Mercurial > repos > iuc > ncbi_datasets

changeset 26:6ba50cbabbb7 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/ncbi_datasets commit 2476209f9710981986d6f959bd21a2d2f78e6a7f
author iuc
date Wed, 18 Mar 2026 11:26:37 +0000
parents bc18e25d4204
children
files datasets_gene.xml datasets_genome.xml macros.xml
diffstat 3 files changed, 120 insertions(+), 6 deletions(-) [+]
line wrap: on
line diff
--- a/datasets_gene.xml	Wed Jan 14 15:05:01 2026 +0000
+++ b/datasets_gene.xml	Wed Mar 18 11:26:37 2026 +0000
@@ -1,4 +1,4 @@
-<tool id="datasets_download_gene" name="NCBI Datasets Gene" profile="@PROFILE@" license="@LICENSE@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
+<tool id="datasets_download_gene" name="NCBI Datasets Gene" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@" license="@LICENSE@" >
     <description>download gene sequences and metadata</description>
     <macros>
         <import>macros.xml</import>
@@ -63,6 +63,7 @@
     $file_choices.kingdom_cond.kingdom_sel
     --package ncbi_dataset.zip
     --fields #echo ",".join($file_choices.kingdom_cond.report_columns)
+    --force
     > gene_data_report.tsv
 ## if ! dataformat tsv gene --package ncbi_dataset.zip > gene_data_report.tsv 2> dataformat.log; then
 ##     dataformat tsv prok-gene --package ncbi_dataset.zip > gene_data_report.tsv 2>> dataformat.log;
@@ -463,6 +464,118 @@
                 <has_text text="include-flanks-bp 100"/>
             </assert_command>
         </test>
+
+        <!-- 10: datasets download gene accession NP_000483.3 NP_001035835.1 include protein,rna -->
+        <test expect_num_outputs="3">
+            <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="NP_000483.3 NP_001035835.1"/>
+                </conditional>
+            </conditional>
+            <section name="file_choices">
+                <conditional name="kingdom_cond">
+                    <param name="kingdom_sel" value="gene"/>
+                    <param name="include" value="protein,rna"/>
+                </conditional>
+            </section>
+            <output name="gene_data_report">
+                <assert_contents>
+                    <has_text text="human"/>
+                    <has_n_lines n="3"/>
+                    <has_n_columns n="8"/>
+                </assert_contents>
+            </output>
+            <output name="rna_fasta">
+                <assert_contents>
+                    <has_text text="&gt;"/>
+                </assert_contents>
+            </output>
+            <output name="protein_fasta">
+                <assert_contents>
+                    <has_text text="&gt;"/>
+                </assert_contents>
+            </output>
+            <assert_command>
+                <has_text text="'NP_000483.3' 'NP_001035835.1'"/>
+            </assert_command>
+        </test>
+
+        <!-- 11: multiple human gene symbols -->
+        <test expect_num_outputs="3">
+            <conditional name="query|subcommand">
+                <param name="download_by" value="symbol"/>
+                <conditional name="text_or_file">
+                    <param name="text_or_file" value="text"/>
+                    <param name="accession" value="brca1,tp53"/>
+                </conditional>
+                <param name="taxon" value="human"/>
+            </conditional>
+            <section name="file_choices">
+                <conditional name="kingdom_cond">
+                    <param name="kingdom_sel" value="gene"/>
+                    <param name="include" value="protein,rna"/>
+                </conditional>
+            </section>
+            <output name="gene_data_report">
+                <assert_contents>
+                    <has_text text="human"/>
+                    <has_text text="BRCA1"/>
+                    <has_text text="TP53"/>
+                    <has_n_lines n="3"/>
+                    <has_n_columns n="8"/>
+                </assert_contents>
+            </output>
+            <output name="rna_fasta">
+                <assert_contents>
+                    <has_text text="&gt;"/>
