view split_tabular_to_collection.xml @ 0:f6254e4e155e draft default tip

planemo upload for repository https://github.com/jj-umn/galaxytools/tree/master/split_to_collection commit b2ce04dd96d8b00103c23b58a4c6539a6b30809a-dirty

<tool id="split_tabular_to_collection" name="Split Tabular into Collection" version="0.1.0">
    <description>by lines</description>
    <command><![CDATA[
        #set $width = len(str($input.dataset.metadata.data_lines))
        #if $skip_comment_lines:
            #set $skip = $input.dataset.metadata.comment_lines 
        #else
            #set $skip = 0
        #end if 
        #set $offset = $skip + 1
        awk 'NR > $skip{ print \$0 > (sprintf("%s_%.${width}d","${input.name}",int((NR-${offset})/${lines})*${lines}) ) }' $input
    ]]></command>
    <inputs>
        <param name="input" type="data" format="tabular" label="Tabular dataset to split"/>
        <param name="lines" type="integer" value="1000" min="1" label="Number of lines per output dataset"/>
        <param name="skip_comment_lines" type="boolean" truevalue="yes" falsevalue="no" checked="true" 
            label="Skip comment lines"/>
    </inputs>
    <outputs>
        <collection name="output_set" type="list" label="${input.name} Split List">
            <discover_datasets pattern="__name__" ext="tabular" visible="false"/>
        </collection>
    </outputs>
    <tests>
        <test>
          <param name="input" value="input.tsv" ftype="tabular"/>
          <param name="lines" value="20"/>
          <output_collection name="output_set" type="list">
              <element name="input.tsv_00">
                  <assert_contents>
                      <has_text_matching expression="20\tt\tT" />
                  </assert_contents>
              </element>
              <element name="input.tsv_00">
                  <assert_contents>
                      <has_text_matching expression="21\tu\tU" />
                  </assert_contents>
              </element>
          </output_collection>
        </test>
    </tests>
    <help><![CDATA[
    Splits a tabular dataset into multiple datsets in a dataset collection.  
    This can be used in a workflow to process datasets in the collection in parallel.

    ]]></help>
</tool>