seaweedfs/.github/workflows/rust-vector-tests.yml

name: "Rust Vector Tests"

on:
  pull_request:
    branches: [ master ]
    paths:
      - 'seaweed-vector/**'
      - 'seaweed-volume/**'
      - 'seaweed-worker/**'
      - 'seaweed-common/**'
      - 'weed/pb/plugin.proto'
      - 'weed/pb/vector.proto'
      - 'weed/pb/vector_pb/**'
      - 'weed/s3api/**'
      - 'weed/command/**'
      - 'test/vectors/**'
      - '.github/workflows/rust-vector-tests.yml'
  push:
    branches: [ master, main ]
    paths:
      - 'seaweed-vector/**'
      - 'seaweed-volume/**'
      - 'seaweed-worker/**'
      - 'seaweed-common/**'
      - 'weed/pb/plugin.proto'
      - 'weed/pb/vector.proto'
      - 'weed/pb/vector_pb/**'
      - 'weed/s3api/**'
      - 'weed/command/**'
      - 'test/vectors/**'
      - '.github/workflows/rust-vector-tests.yml'

concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || (github.event_name == 'push' && github.ref) || github.run_id }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' || (github.event_name == 'push' && !startsWith(github.ref, 'refs/tags/')) }}

permissions:
  contents: read

jobs:
  rust-vector-build:
    name: Rust Vector Build and Unit Tests
    runs-on: ubuntu-24.04
    timeout-minutes: 45

    steps:
      - name: Checkout code
        uses: actions/checkout@v7
        with:
          persist-credentials: false

      - name: Install Rust toolchain
        uses: dtolnay/rust-toolchain@stable

      - name: Fingerprint build toolchain
        id: toolchain
        run: echo "fingerprint=$(getconf GNU_LIBC_VERSION | tr ' ' '-')-rustc-$(rustc -V | awk '{print $2}')" >> "$GITHUB_OUTPUT"

      - name: Cache cargo registry and target
        if: runner.environment == 'github-hosted'
        uses: actions/cache@v6
        with:
          path: |
            ~/.cargo/registry
            ~/.cargo/git
            seaweed-vector/target/release
          key: rust-vector-${{ steps.toolchain.outputs.fingerprint }}-${{ hashFiles('seaweed-vector/Cargo.lock') }}
          restore-keys: |
            rust-vector-${{ steps.toolchain.outputs.fingerprint }}-

      # lance's build scripts compile their own protos and look for a protoc.
      # Point them at the one protoc-bin-vendored ships, so no job depends on a
      # system package and every build sees the same version.
      - name: Use the vendored protoc
        run: |
          cd seaweed-vector
          cargo fetch
          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
          echo "PROTOC=$protoc" >> "$GITHUB_ENV"

      - name: Build the vector crates
        run: cd seaweed-vector && cargo build --release

      - name: Run unit tests
        run: cd seaweed-vector && cargo test --release --workspace


  vectors-e2e:
    name: S3 Vectors Go/Rust Volume Parity
    runs-on: ubuntu-24.04
    timeout-minutes: 45
    env:
      CARGO_PROFILE_DEV_DEBUG: "0"
      CARGO_BUILD_JOBS: "2"
      CARGO_TARGET_DIR: ${{ github.workspace }}/seaweed-vector/target
      VOLUME_SERVER_IMPL: go,rust
      VECTOR_QUERY_MODE: single
    steps:
      - uses: actions/checkout@v7
        with:
          persist-credentials: false
      - uses: actions/setup-go@v5
        with:
          go-version-file: go.mod
          cache: ${{ runner.environment == 'github-hosted' }}
      - uses: dtolnay/rust-toolchain@stable
      - name: Fingerprint build toolchain
        id: toolchain
        run: echo "fingerprint=$(getconf GNU_LIBC_VERSION | tr ' ' '-')-rustc-$(rustc -V | awk '{print $2}')" >> "$GITHUB_OUTPUT"
      - name: Cache cargo registry and target
        if: runner.environment == 'github-hosted'
        uses: actions/cache@v6
        with:
          path: |
            ~/.cargo/registry
            ~/.cargo/git
            seaweed-vector/target/debug
          key: vectors-e2e-${{ runner.os }}-${{ runner.arch }}-${{ steps.toolchain.outputs.fingerprint }}-${{ hashFiles('seaweed-vector/Cargo.lock', 'seaweed-volume/Cargo.lock') }}
          restore-keys: |
            vectors-e2e-${{ runner.os }}-${{ runner.arch }}-${{ steps.toolchain.outputs.fingerprint }}-
      - name: Use the vendored protoc
        run: |
          cd seaweed-vector
          cargo fetch
          version=$(awk '/^name = "protoc-bin-vendored-linux-x86_64"$/{found=1; next} found && /^version = /{gsub(/"/,"",$3); print $3; exit}' Cargo.lock)
          test -n "$version" || { echo "protoc-bin-vendored-linux-x86_64 is not in Cargo.lock" >&2; exit 1; }
          protoc=$(find ~/.cargo/registry/src -path "*protoc-bin-vendored-linux-x86_64-$version/bin/protoc" | head -1)
          test -x "$protoc" || { echo "no vendored protoc $version in the registry" >&2; exit 1; }
          echo "PROTOC=$protoc" >> "$GITHUB_ENV"
      - name: Test Go vector gateway
        run: |
          go test ./weed/s3api/s3vectors -count=1
          go test ./weed/command -run 'Vector|Vectors' -count=1
      - name: Build integration binaries
        working-directory: test/vectors
        run: make build CARGO_PROFILE=dev
      - uses: actions/setup-python@v5
        with:
          python-version: "3.12"
      - name: Install test dependencies
        run: python -m pip install -r test/vectors/requirements.txt
      - name: Run the S3 Vectors integration matrix
        working-directory: test/vectors
        run: |
          ./run_test.sh --basetemp="$RUNNER_TEMP/vector-tests" --junitxml="$RUNNER_TEMP/vector-results.xml"
          python - <<'PYTHON'
          import os
          from pathlib import Path
          import xml.etree.ElementTree as ET
          cases = ET.parse(Path(os.environ["RUNNER_TEMP"]) / "vector-results.xml").findall(".//testcase")
          assert len(cases) >= 34, f"expected at least 34 cases, got {len(cases)}"
          assert not any(case.find("skipped") is not None for case in cases), "integration cases were skipped"
          for volume in ("go", "rust"):
              assert sum(case.get("name", "").endswith(f"[{volume}-single]") for case in cases) >= 17, volume
          PYTHON
      - name: Upload integration diagnostics
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: vectors-e2e-diagnostics
          path: |
            ${{ runner.temp }}/vector-tests
            ${{ runner.temp }}/vector-results.xml
          if-no-files-found: ignore
          retention-days: 7