comparison datasets_genome.xml @ 21:0f3b3813b6ae draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_datasets commit c1c3f90e4aa7dc258aa61d98ec4eac0b97eef426

20:7b925f7c50b2

    <description>download genome sequence, annotation and metadata</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"></expand>
    <expand macro="version_command"/>
    <command><![CDATA[
#import re
@SETUP_CERTIFICATES@
datasets download genome $query.subcommand.download_by
#if $query.subcommand.download_by == 'accession':
    #if $query.subcommand.text_or_file.text_or_file == 'text':

                <option value="only" selected="false">Limit to MAGs</option>
                <option value="exclude" selected="false">Exclude MAGs</option>
            </param>
            <expand macro="released_options"/>
            <expand macro="released_options" before_or_after="after"/>

            <repeat name="search" title="Add search terms">
                <param argument="--search" type="text" label="Only include genomes that have the specified text in the searchable fields" help="Searchable fields are species and infraspecies, assembly name and submitter"/>
            </repeat>
        </section>
        <section name="file_choices" title="Output options" expanded="true">

        </section>
    </inputs>
    <outputs>
        <data name="genome_data_report" format="tabular" label="NCBI Genome Datasets: Data Report" from_work_dir="genome_data_report.tsv"/>
        <collection name="sequence_report" label="NCBI Genome Datasets: Sequence Data Report" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/sequence_report.tsv" ext="tabular" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "seq-report" in file_choices['include']</filter>
        </collection>
        <collection name="genome_fasta" label="NCBI Genome Datasets: genome fasta" type="list:list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)/(?!rna|cds_from)(?P&lt;identifier_1&gt;.*?)(_genomic)?\.(?P&lt;ext&gt;fasta(\.gz)?)"  directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "genome" in file_choices['include']</filter>
        </collection>
        <collection name="rna_fasta" label="NCBI Genome Datasets: RNA fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/rna\.(?P&lt;ext&gt;fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "rna" in file_choices['include']</filter>
        </collection>
        <collection name="protein_fasta" label="NCBI Genome Datasets: protein fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/protein\.(?P&lt;ext&gt;fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "protein" in file_choices['include']</filter>
        </collection>
        <collection name="genomic_cds" label="NCBI Genome Datasets: genomic cds fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/cds_from_genomic\.(?P&lt;ext&gt;fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "cds" in file_choices['include']</filter>
        </collection>
        <collection name="genomic_gff" label="NCBI Genome Datasets: genomic gff3" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gff" ext="gff3" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "gff3" in file_choices['include']</filter>
        </collection>
        <collection name="genomic_gtf" label="NCBI Genome Datasets: gtf" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gtf" ext="gtf" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "gtf" in file_choices['include']</filter>
        </collection>
        <collection name="genomic_gbff" label="NCBI Genome Datasets: GenBank flatfile" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gbff" ext="txt" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "gbff" in file_choices['include']</filter>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="3">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>
            </conditional>
            <param name="chromosomes" value="21"/>
            <param name="released_before" value="01/01/2018"/>
            <section name="file_choices">
                <!-- include a sequence (which should be downloaded as fasta.gz)
                     and one non-sequence (which should be decompressed) output -->
                <param name="include" value="rna,gff3"/>
            </section>
            <output name="genome_data_report">
                <assert_contents>
                    <has_text text="Assembly Accession&#009;Assembly Name&#009;Assembly Submitter&#009;Organism Name"/>
                    <has_n_lines n="142"/>
                    <has_n_columns n="4"/>
                </assert_contents>
            </output>
            <output_collection name="rna_fasta" type="list" count="1">
                <element name="GCF_000306695.2" decompress="true">
                    <assert_contents>
                        <has_text text=">"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="genomic_gff" type="list">
                <element name="GCF_000306695.2">
                    <assert_contents>
                        <has_n_lines min="1000000"/>
                        <has_line line="##gff-version 3"/>
                        <has_n_columns n="9" comment="#"/>

