<?xml version="1.0"?>
<tool id="bax2bam" name="bax2bam" version="@TOOL_VERSION@+@WRAPPER_VERSION@">
    <description>converts PacBio basecall format (bax.h5) into BAM</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <stdio></stdio>
    <command detect_errors="exit_code"><![CDATA[
        bax2bam
            #for $file in $files
                '$file'
            #end for
            -o output
            $readtype
            #if $pulsefeatures
                --pulsefeatures=$pulsefeatures
            #end if
            $losslessframes
            $internal
    ]]></command>
    <inputs>
        <param name="files" type="data" format="h5" multiple="true" label="Files" help="Should be from the same movie."/>
        <param name="readtype" type="select" label="Output read type" help="">
            <option value="--subread">subread</option>
            <option value="--hqregion">hqregion</option>
            <option value="--polymeraseread">polymeraseread</option>
        </param>
        <param argument="--pulsefeatures" type="select" multiple="true" label="Select pulse features in the output BAM." help="">
            <option value="DeletionQV" selected="true">dq - DeletionQV</option>
            <option value="DeletionTag" selected="true">dt - DeletionTag</option>
            <option value="InsertionQV" selected="true">iq - InsertionQV</option>
            <option value="IPD" selected="true">ip - IPD</option>
            <option value="PulseWidth" selected="true">pw - PulseWidth</option>
            <option value="MergeQV" selected="true">mq - MergeQV</option>
            <option value="SubstitutionQV" selected="true">sq - SubstitutionQV</option>
            <option value="SubstitutionTag" selected="false">st - SubstitutionTag</option>
        </param>
        <param argument="--losslessframes" type="boolean" truevalue="--losslessframes" falsevalue="" checked="false" label="Store full, 16-bit IPD/PulseWidth data" help="Instead of (default) downsampled, 8-bit encoding."/>
        <param argument="--internal" type="boolean" truevalue="--internal" falsevalue="" checked="false" label="Output BAMs in internal mode." help="Currently this indicates that non-sequencing ZMWs should be included in the output scraps BAM file, if applicable."/>
    </inputs>

    <outputs>
        <data name="output_scrap" from_work_dir="output.scraps.bam" format="bam" label="${tool.name} on ${on_string}: scraps">
            <filter>readtype == '--subread'</filter>
        </data>
        <data name="output_subread" from_work_dir="output.subreads.bam" format="bam" label="${tool.name} on ${on_string}: subreads">
            <filter>readtype == '--subread'</filter>
        </data>
        <data name="output_hqregion" from_work_dir="output.hqregions.bam" format="bam" label="${tool.name} on ${on_string}: hqregions">
            <filter>readtype == '--hqregion'</filter>
        </data>
        <data name="output_lqregion" from_work_dir="output.lqregions.bam" format="bam" label="${tool.name} on ${on_string}: lqregions">
            <filter>readtype == '--hqregion'</filter>
        </data>
        <data name="output_polymeraseread" from_work_dir="output.polymerase.bam" format="bam" label="${tool.name} on ${on_string}: polymerase">
            <filter>readtype == '--polymeraseread'</filter>
        </data>
    </outputs>
        
    <tests>
        <!-- source of test data: https://github.com/PacificBiosciences/PacBioTestData/tree/master/data/HdfSubreadSet/Analysis_Results/ -->
        <!-- #1: read type: subread -->
        <test>
            <param name="files" value="set.3.bax.h5,set.2.bax.h5,set.1.bax.h5"/>
            <param name="readtype" value="--subread"/>
            <output name="output_scrap" file="scraps.bam" compare="sim_size" delta="100"/>
            <output name="output_subread" file="subreads.bam" compare="sim_size" delta="100"/>
        </test>
        <!-- #2: read type: hqregion -->
        <test>
            <param name="files" value="set.3.bax.h5,set.2.bax.h5,set.1.bax.h5"/>
            <param name="readtype" value="--hqregion"/>
            <output name="output_hqregion" file="hqregions.bam" compare="sim_size" delta="100"/>
            <output name="output_hqregion" file="lqregions.bam" compare="sim_size" delta="100"/>
        </test>
        <!-- #3: read type: polymeraseread -->
        <test>
            <param name="files" value="set.3.bax.h5,set.2.bax.h5,set.1.bax.h5"/>
            <param name="readtype" value="--polymeraseread" compare="sim_size" delta="100"/>
            <output name="output_polymeraseread" file="polymerase.bam" compare="sim_size" delta="100"/>
        </test>
        <!-- #4: read type: subread, custom parameters -->
        <test>
            <param name="files" value="set.3.bax.h5,set.2.bax.h5,set.1.bax.h5"/>
            <param name="readtype" value="--subread"/>
            <param name="pulsefeatures" value="SubstitutionTag"/>
            <param name="losslessframes" value="true"/>
            <param name="internal" value="true"/>
            <output name="output_scrap" file="scraps_custom.bam" compare="sim_size" delta="100"/>
            <output name="output_subread" file="subreads_custom.bam" compare="sim_size" delta="100"/>
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**What it does**

bax2bam converts the legacy PacBio basecall format (bax.h5) into the BAM basecall format.

**Input**

bax.h5 files that should be from the same movie.

**Output**

A single BAM file. 

.. class:: infomark

**References**

 More information can be found on the github repositories `bax2bam <https://github.com/pacificbiosciences/bax2bam/>`_ and `PacBio Bioconda <https://github.com/PacificBiosciences/pbbioconda>`_.
    ]]></help>
    <citations>
        <citation type="bibtex">
@misc{PacificBiosciences2018,
  author = {Pacific Biosciences},
  year = {2018},
  title = {bax2bam},
  publisher = {GitHub},
  journal = {GitHub repository},
  url = {https://github.com/pacificbiosciences/bax2bam/},
}
        </citation>
    </citations>
</tool>