititem};
|
|
|
|
$htmldir = $Options{htmldir} if defined $Options{htmldir};
|
|
$htmlroot = $Options{htmlroot} if defined $Options{htmlroot};
|
|
$podroot = $Options{podroot} if defined $Options{podroot};
|
|
$splitpod = $Options{splitpod} if defined $Options{splitpod};
|
|
|
|
$recurse = $Options{recurse} if defined $Options{recurse};
|
|
$verbose = $Options{verbose} if defined $Options{verbose};
|
|
|
|
@ignore = map "$podroot/$_", split(",", $Options{ignore}) if defined $Options{ignore};
|
|
}
|
|
|
|
|
|
sub create_index {
|
|
my($html, $dir) = @_;
|
|
(my $pod = $dir) =~ s,^.*/,,;
|
|
|
|
# get the list of .html files in this directory
|
|
opendir(DIR, $dir) ||
|
|
die "$0: error opening directory $dir for reading: $!\n";
|
|
my @files = sort(grep(/\.html?$/, readdir(DIR)));
|
|
closedir(DIR);
|
|
|
|
open(HTML, '>', $html) ||
|
|
die "$0: error opening $html for output: $!\n";
|
|
|
|
# for each .html file in the directory, extract the index
|
|
# embedded in the file and throw it into the big index.
|
|
print HTML "<DL COMPACT>\n";
|
|
foreach my $file (@files) {
|
|
|
|
my $filedata = do {
|
|
open(my $in, '<', "$dir/$file") ||
|
|
die "$0: error opening $dir/$file for input: $!\n";
|
|
local $/ = undef;
|
|
<$in>;
|
|
};
|
|
|
|
# pull out the NAME section
|
|
my($lcp1, $lcp2) =
|
|
($filedata =~
|
|
m#<h1 id="NAME">NAME</h1>\s*<p>\s*(\S+)\s+-\s+(\S.*?\S)</p>#);
|
|
defined $lcp1 or die "$0: can't find NAME section in $dir/$file\n";
|
|
|
|
my $url= "$dir/$file" ;
|
|
if ( ! defined $Options{htmlroot} || $Options{htmlroot} eq '' ) {
|
|
$url = relativize_url( $url, $html ) ;
|
|
}
|
|
|
|
print HTML qq(<DT><A HREF="$url">);
|
|
print HTML "$lcp1</A></DT><DD>$lcp2</DD>\n";
|
|
}
|
|
print HTML "</DL>\n";
|
|
|
|
close(HTML);
|
|
}
|
|
|
|
|
|
sub split_on_head {
|
|
my($podroot, $htmldir, $splitdirs, $ignore, @splithead) = @_;
|
|
my($pod, $dirname, $filename);
|
|
|
|
# split the files specified in @splithead on =head[1-6] pod directives
|
|
print "splitting files by head.\n" if $verbose && $#splithead >= 0;
|
|
foreach $pod (@splithead) {
|
|
# figure out the directory name and filename
|
|
$pod =~ s,^([^/]*)$,/$1,;
|
|
$pod =~ m,(.*)/(.*?)(\.pod)?$,;
|
|
$dirname = $1;
|
|
$filename = "$2.pod";
|
|
|
|
# since we are splitting this file it shouldn't be converted.
|
|
push(@$ignore, "$podroot/$dirname/$filename");
|
|
|
|
# split the pod
|
|
splitpod("$podroot/$dirname/$filename", "$podroot/$dirname", $htmldir,
|
|
$splitdirs);
|
|
}
|
|
}
|
|
|
|
|
|
sub split_on_item {
|
|
my($podroot, $splitdirs, $ignore, @splititem) = @_;
|
|
my($pwd, $dirname, $filename);
|
|
|
|
print "splitting files by item.\n" if $verbose && $#splititem >= 0;
|
|
$pwd = getcwd();
|
|
my $splitter = rel2abs("$splitpod/splitpod", $pwd);
|
|
my $perl = rel2abs($^X, $pwd);
|
|
foreach my $pod (@splititem) {
|
|
# figure out the directory to split into
|
|
$pod =~ s,^([^/]*)$,/$1,;
|
|
$pod =~ m,(.*)/(.*?)(\.pod)?$,;
|
|
$dirname = "$1/$2";
|
|
$filename = "$2.pod";
