.github/workflows/build.yml

name: build

on:
  push:
  pull_request:
  workflow_dispatch:

jobs:
  build:
    name: ${{ matrix.os }}
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: false
      matrix:
        os: [ubuntu-latest, macos-latest]

    steps:
      - uses: actions/checkout@v4

      - name: Install dependencies (Linux)
        if: runner.os == 'Linux'
        run: |
          sudo apt-get update
          sudo apt-get install -y cmake librocksdb-dev libgflags-dev libsnappy-dev \
                                  zlib1g-dev libbz2-dev liblz4-dev libzstd-dev

      - name: Install dependencies (macOS)
        if: runner.os == 'macOS'
        run: brew install cmake rocksdb snappy lz4 zstd gflags

      - name: Build and install collocatordb
        run: |
          EXTRA=""
          [ "$RUNNER_OS" = "macOS" ] && EXTRA="-DCMAKE_PREFIX_PATH=$(brew --prefix)"
          git clone --depth 1 https://korap.ids-mannheim.de/gerrit/ids-kl/collocatordb
          cmake -S collocatordb -B collocatordb/build -DCMAKE_INSTALL_PREFIX=/usr/local $EXTRA
          cmake --build collocatordb/build -j
          sudo cmake --install collocatordb/build
          if [ "$RUNNER_OS" = "Linux" ]; then sudo ldconfig; fi

      # The build directory has to be build/ inside the sources, the test looks
      # for the binary relative to it.
      - name: Configure
        run: |
          EXTRA=""
          [ "$RUNNER_OS" = "macOS" ] && EXTRA="-DCMAKE_PREFIX_PATH=$(brew --prefix)"
          cmake -S . -B build -DCMAKE_INSTALL_PREFIX=/usr/local $EXTRA

      - name: Build
        run: cmake --build build -j

      - name: Test
        run: ctest --test-dir build --output-on-failure

      # The count based part of the test traps on MacOS, while it runs on Linux
      # with rocksdb 8.9, 10.2 and 11.0. Without a backtrace there is nothing to
      # go by, so produce one.
      - name: Backtrace of the crash (macOS)
        if: failure() && runner.os == 'macOS'
        run: |
          D=$(mktemp -d)
          ./build/dereko2vec -train tests/data/wpd19_10000.w2vinput -output "$D/m.vecs" \
              -type 3 -save-vocab "$D/m.vocab" -size 50 -window 5 -negative 5 \
              -threads 4 -iter 1 -min-count 2 -binary 1 > /dev/null 2>&1
          lldb --batch -o run -o 'bt all' -o quit -- ./build/dereko2vec \
              -train tests/data/wpd19_10000.w2vinput -output "$D/m.rocksdb" \
              -type 5 -read-vocab "$D/m.vocab" -threads 8 2>&1 | tail -80

      # The training writes the memory mappable form of the model, which
      # derekovecs maps. vecs2mmap does the same for models trained earlier.
      - name: Check the memory mappable model form
        run: |
          ./build/dereko2vec -train tests/data/wpd19_10000.w2vinput -output /tmp/m.vecs \
              -type 3 -size 50 -window 5 -negative 5 -threads 2 -iter 1 -min-count 5 -binary 1
          echo "written by the training:"
          ls -l /tmp/m.vecs.vecs /tmp/m.vecs.words
          rm /tmp/m.vecs.vecs /tmp/m.vecs.words
          ./build/vecs2mmap /tmp/m.vecs
          echo "written by vecs2mmap:"
          ls -l /tmp/m.vecs.vecs /tmp/m.vecs.words

      - name: Install
        run: |
          sudo cmake --install build
          dereko2vec 2>&1 | head -1
          vecs2mmap -h | head -1