acc58669e6546b8705ab44c76add237111279610
angie
  Mon Aug 16 15:30:22 2021 -0700
Use unzip -o (overwrite) so reruns don't get hung up on a prompt.

diff --git src/hg/utils/otto/sarscov2phylo/getNcbi.sh src/hg/utils/otto/sarscov2phylo/getNcbi.sh
index 4117416..75c4c8e 100755
--- src/hg/utils/otto/sarscov2phylo/getNcbi.sh
+++ src/hg/utils/otto/sarscov2phylo/getNcbi.sh
@@ -14,31 +14,31 @@
 
 ottoDir=/hive/data/outside/otto/sarscov2phylo
 
 mkdir -p $ottoDir/ncbi.$today
 cd $ottoDir/ncbi.$today
 
 datasets download virus genome taxon 2697049 \
     --exclude-cds \
     --exclude-protein \
     --exclude-gpff \
     --exclude-pdb \
     --filename ncbi_dataset.zip \
 |& tail -50 \
     > datasets.log
 rm -rf ncbi_dataset
-unzip ncbi_dataset.zip
+unzip -o ncbi_dataset.zip
 # Creates ./ncbi_dataset/
 
 # This makes something just like ncbi.datasets.tsv from the /table/ API query:
 jq -c -r '[.accession, .biosample, .isolate.collectionDate, .location.geographicLocation, .host.sciName, .isolate.name, .completeness, (.length|tostring)] | join("\t")' \
     ncbi_dataset/data/data_report.jsonl \
 | sed -e 's/COMPLETE/complete/; s/PARTIAL/partial/;' \
 | sort \
     > ncbi_dataset.tsv
 
 # Use EUtils (esearch) to get all SARS-CoV-2 BioSample GI# IDs:
 $scriptDir/searchAllSarsCov2BioSample.sh
 sort all.biosample.gids.txt > all.biosample.gids.sorted.txt
 
 # Copy yesterday's all.bioSample.txt so we don't have to refetch all the old stuff.
 if [ -e ../ncbi.latest/all.bioSample.txt.xz ]; then