xcat-core/xCAT-client/bin/getxcatdocs

#!/usr/bin/perl
# IBM(c) 2007 EPL license http://www.eclipse.org/legal/epl-v10.html

# Downloads/converts the xCAT docs on the sourceforge wiki to local HTML and PDF.
# This script is not dependent on other xCAT code, so you can copy it to a machine
# that has internet access to run it.  Before running this command, you must have
# wget, python, and pisa installed.  See: https://sourceforge.net/apps/mediawiki/xcat/index.php?title=Editing_xCAT_Documentation_Pages#Converting_Wiki_Pages_to_HTML_and_PDFs .

# Note: do not use the --upload option, unless your machine has authority to write to http://xcat.sourceforge.net/doc/ .
#       You also need to set $UPLOADUSER to your sourceforge user.

#BEGIN
#{
#    $::XCATROOT = $ENV{'XCATROOT'} ? $ENV{'XCATROOT'} : -d '/opt/xcat' ? '/opt/xcat' : '/usr';
#}
use strict;
#use lib "$::XCATROOT/lib/perl";
#use xCAT::Utils;
use Getopt::Long;
#use Data::Dumper;

#my $VERSION;
my $HELP;
my $UPLOAD;
my $UPLOADONLY;
 
my $usage = sub {
   	my $exitcode = shift @_;
   	print "Usage: getxcatdocs [-?|-h|--help] [-u|--upload] [--uploadonly] [<destination-dir>]\n";
	exit $exitcode;
};

# Process the cmd line args
Getopt::Long::Configure("bundling");
#Getopt::Long::Configure("pass_through");
Getopt::Long::Configure("no_pass_through");
if (!GetOptions('h|?|help'  => \$HELP, 'u|upload' => \$UPLOAD, 'uploadonly' => \$UPLOADONLY )) { $usage->(1); }

if ($HELP) { $usage->(0); }

#if ($VERSION) {
    #print xCAT::Utils->Version(), "\n";
#    exit;
#}

if ($^O =~ /^aix/i) { die "Error: this command is not yet supported on AIX.\n"; }

my $destdir = scalar(@ARGV) ? $ARGV[0] : '.';
chdir($destdir) or die "Can not cd to $destdir: $!\n";
#my $docdir = $ENV{'PWD'};

# Download the HTML
my @dir;
if (!$UPLOADONLY) {
	mkdir('html');
	chdir('html');
	#system('pwd');
	unlink <*>;		# delete all the files in the dir, in case they previously ran this
	#system('rm -rf nfs skins');
	#system('ls');
	print "Downloading the xCAT wiki documentation...\n";
	#    --html-extension --restrict-file-names=windows  --cut-dirs=3
	# options that do not work:  --relative
	my $wgetcmd = q(wget --recursive --convert-links --no-verbose --progress=bar --level=1 --page-requisites --no-parent --no-host-directories --no-directories --execute robots=off --post-data='printable=yes' --reject '*title=Special:*,*title=Talk:*,*title=-&*,*title=HowTos,*title=Main_Page,*title=MediaWiki:*,*title=Release_Notes,*title=Wish_List_for_xCAT_2,*&action=edit*,*&action=history*,*&printable=yes*,*&oldid=*,index.html,opensearch_desc.php,xcat,login.php,support' 'https://sourceforge.net/apps/mediawiki/xcat/index.php?title=XCAT_Documentation&printable=yes');
	runwget($wgetcmd);
	# remove the dir portion of links to other docs
	#my $sedcmd = q(sed -i 's/<a href="\/apps\/mediawiki\/xcat\/index.php?title/<a href="index.php%3Ftitle/' *);
	my $sedcmd = q(sed -i 's/<a href="index.php?title/<a href="index.php%3Ftitle/' *);
	print "$sedcmd\n";
	system($sedcmd);
	# get the list of docs
	opendir(DIR, '.') or die "Error: could not read the just created html directory.\n";
	@dir = grep /^index.php\?title=/, readdir(DIR);		# /
	close(DIR);
	chdir('..');
}

# Convert to pdf
if (!$UPLOADONLY) {
	if (system('which xhtml2pdf >/dev/null 2>&1')) { die "xhtml2pdf is not installed.  See http://sourceforge.net/apps/mediawiki/xcat/index.php?title=Editing_xCAT_Documentation_Pages#Converting_Wiki_Pages_to_HTML_and_PDFs .\n"; }
	mkdir('pdf');
	chdir('pdf');
	unlink <*>;		# delete all the files in the dir, in case they previously ran this
	foreach my $file (@dir) {
		if ($file =~ /^index.php\?title=MediaWiki:/ || $file eq 'index.php?title=XCAT_Documentation') { next; }
		my ($docname) = $file =~ /^index.php\?title=(.+)$/;
		print "Converting $docname to PDF format...\n";
		my $url = "https://sourceforge.net/apps/mediawiki/xcat/$file&printable=yes";
		my $destfile = "$docname.pdf";
		my $cmd = "xhtml2pdf '$url' '$destfile' ";
		#print "$cmd\n";
		runh2p($cmd);
	}
	chdir('..');
}

# tar/compress
my $date=`date +%Y%m%d%H%M`;
chop $date;
my $docname="xcat-docs-snap$date.tar.gz";
#system('pwd');
system("tar -zcf $docname html pdf 2>&1");

# Optionally upload the tarball to sourceforge
if ($UPLOAD || $UPLOADONLY) {
	my $UPLOADUSER = 'bp-sawyers';
	my $count = 1;
	#my $cmd = "rsync -v $docname $UPLOADUSER," . 'xcat@web.sourceforge.net:htdocs/doc/';
	my $cmd = "rsync -v $docname $UPLOADUSER," . 'xcat@web.sourceforge.net:/home/frs/project/x/xc/xcat/doc/';
	print "$cmd\n";
	while ($count<=5 && system("$cmd 2>&1")) { $count++; }
}
exit 0;


# Run the wget cmd and filter out some of the silly output
sub runwget {
	my $cmd = shift;
	#print "$cmd\n";
	open(OUT, "$cmd 2>&1 |") || die "can't fork $cmd: $!\n";
	while (<OUT>) {
		if (/URL:https*:\/\/sourceforge\.net.+\s+->\s+\"(\S+)\"\s+\[/) { print "Downloaded $1.\n"; }
		else { print; }
	}
	close OUT || die "Error running $cmd: $! $?";
}

# Run the xhtml2pdf cmd and filter out some of the silly output
sub runh2p {
	my $cmd = shift;
	#print "$cmd\n";
	open(OUT, "$cmd 2>&1 |") || die "can't fork $cmd: $!\n";
	while (<OUT>) {
		next if /DeprecationWarning:\sthe sets module is deprecated/;
		next if /from sets import ImmutableSet/;
		next if /^Converting\ssourceforge.net/;
		print;
	}
	close OUT || die "Error running $cmd: $! $?";
}