Merge pull request #69 from pirovc/dev

genome_updater v0.5.1

.travis.yml

@@ -4,6 +4,7 @@ dist: focal
 before_install:
   - gem install bashcov codecov
   - sudo apt-get install parallel
+  - echo -e "require 'codecov'\nrequire 'simplecov'\nSimpleCov.formatter = Codecov::SimpleCov::Formatter" > .simplecov
 
 script:
   - bashcov tests/libs/bats/bin/bats tests/integration_offline.bats

README.md

@@ -179,7 +179,7 @@ or
 		2) representative genome
 		3) na
 	B) Assembly level:
-		1) Complete genome
+		1) Complete Genome
 		2) Chromosome
 		3) Scaffold
 		4) Contig
@@ -200,7 +200,7 @@ or
 	┌─┐┌─┐┌┐┌┌─┐┌┬┐┌─┐    ┬ ┬┌─┐┌┬┐┌─┐┌┬┐┌─┐┬─┐
 	│ ┬├┤ ││││ ││││├┤     │ │├─┘ ││├─┤ │ ├┤ ├┬┘
 	└─┘└─┘┘└┘└─┘┴ ┴└─┘────└─┘┴  ─┴┘┴ ┴ ┴ └─┘┴└─
-	                                     v0.5.0 
+	                                     v0.5.1 
 
 	Database options:
 	 -d Database (comma-separated entries)

genome_updater.sh

@@ -25,7 +25,7 @@ IFS=$' '
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 # THE SOFTWARE.
 
-version="0.5.0"
+version="0.5.1"
 
 # Define base_url or use local files (for testing)
 local_dir=${local_dir:-}
@@ -114,7 +114,7 @@ check_assembly_summary() # parameter: ${1} assembly_summary file - return 0 true
     if [ ! -z $(tail -c -1 "${1}") ]; then return 1; fi
 
     # if contains header char parts of the header anywhere starting lines
-    grep -m 1 "^#" "${1}" #> /dev/null
+    grep -m 1 "^#" "${1}" > /dev/null 2>&1
     if [ $? -eq 0 ]; then return 1; fi
 
     # if contains parts of the header anywhere
@@ -474,7 +474,7 @@ filter_top_assemblies() # parameter: ${1} assembly_summary file, ${2} modified a
             col5["reference genome"]=1;
             col5["representative genome"]=2;
             col5["na"]=3;
-            col12["Complete genome"]=1;
+            col12["Complete Genome"]=1;
             col12["Chromosome"]=2;
             col12["Scaffold"]=3;
             col12["Contig"]=4;
@@ -1048,7 +1048,7 @@ elif [[ "${tax_mode}" == "gtdb" ]]; then
 fi
 
 # top assemblies by rank
-if [[ ! "${top_assemblies}" =~ ^[0-9]+$ && ! "${top_assemblies}" =~ ^(superkingdom|phylum|class|order|family|genus|species)\:[1-9]+$ ]]; then
+if [[ ! "${top_assemblies}" =~ ^[0-9]+$ && ! "${top_assemblies}" =~ ^(superkingdom|phylum|class|order|family|genus|species)\:[1-9][0-9]*$ ]]; then
     echo "${top_assemblies}: invalid top assemblies - should be a number > 0 or [superkingdom|phylum|class|order|family|genus|species]:number"; exit 1;
 else
     top_assemblies_rank=""

tests/integration_offline.bats

@@ -265,7 +265,7 @@ setup_file() {
 @test "Top 1 superkingdom ncbi" {
     outdir=${outprefix}top-superkingdom-ncbi/
     label="test"
-    # Keep only top 1 for selected species
+    # Keep only top 1 for superkingdom
     run ./genome_updater.sh -d refseq -g archaea,fungi -A superkingdom:1 -b ${label} -o ${outdir}
     sanity_check ${outdir} ${label}
 
@@ -303,6 +303,72 @@ setup_file() {
     assert [ $(count_files ${outdir} ${label_phylum}) -gt 0 ]
 }
 
+@test "Top assemblies order" {
+
+    outdir=${outprefix}top-assemblies-order-refseq-category/
+
+    # Selection order
+    # col5["reference genome"]=1;
+    # col5["representative genome"]=2;
+    # col5["na"]=3;
+    # should always pick the correct refseq category for top superkingdom (just one)
+
+    label="3"
+    rscat="reference genome,representative genome,na"
+    run ./genome_updater.sh -d refseq -g archaea -c "${rscat}" -A superkingdom:1 -b ${label} -o ${outdir}    
+    sanity_check ${outdir} ${label}
+    # --- no reference genome in example files ---
+    assert_equal "representative genome" "$(get_values_as ${outdir}assembly_summary.txt 5)"
+
+    label="2"
+    rscat="representative genome,na"
+    run ./genome_updater.sh -d refseq -g archaea -c "${rscat}" -A superkingdom:1 -b ${label} -o ${outdir}    
+    sanity_check ${outdir} ${label}
+    assert_equal "representative genome" "$(get_values_as ${outdir}assembly_summary.txt 5)"
+
+    label="1"
+    rscat="na"
+    run ./genome_updater.sh -d refseq -g archaea -c "${rscat}" -A superkingdom:1 -b ${label} -o ${outdir}    
+    sanity_check ${outdir} ${label}
+    assert_equal "na" "$(get_values_as ${outdir}assembly_summary.txt 5)"
+
+
+    outdir=${outprefix}top-assemblies-order-assembly-level/
+
+    # Selection order
+    # col12["Complete Genome"]=1;
+    # col12["Chromosome"]=2;
+    # col12["Scaffold"]=3;
+    # col12["Contig"]=4;
+
+    # should always pick the correct assembly level for top superkingdom (just one)
+
+    label="4"
+    aslvl="complete genome,chromosome,scaffold,contig"
+    run ./genome_updater.sh -d refseq -g archaea -l "${aslvl}" -A superkingdom:1 -b ${label} -o ${outdir}    
+    sanity_check ${outdir} ${label}
+    assert_equal "Complete Genome" "$(get_values_as ${outdir}assembly_summary.txt 12)"
+
+    label="3"
+    aslvl="chromosome,scaffold,contig"
+    run ./genome_updater.sh -d refseq -g archaea -l "${aslvl}" -A superkingdom:1 -b ${label} -o ${outdir}    
+    sanity_check ${outdir} ${label}
+    assert_equal "Chromosome" "$(get_values_as ${outdir}assembly_summary.txt 12)"
+
+    label="2"
+    aslvl="scaffold,contig"
+    run ./genome_updater.sh -d refseq -g archaea -l "${aslvl}" -A superkingdom:1 -b ${label} -o ${outdir}    
+    sanity_check ${outdir} ${label}
+    assert_equal "Scaffold" "$(get_values_as ${outdir}assembly_summary.txt 12)"
+
+    label="1"
+    aslvl="contig"
+    run ./genome_updater.sh -d refseq -g archaea -l "${aslvl}" -A superkingdom:1 -b ${label} -o ${outdir}    
+    sanity_check ${outdir} ${label}
+    assert_equal "Contig" "$(get_values_as ${outdir}assembly_summary.txt 12)"
+
+
+}
 
 @test "Date start filter" {
     outdir=${outprefix}date-start-filter/