main.yml

name: Build and tests

on:
  push:
    branches: [ master, develop]
    paths-ignore:
      - '**.md'
  workflow_dispatch:

jobs:


########################################################################################
  make:
    name: Make
    strategy:
      fail-fast: false
      matrix:
        machine: [ubuntu-latest]
        gmake_install_command: ['gmake --version']
        include:
        - {machine: macOS-13, gmake_install_command: 'brew install make && gmake --version'}
    runs-on: ['${{ matrix.machine }}']   
   
    steps:
    - uses: actions/checkout@v4
      with:
        submodules: recursive
    - name: install gmake
      run: ${{ matrix.gmake_install_command }}    
    
    - name: make
      run: | 
        gmake -j CXX=g++-12 CC=gcc-12 STATIC_LINK=true

    - name: tar artifacts
      run: tar -cvf kmer-db.tar ./test/virus -C ./bin kmer-db
    
    - uses: actions/upload-artifact@v4
      with:
        name: executable-artifact-${{ matrix.machine }}
        path: ./kmer-db.tar    

########################################################################################
  virus:
    needs: make
    name: Virus data
    strategy:
      fail-fast: false
      matrix:
        machine: [ubuntu-latest, macOS-13]
    runs-on: ['${{ matrix.machine }}']
    env: 
      INPUT_DIR: ./test/virus
    
    steps:
    - uses: actions/download-artifact@v4
      with:
        name: executable-artifact-${{ matrix.machine }}
        path: ./
        
    - name: untar artifacts
      run: tar -xf kmer-db.tar
        
    - name: help
      run: ./kmer-db
    
    - name: version
      run: ./kmer-db -version
    
    - name: build 
      run: |
        ./kmer-db build ${INPUT_DIR}/seqs.part1.list k18.parts.db
    
    - name: new2all 
      run: |
        ./kmer-db new2all k18.parts.db ${INPUT_DIR}/seqs.part2.list k18.n2a.csv
        cmp k18.n2a.csv ${INPUT_DIR}/k18.n2a.csv
        
    - name: new2all (sparse)
      run: |
        ./kmer-db new2all -sparse k18.parts.db ${INPUT_DIR}/seqs.part2.list k18.n2a.sparse.csv
        cmp k18.n2a.sparse.csv ${INPUT_DIR}/k18.n2a.sparse.csv
    
    - name: extend  
      run: |     
        ./kmer-db build -extend -k 25 ${INPUT_DIR}/seqs.part2.list k18.parts.db
        
    - name: all2all  
      run: |     
        ./kmer-db all2all k18.parts.db k18.csv
        cmp k18.csv ${INPUT_DIR}/k18.csv
        
    - name: all2all (sparse)
      run: |     
        ./kmer-db all2all -sparse k18.parts.db k18.sparse.csv
        cmp k18.sparse.csv ${INPUT_DIR}/k18.sparse.csv

    - name: distance
      run: | 
        ./kmer-db distance jaccard k18.csv k18.csv.jaccard
        ./kmer-db distance min k18.csv k18.csv.min
        ./kmer-db distance max k18.csv k18.csv.max
        ./kmer-db distance cosine k18.csv k18.csv.cosine
        ./kmer-db distance mash k18.csv k18.csv.mash
        cmp k18.csv.jaccard ${INPUT_DIR}/k18.csv.jaccard
        cmp k18.csv.min ${INPUT_DIR}/k18.csv.min
        cmp k18.csv.max ${INPUT_DIR}/k18.csv.max
        cmp k18.csv.cosine ${INPUT_DIR}/k18.csv.cosine
        cmp k18.csv.mash ${INPUT_DIR}/k18.csv.mash
        
    - name: build (default k) + all2all 
      run: |
        ./kmer-db build ${INPUT_DIR}/seqs.list k18.db
        ./kmer-db all2all k18.db k18.csv
        cmp k18.csv ${INPUT_DIR}/k18.csv
        
    - name: build (default k, multifasta) + all2all 
      run: |
        ./kmer-db build -multisample-fasta ${INPUT_DIR}/multi.list k18.multi.db
        ./kmer-db all2all k18.multi.db k18.multi.csv
        cmp k18.multi.csv ${INPUT_DIR}/k18.csv

    - name: build (default k, 2 x multifasta) + all2all 
      run: |
        ./kmer-db build -multisample-fasta ${INPUT_DIR}/multi.split.list k18.multi.split.db
        ./kmer-db all2all k18.multi.split.db k18.multi.split.csv
        cmp k18.multi.split.csv ${INPUT_DIR}/k18.csv
    
    - name: build (default k) + extend + all2all 
      run: |
        ./kmer-db build ${INPUT_DIR}/seqs.part1.list k18.parts.db
        ./kmer-db build -extend -k 25 ${INPUT_DIR}/seqs.part2.list k18.parts.db
        ./kmer-db all2all k18.parts.db k18.parts.csv
        cmp k18.parts.csv ${INPUT_DIR}/k18.csv
        
    - name: build (default k, fraction 0.1) + all2all 
      run: |    
        ./kmer-db build -f 0.1 ${INPUT_DIR}/seqs.list k18.frac.db
        ./kmer-db all2all k18.frac.db k18.frac.csv
        cmp k18.frac.csv ${INPUT_DIR}/k18.frac.csv

    - name: minhash (default k, fraction 0.1) + build + all2all 
      run: |
        ./kmer-db minhash -f 0.1 ${INPUT_DIR}/seqs.list
        ./kmer-db build -from-minhash ${INPUT_DIR}/seqs.list k18.minhash.db
        ./kmer-db all2all k18.minhash.db k18.minhash.csv
        cmp k18.minhash.csv ${INPUT_DIR}/k18.frac.csv
        
    - name: build (k=24) + all2all 
      run: |
        ./kmer-db build -k 24 ${INPUT_DIR}/seqs.list k24.db
        ./kmer-db all2all k24.db k24.csv
        cmp k24.csv ${INPUT_DIR}/k24.csv
        
    - name: build (k=25, f=0.1) + one2all 
      run: |
        ./kmer-db build -k 25 -f 0.1 ${INPUT_DIR}/seqs.part1.list k25.db
        ./kmer-db one2all k25.db ${INPUT_DIR}/data/MT159713 MT159713.csv
        cmp MT159713.csv ${INPUT_DIR}/MT159713.csv    
        
    - name: new2all (against itself)
      run: |
        ./kmer-db new2all k18.db ${INPUT_DIR}/seqs.list k18.n2a.itself.csv
        cmp k18.n2a.itself.csv ${INPUT_DIR}/k18.n2a.itself.csv