gh-pages.yml

name: Deploy Jekyll

on:
  push:
    branches: ["main"]
  workflow_dispatch:

permissions:
  contents: write
  pages: write
  id-token: write

concurrency:
  group: 'gh-pages'
  cancel-in-progress: false

jobs:
  build:
    runs-on: ubuntu-latest
    environment: github-pages
    steps:
      - name: Checkout Repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 5

      - name: Setup Python 3.10.x
        uses: actions/setup-python@v4
        with:
          python-version: "3.10.x"

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

      - name: Update Notes Links
        id: update_notes_links
        run: |
          OUTPUT=$(python scripts/generate/update_notes_link.py)
          if [[ "$OUTPUT" == *"Notes files changed, regenerating notes links."* ]]; then
            echo "notes_updated=true" >> "$GITHUB_OUTPUT"
          else
            echo "notes_updated=false" >> "$GITHUB_OUTPUT"
          fi
      
      - name: Commit Notes Link Changes
        if: steps.update_notes_links.outputs.notes_updated == 'true'
        run: |
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"
          git add original/2025-01-11-notes-en.md
          git diff --cached --quiet || git commit -m "chore(notes): Update notes links"
          git push || {
            echo "Push failed, attempting pull and merge"
            git pull --rebase
            git push
          }
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      - name: Update Language Files
        id: updated_lang_files
        run: |
          DRY_RUN_LANG_OUTPUT=$(python scripts/translation/update_lang.py --dry_run)
          TOTAL_POSTS=$(echo "$DRY_RUN_LANG_OUTPUT" | grep "Total Markdown files to process:" | awk '{print $NF}')
          echo "Total posts to process: $TOTAL_POSTS"

          if [[ "$TOTAL_POSTS" -eq 0 ]]; then
            echo "No language files to update."
          else
            for i in $(seq 1 "$((2 + TOTAL_POSTS / 9 + (TOTAL_POSTS % 9 != 0)))"); do
              python scripts/translation/update_lang.py --max_files 9 --model mistral
              git config user.name "github-actions[bot]"
              git config user.email "github-actions[bot]@users.noreply.github.com"
              git add _posts/**/*.md
              git diff --cached --quiet || git commit -m "chore(lang): Update language files"
              git push || {
                echo "Push failed, attempting pull and merge"
                git pull --rebase
                git push
              }
            done
          fi
        env:
          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}          
          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}

      - name: Dry Run Pdf Files
        id: dry_run_pdf
        run: |
          DRY_RUN_PDF_OUTPUT=$(python scripts/pdf/update_pdf.py --max_files 1000 --dry_run)
          echo "$DRY_RUN_PDF_OUTPUT" 

          if [[ "$DRY_RUN_PDF_OUTPUT" == *'Total Markdown files to process: 0'* ]]; then
            echo "pdf_updated=false" >> "$GITHUB_OUTPUT"
          else
            echo "pdf_updated=true" >> "$GITHUB_OUTPUT"
          fi

      - name: Install Microsoft Core Fonts
        if: steps.dry_run_pdf.outputs.pdf_updated == 'true'      
        run: |
          sudo apt-get install -y ttf-mscorefonts-installer
          fc-cache -fv

      - name: Install Noto Fonts
        if: steps.dry_run_pdf.outputs.pdf_updated == 'true'      
        run: |
          sudo apt-get install -y fonts-noto

      - name: Install Noto CJK
        if: steps.dry_run_pdf.outputs.pdf_updated == 'true'      
        run: |
          sudo apt-get install -y fonts-noto-cjk

      - name: Install DejaVu Fonts
        if: steps.dry_run_pdf.outputs.pdf_updated == 'true'      
        run: |
          sudo apt-get install -y fonts-dejavu

      - name: List Installed Fonts
        if: steps.dry_run_pdf.outputs.pdf_updated == 'true'      
        run: fc-list

      - name: Setup TeX Live
        if: steps.dry_run_pdf.outputs.pdf_updated == 'true'      
        uses: teatimeguest/setup-texlive-action@v3
        with:
          packages: |
            xeCJK
            etoolbox
            adjustbox
            roboto
            sourcesanspro
            fontawesome5
            tcolorbox
            setspace
            unicode-math
            fancyvrb
            olyglossia
            polyglossia
            bidi
            booktabs
            footnote

      - name: Install Pandoc
        if: steps.dry_run_pdf.outputs.pdf_updated == 'true'      
        run: sudo apt-get update && sudo apt-get install -y pandoc

      - name: Run Pdf-Pipeline.py
        if: steps.dry_run_pdf.outputs.pdf_updated == 'true'
        run: |
          python scripts/pdf/update_pdf.py --max_files 1000
          
