view unsorted_uniq.xml @ 3:7068d1548234 draft

Uploaded
author bgruening
date Sun, 06 Oct 2013 08:22:36 -0400
parents a4ad586d1403
children 56e80527c482
line wrap: on
line source

<tool id="tp_sorted_uniq" name="Unique" version="0.3">
  <description>occurrences of each record</description>
    <requirements>
        <requirement type="package" version="8.21">gnu_coreutils</requirement>
    </requirements>
    <command interpreter='python'>
        unsorted_uniq.py 
            $ignore_case 
            $is_numeric
            #if $adv_opts.adv_opts_selector=="advanced":
                $adv_opts.column_start
                $adv_opts.column_end
            #end if
            $outfile
            $infile
    </command>
    <inputs>
        <param name="infile" type="data" format="tabular,txt" label="File to scan for unique values" /> 
        <param name="ignore_case" type="boolean" label="ignore differences in case when comparing (-f)" truevalue="-f" falsevalue="false" checked="false"/>
        <param name="is_numeric" type="boolean" label="column only contains numeric values (-n)" truevalue="-n" falsevalue="false" checked="false" />
        <conditional name="adv_opts">
            <param name="adv_opts_selector" type="select" label="Advanced Options">
              <option value="basic" selected="True">Hide Advanced Options</option>
              <option value="advanced">Show Advanced Options</option>
            </param>
            <when value="basic" />
            <when value="advanced">
                <param name="column_start" label="Column start" type="data_column" data_ref="infile" help="Unique on specific column range"/>
                <param name="column_end" label="Column end" type="data_column" data_ref="infile" help="Unique on specific column range"/>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format="infile" name="outfile" metadata_source="infile"/>
    </outputs>
    <tests>
        <test>
        </test>
    </tests>
    <help>

 .. class:: infomark

**Syntax**

This tool returns all unique lines using the 'sort -u' command. It can be used with unsorted files. 
If you need additional options, like grouping or counting your unique results, please use the 'Unique lines from sorted file' tool.

-----

.. class:: infomark

The input file needs to be tab separated. Please convert your file if necessary.

-----

**Example**

- Input file::
     
       chr1   10  100  gene1
       chr1  105  200  gene2
       chr1   10  100  gene1
       chr2   10  100  gene4
       chr2 1000 1900  gene5
       chr3   15 1656  gene6
       chr2   10  100  gene4

- Unique lines will result in::

       chr1   10  100  gene1
       chr1  105  200  gene2
       chr2   10  100  gene4
       chr2 1000 1900  gene5
       chr3   15 1656  gene6


</help>
</tool>