        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>
            </conditional>
            <param name="chromosomes" value="21"/>
            <param name="assembly_level" value="chromosome,complete"/>
            <param name="released_before" value="01/01/2018"/>
            <section name="file_choices">
                <param name="include" value="genome"/>
                <param name="decompress" value="true"/>
            </section>
            <output_collection name="genome_fasta" type="list:list" count="12">
                <expand macro="genome_fasta_assert" el1="GCA_000002115.2" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_000002125.2" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_000212995.1" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_000252825.1" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_000306695.2" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_000365445.1" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_001292825.2" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_001524155.4" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_001712695.1" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCA_022833125.2" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCF_000002125.1" el2="chr21" expression=">"/>
                <expand macro="genome_fasta_assert" el1="GCF_000306695.2" el2="chr21" expression=">"/>
                <!-- According to  https://github.com/ncbi/datasets/issues/188, the following should not be included among the returned results anymore 09/2023 -->
                <!--
                <expand macro="genome_fasta_assert" el1="GCA_000442335.2" el2="GCA_000442335.2_LinearCen1.1_normalized" expression=">" expression_n="25"/>
                <expand macro="genome_fasta_assert" el1="GCA_000002135.3" el2="GCA_000002135.3_CRA_TCAGchr7v2" expression=">"/>
                -->

        <test expect_failure="true">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>
            </conditional>
            <param name="chromosomes" value="21"/>
            <param name="assembly_level" value="chromosome,complete"/>
            <param name="assembly_source" value="refseq"/>
            <param name="released_before" value="01/01/2018"/>
            <section name="file_choices">
                <param name="include" value="genome"/>
                <param name="decompress" value="true"/>
            </section>
            <assert_stderr>

                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="GCF_000013305.1 GCF_000007445.1"/>
                </conditional>
            </conditional>
            <param name="released_before" value="01/01/2007"/>
            <section name="file_choices">
                <param name="include" value="seq-report,gtf,cds"/>
                <param name="decompress" value="true"/>
            </section>
            <output name="genome_data_report">

                    <has_text text="GCF_000013305.1"/>
                    <has_n_lines n="3"/>
                    <has_n_columns n="4"/>
                </assert_contents>
            </output>
            <output_collection name="sequence_report" type="list" count="2" >
                <element name="GCF_000007445.1">
                    <assert_contents>
                        <has_text text="GCF_000007445.1"/>
                        <has_n_lines n="2"/>
                        <has_n_columns n="15"/>

                        <has_n_lines n="2"/>
                        <has_n_columns n="15"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="genomic_gtf" type="list">
                <element name="GCF_000007445.1" file="GCF_000007445.1.genomic.gtf" compare="contains"/>
                <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.gtf" compare="contains"/>
            </output_collection>
            <output_collection name="genomic_cds" type="list">
                <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.genomic.cds" compare="contains"/>

                <conditional name="text_or_file">
                    <param name="text_or_file" value="file"/>
                    <param name="inputfile" value="accessions.txt"/>
                </conditional>
            </conditional>
            <param name="released_before" value="01/01/2007"/>
            <section name="file_choices">
                <param name="include" value="seq-report,gff3,gbff"/>
                <param name="decompress" value="true"/>
            </section>
            <output name="genome_data_report">

            <output_collection name="genomic_gbff" type="list">
                <element name="GCF_000007445.1" file="genome.3.GCF_000007445.1.genomic.gbff" compare="contains"/>
                <element name="GCF_000013305.1" file="genome.3.GCF_000013305.1.genomic.gbff" compare="contains"/>
            </output_collection>
        </test>

        <!-- should not fail https://github.com/ncbi/datasets/issues/194 -->
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="accession"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="GCF_000001405"/>
                </conditional>
            </conditional>
            <param name="released_before" value="01/01/2015"/>
            <param name="assembly_version" value="all"/>
            <section name="file_choices">
                <param name="include" value="seq-report"/>
            </section>
            <output name="genome_data_report">
                <!-- assert that we get at least the 16 versions available at the time of writing this test -->

            <section name="file_choices">
                <param name="include" value="genome,protein,rna,cds"/>
                <param name="decompress" value="true"/>
            </section>
            <output_collection name="genome_fasta" type="list:list" count="1">
                <expand macro="genome_fasta_assert" el1="GCF_000146045.2" el2="GCF_000146045.2_R64" expression=">NC_[0-9]+\.[0-9]+ Saccharomyces cerevisiae S288[Cc] (mitochondrion|chromosome .*), complete (sequence|genome)" expression_n="17"/>
            </output_collection>
            <output_collection name="protein_fasta" type="list" count="1">
                <element name="GCF_000146045.2" decompress="true">
                    <assert_contents>
                        <has_text text=">"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="rna_fasta" type="list" count="1">
                <element name="GCF_000146045.2" decompress="true">
                    <assert_contents>
                        <has_text text=">"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- same as the previous test, but use the default value for decompress,

