Final GSoC '25 Report: Reimplementing the Core Samplers of the dirichletprocess R Package in C++

.Rbuildignore

@@ -13,3 +13,9 @@
 ^pkgdown$
 ^\.github$
 ^CRAN-SUBMISSION$
+^profiling$
+^analysis$
+^inst/benchmarks$
+^\.vscode$
+^CLAUDE\.md$
+^benchmark$

.github/workflows/R-CMD-check.yml

@@ -0,0 +1,91 @@
+name: R-CMD-check
+
+on:
+  push:
+    branches:
+      - '**'
+  pull_request:
+    branches:
+      - '**'
+
+jobs:
+  R-CMD-check:
+    runs-on: ${{ matrix.config.os }}
+    timeout-minutes: 120
+
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {os: ubuntu-latest,   r: 'release'}
+          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
+          - {os: windows-latest,  r: 'release'}
+          - {os: macOS-latest,    r: 'release'}
+
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: ${{ matrix.config.r }}
+          http-user-agent: ${{ matrix.config.http-user-agent }}
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: |
+            any::rcmdcheck
+            any::roxygen2
+            any::devtools
+          needs: check
+
+      - name: Install system dependencies on Linux
+        if: runner.os == 'Linux'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libcurl4-openssl-dev libssl-dev libxml2-dev libharfbuzz-dev libfribidi-dev liblapack-dev libblas-dev libgfortran-13-dev
+
+      - name: Install system dependencies on macOS
+        if: runner.os == 'macOS'
+        run: |
+          brew install harfbuzz fribidi
+
+      - name: Session info
+        run: |
+          options(width = 100)
+          pkgs <- installed.packages()[, "Package"]
+          sessioninfo::session_info(pkgs, include_base = TRUE)
+        shell: Rscript {0}
+
+      - name: Compile C++ exports
+        run: |
+          Rcpp::compileAttributes()
+        shell: Rscript {0}
+
+      - name: Check package
+        uses: r-lib/actions/check-r-package@v2
+        with:
+          args: 'c("--no-manual", "--as-cran", "--no-build-vignettes")'
+          build_args: 'c("--no-manual", "--no-build-vignettes")'
+          error-on: '"error"'
+          check-dir: '"check"'
+
+      - name: Show testthat output
+        if: always()
+        run: find check -name 'testthat.Rout*' -exec cat '{}' \; || true
+        shell: bash
+
+      - name: Upload check results
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ runner.os }}-r${{ matrix.config.r }}-results
+          path: check

