# HG changeset patch
# User iuc
# Date 1753126096 0
# Node ID 0f3b3813b6aef17440d0252b681c9a1096417125
# Parent 7b925f7c50b2d8232de647b3380c71caed41f364
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_datasets commit c1c3f90e4aa7dc258aa61d98ec4eac0b97eef426
diff -r 7b925f7c50b2 -r 0f3b3813b6ae datasets_gene.xml
--- a/datasets_gene.xml Mon Mar 17 11:05:45 2025 +0000
+++ b/datasets_gene.xml Mon Jul 21 19:28:16 2025 +0000
@@ -4,7 +4,7 @@
<import>macros.xml</import>
</macros>
<expand macro="bio_tools"/>
- <expand macro="requirements"></expand>
+ <expand macro="requirements"/>
<expand macro="version_command"/>
<command><![CDATA[
#import re
@@ -41,7 +41,7 @@
#if $filters.fasta_filter_cond.fasta_filter_select
#if $filters.fasta_filter_cond.fasta_filter_select == 'text'
- --fasta-filter #echo ",".join(f"'{x}'" for x in $filters.fasta_filter_cond.fasta_filter.split(',') if x)
+ --fasta-filter #echo ",".join(f"'{x}'" for x in str($filters.fasta_filter_cond.fasta_filter).split(',') if x)
#else
--fasta-filter-file '$filters.fasta_filter_cond.fasta_filter_file'
#end if
@@ -97,8 +97,8 @@
<param argument="--taxon" type="text" value="human" label="Species for gene symbol" help="NCBI taxid, common or scientific name">
<sanitizer invalid_char="">
<valid initial="string.letters">
- <add value=" " />
- <add value="-" />
+ <add value=" "/>
+ <add value="-"/>
</valid>
</sanitizer>
</param>
@@ -109,8 +109,8 @@
<param argument="--taxon-filter" type="text" value="" label="Limit gene sequences and annotation report file to specified taxon" help="any rank, only available for WP accessions">
<sanitizer invalid_char="">
<valid initial="string.letters">
- <add value=" " />
- <add value="-" />
+ <add value=" "/>
+ <add value="-"/>
</valid>
</sanitizer>
</param>
@@ -133,7 +133,7 @@
<param argument="--fasta-filter" type="text" label="RefSeq nucleotide and protein accessions" help="Comma separated">
<sanitizer invalid_char="">
<valid initial="string.letters,string.digits">
- <add value="," />
+ <add value=","/>
</valid>
</sanitizer>
</param>
@@ -235,12 +235,12 @@
</output>
<output name="rna_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
<output name="protein_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
</test>
@@ -263,12 +263,12 @@
</output>
<output name="rna_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
<output name="protein_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
</test>
@@ -284,6 +284,7 @@
</conditional>
<section name="file_choices">
<conditional name="kingdom_cond">
+ <param name="kingdom_sel" value="gene"/>
<param name="include" value="gene,cds"/>
</conditional>
</section>
@@ -297,17 +298,17 @@
</output>
<output name="gene_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
<output name="cds_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
</test>
<!-- 4: datasets download gene symbol tp53 -->
- <test expect_num_outputs="1">
+ <test expect_num_outputs="3">
<conditional name="query|subcommand">
<param name="download_by" value="symbol"/>
<conditional name="text_or_file">
@@ -315,11 +316,6 @@
<param name="accession" value="tp53"/>
</conditional>
</conditional>
- <section name="file_choices">
- <conditional name="kingdom_cond">
- <param name="include" value=""/>
- </conditional>
- </section>
<output name="gene_data_report">
<assert_contents>
<has_text text="human"/>
@@ -361,17 +357,17 @@
</output>
<output name="threep_utr_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
<output name="fivep_utr_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
</test>
<!-- 6: datasets download gene symbol brca1 \-\-ortholog -->
- <test expect_num_outputs="1">
+ <test expect_num_outputs="3">
<conditional name="query|subcommand">
<param name="download_by" value="symbol"/>
<conditional name="text_or_file">
@@ -380,11 +376,6 @@
</conditional>
<param name="ortholog" value="rodentia"/>
</conditional>
- <section name="file_choices">
- <conditional name="kingdom_cond">
- <param name="include" value=""/>
- </conditional>
- </section>
<output name="gene_data_report">
<assert_contents>
<has_text text="rat"/>
@@ -395,7 +386,7 @@
</output>
</test>
<!-- 7: datasets download gene accession NP_000483.3 -->
- <test expect_num_outputs="1">
+ <test expect_num_outputs="3">
<conditional name="query|subcommand">
<param name="download_by" value="accession"/>
<conditional name="text_or_file">
@@ -403,11 +394,6 @@
<param name="accession" value="NP_000483.3"/>
</conditional>
</conditional>
- <section name="file_choices">
- <conditional name="kingdom_cond">
- <param name="include" value=""/>
- </conditional>
- </section>
<output name="gene_data_report">
<assert_contents>
<has_text text="human"/>
