use md5sum to check download integrity with vdb-validate as fallback

modules/nf-core/sratools/prefetch/environment.yml

@@ -4,4 +4,5 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::sra-tools=3.0.8
+  - bioconda::sra-tools=3.1.0
+  - conda-forge::curl=8.5.0

modules/nf-core/sratools/prefetch/main.nf

@@ -4,8 +4,8 @@ process SRATOOLS_PREFETCH {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/sra-tools:3.0.8--h9f5acd7_0' :
-        'biocontainers/sra-tools:3.0.8--h9f5acd7_0' }"
+        'https://depot.galaxyproject.org/singularity/sra-tools:3.1.0--h9f5acd7_0' :
+        'biocontainers/sra-tools:3.1.0--h9f5acd7_0' }"
 
     input:
     tuple val(meta), val(id)

modules/nf-core/sratools/prefetch/templates/retry_with_backoff.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 
-set -u
+set -u -x
 
 retry_with_backoff() {
     local max_attempts=${1}
@@ -47,9 +47,16 @@ retry_with_backoff !{args2} \
     !{args} \
     !{id}
 
-[ -f !{id}.sralite ] && vdb-validate !{id}.sralite || vdb-validate !{id}
+# check file integrity using vdb-validate or (when archive contains no checksums) md5sum
+vdb-validate !{id} > vdb-validate_result.txt 2>&1 || exit 1
+if grep -q "checksums missing" vdb-validate_result.txt; then
+	VALID_MD5SUMS=$(curl -s -f -L --retry 3 --retry-delay 60 'https://locate.ncbi.nlm.nih.gov/sdl/2/retrieve?filetype=run&acc=!{id}')
+	LOCAL_MD5SUMS=$(md5sum !{id}/* | cut -f1 -d' ')
+	grep -q -F -f <(echo "$LOCAL_MD5SUMS") <(echo "$VALID_MD5SUMS") || exit 1
+fi
 
 cat <<-END_VERSIONS > versions.yml
 "!{task.process}":
     sratools: $(prefetch --version 2>&1 | grep -Eo '[0-9.]+')
+    curl: $(curl --version | head -n 1 | sed 's/^curl //; s/ .*$//')
 END_VERSIONS