hacktricks-cloud/.github/workflows/build_master.yml

name: Build Master

on:
  push:
    branches:
      - master
    paths-ignore:
      - 'scripts/**'
      - '.gitignore'
      - '.github/**'
      - 'book/**'
  workflow_dispatch:

concurrency: build_master

permissions:
  packages: write
  id-token: write
  contents: write

jobs:
  run-translation:
    runs-on: ubuntu-latest
    container:
      image: ghcr.io/hacktricks-wiki/hacktricks-cloud/translator-image:latest
    environment: prod

    steps:
      - name: Checkout code
        uses: actions/checkout@v4
        with:
          fetch-depth: 0 #Needed to download everything to be able to access the master & language branches
      
      # Build the mdBook
      - name: Build mdBook
        run: MDBOOK_BOOK__LANGUAGE=en mdbook build || (echo "Error logs" && cat hacktricks-preprocessor-error.log && echo "" && echo "" && echo "Debug logs" && (cat hacktricks-preprocessor.log | tail -n 20) && exit 1)
      
      - name: Push search index to hacktricks-searchindex repo
        shell: bash
        env:
          PAT_TOKEN: ${{ secrets.PAT_TOKEN }}
        run: |
          set -euo pipefail

          ASSET="book/searchindex.js"
          TARGET_REPO="HackTricks-wiki/hacktricks-searchindex"
          FILENAME="searchindex-cloud-en.js"

          if [ ! -f "$ASSET" ]; then
            echo "Expected $ASSET to exist after build" >&2
            exit 1
          fi

          TOKEN="${PAT_TOKEN}"
          if [ -z "$TOKEN" ]; then
            echo "No PAT_TOKEN available" >&2
            exit 1
          fi

          # Clone the searchindex repo
          git clone https://x-access-token:${TOKEN}@github.com/${TARGET_REPO}.git /tmp/searchindex-repo
          
          cd /tmp/searchindex-repo
          git config user.name "GitHub Actions"
          git config user.email "github-actions@github.com"
          
          # Save all current files from main branch to temp directory
          mkdir -p /tmp/searchindex-backup
          cp -r * /tmp/searchindex-backup/ 2>/dev/null || true
          
          # Create a fresh orphan branch (no history)
          git checkout --orphan new-main
          
          # Remove all files from git index (but keep working directory)
          git rm -rf . 2>/dev/null || true
          
          # Restore all the files from backup (keeps all language files)
          cp -r /tmp/searchindex-backup/* . 2>/dev/null || true
          
          # Now update/add our English searchindex file
          # First, compress the original file (in the build directory)
          cd "${GITHUB_WORKSPACE}"
          gzip -9 -k -f "$ASSET"
          
          # Show compression stats
          ORIGINAL_SIZE=$(wc -c < "$ASSET")
          COMPRESSED_SIZE=$(wc -c < "${ASSET}.gz")
          RATIO=$(awk "BEGIN {printf \"%.1f\", ($COMPRESSED_SIZE / $ORIGINAL_SIZE) * 100}")
          echo "Compression: ${ORIGINAL_SIZE} bytes -> ${COMPRESSED_SIZE} bytes (${RATIO}%)"
          
          # XOR encrypt the compressed file
          KEY='Prevent_Online_AVs_From_Flagging_HackTricks_Search_Gzip_As_Malicious_394h7gt8rf9u3rf9g'
          cat > /tmp/xor_encrypt.py << 'EOF'
          import sys
          key = sys.argv[1]
          input_file = sys.argv[2]
          output_file = sys.argv[3]
          with open(input_file, 'rb') as f:
              data = f.read()
          key_bytes = key.encode('utf-8')
          encrypted = bytearray(len(data))
          for i in range(len(data)):
              encrypted[i] = data[i] ^ key_bytes[i % len(key_bytes)]
          with open(output_file, 'wb') as f:
              f.write(encrypted)
          print(f"Encrypted: {len(data)} bytes")
          EOF
          python3 /tmp/xor_encrypt.py "$KEY" "${ASSET}.gz" "${ASSET}.gz.enc"
          
          # Copy ONLY the encrypted .gz version to the searchindex repo (no uncompressed .js)
          cd /tmp/searchindex-repo
          cp "${GITHUB_WORKSPACE}/${ASSET}.gz.enc" "${FILENAME}.gz"
          
          # Stage all files
          git add -A
          
          # Commit with timestamp
          TIMESTAMP=$(date -u +"%Y-%m-%d %H:%M:%S UTC")
          git commit -m "Update searchindex files - ${TIMESTAMP}" --allow-empty
          
          # Force push to replace master branch (deletes history, keeps all files)
          git push -f origin new-main:master
          
          echo "Successfully reset repository history and pushed all searchindex files"

      # Login in AWs
      - name: Configure AWS credentials using OIDC
        uses: aws-actions/configure-aws-credentials@v3
        with:
          role-to-assume: ${{ secrets.AWS_ROLE_ARN }}
          aws-region: us-east-1
      
      # Sync the build to S3
      - name: Sync to S3
        run: aws s3 sync ./book s3://hacktricks-cloud/en --delete