@@ -417,7 +403,7 @@
</output>
</test>
<!-- 8: datasets download gene accession NM_000546.6 NM_000492.4 + ortholog-->
- <test expect_num_outputs="1">
+ <test expect_num_outputs="3">
<conditional name="query|subcommand">
<param name="download_by" value="accession"/>
<conditional name="text_or_file">
@@ -426,11 +412,6 @@
</conditional>
<param name="ortholog" value="all"/>
</conditional>
- <section name="file_choices">
- <conditional name="kingdom_cond">
- <param name="include" value=""/>
- </conditional>
- </section>
<output name="gene_data_report">
<assert_contents>
<has_text text="human"/>
@@ -439,7 +420,6 @@
</assert_contents>
</output>
</test>
-
<!-- 9: datasets download gene accession WP_003249567.1 + include_flanks_bp -->
<test expect_num_outputs="4">
<conditional name="query|subcommand">
@@ -466,24 +446,23 @@
</output>
<output name="gene_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
<output name="gene_flanks">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
<output name="protein_fasta">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</output>
<assert_command>
<has_text text="include-flanks-bp 100"/>
</assert_command>
- </test>
-
+ </test>
<!-- 10: datasets download gene taxon human -->
<!-- <test expect_num_outputs="1">
<conditional name="query|subcommand">
diff -r 7b925f7c50b2 -r 0f3b3813b6ae datasets_genome.xml
--- a/datasets_genome.xml Mon Mar 17 11:05:45 2025 +0000
+++ b/datasets_genome.xml Mon Jul 21 19:28:16 2025 +0000
@@ -4,9 +4,14 @@
<import>macros.xml</import>
</macros>
<expand macro="bio_tools"/>
- <expand macro="requirements"></expand>
+ <expand macro="requirements"/>
<expand macro="version_command"/>
- <command><![CDATA[
+ <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 $query.subcommand.download_by
@@ -116,7 +121,6 @@
</param>
<expand macro="released_options"/>
<expand macro="released_options" before_or_after="after"/>
-
<repeat name="search" title="Add search terms">
<param argument="--search" type="text" label="Only include genomes that have the specified text in the searchable fields" help="Searchable fields are species and infraspecies, assembly name and submitter"/>
</repeat>
@@ -137,35 +141,35 @@
<outputs>
<data name="genome_data_report" format="tabular" label="NCBI Genome Datasets: Data Report" from_work_dir="genome_data_report.tsv"/>
<collection name="sequence_report" label="NCBI Genome Datasets: Sequence Data Report" type="list">
- <discover_datasets pattern="(?P<identifier_0>.*?)\/sequence_report.tsv" ext="tabular" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
+ <discover_datasets pattern="(?P<identifier_0>.*?)\/sequence_report.tsv" ext="tabular" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
<filter>file_choices['include'] and "seq-report" in file_choices['include']</filter>
</collection>
<collection name="genome_fasta" label="NCBI Genome Datasets: genome fasta" type="list:list">
- <discover_datasets pattern="(?P<identifier_0>.*?)/(?!rna|cds_from)(?P<identifier_1>.*?)(_genomic)?\.(?P<ext>fasta(\.gz)?)" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
+ <discover_datasets pattern="(?P<identifier_0>.*?)/(?!rna|cds_from)(?P<identifier_1>.*?)(_genomic)?\.(?P<ext>fasta(\.gz)?)" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
<filter>file_choices['include'] and "genome" in file_choices['include']</filter>
</collection>
<collection name="rna_fasta" label="NCBI Genome Datasets: RNA fasta" type="list">
- <discover_datasets pattern="(?P<identifier_0>.*?)\/rna\.(?P<ext>fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
+ <discover_datasets pattern="(?P<identifier_0>.*?)\/rna\.(?P<ext>fasta(\.gz)?)$" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
<filter>file_choices['include'] and "rna" in file_choices['include']</filter>
</collection>
<collection name="protein_fasta" label="NCBI Genome Datasets: protein fasta" type="list">
- <discover_datasets pattern="(?P<identifier_0>.*?)\/protein\.(?P<ext>fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
+ <discover_datasets pattern="(?P<identifier_0>.*?)\/protein\.(?P<ext>fasta(\.gz)?)$" directory="ncbi_dataset/data/" recurse="true" match_relative_path="true"/>
<filter>file_choices['include'] and "protein" in file_choices['include']</filter>
</collection>
<collection name="genomic_cds" label="NCBI Genome Datasets: genomic cds fasta" type="list">
- <discover_datasets pattern="(?P<identifier_0>.*?)\/cds_from_genomic\.(?P<ext>fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
+ <discover_datasets pattern="(?P<identifier_0>.*?)\/cds_from_genomic\.(?P<ext>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<identifier_0>.*?)\/genomic\.gff" ext="gff3" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
