<tool id="fastq_seq_count" name="Count sequences in fastq files" version="0.1.1" python_template_version="3.5">
    <description></description>
    <requirements>
        <requirement type="package" version="3.8">python</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #set $qcol = int(str($query_col))-1
        python $__tool_directory__/fastq_seq_count.py
        -p $fastqs_file
        -i $query_file
        #if $id_col
            #set $id_col_list = ','.join([str(int(x)-1) for x in str($id_col).split(',')])
            -I '$id_col_list'
        #end if
        -q $qcol
        #if $query_label
          -Q $query_label
        #end if
        #if $compare_col
           #set $ccol = int(str($compare_col))-1
          -c $ccol
        #end if
        #if $compare_label
          -C $compare_label
        #end if
        $reverse_complements
        -T "\${GALAXY_SLOTS:-4}"
        $report_fastq_counts
        -s $report
    ]]></command>
    <configfiles>
        <configfile name="fastqs_file"><![CDATA[#slurp
#for $f in $fastqs:
#set $line = str($f) + '\t' + $f.element_identifier
$line
#end for
]]></configfile>
    </configfiles>
    <inputs>
        <param name="fastqs" type="data" format="fastq" multiple="true" label="fastq files to search"/>
        <param name="query_file" type="data" format="tabular" label="query sequences"/>
        <param name="id_col" type="data_column" data_ref="query_file" multiple="true" optional="true" numerical="false" label="Identifier column(s)" help="Columns to keep as identifiers for the summary report"/>
        <param name="query_col" type="data_column" data_ref="query_file" label="query sequence column"/>
        <param name="query_label" type="text" value="mutant" label="query sequence label"/>
        <param name="compare_col" type="data_column" data_ref="query_file" optional="true" label="comparison sequence column"/>
        <param name="compare_label" type="text" value="normal" label="comparison sequence label"/>
        <param name="reverse_complements" type="boolean" truevalue="-r" falsevalue="" checked="true" label="Also search for reverse complements"/>
        <param name="report_fastq_counts" type="boolean" truevalue="-n counts" falsevalue="" checked="false" label="report of per fastq counts"/>
    </inputs>
    <outputs>
        <data name="report" format="tabular" label="${tool.name} on ${on_string} summary report"/> 
        <data name="hits" format="tabular" label="${tool.name} on ${on_string} count details" from_work_dir="counts"> 
            <filter>report_fastq_counts</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="fastqs" ftype="fastq" value="reads1.fastq,reads2.fastq"/>
            <param name="query_file" ftype="tabular" value="query_seqs.tabular"/>
            <param name="id_col" value="1,2,3,4,5"/>
            <param name="query_col" value="4"/>
            <param name="query_label" value="mutant"/>
            <param name="compare_col" value="5"/>
            <param name="compare_label" value="normal"/>
            <param name="reverse_complements" value="True"/>
            <param name="report_fastq_counts" value="True"/>
            <output name="report" ftype="tabular" file="summary_report.out" />
            <output name="hits" ftype="tabular" file="count_details.out" />
        </test>
    </tests>
    <help><![CDATA[
**Report fastq reads that contain sequences**

This tool searches fastq reads for given nucleic acid query sequences. 
A typical use would be to compare the relative occurrence of two sequences. 

**NOTE:** This only reports complete matches to the sequences, and reads that may partially match at the ends will not be counted. 

**INPUTS**

  fastq files 
         - the sequence files to search

  query file - a tabular file
         - that contains a column of "query" sequences to match in fastq reads
         - it may contain a second "comparison" sequence column to match

**OUTPUTS**

  summary report - a tabular file
         - the first column is the line number from the query file
         - columns from the query file selected as identifiers
         - the count of fastq entries for the query sequence
         - the count of fastq entries for the comparison sequence (if selected)
         - the fraction of query sequence matches compared to the total of query and comparison matches

  count details - an optional tabular file of match count
         - the fastq name
         - the first column is the line number from the query file
         - the sequence that matched 
         - the label of the sequence that matched
         - the strand that matched 
         - the number reads that matched 

    ]]></help>
</tool>