diff nested_collection.xml @ 1:86770eea5b09 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/percolator commit 0a5f9eb82877545be1c924357e585b17e01cfd1c

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/nested_collection.xml	Sat Mar 04 20:36:03 2017 -0500
@@ -0,0 +1,137 @@
+<tool id="batched_set_list_creator" name="Create nested list" version="3.0.1">
+    <description>based on filenames and batch sizes</description>
+    <stdio>
+        <exit_code range="1:" />
+    </stdio>
+    <command>python $__tool_directory__/nested_collection.py
+        #if $batchsize
+            --batchsize $batchsize
+        #end if
+        #if len($poolids) > 0
+            --pool-ids
+            #for $pool in $poolids
+                '${pool.pool_identifier}'
+            #end for
+        #end if
+        --real-names
+        #for $fname in $listtobatch.keys()
+            '$fname'
+        #end for
+        --galaxy-files
+        #for $fname in $listtobatch.keys()
+            '$listtobatch[$fname]'
+        #end for
+    </command>
+    <inputs>
+        <param name="batchsize" type="integer" optional="true" value="" label="Maximal amount of fractions to batch." help="No value means no maximum" />
+        <repeat name="poolids" title="Batch pools" help="Pools containing batches (optional, not using this will result in one pool)">
+            <param name="pool_identifier" type="text" label="Filename part identifying batchpool" 
+            help="Specify part of the input filenames that are unique for each pool, e.g set_A. Do not use 3 consecutive underscores."/>
+        </repeat>
+        <param name="listtobatch" type="data_collection" collection_type="list" label="List of files to batch" />
+    </inputs>
+    <outputs>
+        <collection name="batched_fractions" type="list:list" label="Pooled batched data">
+          <discover_datasets pattern="[a-zA-z0-9_]*___(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.mzid" ext="mzid" visible="true" />
+        </collection>
+    </outputs>
+    <tests>
+        <test>
+            <param name="batchsize" value="2"/>
+            <param name="listtobatch">
+                <collection type="list">
+                    <element name="fraction_one_spectra" value="empty_file1.mzid"/>
+                    <element name="fraction_two_spectra" value="empty_file2.mzid"/>
+                    <element name="fraction_three_spectra" value="empty_file3.mzid"/>
+                    <element name="fraction_four_spectra" value="empty_file4.mzid"/>
+                </collection>
+            </param>
+            <output_collection name="batched_fractions" type="list:list">
+                <element name="batch0">
+                    <element name="inputfn0" file="empty_file1.mzid"/>
+                    <element name="inputfn1" file="empty_file2.mzid"/>
+                </element>
+                <element name="batch1">
+                    <element name="inputfn0" file="empty_file3.mzid"/>
+                    <element name="inputfn1" file="empty_file4.mzid"/>
+                </element>
+            </output_collection>
+        </test>
+        <test>
+            <repeat name="poolids">
+                <param name="pool_identifier" value="set1"/>
+            </repeat>
+            <repeat name="poolids">
+                <param name="pool_identifier" value="set2"/>
+            </repeat>
+            <param name="listtobatch">
+                <collection type="list">
+                    <element name="fr_one_set1_spectra" value="empty_file1.mzid"/>
+                    <element name="fr_two_set1_spectra" value="empty_file2.mzid"/>
+                    <element name="fr_three_set1_spectra" value="empty_file3.mzid"/>
+                    <element name="fr_one_set2_spectra" value="empty_file4.mzid"/>
+                    <element name="fr_two_set2_spectra" value="empty_file5.mzid"/>
+                    <element name="fr_three_set2_spectra" value="empty_file6.mzid"/>
+                </collection>
+            </param>
+            <output_collection name="batched_fractions" type="list:list">
+                <element name="batch0">
+                    <element name="inputfn0" file="empty_file1.mzid"/>
+                    <element name="inputfn1" file="empty_file2.mzid"/>
+                    <element name="inputfn2" file="empty_file3.mzid"/>
+                </element>
+                <element name="batch1">
+                    <element name="inputfn0" file="empty_file4.mzid"/>
+                    <element name="inputfn1" file="empty_file5.mzid"/>
+                    <element name="inputfn2" file="empty_file6.mzid"/>
+                </element>
+            </output_collection>
+        </test>
+        <test>
+            <param name="batchsize" value="2"/>
+            <repeat name="poolids">
+                <param name="pool_identifier" value="set1"/>
+            </repeat>
+            <repeat name="poolids">
+                <param name="pool_identifier" value="set2"/>
+            </repeat>
+            <param name="listtobatch">
+                <collection type="list">
+                    <element name="fr_one_set1_spectra" value="empty_file1.mzid"/>
+                    <element name="fr_two_set1_spectra" value="empty_file2.mzid"/>
+                    <element name="fr_three_set1_spectra" value="empty_file3.mzid"/>
+                    <element name="fr_one_set2_spectra" value="empty_file4.mzid"/>
+                    <element name="fr_two_set2_spectra" value="empty_file5.mzid"/>
+                    <element name="fr_three_set2_spectra" value="empty_file6.mzid"/>
+                </collection>
+            </param>
+            <output_collection name="batched_fractions" type="list:list">
+                <element name="batch0">
+                    <element name="inputfn0" file="empty_file1.mzid"/>
+                    <element name="inputfn1" file="empty_file2.mzid"/>
+                </element>
+                <element name="batch1">
+                    <element name="inputfn0" file="empty_file3.mzid"/>
+                </element>
+                <element name="batch2">
+                    <element name="inputfn0" file="empty_file4.mzid"/>
+                    <element name="inputfn1" file="empty_file5.mzid"/>
+                </element>
+                <element name="batch3">
+                    <element name="inputfn0" file="empty_file6.mzid"/>
+                </element>
+            </output_collection>
+        </test>
+    </tests>
+    <help>
+    Creates nested collection containing from a list containing datasets in batches of
+    a specific size. Useful when e.g. creating inputs to sqt2pin, msgfplus2pin or tandem2pin.
+    Use this feature when you want to batch a specific amount of datasets, or datasets with
+    a common file name pattern, or both.
+    The tool generates a collection containing batches which contain multiple batches 
+    of input files. The pools are specified as a pattern in the input
+    files which makes sure the batching isn't continued through very different input sets
+    if that is a problem. Instead, for each filename-pattern it generates batches of the
+    specified size.
+    </help>
+</tool>