diff pyega3.xml @ 4:9564758e8638 draft

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

--- a/pyega3.xml	Thu Oct 27 15:12:30 2022 +0000
+++ b/pyega3.xml	Wed Dec 07 15:26:17 2022 +0000
@@ -1,7 +1,7 @@
 <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>
+        <token name="@VERSION_SUFFIX@">2</token>
     </macros>
     <requirements>
         <requirement type="package" version="@TOOL_VERSION@">pyega3</requirement>
@@ -49,15 +49,14 @@
 #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)
+    #for f in $file_ids
       #if not f.startswith("EGAF")
         && >&2 echo "Ignoring \"$f\": no EGA file ID"
         #continue
       #end if
       && 
-      echo 'Downloading $f: $o'
+      echo 'Downloading $f'
       &&
       pyega3 -c \${PYEGA_CONNECTIONS:-30} -cf '$credentials'
         fetch '$f'
@@ -72,17 +71,8 @@
           #end if
         #end if
         --output-dir downloads
-      #if re.match(".*vcf(_genomic_range_.*|).gz$", 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
+    && 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
@@ -128,7 +118,6 @@
             <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"/>
@@ -153,7 +142,7 @@
         </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" />
+            <discover_datasets pattern="__name_and_ext__" recurse="true" directory="downloads" />
         </collection>
     </outputs>
     <tests>
@@ -187,7 +176,13 @@
             <param name="file_id" value="EGAF00001775036"/>
             <output name="downloaded_file" md5="3b89b96387db5199fef6ba613f70e27c"/>
         </test>
-        <!-- download a single file, with genomic range specified -->
+        <!-- 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"/>
@@ -201,7 +196,6 @@
             <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" />
@@ -215,7 +209,6 @@
             <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"/>
@@ -232,10 +225,9 @@
             <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" />
+                <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>