<tool id="extract_duplicates" name="Extract Duplicates" version="1.1.0">
  <description>to a new dataset</description>
  <command interpreter="bash">
    extract_duplicates.sh $input $column $header "$regex_filter" $out_file
  </command>
  <inputs>
    <param format="tabular" name="input" type="data" label="Input"/>
		<param name="column" label="on column" type="data_column" data_ref="input" accept_default="true" />
		<param name="regex_filter" type="text" label="Filter to sanitize the column" value="\\(.*" size='70'/>
		<param name="header" type="boolean" checked="False" truevalue="yes" falsevalue="no" label="Input file has a header?" help="if checked, the first line of the input will be treated as a header"/>
  </inputs>
  <outputs>
    <data format="input" name="out_file" metadata_source="input"/>
  </outputs>
  <help>
</help>
</tool>