--- a/clustering.xml	Thu May 21 03:58:09 2015 -0400
+++ b/clustering.xml	Wed Aug 26 13:34:22 2015 -0400
@@ -1,4 +1,4 @@
-<tool id="vsearch_clustering" name="VSearch clustering" version="@VERSION@.0">
+<tool id="vsearch_clustering" name="VSearch clustering" version="@VERSION@.1">
     <description></description>
     <macros>
         <import>vsearch_macros.xml</import>
@@ -10,8 +10,12 @@
 <![CDATA[
     vsearch
         @GENERAL@
-        --cluster_fast "$infile"
-        ##--cluster_smallmem FILENAME  cluster sequences using a small amount of memory
+	
+	#if $clustering_mode.clustering_mode_select == 'cluster_fast':
+            --cluster_fast "$infile"
+	#else if $clustering_mode.clustering_mode_select == 'cluster_smallmem':
+            --cluster_smallmem "$infile"
+        #end if
         ##--clusters STRING            output each cluster to a separate FASTA file
 
         #if $maxrejects:
@@ -23,7 +27,7 @@
 
         $cons_truncate
         --id $id
-        ##--iddef $iddef
+        --iddef $iddef
 
         #if '--msaout' in str($outputs):
             --msaout $msaout
@@ -52,24 +56,33 @@
         #if $qmask != 'no':
             --qmask $qmask
         #end if
-        #if $sizein:
-            --sizein $sizein
-        #end if
-        #if $sizeout:
-            --sizeout $sizeout
-        #end if
+        $sizein
+        $sizeout
         --strand $strand
-        --usersort $usersort
+	$usersort
+	#if $uc:
+            --uc "$uc_outfile"
+	#end if
 
 ]]>
     </command>
     <inputs>
-        <param name="infile" type="data" format="fasta" label="Select your FASTA file" help="(--cluster_fast)" />
+        <param name="infile" type="data" format="fasta" label="Select your input FASTA file" help="" />
+        <conditional name="clustering_mode">
+            <param name="clustering_mode_select" type="select" label="Choose sorting method to use before clustering" help="">
+                <option value="cluster_fast" default="True">Cluster sequences after sorting by length (--cluster-fast)</option>
+                <option value="cluster_smallmem">Cluster already sorted sequences (--cluster-smallmem)</option>
+            </param>
+            <when value="cluster_fast">
+            </when>
+            <when value="cluster_smallmem">
+          </when>
+        </conditional>
+        <param name="usersort" type="boolean" truevalue="--usersort" falsevalue="" checked="False" 
+            label="Indicate that input sequences are not presorted by length" help="(--usersort)"/>
         <expand macro="id_and_iddef" />
         <param name="cons_truncate" type="boolean" truevalue="--cons_truncate" falsevalue="" checked="False" 
             label="Do not ignore terminal gaps in MSA for consensus" help="(--cons_truncate)"/>
-        <param name="usersort" type="boolean" truevalue="--usersort" falsevalue="" checked="False" 
-            label="Indicate that input sequences are presorted" help="(--usersort)"/>
         <expand macro="qmask" />
         <expand macro="sizein" />
         <expand macro="sizeout" />
@@ -83,6 +96,7 @@
             <option value="--notmatched">Write non-matching query sequences to separate file</option>
             <option value="--matched">Write matching query sequences to separate file</option>
         </expand>
+        <expand macro="uclust_like_output" />
 