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"
          git add assets/pdfs/**/*.pdf
          git diff --cached --quiet || git commit -m "chore(pdf): Update PDF files"
          
          git push || {
            echo "Push failed, attempting pull and merge"
            git pull --rebase
            git push
          }
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      - name: Authenticate with GCP
        uses: google-github-actions/auth@v1
        with:
          credentials_json: ${{ secrets.GCP_SA_KEY }}

      - name: Dry run Audio Pipeline
        id: dry_run_audio
        run: |
          DRY_RUN_OUTPUT=$(python scripts/audio/audio_pipeline.py --task posts --n 2 --dry_run)
          echo "$DRY_RUN_OUTPUT"
          FILES_PROCESSED=$(echo "$DRY_RUN_OUTPUT" | grep "Processing complete!" | awk '{print $3}' | cut -d'/' -f1)
          TOTAL_FILES=$(echo "$DRY_RUN_OUTPUT" | grep "Processing complete!" | awk '{print $3}' | cut -d'/' -f2)

          if [[ "$FILES_PROCESSED" -gt 0 ]]; then
            echo "audio_updated=true" >> "$GITHUB_OUTPUT"
          else
            echo "audio_updated=false" >> "$GITHUB_OUTPUT"
          fi

      - name: Dry run Conversation Pipeline
        id: dry_run_conversation
        run: |
          DRY_RUN_CONVERSATION_OUTPUT=$(python scripts/audio/conversation_pipeline.py --dry_run)
          echo "$DRY_RUN_CONVERSATION_OUTPUT"
          CONVERSATIONS_PROCESSED=$(echo "$DRY_RUN_CONVERSATION_OUTPUT" | grep "Processing complete!" | awk '{print $3}' | cut -d'/' -f1)
          TOTAL_CONVERSATIONS=$(echo "$DRY_RUN_CONVERSATION_OUTPUT" | grep "Processing complete!" | awk '{print $3}' | cut -d'/' -f2)

          if [[ "$CONVERSATIONS_PROCESSED" -gt 0 ]]; then
            echo "conversation_updated=true" >> "$GITHUB_OUTPUT"
          else
            echo "conversation_updated=false" >> "$GITHUB_OUTPUT"
          fi

      - name: Install FFmpeg
        if: steps.dry_run_audio.outputs.audio_updated == 'true' || steps.dry_run_conversation.outputs.conversation_updated == 'true'
        run: |
          sudo apt-get update
          sudo apt-get install -y ffmpeg

      - name: Run Audio Pipeline
        if: steps.dry_run_audio.outputs.audio_updated == 'true'
        run: |
          python scripts/audio/audio_pipeline.py --task posts --n 2 --max_files 20          

      - name: Commit generated audio files
        if: steps.dry_run_audio.outputs.audio_updated == 'true'
        run: |
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"
          git add assets/audios/*.mp3
          git diff --cached --quiet || git commit -m "feat(audio): Add generated audio files"
          git push || {
            echo "Push failed, attempting pull and merge"
            git pull --rebase
            git push
          }
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      - name: Update audio Flags
        if: steps.dry_run_audio.outputs.audio_updated == 'true'
        run: |
          python scripts/audio/audio_flag.py
          python scripts/feed/feed.py --lang en
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"
          git add _posts/**/*.md
          git add *.xml
          git diff --quiet --staged || git commit -m "feat(audio): Update Audio flag and update audo feed"
          git push || {
            echo "Push failed, attempting pull and merge"
            git pull --rebase
            git push
          }
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      - name: Run Conversation Pipeline
        if: steps.dry_run_conversation.outputs.conversation_updated == 'true'
        run: |
          python scripts/audio/conversation_pipeline.py
          python scripts/feed/conversation_feed.py
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"
          git add assets/conversations/*.mp3
          git add *.xml          
          git diff --cached --quiet || git commit -m "feat(audio): Add generated conversation audio files"
          git push || {
            echo "Push failed, attempting pull and merge"
            git pull --rebase
            git push
          }
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      - name: Clean Up Credentials
        run: |
          rm -f ./gha-creds-*.json            

      - name: Update Release Hash
        run: python scripts/release/update_release.py

      - name: Setup Pages
        uses: actions/configure-pages@v5

      - name: Build with Jekyll
        uses: actions/jekyll-build-pages@v1
        with:
          source: ./
          destination: ./_site

      - name: Upload Artifact
        uses: actions/upload-pages-artifact@v3

      - name: Deploy to GitHub Pages
        id: deployment
        uses: actions/deploy-pages@v4

      - name: Send Telegram Message
        run: |
          python scripts/release/telegram_bot.py --job send_message
        env:
          TELEGRAM_BOT_API_KEY: ${{ secrets.TELEGRAM_BOT_API_KEY }}