Initial Commit

Author: criticic

.github/scripts/minify.sh

@@ -0,0 +1,32 @@
+#!/bin/bash
+
+set -e  # Exit on error
+
+# Variables from environment
+PACKAGE_NAME="$PACKAGE"
+PACKAGE_VERSION="$VERSION"
+TARBALL="${PACKAGE_NAME}_${PACKAGE_VERSION}.tar.gz"
+EXTRACT_DIR="./extracted"
+MINIFIED_TARBALL="${PACKAGE_NAME}_${PACKAGE_VERSION}_minified.tar.gz"
+CRAN_URL="https://cran.r-project.org/src/contrib/Archive/${PACKAGE_NAME}/${TARBALL}"
+
+# Fetch tarball
+if [ ! -f "$TARBALL" ]; then
+    curl -L "$CRAN_URL" -o "$TARBALL"
+fi
+
+# Extract tarball
+mkdir -p "$EXTRACT_DIR"
+export COPYFILE_DISABLE=1
+tar --no-xattrs -xvf "$TARBALL" -C "$EXTRACT_DIR"
+
+# Clean and repack
+rm -rf "$EXTRACT_DIR/$PACKAGE_NAME/tests" \
+           "$EXTRACT_DIR/$PACKAGE_NAME/man" \
+           "$EXTRACT_DIR/$PACKAGE_NAME/vignettes" \
+           "$EXTRACT_DIR/$PACKAGE_NAME/inst"
+
+tar --no-xattrs -czvf "$MINIFIED_TARBALL" -C "$EXTRACT_DIR" .
+
+# Install package
+R CMD INSTALL "$MINIFIED_TARBALL"

.github/workflows/minify.yaml

@@ -0,0 +1,85 @@
+name: R Package Size Optimization Workflow
+
+on:
+  issues:
+    types: [opened]
+
+jobs:
+  package-optimization:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout source code
+        uses: actions/checkout@v3
+
+      - name: Parse package metadata from issue
+        id: parse-description
+        run: |
+          DESCRIPTION='${{ github.event.issue.body }}'
+          PACKAGE=$(echo "$DESCRIPTION" | jq -r '.package')
+          VERSION=$(echo "$DESCRIPTION" | jq -r '.version')
+          echo "PACKAGE=$PACKAGE" >> $GITHUB_ENV
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
+
+      - name: Setup R runtime environment
+        uses: r-lib/actions/setup-r@v2
+
+      - name: Query existing optimized package
+        id: check-artifact
+        run: |
+          ARTIFACT_INFO=$(gh api /repos/${{ github.repository }}/actions/artifacts --jq '.artifacts[] | select(.name=="${{ env.PACKAGE }}-${{ env.VERSION }}") | {id: .id, run_id: .workflow_run.id}')
+          ARTIFACT_ID=$(echo "$ARTIFACT_INFO" | jq -r '.id')
+          RUN_ID=$(echo "$ARTIFACT_INFO" | jq -r '.run_id')
+          echo "ARTIFACT_ID=$ARTIFACT_ID" >> $GITHUB_ENV
+          echo "RUN_ID=$RUN_ID" >> $GITHUB_ENV
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Retrieve cached optimized package
+        if: env.ARTIFACT_ID != ''
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ env.PACKAGE }}-${{ env.VERSION }}
+          run-id: ${{ env.RUN_ID }}
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          path: .
+
+      - name: Install cached optimized package
+        if: env.ARTIFACT_ID != ''
+        run: R CMD INSTALL ${{ env.PACKAGE }}_${{ env.VERSION }}_minified.tar.gz
+
+      - name: Generate and install optimized package
+        if: env.ARTIFACT_ID == ''
+        run: |
+          # Fetch Package & Run minification
+          .github/scripts/minify.sh
+
+          # Get original size
+          ORIG_SIZE=$(du -h ./${{ env.PACKAGE }}_${{ env.VERSION }}.tar.gz | cut -f1)
+          echo "ORIG_SIZE=$ORIG_SIZE" >> $GITHUB_ENV
+          
+          # Get minified size
+          MIN_SIZE=$(du -h ./${{ env.PACKAGE }}_${{ env.VERSION }}_minified.tar.gz | cut -f1)
+          echo "MIN_SIZE=$MIN_SIZE" >> $GITHUB_ENV
+
+      - name: Archive optimized package
+        if: env.ARTIFACT_ID == ''
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ env.PACKAGE }}-${{ env.VERSION }}
+          path: ./${{ env.PACKAGE }}_${{ env.VERSION }}_minified.tar.gz
+          retention-days: 90
+
+      - name: Report optimization results
+        run: |
+          if [[ "${{ job.status }}" == "success" ]]; then
+            if [[ -n "${{ env.ORIG_SIZE }}" ]]; then
+              COMMENT="✅ Package successfully optimized!\nOriginal size: ${{ env.ORIG_SIZE }}\nOptimized size: ${{ env.MIN_SIZE }}"
+            else
+              COMMENT="✅ Package successfully installed from cache."
+            fi
+          else
+            COMMENT="❌ Package optimization failed. Please check workflow logs."
+          fi
+          gh issue comment "${{ github.event.issue.number }}" --body "$COMMENT"
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

README.md

@@ -0,0 +1,8 @@
+# Medium Task for GSoC-R 2025 Project: Optimizing a performance testing workflow by reusing minified R package versions between CI runs
+
+## Description
+
+Write a YAML snippet that:
+Checks if a precompiled artifact for a specific historical version of data.table exists.
+If it is found, it downloads and installs the artifact, else it builds the version from source, minifies it, and then uploads it as an artifact for future runs. (Name the artifacts based on version numbers for keeping them distinct)
+Implement a fallback mechanism in the workflow to build the missing version from source in case artifact retrieval fails.