                </element>
            </output_collection>
            <output_collection name="protein_fasta" type="list" count="1">
                <element name="GCF_000146045.2" ftype="fasta.gz">
                    <assert_contents>
                        <has_size value="1845038" delta="2000"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="rna_fasta" type="list" count="1">
                <element name="GCF_000146045.2" ftype="fasta.gz">

                <param name="include" value="seq-report,genome"/>
                <param name="decompress" value="true"/>
            </section>
            <output_collection name="sequence_report" type="list" count="2"/>
            <output_collection name="genome_fasta" type="list:list" count="2">
                <expand macro="genome_fasta_assert" el1="GCF_000002945.2" el2="GCF_000002945.2_ASM294v3" expression=">NC_[0-9]+\.[0-9]+ Schizosaccharomyces pombe.*" expression_n="4"/>
                <expand macro="genome_fasta_assert" el1="GCF_000146045.2" el2="GCF_000146045.2_R64" expression=">NC_[0-9]+\.[0-9]+ Saccharomyces cerevisiae S288[Cc].*" expression_n="17"/>
            </output_collection>
        </test>
        <!-- tax_exact_match should filter out strains
             https://github.com/ncbi/datasets/issues/187 -->
        <test expect_num_outputs="1">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="4932"/>
                <param name="tax_exact_match" value="true"/>
            </conditional>
            <param name="include" value=""/>
            <output name="genome_data_report">
                <assert_contents>
                   <has_text text="Saccharomyces cerevisiae ZTW1" negate="true"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>

21:0f3b3813b6ae

    <description>download genome sequence, annotation and metadata</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"/>
    <expand macro="version_command"/>
    <stdio>
        <regex match="Warning" source="stderr" level="warning" description=""/>
        <regex match="skipping" source="stderr" level="warning" description=""/>
        <regex match="ERROR" level="fatal"/>
    </stdio>
    <command detect_errors="exit_code"><![CDATA[
#import re
@SETUP_CERTIFICATES@
datasets download genome $query.subcommand.download_by
#if $query.subcommand.download_by == 'accession':
    #if $query.subcommand.text_or_file.text_or_file == 'text':

                <option value="only" selected="false">Limit to MAGs</option>
                <option value="exclude" selected="false">Exclude MAGs</option>
            </param>
            <expand macro="released_options"/>
            <expand macro="released_options" before_or_after="after"/>
            <repeat name="search" title="Add search terms">
                <param argument="--search" type="text" label="Only include genomes that have the specified text in the searchable fields" help="Searchable fields are species and infraspecies, assembly name and submitter"/>
            </repeat>
        </section>
        <section name="file_choices" title="Output options" expanded="true">

