CI #52
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: CI | |
| # Controls when the workflow will run | |
| on: | |
| schedule: | |
| # * is a special character in YAML so you have to quote this string | |
| - cron: '0 0 * * *' | |
| # Allows you to run this workflow manually from the Actions tab | |
| workflow_dispatch: | |
| # A workflow run is made up of one or more jobs that can run sequentially or in parallel | |
| jobs: | |
| # This workflow contains a single job called "build" | |
| build: | |
| # The type of runner that the job will run on | |
| runs-on: ubuntu-latest | |
| # Steps represent a sequence of tasks that will be executed as part of the job | |
| steps: | |
| - name: Checkout repo | |
| uses: actions/checkout@v3 | |
| - name: Environment Variables from Dotenv | |
| uses: c-py/action-dotenv-to-setenv@v4 | |
| - name: Install required NCBI packages | |
| run: | | |
| #retrieve packages and set permissions | |
| curl -O 'https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/v2/linux-amd64/dataformat' | |
| curl -O 'https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/v2/linux-amd64/datasets' | |
| chmod +x datasets dataformat | |
| - name: Run query and get new rows | |
| run: | | |
| existing_assemblies="${{env.MATRIX_PATH}}" | |
| new_assemblies="output.tsv" | |
| ncbi_assemblies="ncbi.tsv" | |
| column_name="${{env.COLUMN_NAME}}" | |
| # Get TSV from dataset | |
| ./datasets summary genome accession ${{env.PROJECT_ACCESSION}} ${{env.DATASET_EXTRA_ARGS}} | ./dataformat tsv genome --fields ${{env.TSV_FIELDS}} >> "$ncbi_assemblies" | |
| function url_exists(){ | |
| local url="$1" | |
| echo "$url" | |
| if curl -s -m 60 --head "$url" | head -n 1 | grep -q "HTTP/1.1 404"; then | |
| return 1 #url returns 404 | |
| else | |
| return 0 #url exists | |
| fi | |
| } | |
| if [ ! -s "$existing_assemblies" ]; then | |
| cat "$ncbi_assemblies" >> "$new_assemblies" | |
| sed -i "1s/$/\t$column_name/" "$existing_assemblies" | |
| else | |
| awk -F'\t' 'NR==FNR{a[$1];next} !($1 in a)' "$existing_assemblies" "$ncbi_assemblies" >> "$new_assemblies" | |
| fi | |
| added_rows=0 | |
| # Process the input file and create the output file | |
| while IFS=$'\t' read -r col1 rest_of_line; do | |
| if [[ "$added_rows" -ge 200 ]]; then | |
| break | |
| fi | |
| if [[ "$col1" == "Assembly Accession" ]]; then | |
| continue | |
| fi | |
| url="https://www.ebi.ac.uk/ena/browser/api/fasta/$col1?download=true" | |
| if url_exists "$url"; then | |
| url_to_add="$url&gzip=true" | |
| echo "$url_to_add" | |
| echo -e "$col1\t$rest_of_line\t$url_to_add" >> "$existing_assemblies" | |
| ((added_rows++)) | |
| fi | |
| done < "$new_assemblies" | |
| sort -k3 $existing_assemblies | |
| # Count new rows and set the environment variable | |
| new_rows=$(wc -l < "$new_assemblies") | |
| echo "new_rows=$new_rows" >> "$GITHUB_ENV" | |
| rm $new_assemblies | |
| rm $ncbi_assemblies | |
| - name: Commit & Push changes | |
| uses: actions-js/push@master | |
| with: | |
| github_token: ${{ secrets.GITHUB_TOKEN }} | |
| message: "Added ${{ env.new_rows }} new row(s)" |