fetch-sfs-workflow.yml

name: Hämta nya SFS-författningar från Regeringskansliets publika söktjänst

on:
  schedule:
    # Kör varje natt kl 02:00 UTC (03:00/04:00 svensk tid beroende på säsong)
    - cron: '0 2 * * *'
  workflow_dispatch:  # Tillåter manuell körning
    inputs:
      days:
        description: 'Antal dagar bakåt att hämta dokument för (vid manuell körning)'
        required: false
        default: '30'
        type: string
      enable_git_commit:
        description: 'Aktivera git commits av markdown-filer'
        required: false
        default: true
        type: boolean
      branch_name:
        description: 'Branch namn att använda (krävs om enable_git_commit är true)'
        required: false
        default: 'workflow-artifact-data'
        type: string

permissions:
  contents: write
  actions: write

jobs:
  fetch-documents:
    runs-on: ubuntu-latest
    environment: Test  # Använd Test environment för R2 secrets

    steps:
    - name: Checkout repository
      uses: actions/checkout@v4
      with:
        token: ${{ secrets.GITHUB_TOKEN }}

    - name: Set up Python
      uses: actions/setup-python@v4
      with:
        python-version: '3.11'

    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        pip install -r requirements.txt

    - name: Fetch JSON from beta.rkrattsbaser.gov.se
      run: |
        python downloaders/fetch_new_sfs_docs.py --days ${{ inputs.days || '1' }} --output data/sfs_json
      env:
        PYTHONPATH: ${{ github.workspace }}

    - name: Process JSON files to Markdown files with Selex tags
      run: |
        python sfs_processor.py --input data/sfs_json --output data/md-markers --formats md-markers
      env:
        PYTHONPATH: ${{ github.workspace }}

    - name: Upload JSON source files to Cloudflare R2 for permanent storage
      run: |
        aws configure set aws_access_key_id ${{ secrets.CLOUDFLARE_R2_ACCESS_KEY_ID }}
        aws configure set aws_secret_access_key ${{ secrets.CLOUDFLARE_R2_SECRET_ACCESS_KEY }}
        aws configure set region us-east-1
        aws configure set output json

        # Upload all JSON files to R2 for backup
        aws s3 sync data/sfs_json/ s3://${{ vars.CLOUDFLARE_R2_RAWDATA_BUCKET_NAME }}/ \
          --endpoint-url https://${{ secrets.CLOUDFLARE_R2_ACCOUNT_ID }}.r2.cloudflarestorage.com \
          --content-type "application/json" \
          --exclude "*.md" \
          --include "*.json"
      env:
        AWS_DEFAULT_REGION: us-east-1

    - name: Configure Git
      if: inputs.enable_git_commit != 'false'
      run: |
        git config --local user.email "action@github.com"
        git config --local user.name "GitHub Action"

    - name: Commit and push changes
      if: inputs.enable_git_commit != 'false'
      id: commit_changes
      run: |
        # Get current branch
        CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)

        # Check if we have changes (without staging yet)
        if git diff --quiet data/md-markers/ data/sfs_json/ && \
           ! git ls-files --others --exclude-standard data/md-markers/ data/sfs_json/ | grep -q .; then
          echo "Inga nya filer att committa"
          echo "has_changes=false" >> $GITHUB_OUTPUT
        else
          # Use fixed branch name from input (default: workflow-artifact-data)
          COMMIT_BRANCH="${{ inputs.branch_name || 'workflow-artifact-data' }}"

          # Check if branch exists remotely
          if git ls-remote --heads origin "$COMMIT_BRANCH" | grep -q "$COMMIT_BRANCH"; then
            echo "📥 Branch '$COMMIT_BRANCH' exists, checking out and merging with main..."
            # Branch exists - stash new untracked files to avoid checkout conflict
            git fetch origin "$COMMIT_BRANCH"
            git stash push --include-untracked -m "temp: new sfs files before branch switch"
            git checkout "$COMMIT_BRANCH"
            # Merge latest main into fixed branch to keep it updated
            git merge origin/main --no-edit --strategy-option theirs || echo "Merge completed (conflicts auto-resolved)"
            # Restore the newly generated files
            git stash pop
          else
            echo "🆕 Branch '$COMMIT_BRANCH' doesn't exist, creating new..."
            # Branch doesn't exist - create new
            git checkout -b "$COMMIT_BRANCH"
          fi

