diff splitFasta.xml @ 5:733ca84b21ee draft default tip

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/splitfasta commit 31945d5d8c5ebee64ebf29c6ea022fb831f47274"
author rnateam
date Mon, 21 Sep 2020 15:40:14 +0000
parents ae4d5733272f
children
line wrap: on
line diff
--- a/splitFasta.xml	Fri Oct 16 16:13:34 2015 -0400
+++ b/splitFasta.xml	Mon Sep 21 15:40:14 2020 +0000
@@ -1,35 +1,59 @@
-<tool id="rbc_splitfasta" name="Split Fasta" version="0.2.0">
+<tool id="rbc_splitfasta" name="Split Fasta" version="0.4.0">
     <description>files into a collection</description>
     <requirements>
-        <requirement type="package" version="1.65">biopython</requirement>
+        <requirement type="package" version="1.76">biopython</requirement>
     </requirements>
-    <stdio>
-        <exit_code range="1:" />
-    </stdio>
-    <command interpreter="python">
+    <command detect_errors="aggressive">
     <![CDATA[
-        splitFasta.py $inputFile
+        #if $splitmode.splitmode_select == "each":
+            python $__tool_directory__/split_fasta.py '$inputFile'
+        #else if $splitmode.splitmode_select == "chunks":
+            python $__tool_directory__/split_fasta.py '$inputFile' $splitmode.num_chunks
+        #end if
     ]]></command>
     <inputs>
         <param name="inputFile" type="data" format="fasta" label="Fasta file to split"/>
+        <conditional name="splitmode">
+            <param name="splitmode_select" type="select" label="Split mode">
+                <option value="each">Each sequence in its own dataset</option>
+                <option value="chunks">Split into a number of chunks</option>
+            </param>
+            <when value="chunks">
+                <param name="num_chunks" type="integer" value="10" label="Number of chunks to split into" />
+            </when>
+            <when value="each"/>
+        </conditional>
     </inputs>
     <outputs>
-        <collection name="splitted_fasta" type="list" label="Sequence collection in FASTA format">
+        <collection name="splitted_fasta" type="list" label="${tool.name} on ${on_string}">
             <discover_datasets pattern="(?P&lt;designation&gt;.*)" directory="splits" ext="fasta" visible="false"/>
         </collection>
     </outputs>
     <tests>
         <test>
-            <param name="inputFile" value="test.fasta" />
-            <output_collection name="splitted_fasta">
-                <element name="ID1.fasta" file="ID1_result1.fasta" ftype="fasta" />
-                <element name="ID2.fasta" file="ID2_result1.fasta" ftype="fasta" />
-                <element name="ID3.fasta" file="ID3_result1.fasta" ftype="fasta" />
+            <param name="inputFile" value="sample1.fasta" />
+            <param name="splitmode|splitmode_select" value="each" />
+            <output_collection name="splitted_fasta" count="3">
+                <element name="ID1" file="ID1.fasta" ftype="fasta" />
+                <element name="ID2" file="ID2.fasta" ftype="fasta" />
+                <element name="ID3" file="ID3.fasta" ftype="fasta" />
+            </output_collection>
+        </test>
+        <test>
+            <param name="inputFile" value="sample2.fasta" />
+            <param name="splitmode|splitmode_select" value="chunks" />
+            <param name="num_chunks" value="4" />
+            <output_collection name="splitted_fasta" count="4">
+                <element name="part1" file="part1.fasta" ftype="fasta" />
+                <element name="part2" file="part2.fasta" ftype="fasta" />
+                <element name="part3" file="part3.fasta" ftype="fasta" />
+                <element name="part4" file="part4.fasta" ftype="fasta" />
             </output_collection>
         </test>
     </tests>
     <help><![CDATA[
-        Takes an input file and writes each consecutive two lines to a separate file, in a dataset collection.
+        Takes an input FASTA file and writes entries (i.e. sequences) to separate datasets, which are organized in a dataset collection.
+        There are two modes: 1) each sequence is written to its own data set which is named by the ID of the sequence or 2) The file is split into a given number of chunks which are numbered.
     ]]></help>
     <citations>
         <citation type="bibtex">