+ <discover_datasets pattern="(?P<identifier_0>.*?)\/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<identifier_0>.*?)\/genomic\.gtf" ext="gtf" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
+ <discover_datasets pattern="(?P<identifier_0>.*?)\/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<identifier_0>.*?)\/genomic\.gbff" ext="txt" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/>
+ <discover_datasets pattern="(?P<identifier_0>.*?)\/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>
@@ -175,8 +179,10 @@
<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="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 -->
@@ -184,19 +190,19 @@
</section>
<output name="genome_data_report">
<assert_contents>
- <has_text text="Assembly Accession	Assembly Name	Assembly Submitter	Organism Name"/>
+ <has_text text="Assembly Accession	Assembly Name	Assembly Submitter	Organism Name"/>
<has_n_lines n="142"/>
<has_n_columns n="4"/>
</assert_contents>
</output>
- <output_collection name="rna_fasta" type="list" count="1">
+ <output_collection name="rna_fasta" type="list" count="2">
<element name="GCF_000306695.2" decompress="true">
<assert_contents>
- <has_text text=">"/>
+ <has_text text=">"/>
</assert_contents>
</element>
</output_collection>
- <output_collection name="genomic_gff" type="list">
+ <output_collection name="genomic_gff" type="list" count="12">
<element name="GCF_000306695.2">
<assert_contents>
<has_n_lines min="1000000"/>
@@ -214,26 +220,27 @@
<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="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="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=">"/>
+ <output_collection name="genome_fasta" type="list:list" count="11">
+ <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_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"/>
@@ -253,10 +260,12 @@
<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="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"/>
@@ -288,7 +297,9 @@
<param name="accession" value="GCF_000013305.1 GCF_000007445.1"/>
</conditional>
</conditional>
- <param name="released_before" value="01/01/2007"/>
+ <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"/>
@@ -300,7 +311,7 @@
<has_n_columns n="4"/>
</assert_contents>
</output>
- <output_collection name="sequence_report" type="list" count="2" >
+ <output_collection name="sequence_report" type="list" count="2">
<element name="GCF_000007445.1">
<assert_contents>
<has_text text="GCF_000007445.1"/>
@@ -316,7 +327,7 @@
</assert_contents>
</element>
</output_collection>
- <output_collection name="genomic_gtf" type="list">
+ <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>
@@ -333,7 +344,9 @@
<param name="inputfile" value="accessions.txt"/>
</conditional>
</conditional>
- <param name="released_before" value="01/01/2007"/>
+ <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"/>
@@ -355,7 +368,6 @@
<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">
@@ -365,8 +377,10 @@
<param name="accession" value="GCF_000001405"/>
</conditional>
</conditional>
- <param name="released_before" value="01/01/2015"/>
- <param name="assembly_version" value="all"/>
+ <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>
@@ -395,19 +409,19 @@
<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"/>
+ <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=">"/>
+ <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=">"/>
+ <has_text text=">"/>
</assert_contents>
</element>
</output_collection>
@@ -437,7 +451,7 @@
<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"/>
+ <has_size value="1847862" delta="2000"/>
</assert_contents>
</element>
</output_collection>
@@ -463,22 +477,21 @@
</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"/>
+ <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">
+ <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>
- <param name="include" value=""/>
<output name="genome_data_report">
<assert_contents>
- <has_text text="Saccharomyces cerevisiae ZTW1" negate="true"/>
+ <has_text text="Saccharomyces cerevisiae ZTW1" negate="true"/>
</assert_contents>
</output>
</test>
diff -r 7b925f7c50b2 -r 0f3b3813b6ae macros.xml
--- a/macros.xml Mon Mar 17 11:05:45 2025 +0000
+++ b/macros.xml Mon Jul 21 19:28:16 2025 +0000
@@ -1,5 +1,5 @@
<macros>
- <token name="@TOOL_VERSION@">17.1.0</token>
+ <token name="@TOOL_VERSION@">18.4.1</token>
<token name="@VERSION_SUFFIX@">0</token>
<token name="@PROFILE@">23.0</token>
<token name="@LICENSE@">MIT</token>
@@ -12,7 +12,8 @@
<requirements>
<requirement type="package" version="@TOOL_VERSION@">ncbi-datasets-cli</requirement>
