Create devdocs as .pdf and .html

.github/workflows/convert-docs-to-pdf.yml

@@ -0,0 +1,205 @@
+name: Convert DevDocs to PDF
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - '.github/workflows/convert-docs-to-pdf.yml'
+  pull_request:
+     # always build - therefore disabled
+#    paths:
+#      - '.github/workflows/convert-docs-to-pdf.yml'
+
+concurrency:
+  group: "${{ github.workflow }}-${{ github.head_ref || github.ref }}"
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - uses: actions/setup-node@v4
+      with:
+        node-version: '22'
+
+    - uses: awalsh128/cache-apt-pkgs-action@latest
+      with:
+        packages: poppler-utils xmlstarlet
+        version: 1.0
+
+    - run: npm install puppeteer
+
+    - name: Crawl URLs from sitemap
+      run: |
+        set -e
+
+        mkdir -p urls
+
+        # Debug: Check tool versions
+        curl --version
+        xmlstarlet --version
+
+        # Step 1: Download sitemap
+        curl -s https://devdocs.jabref.org/sitemap.xml > urls/sitemap.xml
+        echo "=== sitemap.xml ==="
+        cat urls/sitemap.xml
+
+        # Step 2: Extract <loc> entries using xmlstarlet
+        xmlstarlet sel \
+          -N x="http://www.sitemaps.org/schemas/sitemap/0.9" \
+          -t -m '//x:url/x:loc' -v . -n urls/sitemap.xml \
+          > urls/raw.txt
+        echo "=== raw.txt (raw <loc> entries) ==="
+        cat urls/raw.txt
+
+        # Step 3: Ensure full URLs (prefix relative paths)
+        sed 's|^/|https://devdocs.jabref.org/|' urls/raw.txt > urls/list.txt
+        echo "=== list.txt (final full URLs) ==="
+        cat urls/list.txt
+
+    - name: Download pages as PDFs
+      run: |
+        mkdir pdfs
+        node <<'EOF'
+        const fs = require('fs');
+        const puppeteer = require('puppeteer');
+
+        (async () => {
+            const urls = fs.readFileSync('urls/list.txt', 'utf-8')
+                           .split('\n')
+                           .filter(Boolean);
+
+            const browser = await puppeteer.launch({
+              headless: "new",
+              args: ["--no-sandbox", "--disable-setuid-sandbox"]
+            });
+
+            for (let i = 0; i < urls.length; i++) {
+              const url = urls[i];
+              const urlPath = new URL(url).pathname.replace(/^\/|\/$/g, '');
+              const safeName = decodeURIComponent(urlPath).replace(/\//g, '--') || 'index';
+              const basePath = `pdfs/${safeName.replace(/\.html$/, '')}`;
+
+              console.log(`Rendering ${url} → ${basePath}.html/pdf`);
+
+              const page = await browser.newPage();
+              await page.goto(url, { waitUntil: 'networkidle2' });
+
+              const content = await page.content();
+              fs.writeFileSync(`${basePath}.html`, content);
+
+              await page.pdf({
+                path: `${basePath}.pdf`,
+                format: 'A4',
+                printBackground: true
+              });
+
+              await page.close();
+            }
+
+            await browser.close();
+         })();
+        EOF
+
+    - name: Install TeX Live
+      uses: zauguin/install-texlive@v4
+      with:
+        packages: >
+          bigintcalc
+          bitset
+          catchfile
+          cm
+          epstopdf-pkg
+          eso-pic
+          etexcmds
+          etoolbox
+          gettitlestring
+          graphics
+          graphics-cfg
+          graphics-def
+          hycolor
+          hyperref
+          iftex
+          infwarerr
+          intcalc
+          kvdefinekeys
+          kvoptions
+          kvsetkeys
+          l3backend
+          latex
+          latex-bin
+          latex-fonts
+          latexconfig
+          lm
+          ltxcmds
+          metafont
+          mfware
+          pdfescape
+          pdflscape
+          pdfpages
+          pdftexcmds
+          refcount
+          rerunfilecheck
+          stringenc
+          tools
+          uniquecounter
+          url
+          xcolor
+          xstring
+    - name: Merge PDFs into one PDF file
+      run: |
+        # Currently, filenames with % and # cannot be handled; thus we filter it
+        (echo pdfs/index.pdf; find pdfs/ -type f -name '*.pdf' ! -name 'index.pdf' | grep -v '%' | grep -v '#' | sort) | paste -sd, - > filelist.txt
+        cat filelist.txt
+
+        cat <<EOF > jabref-devdocs.tex
+        \documentclass[a4paper]{article}
+        \usepackage{pdfpages}
+        \usepackage[bookmarks=true,linktoc=all]{hyperref}
+        \usepackage{catchfile}
+        \usepackage{xstring}
+        \usepackage{etoolbox}
+
+        \begin{document}
+
+        \renewcommand{\do}[1]{%
+          \StrBehind{#1}{/}[\filename]%
+          \StrBefore{\filename}{.pdf}[\bookmarktitle]%
+          \clearpage
+          \phantomsection
+          \addcontentsline{toc}{section}{\bookmarktitle}
+          \includepdf[pages=-]{\detokenize{#1}}%
+        }
+
+        \CatchFileDef{\filelist}{filelist.txt}{}
+
+        \pdfbookmark[1]{Contents}{Contents}%
+        \tableofcontents
+
+        \expandafter\docsvlist\expandafter{\filelist}
+
+        \end{document}
+        EOF
+
+        pdflatex -shell-escape jabref-devdocs
+        pdflatex -shell-escape jabref-devdocs
+        mv jabref-devdocs.pdf pdfs/
+
+    - uses: actions/upload-artifact@v4
+      with:
+        name: docs
+        path: pdfs/
+
+    - name: Publish
+      if: github.ref == 'main' || github.head_ref == 'publish-devdocs-as-pdf'
+      uses: peaceiris/actions-gh-pages@v4
+      with:
+        github_token: ${{ secrets.GITHUB_TOKEN }}
+        publish_dir: ./pdfs
+        publish_branch: devdocs
+        force_orphan: true
+        enable_jekyll: false