<tool profile="16.07" id="mothur_cluster_fragments" name="Cluster.fragments" version="@WRAPPER_VERSION@.0">
    <description> Group sequences that are part of a larger sequence</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <expand macro="stdio"/>
    <expand macro="version_command"/>
    <command><![CDATA[
        @SHELL_OPTIONS@

        ## create symlinks to input datasets
        ln -s "$fasta" fasta.dat &&
        ln -s "$names" names.dat &&
        ln -s "$count" count.dat &&

        echo 'cluster.fragments(
            fasta=fasta.dat,
            diffs=$diffs,
            percent=$percent,
            #if $count:
                count=count.dat,
            #end if
            name=names.dat
        )'
        | sed 's/ //g'  ## mothur trips over whitespace
        | mothur
        | tee mothur.out.log
    ]]></command>
    <inputs>
        <param name="fasta" type="data" format="fasta" label="fasta - Sequences to filter"/>
        <param name="names" type="data" format="mothur.names" optional="true" label="name - Sequences Name reference"/>
        <param name="diffs" type="integer" value="0" label="diffs - Number of mismatched bases to allow between sequences in a group (default 0)" min="0"/>
        <param name="percent" type="integer" value="0" label="percent - percentage of differences allowed ( between 1 and 100, default 0)" min="0" max="100"
               help="The percent parameter allows you to set percentage of differences allowed, default=0. percent=2 means if the number of difference is less than or equal to two percent of the length of the fragment, then cluster. You may use diffs and percent at the same time to say something like: If the number or differences is greater than 1 or more than 2% of the fragment length, don't merge."/>
        <param name="count" type="data" format="mothur.count_table" optional="true" label="count - a count_table" help="generated by count.seqs"/>
    </inputs>
    <outputs>
        <expand macro="logfile-output"/>
        <data name="out_fasta" format_source="fasta" from_work_dir="fasta*.fragclust.fasta" label="${tool.name} on ${on_string}: fasta"/>
        <data name="out_names" format="mothur.names" from_work_dir="fasta*.fragclust.names" label="${tool.name} on ${on_string}: names"/>
    </outputs>
    <tests>
        <test>
            <param name="fasta" value="amazon.fasta" ftype="fasta"/>
            <param name="names" value="amazon1.names" ftype="mothur.names"/>
            <output name="out_fasta" file="amazon.fragclust.fasta" ftype="fasta"/>
            <output name="out_names" file="amazon.fragclust.names" ftype="mothur.names"/>
            <expand macro="logfile-test"/>
        </test>
    </tests>
    <help>
<![CDATA[

@MOTHUR_OVERVIEW@

**Command Documentation**

The cluster.fragments_ command groups sequences that are part of a larger sequence.

.. _cluster.fragments: https://www.mothur.org/wiki/Cluster.fragments

v1.21: Updated to Mothur 1.33. Added count parameter.

]]>
    </help>
    <expand macro="citations"/>
</tool>