        </section>
    </inputs>
    <outputs>
        <data name="genome_data_report" format="tabular" label="NCBI Genome Datasets: Data Report" from_work_dir="genome_data_report.tsv"/>
        <collection name="sequence_report" label="NCBI Genome Datasets: Sequence Data Report" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/sequence_report.tsv" ext="tabular" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "seq-report" in file_choices['include']</filter>
        </collection>
        <collection name="genome_fasta" label="NCBI Genome Datasets: genome fasta" type="list:list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)/(?!rna|cds_from)(?P&lt;identifier_1&gt;.*?)(_genomic)?\.(?P&lt;ext&gt;fasta(\.gz)?)" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "genome" in file_choices['include']</filter>
        </collection>
        <collection name="rna_fasta" label="NCBI Genome Datasets: RNA fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/rna\.(?P&lt;ext&gt;fasta(\.gz)?)$" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "rna" in file_choices['include']</filter>
        </collection>
        <collection name="protein_fasta" label="NCBI Genome Datasets: protein fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/protein\.(?P&lt;ext&gt;fasta(\.gz)?)$" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "protein" in file_choices['include']</filter>
        </collection>
        <collection name="genomic_cds" label="NCBI Genome Datasets: genomic cds fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/cds_from_genomic\.(?P&lt;ext&gt;fasta(\.gz)?)$" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "cds" in file_choices['include']</filter>
        </collection>
        <collection name="genomic_gff" label="NCBI Genome Datasets: genomic gff3" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gff" ext="gff3" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "gff3" in file_choices['include']</filter>
        </collection>
        <collection name="genomic_gtf" label="NCBI Genome Datasets: gtf" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gtf" ext="gtf" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "gtf" in file_choices['include']</filter>
        </collection>
        <collection name="genomic_gbff" label="NCBI Genome Datasets: GenBank flatfile" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gbff" ext="txt" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
            <filter>file_choices['include'] and "gbff" in file_choices['include']</filter>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="3">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>
            </conditional>
            <section name="filters">
                <param name="chromosomes" value="21"/>
                <param name="released_before" value="01/01/2018"/>
            </section>
            <section name="file_choices">
                <!-- include a sequence (which should be downloaded as fasta.gz)
                     and one non-sequence (which should be decompressed) output -->
                <param name="include" value="rna,gff3"/>
            </section>
            <output name="genome_data_report">
                <assert_contents>
                    <has_text text="Assembly Accession&#9;Assembly Name&#9;Assembly Submitter&#9;Organism Name"/>
                    <has_n_lines n="142"/>
                    <has_n_columns n="4"/>
                </assert_contents>
            </output>
            <output_collection name="rna_fasta" type="list" count="2">
                <element name="GCF_000306695.2" decompress="true">
                    <assert_contents>
                        <has_text text="&gt;"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="genomic_gff" type="list" count="12">
                <element name="GCF_000306695.2">
                    <assert_contents>
                        <has_n_lines min="1000000"/>
                        <has_line line="##gff-version 3"/>
                        <has_n_columns n="9" comment="#"/>

        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>
            </conditional>
            <section name="filters">
                <param name="chromosomes" value="21"/>
                <param name="assembly_level" value="chromosome,complete"/>  
                <param name="released_before" value="01/01/2018"/>
            </section>
            <section name="file_choices">
                <param name="include" value="genome"/>
                <param name="decompress" value="true"/>
            </section>
            <output_collection name="genome_fasta" type="list:list" count="11">
                <expand macro="genome_fasta_assert" el1="GCA_000002115.2" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCA_000002125.2" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCA_000212995.1" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCA_000306695.2" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCA_000365445.1" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCA_001292825.2" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCA_001524155.4" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCA_001712695.1" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCA_022833125.2" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCF_000002125.1" el2="chr21" expression="&gt;"/>
                <expand macro="genome_fasta_assert" el1="GCF_000306695.2" el2="chr21" expression="&gt;"/>
                <!-- According to  https://github.com/ncbi/datasets/issues/188, the following should not be included among the returned results anymore 09/2023 -->
                <!--
                <expand macro="genome_fasta_assert" el1="GCA_000442335.2" el2="GCA_000442335.2_LinearCen1.1_normalized" expression=">" expression_n="25"/>
                <expand macro="genome_fasta_assert" el1="GCA_000002135.3" el2="GCA_000002135.3_CRA_TCAGchr7v2" expression=">"/>
                -->

        <test expect_failure="true">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>
            </conditional>
            <section name="filters">
                <param name="chromosomes" value="21"/>
                <param name="assembly_level" value="chromosome,complete"/>
                <param name="assembly_source" value="refseq"/>
                <param name="released_before" value="01/01/2018"/>
            </section>
            <section name="file_choices">
                <param name="include" value="genome"/>
                <param name="decompress" value="true"/>
            </section>
            <assert_stderr>

                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="GCF_000013305.1 GCF_000007445.1"/>
                </conditional>
            </conditional>
            <section name="filters">
                <param name="released_before" value="01/01/2007"/>
            </section>
            <section name="file_choices">
                <param name="include" value="seq-report,gtf,cds"/>
                <param name="decompress" value="true"/>
            </section>
            <output name="genome_data_report">

                    <has_text text="GCF_000013305.1"/>
                    <has_n_lines n="3"/>
                    <has_n_columns n="4"/>
                </assert_contents>
            </output>
            <output_collection name="sequence_report" type="list" count="2">
                <element name="GCF_000007445.1">
                    <assert_contents>
                        <has_text text="GCF_000007445.1"/>
                        <has_n_lines n="2"/>
                        <has_n_columns n="15"/>

