<tool id="raptor-build" name="raptor build" version="2.0.0+8" python_template_version="3.5">
    <description>
        Builds an index to be used by `raptor search`.
    </description>
    <requirements>
        <requirement type="package" version="2.0.0">raptor</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        echo "" > files.txt;
        #for $i, $s in enumerate($inputs)
            ln -s '${s}' genome${i}.fasta;
            echo genome${i}.fasta >> files.txt;
        #end for

        raptor build files.text
            #if $window$ --window ${window} #end if#
            --threads ${threads}
            --parts ${parts}
            --kmer ${kmer}
            --size ${size}
            --hash ${hash}
            ${compressed}
            ${compute_minimiser}
            ${disable_cutoffs}
            --output output.index;
    ]]></command>
    <inputs>
        <param name="inputs" label="Files representing a bin each" type="data" format="fasta" multiple="true" />
        <param name="threads" label="Threads" type="integer" value="1" min="1" help="The numer of threads to use. Default: 1. Value must be a positive integer. " />
        <param name="parts" label="Parts" type="integer" value="1" min="1" help="Splits the index in this many parts. Default: 1. Value must be a power of two." />
        <param name="window" label="Window size" type="integer" optional="true" min="1" help="The window size. Default: kmer size. Value must be a positive integer." />
        <param name="kmer" label ="Kmer size" type="integer" value="20" min="1" max="32" help="The k-mer size. Default: 20. Value must be in range [1,32]." />
        <param name="size" label="Index size" type="text" value="1k" help="The size in bytes of the resulting index. Default: 1k. Must be an integer followed by [k,m,g,t] (case insensitive)." >
            <option value="1k">1k</option>
            <option value="1m">1m</option>
            <option value="1g">1g</option>
            <option value="1t">1t</option>
        </param>
        <param name="hash" label="Hash functions" type="integer" value="2" min="1" max="5" help="The number of hash functions to use. Default: 2. Value must be in range [1,5]." />
        <param name="compressed" label="Index compression" type="boolean" truevalue="--compressed" falsevalue="" help="Build a compressed index." />
        <param name="compute_minimiser" label="Compute Minimiser" type="boolean" truevalue="--compute-minimiser" falsevalue="" help="Computes minimisers using cutoffs from Mantis (Pandey et al.). Does not create the index." />
        <param name="disable_cutoffs" label="Disable cutoffs" type="boolean" truevalue="--disable-cutoffs" falsevalue="" help="Do not apply cutoffs when using --compute-minimiser." />
    </inputs>
    <outputs>
        <data name="index" format="binary" from_work_dir="output.index" />
    </outputs>
    <tests>
        <test>
            <param name="inputs" value="genome0.fasta,genome1.fasta" />
            <param name="kmer" value="2" />
            <param name="size" value="1k" />
            <output name="index" file="test_expected.index" />
        </test>
    </tests>

    <help><![CDATA[Raptor - A fast and space-efficient pre-filter for querying very large collections of nucleotide sequences.
===========================================================================================================

POSITIONAL ARGUMENTS
    ARGUMENT-1 (std::filesystem::path)
          File containing file names. The file must contain at least one file
          path per line, with multiple paths being separated by a whitespace.
          Each line in the file corresponds to one bin. Valid extensions for
          the paths in the file are [minimiser] when preprocessing, and
          [embl,fasta,fa,fna,ffn,faa,frn,fas,fastq,fq,genbank,gb,gbk,sam],
          possibly followed by [bz2,gz,bgzf] otherwise. The input file must
          exist and read permissions must be granted.

OPTIONS

  Basic options:
    --threads (unsigned 8 bit integer)
          The numer of threads to use. Default: 1. Value must be a positive
          integer.
    --parts (unsigned 8 bit integer)
          Splits the index in this many parts. Default: 1. Value must be a
          power of two.
    --window (unsigned 32 bit integer)
          The window size. Default: 20. Value must be a positive integer.
    --kmer (unsigned 8 bit integer)
          The k-mer size. Default: 20. Value must be in range [1,32].
    --output (std::filesystem::path)
          Provide an output filepath or an output directory if
          --compute-minimiser is used.
    --size (std::string)
          The size in bytes of the resulting index. Default: 1k. Must be an
          integer followed by [k,m,g,t] (case insensitive).
    --hash (unsigned 64 bit integer)
          The number of hash functions to use. Default: 2. Value must be in
          range [1,5].
    --compressed
          Build a compressed index.
    --compute-minimiser
          Computes minimisers using cutoffs from Mantis (Pandey et al.). Does
          not create the index.
    --disable-cutoffs
          Do not apply cutoffs when using --compute-minimiser.

EXAMPLES
    raptor build --kmer 19 --window 23 --size 8m --output raptor.index
    all_bin_paths.txt

    raptor build --kmer 19 --window 23 --compute-minimiser --output
    precomputed_minimisers all_bin_paths.txt

    raptor build --size 8m --output minimiser_raptor.index
    all_minimiser_paths.txt

VERSION
    Last update: 2021-08-26
    Raptor version: 2.0.0 (raptor-v2.0.0)
    SeqAn version: 3.1.0-rc.2

URL
    https://github.com/seqan/raptor

LEGAL
    Raptor Copyright: BSD 3-Clause License
    Author: Enrico Seiler
    Contact: enrico.seiler@fu-berlin.de
    SeqAn Copyright: 2006-2021 Knut Reinert, FU-Berlin; released under the
    3-clause BSDL.
    In your academic works please cite: Raptor: A fast and space-efficient
    pre-filter for querying very large collections of nucleotide sequences;
    Enrico Seiler, Svenja Mehringer, Mitra Darvish, Etienne Turc, and Knut
    Reinert; iScience 2021 24 (7): 102782. doi:
    https://doi.org/10.1016/j.isci.2021.102782
    For full copyright and/or warranty information see --copyright.
    ]]></help>
    <citations>
        <citation type="bibtex">
@Article{Seiler2021,
author={Seiler, Enrico
and Mehringer, Svenja
and Darvish, Mitra
and Turc, Etienne
and Reinert, Knut},
title={Raptor: A fast and space-efficient pre-filter for querying very large collections of nucleotide sequences},
journal={iScience},
year={2021},
month={Jul},
day={23},
publisher={Elsevier},
volume={24},
number={7},
issn={2589-0042},
doi={10.1016/j.isci.2021.102782},
url={https://doi.org/10.1016/j.isci.2021.102782}
}
</citation>
    </citations>
</tool>