comparison pyega3.xml @ 4:9564758e8638 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/pyega3 commit a7400d366495a3e2bd6e0cb120834a59327537ec

3:8bbe09a52904

<tool id="pyega3" name="EGA Download Client" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.01" >
    <macros>
        <token name="@TOOL_VERSION@">4.0.5</token>
        <token name="@VERSION_SUFFIX@">1</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">pyega3</requirement>
    </requirements>
    <version_command><![CDATA[

    && rm -f downloads/*.md5  ## checksum validation already performed by pyEGA, cleanup downloads folder

#elif $action.action_type == "download_files"
    #import re
    #set file_ids=[x.split('\t')[int(str($action.id_column))-1] for x in open(str($id_table)).readlines()]
    #set outfiles=[x.split('\t')[int(str($action.file_column))-1].replace('\n', '') for x in open(str($id_table)).readlines()]
    mkdir downloads
    #for f, o in zip($file_ids, $outfiles)
      #if not f.startswith("EGAF")
        && >&2 echo "Ignoring \"$f\": no EGA file ID"
        #continue
      #end if
      && 
      echo 'Downloading $f: $o'
      &&
      pyega3 -c \${PYEGA_CONNECTIONS:-30} -cf '$credentials'
        fetch '$f'
          --max-retries 10
          #if $action.range.reference_name

          #if $action.range.end
            --end $action.range.end
          #end if
        #end if
        --output-dir downloads
      #if re.match(".*vcf(_genomic_range_.*|).gz$", o)
        #if $action.range.reference_name or ($action.range.start or $action.range.end)
          && mv 'downloads/$f/'$o[:-3]'_genomic_range_'\$([ -z "$action.range.reference_name" ] && printf "None" || printf "$action.range.reference_name")'_'\$([ -z "$action.range.start" ] && printf "None" || printf "$action.range.reference_name")'_'\$([ -z "$action.range.reference_name" ] && printf "None" || printf "$action.range.end")'.gz' 'downloads/$f/'$o'.vcf_bgzip'
        #else
          && mv 'downloads/$f/$o' 'downloads/$f/'$o'.vcf_bgzip'
        #end if
      #end if
      #if re.match(".*ped$", o)
        && mv 'downloads/$f/$o' 'downloads/$f/'$o'.tabular'
      #end if
    #end for
    && rm -f downloads/**/*.md5  ## checksum validation already performed by pyEGA, clean up downloads folder

#end if
    ]]></command>
    <configfiles>

                </section>
            </when>
            <when value="download_files">
                <param name="id_table" type="data" format="tabular" label="Table with IDs to download" help="A tabular file where one column contains the set of file IDs. This will output a collection. Please select files that are all the same format (e.g. all BAM or all VCF)."/>
                <param name="id_column" type="data_column" data_ref="id_table" label="Column containing the file IDs" help="File Identifiers starting with 'EGAF'. For example: EGAF00001753735" />
                <param name="file_column" type="data_column" data_ref="id_table" label="Column containing the file names" />
                <section name="range" title="Request a specific Genomic range? (will be applied to ALL requested files)" expanded="false">
                    <param argument="--reference-name" type="text" optional="true" label="Reference Sequence Name" help="For example 'chr1', '1', or 'chrX'. If unspecified, all data is returned." />
                    <param argument="--start" type="integer" optional="true" min="0" label="Start Position" help="0-based, inclusive. Only used if a reference sequence name was specified"/>
                    <param argument="--end" type="integer" optional="true" min="0" label="End Position" help="0-based, exclusive. Only used if a reference sequence name was specified"/>
                </section>

        <data name="logfile" format="txt" from_work_dir="pyega3_output.log" label="${tool.name}: log">
            <filter> output_log </filter>
        </data>
        <collection name="downloaded_file_collection" type="list" label="${tool.name} on ${on_string}: Downloaded datasets">
            <filter> action['action_type'] == 'download_files' </filter>
            <discover_datasets pattern="__designation_and_ext__" recurse="true" directory="downloads" />
        </collection>
    </outputs>
    <tests>
        <!-- list datasets with default credentials -->
        <test expect_num_outputs="1">