          # Now add files after we're on the correct branch
          git add data/md-markers/ data/sfs_json/

          # Commit with multi-line message
          git commit -m "Automatisk uppdatering av SFS-författningar $(date +'%Y-%m-%d')" \
                     -m "" \
                     -m "Inkluderar:" \
                     -m "- Käll-JSON (data/sfs_json/)" \
                     -m "- Markdown med selex-taggar (data/md-markers/)" \
                     -m "- Backup till Cloudflare R2"
          echo "has_changes=true" >> $GITHUB_OUTPUT
          echo "commit_branch=${COMMIT_BRANCH}" >> $GITHUB_OUTPUT
          
          # Push the new branch with error handling
          echo "Försöker pusha branch '${COMMIT_BRANCH}' till origin..."
          
          if git push origin "$COMMIT_BRANCH" 2>&1; then
            echo "✅ Git push lyckades för branch '${COMMIT_BRANCH}'"
            echo "push_success=true" >> $GITHUB_OUTPUT
            echo "push_error=" >> $GITHUB_OUTPUT
          else
            PUSH_EXIT_CODE=$?
            PUSH_ERROR="Git push misslyckades med exit code: ${PUSH_EXIT_CODE}"
            echo "❌ ${PUSH_ERROR}"
            echo "push_success=false" >> $GITHUB_OUTPUT
            echo "push_error=${PUSH_ERROR}" >> $GITHUB_OUTPUT
            
            # Logga mer detaljerad information för debugging
            echo "Git status:"
            git status
            echo "Git remote info:"
            git remote -v
            echo "Git log (senaste commit):"
            git log --oneline -1
            
            # Switch back to original branch even if push failed
            git checkout "$CURRENT_BRANCH"
            
            # Fail the job if push failed
            echo "::error::Git push misslyckades: ${PUSH_ERROR}"
            exit 1
          fi

          # Manage PR lifecycle: close old, create new
          echo "🔄 Hanterar PR för branch '$COMMIT_BRANCH'..."

          # Close existing PR for this branch if it exists
          EXISTING_PR=$(gh pr list --head "$COMMIT_BRANCH" --json number --jq '.[0].number' 2>/dev/null || echo "")
          if [ -n "$EXISTING_PR" ]; then
            echo "Stänger befintlig PR #$EXISTING_PR"
            gh pr close "$EXISTING_PR" --comment "🔄 Stänger för att öppna ny PR med uppdaterad data från $(date +'%Y-%m-%d %H:%M')"
          fi

          # Create new PR
          echo "📝 Skapar ny PR..."
          gh pr create --base main --head "$COMMIT_BRANCH" \
            --title "SFS Data Update - $(date +'%Y-%m-%d %H:%M')" \
            --body "Automatisk uppdatering av SFS-data. Inkluderar Käll-JSON, Markdown med selex-taggar och backup till R2. Workflow: fetch-sfs-workflow, Branch: $COMMIT_BRANCH, Run: ${{ github.run_id }}" \
            || echo "⚠️ PR may already exist"

          # Switch back to original branch
          git checkout "$CURRENT_BRANCH"

          echo "✅ Commits gjorda i branch '${COMMIT_BRANCH}'"
        fi

    - name: Trigger HTML export workflow
      if: (inputs.enable_git_commit != 'false' && steps.commit_changes.outputs.has_changes == 'true' && steps.commit_changes.outputs.push_success == 'true') || (inputs.enable_git_commit == 'false')
      uses: actions/github-script@v6
      with:
        github-token: ${{ secrets.GITHUB_TOKEN }}
        script: |
          // Always use the fixed branch name
          const sourceRef = '${{ inputs.branch_name || 'workflow-artifact-data' }}';

          github.rest.actions.createWorkflowDispatch({
            owner: context.repo.owner,
            repo: context.repo.repo,
            workflow_id: 'html-export-workflow.yml',
            ref: sourceRef || context.ref,
            inputs: {
              source_ref: sourceRef || 'workflow-artifact-data'
            }
          })

    - name: Report push failure
      if: steps.commit_changes.outputs.has_changes == 'true' && steps.commit_changes.outputs.push_success == 'false'
      run: |
        echo "::warning::Git push misslyckades: ${{ steps.commit_changes.outputs.push_error }}"
        echo "HTML export workflow kommer inte att triggas på grund av push-fel."