<![CDATA[
#!perl -w
use strict;
# Searching for motifs, Counting ACGT and errors
# documentation written in pod, perldoc perlpod
=head1 NAME
motif.pl
=head1 DESCRIPTION
Check for a motif in any number of files.
=head1 AUTHOR
motif( ) from Beginning Perl for Bioinformatics by James Tisdall,
extended by David Scott to tease out a super simple library.
=cut
my $motif = shift @ARGV;
$motif =~ s/["']$//;
$motif =~ s/^["']//;
while ( my $filename = shift @ARGV ) {
my $sequence = slurp($filename);
$$sequence =~ s/\s//g; # Remove whitespace
print motif($motif, $sequence, $filename);
}
# my $text = motif($re, $sequence, $filename);
sub motif {
my ($motif, $sequence, $filename ) = @_;
if ( $$sequence =~ /$motif/i ) {
return "$motif found: $filename\n";
} else {
return "$motif missing: $filename\n"
}
}
# \$data = slurp($filename);
# slurp in all data into a single variable
# return a reference to avoid copying data
# Recommend: File::Slurp library for this
# This function was benchmarked with reading an array and reading lines
# On a slow PC, it quickly out paced arrays, and did better than lines.
sub slurp {
my ($filename) = @_;
my $inf;
my $fileTerminator = $/;
undef $/;
open($inf, "< $filename") or die("Unable to open $filename: $!");
my $buf = <$inf>;
close $inf;
$/ = $fileTerminator;
return \$buf
}
]]>