        <test expect_num_outputs="1"> 
            <param name="action_type" value="download_file"/>
            <param name="file_id" value="EGAF00001775036"/>
            <output name="downloaded_file" md5="3b89b96387db5199fef6ba613f70e27c"/>
        </test>
        <!-- download a single file, with genomic range specified -->
        <test expect_num_outputs="1">
            <param name="action_type" value="download_file"/>
            <param name="file_id" value="EGAF00001753756"/>
            <param name="reference_name" value="1"/>
            <param name="start" value="0"/>

        <!-- download multiple files -->
        <test expect_num_outputs="1">
            <param name="action_type" value="download_files"/>
            <param name="id_table" value="filelist.tabular"/>
            <param name="id_column" value="1"/>
            <param name="file_column" value="5"/>
            <output_collection name="downloaded_file_collection" type="list" count="2">
                <element name="ENCFF000VWO.bam" md5="b8ae14d5d1f717ab17d45e8fc36946a0" />
                <element name="ENCFF284YOU.bam" md5="3b89b96387db5199fef6ba613f70e27c" />
            </output_collection>
            <assert_stderr>

        <!-- download multiple files, in combination with a genomic range -->
        <test expect_num_outputs="1">
            <param name="action_type" value="download_files"/>
            <param name="id_table" value="filelist2.tabular"/>
            <param name="id_column" value="1"/>
            <param name="file_column" value="5"/>
            <param name="reference_name" value="1"/>
            <param name="start" value="0"/>
            <param name="end" value="10000"/>
            <output_collection name="downloaded_file_collection" count="2">
                <element name="NA19239_genomic_range_1_0_10000" md5="bcdcf18846233cbe5cc8afd95168552c" />

        <!-- download multiple vcf.gz files -->
        <test expect_num_outputs="1">
            <param name="action_type" value="download_files"/>
            <param name="id_table" value="filelist3.tabular"/>
            <param name="id_column" value="1"/>
            <param name="file_column" value="5"/>
            <output_collection name="downloaded_file_collection" type="list" count="2">
                <element name="HG00408.novoBreak__256r__4.100100-10100100__7.200100-9000100.vcf.gz" md5="51cfb69bf3b9416ff425381a58c18a2b" />
                <element name="HG01890.HGSVC__145r__1.900100-10001000__18.2001000-90001000.vcf.gz" md5="ebad4425191a89d3e970c02190a87175" />
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
The pyEGA3 download client is a python-based tool for viewing and downloading files from authorized EGA datasets.

4:9564758e8638

<tool id="pyega3" name="EGA Download Client" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.01" >
    <macros>
        <token name="@TOOL_VERSION@">4.0.5</token>
        <token name="@VERSION_SUFFIX@">2</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">pyega3</requirement>
    </requirements>
    <version_command><![CDATA[

    && rm -f downloads/*.md5  ## checksum validation already performed by pyEGA, cleanup downloads folder

#elif $action.action_type == "download_files"
    #import re
    #set file_ids=[x.split('\t')[int(str($action.id_column))-1] for x in open(str($id_table)).readlines()]
    mkdir downloads
    #for f in $file_ids
      #if not f.startswith("EGAF")
        && >&2 echo "Ignoring \"$f\": no EGA file ID"
        #continue
      #end if
      && 
      echo 'Downloading $f'
      &&
      pyega3 -c \${PYEGA_CONNECTIONS:-30} -cf '$credentials'
        fetch '$f'
          --max-retries 10
          #if $action.range.reference_name

          #if $action.range.end
            --end $action.range.end
          #end if
        #end if
        --output-dir downloads
    #end for
    && for vcf in \$(ls downloads/**/*vcf.gz); do mv "\${vcf}" "\${vcf:0:-6}vcf_bgzip"; done  ## renaming vcf.gz files to vcf_bgzip to recognize format
    && rm -f downloads/**/*.md5  ## checksum validation already performed by pyEGA, clean up downloads folder

