Merge pull request #7 from cellgeni/refactor_metadata_pulling

Refactored metadata collection and fixes an issue with newly loaded datasets

.github/workflows/test.yml

@@ -0,0 +1,57 @@
+name: Test Collect Metadata Script
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - series_id: GSE191067
+            subset_list: ""
+            comment: "No ENA metadata"
+          - series_id: GSE264508
+            subset_list: ""
+            comment: ".fastq and .sra files in ENA metadata"
+          - series_id: GSE274955
+            subset_list: ""
+            comment: "Broken .sra files. Files in .bam format available"
+          - series_id: GSE250130
+            subset_list: ""
+            comment: "No Project or SubProjects in soft_family file"
+          - series_id: E-MTAB-9221
+            subset_list: ""
+            comment: "Regular ENA dataset"
+          - series_id: GSE111360
+            subset_list: test_data/GSE111360/GSE111360.subset.list
+            comment: "Subset list provided"
+          - series_id: GSE117988
+            subset_list: ""
+            comment: "Crap .fastq files, but .sra files are available in ENA metadata"
+          - series_id: GSE160513
+            subset_list: ""
+            comment: "Regular GEO dataset"
+          - series_id: PRJNA511433
+            subset_list: ""
+            comment: "Regular GEO dataset but using BioProject"
+    name: "Test ${{ matrix.series_id }}: ${{ matrix.comment }}"
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v3
+
+    - name: Set up environment
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y wget perl curl jq
+
+    - name: Run metadata collection tests
+      run: |
+        chmod +x ./scripts/*
+        chmod +x ./tests/test_metadata.sh
+        ./tests/test_metadata.sh ${{ matrix.series_id }} ${{ matrix.subset_list }}

reprocess_public_10x.sh

@@ -40,6 +40,7 @@ if [[ $SUBSET != "" ]]
 then 
   >&2 echo "WARNING: Using file $SUBSET to only process select samples!"
   SUBSET=`readlink -f $SUBSET`
+  cp $SUBSET $SERIES.subset.list
   if [[ `grep "^GSM" $SUBSET` == "" && `grep "^SRS" $SUBSET` == "" && `grep "^ERS" $SUBSET` == "" ]]
   then
     >&2 echo "ERROR: The subset file $SUBSET can only contain GSM, SRS, or ERS IDs!"