+                </assert_contents>
+            </output>
+            <output name="protein_fasta">
+                <assert_contents>
+                    <has_text text="&gt;"/>
+                </assert_contents>
+            </output>
+        </test>
+
+        <!-- 12: fly (non-human) NP_ protein accessions -->
+        <test expect_num_outputs="3">
+            <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="NP_524625.1 NP_524660.1"/>
+                </conditional>
+            </conditional>
+            <section name="file_choices">
+                <conditional name="kingdom_cond">
+                    <param name="kingdom_sel" value="gene"/>
+                    <param name="include" value="protein,rna"/>
+                </conditional>
+            </section>
+            <output name="gene_data_report">
+                <assert_contents>
+                    <has_text text="fruit fly"/>
+                    <has_n_lines n="3"/>
+                    <has_n_columns n="8"/>
+                </assert_contents>
+            </output>
+            <output name="rna_fasta">
+                <assert_contents>
+                    <has_text text="&gt;"/>
+                </assert_contents>
+            </output>
+            <output name="protein_fasta">
+                <assert_contents>
+                    <has_text text="&gt;"/>
+                </assert_contents>
+            </output>
+            <assert_command>
+                <has_text text="'NP_524625.1' 'NP_524660.1'"/>
+            </assert_command>
+        </test>
+
         <!-- 10: datasets download gene taxon human   -->
         <!-- <test expect_num_outputs="1">
             <conditional name="query|subcommand">
--- a/datasets_genome.xml	Wed Jan 14 15:05:01 2026 +0000
+++ b/datasets_genome.xml	Wed Mar 18 11:26:37 2026 +0000
@@ -1,4 +1,4 @@
-<tool id="datasets_download_genome" name="NCBI Datasets Genomes" profile="@PROFILE@" license="@LICENSE@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
+<tool id="datasets_download_genome" name="NCBI Datasets Genomes" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@" license="@LICENSE@">
     <description>download genome sequence, annotation and metadata</description>
     <macros>
         <import>macros.xml</import>
@@ -55,6 +55,7 @@
 && dataformat tsv genome 
     --package ncbi_dataset.zip
     --fields #echo ",".join($file_choices.report_columns) 
+    --force
     > genome_data_report.tsv
 
 ## unzip and rehydrate if any data is to be downloaded (include is not None)
@@ -271,7 +272,7 @@
                 <param name="decompress" value="true"/>
             </section>
             <assert_stderr>
-                <has_text text="no genome assemblies were found"/>
+                <has_text text="Error: There are no genome assemblies that match your query."/>
             </assert_stderr>
             <!-- In the current state of the NCBI tool/DB, no output to check.
              But the returned results seem to change from time to time and it might
--- a/macros.xml	Wed Jan 14 15:05:01 2026 +0000
+++ b/macros.xml	Wed Mar 18 11:26:37 2026 +0000
@@ -1,7 +1,7 @@
 <macros>
-    <token name="@TOOL_VERSION@">18.14.0</token>
+    <token name="@TOOL_VERSION@">18.21.0</token>
     <token name="@VERSION_SUFFIX@">0</token>
-    <token name="@PROFILE@">23.0</token>
+    <token name="@PROFILE@">25.0</token>
     <token name="@LICENSE@">MIT</token>
     <token name="@PROFILE_AND_LICENSE@">profile="@PROFILE@" license="@LICENSE@"</token>
     <token name="@SETUP_CERTIFICATES@"><![CDATA[
@@ -11,7 +11,7 @@
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@">ncbi-datasets-cli</requirement>
-            <requirement type="package" version="2026.1.4">ca-certificates</requirement>
+            <requirement type="package" version="2026.2.25">ca-certificates</requirement>
              <!-- Removed line below because it was causing "skipping: [..] need PK compat. v4.5 (can do v2.1)"  -->
              <!-- <requirement type="package" version="6.0">unzip</requirement> -->
         </requirements>