#end if
    ]]></command>
    <configfiles>

                </section>
            </when>
            <when value="download_files">
                <param name="id_table" type="data" format="tabular" label="Table with IDs to download" help="A tabular file where one column contains the set of file IDs. This will output a collection. Please select files that are all the same format (e.g. all BAM or all VCF)."/>
                <param name="id_column" type="data_column" data_ref="id_table" label="Column containing the file IDs" help="File Identifiers starting with 'EGAF'. For example: EGAF00001753735" />
                <section name="range" title="Request a specific Genomic range? (will be applied to ALL requested files)" expanded="false">
                    <param argument="--reference-name" type="text" optional="true" label="Reference Sequence Name" help="For example 'chr1', '1', or 'chrX'. If unspecified, all data is returned." />
                    <param argument="--start" type="integer" optional="true" min="0" label="Start Position" help="0-based, inclusive. Only used if a reference sequence name was specified"/>
                    <param argument="--end" type="integer" optional="true" min="0" label="End Position" help="0-based, exclusive. Only used if a reference sequence name was specified"/>
                </section>

        <data name="logfile" format="txt" from_work_dir="pyega3_output.log" label="${tool.name}: log">
            <filter> output_log </filter>
        </data>
        <collection name="downloaded_file_collection" type="list" label="${tool.name} on ${on_string}: Downloaded datasets">
            <filter> action['action_type'] == 'download_files' </filter>
            <discover_datasets pattern="__name_and_ext__" recurse="true" directory="downloads" />
        </collection>
    </outputs>
    <tests>
        <!-- list datasets with default credentials -->
        <test expect_num_outputs="1">

        <test expect_num_outputs="1"> 
            <param name="action_type" value="download_file"/>
            <param name="file_id" value="EGAF00001775036"/>
            <output name="downloaded_file" md5="3b89b96387db5199fef6ba613f70e27c"/>
        </test>
        <!-- download a single vcf.gz -->
        <test expect_num_outputs="1"> 
            <param name="action_type" value="download_file"/>
            <param name="file_id" value="EGAF00007243775"/>
            <output name="downloaded_file" md5="51cfb69bf3b9416ff425381a58c18a2b" ftype="vcf_bgzip" />
        </test>
        <!-- download a single bam, with genomic range specified -->
        <test expect_num_outputs="1">
            <param name="action_type" value="download_file"/>
            <param name="file_id" value="EGAF00001753756"/>
            <param name="reference_name" value="1"/>
            <param name="start" value="0"/>

        <!-- download multiple files -->
        <test expect_num_outputs="1">
            <param name="action_type" value="download_files"/>
            <param name="id_table" value="filelist.tabular"/>
            <param name="id_column" value="1"/>
            <output_collection name="downloaded_file_collection" type="list" count="2">
                <element name="ENCFF000VWO.bam" md5="b8ae14d5d1f717ab17d45e8fc36946a0" />
                <element name="ENCFF284YOU.bam" md5="3b89b96387db5199fef6ba613f70e27c" />
            </output_collection>
            <assert_stderr>

        <!-- download multiple files, in combination with a genomic range -->
        <test expect_num_outputs="1">
            <param name="action_type" value="download_files"/>
            <param name="id_table" value="filelist2.tabular"/>
            <param name="id_column" value="1"/>
            <param name="reference_name" value="1"/>
            <param name="start" value="0"/>
            <param name="end" value="10000"/>
            <output_collection name="downloaded_file_collection" count="2">
                <element name="NA19239_genomic_range_1_0_10000" md5="bcdcf18846233cbe5cc8afd95168552c" />

        <!-- download multiple vcf.gz files -->
        <test expect_num_outputs="1">
            <param name="action_type" value="download_files"/>
            <param name="id_table" value="filelist3.tabular"/>
            <param name="id_column" value="1"/>
            <output_collection name="downloaded_file_collection" type="list" count="2">
                <element name="HG00408.novoBreak__256r__4.100100-10100100__7.200100-9000100" md5="51cfb69bf3b9416ff425381a58c18a2b" ftype="vcf_bgzip" />
                <element name="HG01890.HGSVC__145r__1.900100-10001000__18.2001000-90001000" md5="ebad4425191a89d3e970c02190a87175" ftype="vcf_bgzip" />
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
The pyEGA3 download client is a python-based tool for viewing and downloading files from authorized EGA datasets.