.github/workflows/cpp-validation.yml

@@ -0,0 +1,215 @@
+# .github/workflows/cpp-validation.yml
+# DISABLED: Temporarily disabled to focus on R CMD check workflow
+
+name: C++ Implementation Validation (DISABLED)
+
+on:
+  # push:
+  #   branches: [ feature/r-cpp-consistency, feature/*, cpp-implementation ]
+  # pull_request:
+  #   branches: [ master, main ]
+  # schedule:
+  #   # Run weekly on Mondays at 2 AM UTC
+  #   - cron: '0 2 * * 1'
+  workflow_dispatch:
+    inputs:
+      test_mode:
+        description: 'Test mode: dev (fast) or prod (full validation)'
+        required: false
+        default: 'dev'
+        type: choice
+        options:
+          - dev
+          - prod
+
+jobs:
+  test-validation:
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 120  # 2 hours max for dev, allows prod mode
+
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        r-version: ['4.3.0', '4.4.0', 'release']
+        include:
+          - os: ubuntu-latest
+            r-version: 'devel'
+
+    env:
+      R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+      DP_DEV_TESTING: ${{ github.event.inputs.test_mode == 'prod' && 'FALSE' || 'TRUE' }}
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - uses: r-lib/actions/setup-r@v2
+      with:
+        r-version: ${{ matrix.r-version }}
+        use-public-rspm: true
+
+    - uses: r-lib/actions/setup-r-dependencies@v2
+      with:
+        extra-packages: |
+          any::devtools
+          any::testthat
+          any::sessioninfo
+          any::rcmdcheck
+        dependencies: '"all"'
+
+    - name: Session info
+      run: |
+        options(width = 100)
+        pkgs <- installed.packages()[, "Package"]
+        sessioninfo::session_info(pkgs, include_base = TRUE)
+        cat("Test mode: ${{ github.event.inputs.test_mode || 'dev' }}\n")
+        cat("DP_DEV_TESTING:", Sys.getenv("DP_DEV_TESTING"), "\n")
+      shell: Rscript {0}
+
+    - name: Compile C++ code
+      run: |
+        devtools::document()
+      shell: Rscript {0}
+
+    - name: Check C++ compilation
+      run: |
+        source("tests/integration/package_checks.R")
+        cpp_check <- check_cpp_compilation()
+        if (length(cpp_check$warnings) > 0) {
+          cat("C++ compilation warnings detected:\n")
+          cat(cpp_check$warnings, sep = "\n")
+        }
+        if (!cpp_check$success) {
+          stop("C++ compilation failed")
+        }
+        cat("✅ C++ compilation successful\n")
+      shell: Rscript {0}
+
+    - name: Install package
+      run: |
+        devtools::install(".", upgrade = "never")
+        cat("✅ Package installed successfully\n")
+      shell: Rscript {0}
+
+    - name: Run testthat test suite
+      run: |
+        source("inst/validation/run_all_validations.R")
+        if (Sys.getenv("DP_DEV_TESTING") == "FALSE") {
+          cat("Running PRODUCTION mode validation...\n")
+          results <- run_complete_validation()
+        } else {
+          cat("Running DEVELOPMENT mode validation...\n")
+          results <- quick_validation()
+        }
+        print(results)
+      shell: Rscript {0}
+
+    - name: Run integration tests
+      run: |
+        cat("Running integration tests in", 
+            ifelse(Sys.getenv("DP_DEV_TESTING") == "FALSE", "PRODUCTION", "DEVELOPMENT"), 
+            "mode...\n")
+
+        # Source and run each integration test
+        source("tests/integration/memory_tests.R")
+        memory_result <- test_memory_stability()
+        cat("Memory test result:", memory_result, "MB\n")
+
+        source("tests/integration/stress_tests.R") 
+        stress_results <- run_stress_tests()
+        cat("Stress test results:\n")
+        print(stress_results)
+
+        source("tests/integration/package_checks.R")
+        package_results <- run_package_checks()
+        cat("Package check results:\n")
+        print(package_results)
+      shell: Rscript {0}
+
+    - name: Run R CMD check
+      if: github.event.inputs.test_mode == 'prod' || github.event_name == 'pull_request'
+      run: |
+        rcmdcheck::rcmdcheck(args = c("--no-manual", "--as-cran"), 
+                           error_on = "warning", 
+                           check_dir = "check")
+      shell: Rscript {0}
+
+    - name: Upload check results
+      if: failure()
+      uses: actions/upload-artifact@v4
+      with:
+        name: ${{ runner.os }}-r${{ matrix.r-version }}-check-results
+        path: check
+
+    - name: Upload test results
+      if: always()
+      uses: actions/upload-artifact@v4
+      with:
+        name: test-results-${{ matrix.os }}-r${{ matrix.r-version }}
+        path: |
+          validation_results/
+          *.rds
+
+  pr-comment:
+    needs: test-validation
+    runs-on: ubuntu-latest
+    if: github.event_name == 'pull_request'
+
+    steps:
+    - name: Comment PR with results
+      uses: actions/github-script@v6
+      with:
+        script: |
+          const comment = `## C++ Implementation Validation Results
+
+          ✅ testthat and integration tests completed
+
+          ### Test Summary
+          - **testthat tests**: Core functionality validation
+          - **Integration tests**: Memory, stress, and package checks
+          - **Mode**: ${{ github.event.inputs.test_mode || 'dev' }}
+
+          See artifacts for detailed results.`;
+
+          github.rest.issues.createComment({
+            issue_number: context.issue.number,
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            body: comment
+          });
+
+  coverage:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - uses: r-lib/actions/setup-r@v2
+      with:
+        use-public-rspm: true
+
+    - uses: r-lib/actions/setup-r-dependencies@v2
+      with:
+        extra-packages: |
+          any::covr
+        dependencies: '"all"'
+
+    - name: Test coverage
+      run: |
+        cov <- covr::package_coverage(
+          type = "all",
+          quiet = FALSE,
+          clean = FALSE,
+          install_path = file.path(Sys.getenv("RUNNER_TEMP"), "package")
+        )
+        print(cov)
+        covr::to_cobertura(cov)
+      shell: Rscript {0}
+
+    - uses: codecov/codecov-action@v3
+      with:
+        file: ./cobertura.xml
+        fail_ci_if_error: false
+        verbose: true

.gitignore

@@ -6,3 +6,12 @@ inst/doc
 clean_bib.sh
 tests/testthat/Rplots.pdf
 
+src/*.o
+src/*.so
+src/*.dll
+
+papers/
+presentation/
+
+.vscode/
+