|
0
|
1 <tool id="extract_duplicates" name="Extract Duplicates" version="1.1.0">
|
|
|
2 <description>to a new dataset</description>
|
|
|
3 <command interpreter="bash">
|
|
2
|
4 extract_duplicates.sh $input $column $header "$regex_filter" $out_file
|
|
0
|
5 </command>
|
|
|
6 <inputs>
|
|
|
7 <param format="tabular" name="input" type="data" label="Input"/>
|
|
|
8 <param name="column" label="on column" type="data_column" data_ref="input" accept_default="true" />
|
|
2
|
9 <param name="regex_filter" type="text" label="Filter to sanitize the column" value="\\(.*" size='70'/>
|
|
0
|
10 <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"/>
|
|
|
11 </inputs>
|
|
|
12 <outputs>
|
|
|
13 <data format="input" name="out_file" metadata_source="input"/>
|
|
|
14 </outputs>
|
|
|
15 <help>
|
|
|
16 </help>
|
|
|
17 </tool>
|
