match lines from file (annotation)

match_fast.pl

+#!/usr/bin/env perl
+use strict;
+
+# 
+# 1. Load key
+#
+my $keyfile = shift @ARGV;
+
+defined $keyfile or die "Please give a key file !\n";
+
+print STDERR "Load keys from $keyfile\n";
+my @keys;
+my $rx = qr/Locus_[[:digit:]]+_Transcript_[[:digit:]]+_[[:digit:]]+_/;;
+{
+	open my $f, "<", $keyfile
+		or die "open error $keyfile";
+	@keys = map { s{[\n\r]+$}{}g; $_} <$f>;
+	close $f;
+
+	print STDERR "$#keys keys in file\n";
+	print STDERR "Build regex\n";
+}
+my %reverse = map { $_ => 1 } @keys;
+
+
+
+#
+# 2. Scan input for lines matching the keys
+#
+print STDERR "Scan input ${ARGV[0]} ...\n";
+my $m = 0;
+my $l = 0;
+my $p = '';
+
+my %matches;
+while ( <> ) {
+	if ( $_ =~ /Locus_[[:digit:]]+_Transcript_[[:digit:]]+_[[:digit:]]+_/ ) {
+		next if (! exists $reverse { $& } );
+		# .. do not print matching lines but store them into hash
+		$matches{ $& } =  $_;
+		++$m;
+		print STDERR "\r${p}Line $l     Found $m / $#keys matches...";
+	}
+} continue {
+	if (((++$l) & 127) == 0) {
+		$p = int(tell() * 100 / (-s $ARGV))  . '% - '
+			if( -e $ARGV);
+		print STDERR "\r${p}Line $l";
+	}	
+}
+
+#
+# 3. for each key either printing matching line or 'NOT FOUND'
+#
+print STDERR "\nWrite results ...\n";
+foreach (@keys) {
+	print $_ . ":\t" . (exists $matches{$_} ? $matches{$_} : 'NOT FOUND!') . "\n";
+}
+print STDERR "Done\n";