<?xml version="1.0"?>
<tool id="seqtk_comp" name="seqtk_comp" version="@TOOL_VERSION@.1">
    <description>get the nucleotide composition of FASTA/Q</description>
    <expand macro="bio_tools"/>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="@AWK_VERSION@">gawk</requirement>
    </expand>
    <expand macro="stdio"/>
    <command><![CDATA[
seqtk comp
#if $in_bed:
    -r '$in_bed'
#end if
'$in_file' | awk 'BEGIN{print "#chr\tlength\t#A\t#C\t#G\t#T\t#2\t#3\t#4\t#CpG\t#tv\t#ts\t#CpG-ts"}1'
> '$default'
    ]]></command>
    <inputs>
        <expand macro="in_faq"/>
        <param name="in_bed" type="data" format="bed" optional="true" label="BED file"/>
    </inputs>
    <outputs>
        <data name="default" format="tabular" label="Nucleotide composition of $in_file.name"/>
    </outputs>
    <tests>
        <test>
            <param name="in_file" value="seqtk_comp.fa" ftype="fasta"/>
            <output name="default" file="seqtk_comp.out" ftype="tabular"/>
        </test>
        <test>
            <param name="in_file" value="seqtk_comp.fa.gz" ftype="fasta.gz"/>
            <output name="default" file="seqtk_comp.out" ftype="tabular"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

Reports composition of fasta/fastq sequences. For an example sequence like

::
    >test0
    ACTGACTGAA
    >ambig_ref
    ACGTCGTGTTVHDBN

The seqtk tool will report:

::

    #chr       length #A #C #G #T #2 #3 #4 #CpG #tv #ts #CpG-ts
    test0      11     4  2  2  2  0  0  1  0    0   0   0
    ambig_ref  15     1  2  3  4  0  4  1  4    0   0   0

@ATTRIBUTION@
    ]]></help>
    <expand macro="citation" />
</tool>