     </inputs>
     <outputs>
@@ -110,6 +124,9 @@
         <data name="fastapairs" format="fasta" label="${tool.name} on ${on_string}: Query/Target sequences">
             <filter>'--fastapairs' in outputs</filter>
         </data>
+        <data name="uc_outfile" format="tabular" label="${tool.name} on ${on_string}: UCLUST like output">
+            <filter>uc is True</filter>
+        </data>
     </outputs>
     <tests>
         <test>
@@ -117,7 +134,7 @@
             <param name="id" value="0.99"/>
             <param name="maxaccepts" value="1"/>
             <param name="maxrejects" value="2"/>
-            <param name="sizeout" value="--sizeout"/>
+            <param name="sizeout" value=""/>
             <param name="outputs" value="--centroids,--alnout,--blast6out,--notmatched" />
             <output name="centroids" file="clustering_centroids_result1.fasta" ftype="fasta" />
             <output name="blast6out" file="clustering_blast6out_result1.tab" ftype="tabular" />
@@ -128,6 +145,56 @@
             <!--output name="fastapairs" file="clustering_fastapairs_result1.fasta" ftype="fasta" /-->
             <!--output name="msaout" file="clustering_msaout_result1.fasta" ftype="fasta" /-->
         </test>
+        <test>
+            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
+            <param name="clustering_mode_select" value="cluster_smallmem"/>
+            <param name="usersort" value="--usersort"/>
+            <param name="id" value="0.99"/>
+            <param name="maxaccepts" value="1"/>
+            <param name="maxrejects" value="2"/>
+            <param name="sizeout" value="--sizeout"/>
+            <param name="outputs" value="--centroids,--blast6out,--notmatched" />
+            <output name="centroids" file="clustering_centroids_result2.fasta" ftype="fasta" />
+            <output name="blast6out" file="clustering_blast6out_result2.tab" ftype="tabular" />
+            <output name="notmatched" file="clustering_notmatched_result2.fasta" ftype="fasta" />
+        </test>
+	<test>
+            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
+            <param name="clustering_mode_select" value="cluster_smallmem"/>
+            <param name="usersort" value="--usersort"/>
+            <param name="id" value="0.99"/>
+            <param name="maxaccepts" value="1"/>
+            <param name="maxrejects" value="2"/>
+            <param name="sizeout" value="--sizeout"/>
+            <param name="outputs" value="--centroids" />
+            <param name="uc" value="--uc"/>
+            <output name="centroids" file="clustering_centroids_result2.fasta" ftype="fasta" />
+            <output name="uc_outfile" file="clustering_uc_result3.uc" ftype="tabular" />
+        </test>
+	<test>
+            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
+            <param name="clustering_mode_select" value="cluster_smallmem"/>
+            <param name="usersort" value="--usersort"/>
+            <param name="id" value="0.99"/>
+            <param name="maxaccepts" value="1"/>
+            <param name="maxrejects" value="2"/>
+            <param name="sizeout" value="--sizeout"/>
+            <param name="outputs" value="--centroids" />
+            <param name="iddef" value="0"/>
+            <output name="centroids" file="clustering_centroids_result4.fasta" ftype="fasta" />
+        </test>
+	<test>
+            <param name="infile" value="BioMarKs5k.fsa.bz2" ftype="fasta" />
+            <param name="clustering_mode_select" value="cluster_fast"/>
+            <param name="usersort" value="--usersort"/>
+            <param name="id" value="0.99"/>
+            <param name="maxaccepts" value="1"/>
+            <param name="maxrejects" value="2"/>
+            <param name="sizeout" value=""/>
+            <param name="outputs" value="--centroids" />
+            <param name="qmask" value="none"/>
+            <output name="centroids" file="clustering_centroids_result1.fasta" ftype="fasta" />
+        </test>
     </tests>
     <help>
 <![CDATA[
@@ -139,19 +206,21 @@
 
 Clustering options (most searching options also apply)
   --centroids FILENAME         output centroid sequences to FASTA file
-  --cluster_fast FILENAME      cluster sequences fast
-  --cluster_smallmem FILENAME  cluster sequences using a small amount of memory
+  --cluster_fast FILENAME      cluster sequences after sorting by length
+  --cluster_size FILENAME      cluster sequences after sorting by abundance
+  --cluster_smallmem FILENAME  cluster already sorted sequences (see -usersort)
   --clusters STRING            output each cluster to a separate FASTA file
   --consout FILENAME           output cluster consensus sequences to FASTA file
   --cons_truncate              do not ignore terminal gaps in MSA for consensus
   --id REAL                    reject if identity lower
   --iddef INT                  id definition, 0-4=CD-HIT,all,int,MBL,BLAST (2)
-  --msaout FILENAME            output multiple seq. alignments to FASTA file 
-  --qmask                      mask seqs with dust, soft or no method (dust)
-  --sizein                     read abundance annotation from input
+  --msaout FILENAME            output multiple seq. alignments to FASTA file
+  --qmask                      seqs with dust, soft or no method (dust)
+  --sizein                     propagate abundance annotation from input
   --sizeout                    write cluster abundances to centroid file
-  --strand                     cluster using "plus" or "both" strands (plus)
-  --usersort                   indicate that input sequences are presorted
+  --strand                     cluster using plus or both strands (plus)
+  --uc FILENAME                filename for UCLUST-like output
+  --usersort                   indicate sequences not presorted by length
 
 
 @EXTERNAL_DOCUMENTATION@