comparison datasets_genome.xml @ 12:d78faac2c6ef draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_datasets commit affffdbe7237a2c0ba5793c0e7dd11cebb8413a9

11:ac24fff14f23

<tool id="datasets_download_genome" name="NCBI Datasets Genomes" profile="@PROFILE@" license="@LICENSE@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description>download genome sequence, annotation and metadata</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"></expand>
    <command><![CDATA[
#import re
@SETUP_CERTIFICATES@
datasets download genome $query.subcommand.download_by
#if $query.subcommand.download_by == 'accession':

    ## rename all faa, fna (resp faa.gz, fna.gz) to fasta (resp fasta.gz) to allow discovery
    && find ncbi_dataset \( -name "*.faa" -o -name "*.fna" -o -name "*.faa.gz" -o -name "*.fna.gz" \) -exec sh -c 'mv {} \$(echo {} | sed "s/.f[an]a\(.gz\)\?\$/.fasta\1/")' \;

    ## unzip all compressed (non-fasta) files (jsonl files are just named .gz)
    && find ncbi_dataset -name "*.jsonl.gz" -exec sh -c 'mv {} \$(dirname {})/\$(basename {} .gz)' \;
    #if $file_choices.decompress
        && find ncbi_dataset \( -name "*.gz" ! -name "*fasta.gz" \) -exec gunzip {} \;
    #end if

    #if "seq-report" in $file_choices.include
        && find ncbi_dataset -name sequence_report.jsonl -exec sh -c 'dataformat tsv genome-seq --inputfile {} > \$(dirname {})/\$(basename {} .jsonl).tsv' \;

            of compressed files https://github.com/galaxyproject/galaxy/pull/15085
        
            So with decompress="true" more powerfull assertions are powerful.
            A single test checks the default, ie decompress="false".
        -->
        <test expect_num_outputs="1">
            <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">
                <param name="include" value=""/>
            </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="144"/>
                    <has_n_columns n="4"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>

12:d78faac2c6ef

<tool id="datasets_download_genome" name="NCBI Datasets Genomes" profile="@PROFILE@" license="@LICENSE@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description>download genome sequence, annotation and metadata</description>
    <expand macro="bio_tools"/>
    <macros>
        <import>macros.xml</import>
    </macros>
    <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':

    ## rename all faa, fna (resp faa.gz, fna.gz) to fasta (resp fasta.gz) to allow discovery
    && find ncbi_dataset \( -name "*.faa" -o -name "*.fna" -o -name "*.faa.gz" -o -name "*.fna.gz" \) -exec sh -c 'mv {} \$(echo {} | sed "s/.f[an]a\(.gz\)\?\$/.fasta\1/")' \;

    ## unzip all compressed (non-fasta) files (jsonl files are just named .gz)
    ## note "not decompress" means that the datasets are provided uncompressed (datasets rehydrate is called we --gzip)
    ##      in this case we need to decompress all datasets that don't have a Galaxy datatype allowing for compression
    && find ncbi_dataset -name "*.jsonl.gz" -exec sh -c 'mv {} \$(dirname {})/\$(basename {} .gz)' \;
    #if not $file_choices.decompress
        && find ncbi_dataset \( -name "*.gz" ! -name "*fasta.gz" \) -exec gunzip {} \;
    #end if

    #if "seq-report" in $file_choices.include
        && find ncbi_dataset -name sequence_report.jsonl -exec sh -c 'dataformat tsv genome-seq --inputfile {} > \$(dirname {})/\$(basename {} .jsonl).tsv' \;

            of compressed files https://github.com/galaxyproject/galaxy/pull/15085
        
            So with decompress="true" more powerfull assertions are powerful.
            A single test checks the default, ie decompress="false".
        -->
        <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="144"/>
                    <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"/>
                        <!-- TODO this will only work when the galaxy python packakes for 22.05 have been released 
                            <has_n_columns n="9" comment="#"/> -->
                    </assert_contents>
                </element>
            </output_collection>
            <assert_command>
                <has_text text="gunzip"/>
            </assert_command>
        </test>
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>