|
|
|
|
# since we are splitting this file it shouldn't be converted.
|
|
push(@$ignore, "$podroot/$dirname.pod");
|
|
|
|
# split the pod
|
|
push(@$splitdirs, "$podroot/$dirname");
|
|
-d "$podroot/$dirname" and remove_tree("$podroot/$dirname", {safe=>1});
|
|
mkdir("$podroot/$dirname", 0755) ||
|
|
die "$0: error creating directory $podroot/$dirname: $!\n";
|
|
chdir("$podroot/$dirname") ||
|
|
die "$0: error changing to directory $podroot/$dirname: $!\n";
|
|
die "$splitter not found. Use '-splitpod dir' option.\n"
|
|
unless -f $splitter;
|
|
system($perl, $splitter, "../$filename") &&
|
|
warn "$0: error running '$splitter ../$filename'"
|
|
." from $podroot/$dirname";
|
|
}
|
|
chdir($pwd);
|
|
}
|
|
|
|
|
|
#
|
|
# splitpod - splits a .pod file into several smaller .pod files
|
|
# where a new file is started each time a =head[1-6] pod directive
|
|
# is encountered in the input file.
|
|
#
|
|
sub splitpod {
|
|
my($pod, $poddir, $htmldir, $splitdirs) = @_;
|
|
my(@poddata, @filedata, @heads);
|
|
my($file, $i, $j, $prevsec, $section, $nextsec);
|
|
|
|
print "splitting $pod\n" if $verbose;
|
|
|
|
# read the file in paragraphs
|
|
$/ = "";
|
|
open(SPLITIN, '<', $pod) ||
|
|
die "$0: error opening $pod for input: $!\n";
|
|
@filedata = <SPLITIN>;
|
|
close(SPLITIN) ||
|
|
die "$0: error closing $pod: $!\n";
|
|
|
|
# restore the file internally by =head[1-6] sections
|
|
@poddata = ();
|
|
for ($i = 0, $j = -1; $i <= $#filedata; $i++) {
|
|
$j++ if ($filedata[$i] =~ /^\s*=head[1-6]/);
|
|
if ($j >= 0) {
|
|
$poddata[$j] = "" unless defined $poddata[$j];
|
|
$poddata[$j] .= "\n$filedata[$i]" if $j >= 0;
|
|
}
|
|
}
|
|
|
|
# create list of =head[1-6] sections so that we can rewrite
|
|
# L<> links as necessary.
|
|
my %heads = ();
|
|
foreach $i (0..$#poddata) {
|
|
$heads{anchorify($1)} = 1 if $poddata[$i] =~ /=head[1-6]\s+(.*)/;
|
|
}
|
|
|
|
# create a directory of a similar name and store all the
|
|
# files in there
|
|
$pod =~ s,.*/(.*),$1,; # get the last part of the name
|
|
my $dir = $pod;
|
|
$dir =~ s/\.pod//g;
|
|
push(@$splitdirs, "$poddir/$dir");
|
|
-d "$poddir/$dir" and remove_tree("$poddir/$dir", {safe=>1});
|
|
mkdir("$poddir/$dir", 0755) ||
|
|
die "$0: could not create directory $poddir/$dir: $!\n";
|
|
|
|
$poddata[0] =~ /^\s*=head[1-6]\s+(.*)/;
|
|
$section = "";
|
|
$nextsec = $1;
|
|
|
|
# for each section of the file create a separate pod file
|
|
for ($i = 0; $i <= $#poddata; $i++) {
|
|
# determine the "prev" and "next" links
|
|
$prevsec = $section;
|
|
$section = $nextsec;
|
|
if ($i < $#poddata) {
|
|
$poddata[$i+1] =~ /^\s*=head[1-6]\s+(.*)/;
|
|
$nextsec = $1;
|
|
} else {
|
|
$nextsec = "";
|
|
}
|
|
|
|
# determine an appropriate filename (this must correspond with
|
|
# what pod2html will try and guess)
|
|
# $poddata[$i] =~ /^\s*=head[1-6]\s+(.*)/;
|
|
$file = "$dir/" . anchorify($section) . ".pod";
|
|
|
|
# create the new .pod file
|
|
print "\tcreating $poddir/$file\n" if $verbose;
|
|
open(SPLITOUT, '>', "$poddir/$file") ||
|
|
die "$0: error opening $poddir/$file for output: $!\n";
|
|
$poddata[$i] =~ s,L<([^<>]*)>,
|
|
defined $heads{anchorify($1)} ? "L<$dir/$1>" : "L<$1>"
|
|
,ge;
|
|
print SPLITOUT $poddata[$i]."\n\n";
|
|
print SPLITOUT "=over 4\n\n";
|
|
print SPLITOUT "=item *\n\nBack to L<$dir/\"$prevsec\">\n\n" if $prevsec;
|
|
print SPLITOUT "=item *\n\nForward to L<$dir/\"$nextsec\">\n\n" if $nextsec;
|
|
print SPLITOUT "=item *\n\nUp to L<$dir>\n\n";
|
|
print SPLITOUT "=back\n\n";
|
|
close(SPLITOUT) ||
|
|
die "$0: error closing $poddir/$file: $!\n";
