name: "ccache-buckets"
description: "Save/restore latest GitHub Actions ccache matching a key prefix to/from HF buckets"
inputs:
  key:
    description: "Cache key prefix to match and load"
    required: true
  folder:
    description: "Bucket folder containing ccache files"
    required: true
  evict-old-files:
    description: "Corresponds to the ccache --evict-older-than AGE option, where AGE is the number of seconds or days followed by the 's' or 'd' suffix respectively."
    default: ''
  save:
    description: "Save ccache"
    required: false
    default: false
    type: boolean
  hf_bucket:
    description: 'Hugging Face buckets path'
    required: true

runs:
  using: "composite"
  steps:
    - name: Install Hugging Face Hub CLI
      shell: bash
      run: |
        python3 -m venv .venv-hf
        .venv-hf/bin/pip install -U huggingface_hub==1.28.0

    - name: Restore ccache from buckets
      if: ${{ inputs.save != 'true' }}
      shell: bash
      run: |
        set +e -uo pipefail
        source .venv-hf/bin/activate
        CCACHE_DIR=$(ccache -k cache_dir)
        if [[ -d "$CCACHE_DIR" ]]; then
            CACHE_PATH=$(hf buckets list "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}" --json | jq -r '[.[] | select(.type == "file") | select(.path | startswith("${{ inputs.folder }}/${{ inputs.key }}") and endswith(".tar.gz"))] | sort_by(.path) | last | .path // ""')
            if [[ -n "$CACHE_PATH" ]]; then
                echo "Restoring ccache from '$CACHE_PATH'."
                hf buckets cp "hf://buckets/${{ inputs.hf_bucket }}/$CACHE_PATH" ccache_bucket.tar.gz
                mkdir -p ccache_bucket
                if tar -xzf ccache_bucket.tar.gz -C ccache_bucket; then
                    rm -rf "$CCACHE_DIR"
                    mv ccache_bucket "$CCACHE_DIR"
                    ccache -z
                fi
                rm ccache_bucket.tar.gz
            else
                echo "No ccache found."
            fi
        else
            echo "'$CCACHE_DIR' not found."
        fi

    - name: Save ccache to buckets
      if: ${{ inputs.save == 'true' }}
      shell: bash
      run: |
        set +e -uo pipefail
        source .venv-hf/bin/activate
        CCACHE_DIR=$(ccache -k cache_dir)
        if [[ -d "$CCACHE_DIR" ]]; then
            ccache -s
            if [[ -n "${{ inputs.evict-old-files }}" ]]; then
                ccache --evict-older-than "${{ inputs.evict-old-files }}"
            fi
            DATESTAMP=$(date -u +'%Y-%m-%dT%H:%M:%SZ')
            CACHEFILE="${{ inputs.key }}-$DATESTAMP.tar.gz"
            if tar -czf ccache_bucket.tar.gz -C "$CCACHE_DIR" .; then
                hf buckets cp ccache_bucket.tar.gz "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}/$CACHEFILE"
            fi
            rm ccache_bucket.tar.gz
        else
            echo "'$CCACHE_DIR' not found."
        fi

    - name: Remove old ccache files from buckets
      if: ${{ inputs.save == 'true' }}
      shell: bash
      run: |
        set +e -uo pipefail
        source .venv-hf/bin/activate
        CACHE_FILES=$(hf buckets list "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}" --json | jq -r '[.[] | select(.type == "file") | select((.uploaded_at | .[:19]+"Z" | fromdateiso8601) < (now - 5 * 60)) | select(.path | startswith("${{ inputs.folder }}/${{ inputs.key }}") and endswith(".tar.gz"))] | sort_by(.path)[:-1] | .[] | [.path // ""] | @tsv')
        if [[ -n "$CACHE_FILES" ]]; then
            echo "Removing old ccache files..."
            while IFS=$'\t' read -r CACHE_PATH; do
                hf buckets rm "hf://buckets/${{ inputs.hf_bucket }}/$CACHE_PATH" -y
            done <<< "$CACHE_FILES"
        fi