                        <has_n_lines n="2"/>
                        <has_n_columns n="15"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="genomic_gtf" type="list" count="2">
                <element name="GCF_000007445.1" file="GCF_000007445.1.genomic.gtf" compare="contains"/>
                <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.gtf" compare="contains"/>
            </output_collection>
            <output_collection name="genomic_cds" type="list">
                <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.genomic.cds" compare="contains"/>

                <conditional name="text_or_file">
                    <param name="text_or_file" value="file"/>
                    <param name="inputfile" value="accessions.txt"/>
                </conditional>
            </conditional>
            <section name="filters">
                <param name="released_before" value="01/01/2007"/>
            </section>
            <section name="file_choices">
                <param name="include" value="seq-report,gff3,gbff"/>
                <param name="decompress" value="true"/>
            </section>
            <output name="genome_data_report">

            <output_collection name="genomic_gbff" type="list">
                <element name="GCF_000007445.1" file="genome.3.GCF_000007445.1.genomic.gbff" compare="contains"/>
                <element name="GCF_000013305.1" file="genome.3.GCF_000013305.1.genomic.gbff" compare="contains"/>
            </output_collection>
        </test>
        <!-- should not fail https://github.com/ncbi/datasets/issues/194 -->
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="accession"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="GCF_000001405"/>
                </conditional>
            </conditional>
            <section name="filters">
                <param name="released_before" value="01/01/2015"/>
                <param name="assembly_version" value="all"/>
            </section>
            <section name="file_choices">
                <param name="include" value="seq-report"/>
            </section>
            <output name="genome_data_report">
                <!-- assert that we get at least the 16 versions available at the time of writing this test -->

            <section name="file_choices">
                <param name="include" value="genome,protein,rna,cds"/>
                <param name="decompress" value="true"/>
            </section>
            <output_collection name="genome_fasta" type="list:list" count="1">
                <expand macro="genome_fasta_assert" el1="GCF_000146045.2" el2="GCF_000146045.2_R64" expression="&gt;NC_[0-9]+\.[0-9]+ Saccharomyces cerevisiae S288[Cc] (mitochondrion|chromosome .*), complete (sequence|genome)" expression_n="17"/>
            </output_collection>
            <output_collection name="protein_fasta" type="list" count="1">
                <element name="GCF_000146045.2" decompress="true">
                    <assert_contents>
                        <has_text text="&gt;"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="rna_fasta" type="list" count="1">
                <element name="GCF_000146045.2" decompress="true">
                    <assert_contents>
                        <has_text text="&gt;"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!-- same as the previous test, but use the default value for decompress,

                </element>
            </output_collection>
            <output_collection name="protein_fasta" type="list" count="1">
                <element name="GCF_000146045.2" ftype="fasta.gz">
                    <assert_contents>
                        <has_size value="1847862" delta="2000"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="rna_fasta" type="list" count="1">
                <element name="GCF_000146045.2" ftype="fasta.gz">

                <param name="include" value="seq-report,genome"/>
                <param name="decompress" value="true"/>
            </section>
            <output_collection name="sequence_report" type="list" count="2"/>
            <output_collection name="genome_fasta" type="list:list" count="2">
                <expand macro="genome_fasta_assert" el1="GCF_000002945.2" el2="GCF_000002945.2_ASM294v3" expression="&gt;NC_[0-9]+\.[0-9]+ Schizosaccharomyces pombe.*" expression_n="4"/>
                <expand macro="genome_fasta_assert" el1="GCF_000146045.2" el2="GCF_000146045.2_R64" expression="&gt;NC_[0-9]+\.[0-9]+ Saccharomyces cerevisiae S288[Cc].*" expression_n="17"/>
            </output_collection>
        </test>
        <!-- tax_exact_match should filter out strains
             https://github.com/ncbi/datasets/issues/187 -->
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="4932"/>
                <param name="tax_exact_match" value="true"/>
            </conditional>
            <output name="genome_data_report">
                <assert_contents>
                    <has_text text="Saccharomyces cerevisiae ZTW1" negate="true"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>