|
|
}
|
|
}
|
|
|
|
|
|
#
|
|
# installdir - takes care of converting the .pod and .pm files in the
|
|
# current directory to .html files and then installing those.
|
|
#
|
|
sub installdir {
|
|
my($dir, $recurse, $podroot, $splitdirs, $ignore) = @_;
|
|
|
|
my @dirlist; # directories to recurse on
|
|
my @podlist; # .pod files to install
|
|
my @pmlist; # .pm files to install
|
|
|
|
# should files in this directory get an index?
|
|
my $doindex = (grep($_ eq "$podroot/$dir", @$splitdirs) ? 0 : 1);
|
|
|
|
opendir(DIR, "$podroot/$dir")
|
|
|| die "$0: error opening directory $podroot/$dir: $!\n";
|
|
|
|
while(readdir DIR) {
|
|
no_upwards($_) or next;
|
|
my $is_dir = -d "$podroot/$dir/$_";
|
|
next if $is_dir and not $recurse;
|
|
my $target
|
|
= $is_dir ? \@dirlist
|
|
: s/\.pod$// ? \@podlist
|
|
: s/\.pm$// ? \@pmlist
|
|
: undef
|
|
;
|
|
push @$target, "$dir/$_" if $target;
|
|
}
|
|
|
|
closedir(DIR);
|
|
|
|
if ($^O eq 'VMS') { s/\.dir$//i for @dirlist }
|
|
|
|
# recurse on all subdirectories we kept track of
|
|
foreach $dir (@dirlist) {
|
|
installdir($dir, $recurse, $podroot, $splitdirs, $ignore);
|
|
}
|
|
|
|
# install all the pods we found
|
|
foreach my $pod (@podlist) {
|
|
# check if we should ignore it.
|
|
next if $pod =~ m(/t/); # comes from a test file
|
|
next if grep($_ eq "$pod.pod", @$ignore);
|
|
|
|
# check if a .pm files exists too
|
|
if (grep($_ eq $pod, @pmlist)) {
|
|
print "$0: Warning both '$podroot/$pod.pod' and "
|
|
. "'$podroot/$pod.pm' exist, using pod\n";
|
|
push(@ignore, "$pod.pm");
|
|
}
|
|
runpod2html("$pod.pod", $doindex);
|
|
}
|
|
|
|
# install all the .pm files we found
|
|
foreach my $pm (@pmlist) {
|
|
# check if we should ignore it.
|
|
next if $pm =~ m(/t/); # comes from a test file
|
|
next if grep($_ eq "$pm.pm", @ignore);
|
|
|
|
runpod2html("$pm.pm", $doindex);
|
|
}
|
|
}
|
|
|
|
|
|
#
|
|
# runpod2html - invokes pod2html to convert a .pod or .pm file to a .html
|
|
# file.
|
|
#
|
|
sub runpod2html {
|
|
my($pod, $doindex) = @_;
|
|
my($html, $i, $dir, @dirs);
|
|
|
|
$html = $pod;
|
|
$html =~ s/\.(pod|pm)$/.html/g;
|
|
|
|
# make sure the destination directories exist
|
|
@dirs = split("/", $html);
|
|
$dir = "$htmldir/";
|
|
for ($i = 0; $i < $#dirs; $i++) {
|
|
if (! -d "$dir$dirs[$i]") {
|
|
mkdir("$dir$dirs[$i]", 0755) ||
|
|
die "$0: error creating directory $dir$dirs[$i]: $!\n";
|
|
}
|
|
$dir .= "$dirs[$i]/";
|
|
}
|
|
|
|
# invoke pod2html
|
|
print "$podroot/$pod => $htmldir/$html\n" if $verbose;
|
|
Pod::Html::pod2html(
|
|
"--htmldir=$htmldir",
|
|
"--htmlroot=$htmlroot",
|
|
"--podpath=".join(":", @podpath),
|
|
"--podroot=$podroot",
|
|
"--header",
|
|
($doindex ? "--index" : "--noindex"),
|
|
"--" . ($recurse ? "" : "no") . "recurse",
|
|
"--infile=$podroot/$pod", "--outfile=$htmldir/$html");
|
|
die "$0: error running $pod2html: $!\n" if $?;
|
|
}
|