batch_seq_summary.pl

#!/usr/bin/perl -w
#-----------------------------------------------------------+
#                                                           |
# batch_seq_summary.pl - Display summary info for a seq dir |
#                                                           |
#-----------------------------------------------------------+
#                                                           |
#  AUTHOR: James C. Estill                                  |
# CONTACT: JamesEstill_@_gmail.com                          |
# STARTED: 10/05/2007                                       |
# UPDATED: 12/13/2007                                       |
#                                                           |
# DESCRIPTION:                                              |
#  Display basic summary information for a directory of     |
#  sequences. Files must end in fasta to be recognized      |
#  as a fasta file.                                         |
#                                                           |
# USAGE:                                                    |
#  batch_seq_summary.pl -i InDir -o Outfile                 |
#                                                           |
# VERSION: $Rev: 948 $                                            |
#                                                           |
# LICENSE:                                                  |
#  GNU General Public License, Version 3                    |
#  http://www.gnu.org/licenses/gpl.html                     |  
#                                                           |
#-----------------------------------------------------------+

package DAWGPAWS;

#-----------------------------+
# INCLUDES                    |
#-----------------------------+
use strict;
use Getopt::Long;
# The following needed for printing help
use Pod::Select;               # Print subsections of POD documentation
use Pod::Text;                 # Print POD doc as formatted text file
use IO::Scalar;                # For print_help subfunction
use IO::Pipe;                  # Pipe for STDIN, STDOUT for POD docs
use File::Spec;                # Convert a relative path to an abosolute path

#-----------------------------+
# PROGRAM VARIABLES           |
#-----------------------------+
my ($VERSION) = q$Rev: 948 $ =~ /(\d+)/;

#-----------------------------+
# VARIABLE SCOPE              |
#-----------------------------+
my $indir;
my $outfile;

# Booleans
my $quiet = 0;
my $verbose = 0;
my $show_help = 0;
my $show_usage = 0;
my $show_man = 0;
my $show_version = 0;

# Counters
my $file_num = 0;

# Set scope
my $cmd;
my $name_root;
my $sum_base_non;

#-----------------------------+
# COMMAND LINE OPTIONS        |
#-----------------------------+
my $ok = GetOptions(# REQUIRED OPTIONS
		    "i|indir=s"   => \$indir,
                    "o|outfile=s" => \$outfile,
		    # ADDITIONAL OPTIONS
		    "q|quiet"     => \$quiet,
		    "verbose"     => \$verbose,
		    # ADDITIONAL INFORMATION
		    "usage"       => \$show_usage,
		    "version"     => \$show_version,
		    "man"         => \$show_man,
		    "h|help"      => \$show_help,);

#-----------------------------+
# SHOW REQUESTED HELP         |
#-----------------------------+
if ( ($show_usage) ) {
#    print_help ("usage", File::Spec->rel2abs($0) );
    print_help ("usage", $0 );
}

if ( ($show_help) || (!$ok) ) {
#    print_help ("help",  File::Spec->rel2abs($0) );
    print_help ("help",  $0 );
}


if ($show_version) {
    print "\n$0:\nVersion: $VERSION\n\n";
    exit;
}

if ($show_man) {
    # User perldoc to generate the man documentation.
    system("perldoc $0");
    exit($ok ? 0 : 2);
}


#-----------------------------+
# CHECK REQUIRED ARGS         |
#-----------------------------+
if ( (!$indir) || (!$outfile) ) {
    print "\a";
    print STDERR "\n";
    print STDERR "ERROR: An input directory was not specified at the".
	" command line\n" if (!$indir);
    print STDERR "ERROR: An output file was not specified at the".
	" command line\n" if (!$outfile);
    print_help ("usage", $0 );
}


#-----------------------------------------------------------+
# MAIN PROGRAM BODY                                         |
#-----------------------------------------------------------+
#-----------------------------+
# CHECK FOR SLASH IN DIR      |
# VARIABLES                   |
#-----------------------------+
# If the indir does not end in a slash then append one
# TO DO: Allow for backslash
unless ($indir =~ /\/$/ ) {
    $indir = $indir."/";
}

