# HG changeset patch
# User alan-blakely
# Date 1408651098 14400
# Node ID b41c88a535789b434d7f9a738a592e9bb8f6bab9
# Parent  397067d90a7782286762cac77a8cb574862c68d2
Uploaded

diff -r 397067d90a77 -r b41c88a53578 submatch.pl
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/submatch.pl	Thu Aug 21 15:58:18 2014 -0400
@@ -0,0 +1,41 @@
+#!/usr/bin/perl -w                 
+use strict;
+my (@seq, @rep, $i, $n, $l, $t);
+
+open (SEQ, "<$ARGV[0]");
+open (REP, "<$ARGV[1]");
+open (OUT, ">$ARGV[2]");
+
+
+$i=$n=$l=0;
+
+
+
+while (<SEQ>){
+	chomp();
+	$seq[$i] = $_;
+	$i++;
+}
+while (<REP>){
+	$rep[$n] = $_;
+	$n++;
+
+}
+while ($l < $i){
+	$t=0;
+	while ($t < $n){
+		print OUT $rep[$t] if $rep[$t] =~ /$seq[$l]/;
+		$t++;
+	}
+	$l++;
+}
+
+
+
+close (SEQ);
+close (REP);
+close (OUT);
+
+#optional: remove duplicate lines using server-side shell command
+system("sort", "-u", "-o", "$ARGV[2]", "$ARGV[2]"); 
+    
diff -r 397067d90a77 -r b41c88a53578 submatch.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/submatch.xml	Thu Aug 21 15:58:18 2014 -0400
@@ -0,0 +1,49 @@
+
+<tool id="submatch" name="Filter by Substring Match">
+
+    <description>This tool allows for partial sequences to match lines containing a larger, more complete sequence. </description>
+
+    <command interpreter="perl">submatch.pl $sequences $report $output </command>
+
+    <inputs>
+
+	<param format="tabular" name="sequences" type="data" label="Tabular file containing list to filter on."/>
+	<param format="tabular" name="report" type="data" label="Tabular file to be filtered."/>
+
+    </inputs>
+
+    <outputs>
+        <data format="tabular" name="output" />
+    </outputs>
+  <tests>
+    <test>
+      <param name="sequences" value="submatch_input.tab"/>
+      <param name="report" value="submatch_input2.tab"/>
+      <output name="output" file="submatch_output.tab"/>
+    </test>
+  </tests>
+
+<help>
+
+
+
+Each line from the list file is converted to a regular expression of the form .*LINE.* 
+
+
+
+Lines from the second file that match the expression are returned. 
+
+
+
+
+This tool allows for partial sequences to match lines containing a larger more complete sequence. 
+
+Example: a file containing fragment amino acid sequences is used to select corresponding lines from a peptide report.  
+
+
+
+
+
+</help>
+
+</tool>