<requirement type="package" version="2025.1.31">ca-certificates</requirement>
- <requirement type="package" version="6.0">unzip</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>
</xml>
<xml name="bio_tools">
diff -r 7b925f7c50b2 -r 0f3b3813b6ae test-data/GCF_000007445.1.genomic.gtf
--- a/test-data/GCF_000007445.1.genomic.gtf Mon Mar 17 11:05:45 2025 +0000
+++ b/test-data/GCF_000007445.1.genomic.gtf Mon Jul 21 19:28:16 2025 +0000
@@ -1,6 +1,5 @@
-#!annotation-source NCBI RefSeq
NC_004431.1 RefSeq gene 190 255 . + . gene_id "C_RS00005"; transcript_id ""; gbkey "Gene"; gene "thrL"; gene_biotype "protein_coding"; locus_tag "C_RS00005"; old_locus_tag "c5491";
-NC_004431.1 Protein Homology CDS 190 252 . + 0 gene_id "C_RS00005"; transcript_id "unassigned_transcript_1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "C_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11";
-NC_004431.1 Protein Homology start_codon 190 192 . + 0 gene_id "C_RS00005"; transcript_id "unassigned_transcript_1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "C_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11";
-NC_004431.1 Protein Homology stop_codon 253 255 . + 0 gene_id "C_RS00005"; transcript_id "unassigned_transcript_1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "C_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11";
+NC_004431.1 Protein Homology CDS 190 252 . + 0 gene_id "C_RS00005"; transcript_id "unassigned_transcript_1"; db_xref "GenBank:WP_001386572.1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "C_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11"; exon_number "1";
+NC_004431.1 Protein Homology start_codon 190 192 . + 0 gene_id "C_RS00005"; transcript_id "unassigned_transcript_1"; db_xref "GenBank:WP_001386572.1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "C_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11"; exon_number "1";
+NC_004431.1 Protein Homology stop_codon 253 255 . + 0 gene_id "C_RS00005"; transcript_id "unassigned_transcript_1"; db_xref "GenBank:WP_001386572.1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "C_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11"; exon_number "1";
NC_004431.1 RefSeq gene 453 911 . + . gene_id "C_RS00010"; transcript_id ""; gbkey "Gene"; gene "tnpA"; gene_biotype "protein_coding"; locus_tag "C_RS00010"; old_locus_tag "c0002";
diff -r 7b925f7c50b2 -r 0f3b3813b6ae test-data/genome.2.GCF_000013305.1.genomic.gtf
--- a/test-data/genome.2.GCF_000013305.1.genomic.gtf Mon Mar 17 11:05:45 2025 +0000
+++ b/test-data/genome.2.GCF_000013305.1.genomic.gtf Mon Jul 21 19:28:16 2025 +0000
@@ -1,6 +1,5 @@
-#!annotation-source NCBI RefSeq
NC_008253.1 RefSeq gene 190 255 . + . gene_id "ECP_RS00005"; transcript_id ""; gbkey "Gene"; gene "thrL"; gene_biotype "protein_coding"; locus_tag "ECP_RS00005"; old_locus_tag "ECP_0001";
-NC_008253.1 Protein Homology CDS 190 252 . + 0 gene_id "ECP_RS00005"; transcript_id "unassigned_transcript_1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "ECP_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11";
-NC_008253.1 Protein Homology start_codon 190 192 . + 0 gene_id "ECP_RS00005"; transcript_id "unassigned_transcript_1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "ECP_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11";
-NC_008253.1 Protein Homology stop_codon 253 255 . + 0 gene_id "ECP_RS00005"; transcript_id "unassigned_transcript_1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "ECP_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11";
+NC_008253.1 Protein Homology CDS 190 252 . + 0 gene_id "ECP_RS00005"; transcript_id "unassigned_transcript_1"; db_xref "GenBank:WP_001386572.1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "ECP_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11"; exon_number "1";
+NC_008253.1 Protein Homology start_codon 190 192 . + 0 gene_id "ECP_RS00005"; transcript_id "unassigned_transcript_1"; db_xref "GenBank:WP_001386572.1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "ECP_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11"; exon_number "1";
+NC_008253.1 Protein Homology stop_codon 253 255 . + 0 gene_id "ECP_RS00005"; transcript_id "unassigned_transcript_1"; db_xref "GenBank:WP_001386572.1"; gbkey "CDS"; gene "thrL"; inference "COORDINATES: similar to AA sequence:RefSeq:NP_414542.1"; locus_tag "ECP_RS00005"; product "thr operon leader peptide"; protein_id "WP_001386572.1"; transl_table "11"; exon_number "1";
NC_008253.1 RefSeq gene 336 2798 . + . gene_id "ECP_RS00010"; transcript_id ""; gbkey "Gene"; gene "thrA"; gene_biotype "protein_coding"; locus_tag "ECP_RS00010"; old_locus_tag "ECP_0002";