#-----------------------------+
# Get the FASTA files from the|
# directory provided by the   |
# var $indir                  |
#-----------------------------+
opendir( DIR, $indir ) || 
    die "Can't open directory:\n$indir"; 
my @fasta_files = grep /\.fasta$|\.fa$/, readdir DIR ;
closedir( DIR );
my $num_files = @fasta_files;
#sort @fasta_files;

if ($num_files == 0) {
    print "\a";
    print "ERROR: No input fasta files were found in the directroy:\n$indir\n";
    print "Fasta files must end with the fasta or fa extension\n";
    exit;
}


for my $ind_file (@fasta_files) {

    $file_num++;

    # Get root file name
    if ($ind_file =~ m/(.*)\.fasta$/ ) {	    
	$name_root = "$1";
    }  
    elsif ($ind_file =~ m/(.*)\.fa$/ ) {	    
	$name_root = "$1";
    } 
    else {
	$name_root = "UNDEFINED";
    }


#    my $sum_base_result = system($cmd);
    print STDOUT "$name_root\t";
    $cmd = "seq_countbase_non.sh $indir$ind_file";
    system($cmd);
    
}

exit;

#-----------------------------------------------------------+ 
# SUBFUNCTIONS                                              |
#-----------------------------------------------------------+

sub print_help {
    my ($help_msg, $podfile) =  @_;
    # help_msg is the type of help msg to use (ie. help vs. usage)
    
    print "\n";
    
    #-----------------------------+
    # PIPE WITHIN PERL            |
    #-----------------------------+
    # This code made possible by:
    # http://www.perlmonks.org/index.pl?node_id=76409
    # Tie info developed on:
    # http://www.perlmonks.org/index.pl?node=perltie 
    #
    #my $podfile = $0;
    my $scalar = '';
    tie *STDOUT, 'IO::Scalar', \$scalar;
    
    if ($help_msg =~ "usage") {
	podselect({-sections => ["SYNOPSIS|MORE"]}, $0);
    }
    else {
	podselect({-sections => ["SYNOPSIS|ARGUMENTS|OPTIONS|MORE"]}, $0);
    }

    untie *STDOUT;
    # now $scalar contains the pod from $podfile you can see this below
    #print $scalar;

    my $pipe = IO::Pipe->new()
	or die "failed to create pipe: $!";
    
    my ($pid,$fd);

    if ( $pid = fork() ) { #parent
	open(TMPSTDIN, "<&STDIN")
	    or die "failed to dup stdin to tmp: $!";
	$pipe->reader();
	$fd = $pipe->fileno;
	open(STDIN, "<&=$fd")
	    or die "failed to dup \$fd to STDIN: $!";
	my $pod_txt = Pod::Text->new (sentence => 0, width => 78);
	$pod_txt->parse_from_filehandle;
	# END AT WORK HERE
	open(STDIN, "<&TMPSTDIN")
	    or die "failed to restore dup'ed stdin: $!";
    }
    else { #child
	$pipe->writer();
	$pipe->print($scalar);
	$pipe->close();	
	exit 0;
    }
    
    $pipe->close();
    close TMPSTDIN;

    print "\n";

    exit 0;
   
}


1;
__END__

# Deprecated print_help
sub print_help {

    # Print requested help or exit.
    # Options are to just print the full 
    my ($opt) = @_;

    my $usage = "USAGE:\n". 
	"MyProg.pl -i InDir -o OutFile";
    my $args = "REQUIRED ARGUMENTS:\n".
	"  --infile       # Path to the input file\n".
	"  --outfile      # Path to the output file\n".
	"\n".
	"OPTIONS::\n".
	"  --version      # Show the program version\n".     
	"  --usage        # Show program usage\n".
	"  --help         # Show this help message\n".
	"  --man          # Open full program manual\n".
	"  --quiet        # Run program with minimal output\n";
	
    if ($opt =~ "full") {
	print "\n$usage\n\n";
	print "$args\n\n";
    }
    else {
	print "\n$usage\n\n";
    }
    
    exit;
}


=head1 NAME

batch_seq_sumary.pl - Print summary info for a directory of sequence files

=head1 VERSION

This documentation refers to program version $Rev: 948 $

=head1 SYNOPSIS

=head2 Usage

    batch_seq_summary.pl -i InFile -o OutFile

=head2 Required Arguments

    -i, --indir    # Directory of fasta files to process
    -o, --outfile  # Path to file to print program output

=head1 DESCRIPTION

Display basic summary information for a directory of
sequences. Files must end in fasta to be recognized
as a fasta file.

=head1 REQUIRED ARGUMENTS

=over 2

=item -i,--indir

Path of the directory containing the sequences to process.

=item -o,--outfile

Path of the output file that will contain information for the
input sequence files.

=back

=head1 OPTIONS

=over 2

=item --usage

Short overview of how to use program from command line.

=item --help

Show program usage with summary of options.

=item --version

Show program version.

=item --man

Show the full program manual. This uses the perldoc command to print the 
POD documentation for the program.

=item -q,--quiet

Run the program with minimal output.

=item --verbose

Run the program in verbose mode.

=back

=head1 DIAGNOSTICS

Error messages generated by this program and possible solutions are listed
below.

=over 2

=item ERROR: No fasta files were found in the input directory

The input directory does not contain fasta files in the expected format.
This could happen because you gave an incorrect path or because your sequence 
files do not have the expected *.fasta extension in the file name.

=item ERROR: Could not create the output file

The output file path may be to a directory that does not exist
or you may not have write permission to the directory that you
are trying to write to.

=back

=head1 CONFIGURATION AND ENVIRONMENT

the batch_seq_summary.pl program does not require an external configuration
file or make use of variables set in the user's environment.

=head1 DEPENDENCIES

=head2 Required Software

=over 2

=item * seq_countbase_non.sh

This shell script is included in the DAWG-PAWS package. This will
count the non N bases in an input sequence file.

=back

=head2 Required Perl Modules

=over

=item * Getopt::Long

This module is required to accept options at the command line.

=back

=head1 BUGS AND LIMITATIONS

=head2 Bugs

=over 2

=item * No bugs currently known 

If you find a bug with this software, file a bug report on the DAWG-PAWS
Sourceforge website: http://sourceforge.net/tracker/?group_id=204962

=back

=head2 Limitations

=over

=item * Limited to Linux/Unix environments

This program requires the use of a shell script that will only
work in a Linux or Unix environment.

=back

=head1 SEE ALSO

The batch_seq_summary.pl program is part of the DAWG-PAWS package of genome
annotation programs. See the DAWG-PAWS web page 
( http://dawgpaws.sourceforge.net/ )
or the Sourceforge project page 
( http://sourceforge.net/projects/dawgpaws ) 
for additional information about this package.

=head1 LICENSE

GNU GENERAL PUBLIC LICENSE, VERSION 3

http://www.gnu.org/licenses/gpl.html

THIS SOFTWARE COMES AS IS, WITHOUT ANY EXPRESS OR IMPLIED
WARRANTY. USE AT YOUR OWN RISK.

=head1 AUTHOR

James C. Estill E<lt>JamesEstill at gmail.comE<gt>

=head1 HISTORY

STARTED: 10/05/2007

UPDATED: 12/13/2007

VERSION: $Rev: 948 $

=cut

#-----------------------------------------------------------+
# HISTORY                                                   |
#-----------------------------------------------------------+
#
# 10/05/07
# - Main program body written
# - Uses shell script to fetch non N characters for 
#   each of the sequence files
# 
# 12/13/2007
# - Updated POD documentation
# - Added print_help subfunction that extracts usage and
#   help messages from the POD documentation
# - Added check for required arguments