feat: add markdown-to-pdf converter with Puppeteer

Introduce a Node.js CLI tool that converts Markdown files to styled PDFs using `marked` for parsing and `puppeteer` for rendering. - Add `md-to-pdf.js` as the main conversion script with: - CLI argument handling for input/output file paths - Automatic output directory creation alongside the input file - Pre-processing to strip thematic breaks (`---`) before headings - Embedded CSS for clean, print-ready styling (headings, tables, code blocks, blockquotes, page breaks, etc.) - PDF generation via Puppeteer with A4 format and custom margins - Add `.gitignore` to exclude `node_modules/` and `output/` directories - Add `package-lock.json` with resolved dependencies (marked, puppeteer)
2026-04-15 11:28:16 -04:00
parent ffeaea1f38
commit 0f09b30164
4 changed files with 1416 additions and 0 deletions
@@ -0,0 +1,2 @@
+node_modules/
+output/
@@ -0,0 +1,243 @@
+#!/usr/bin/env node
+
+const fs = require('fs');
+const path = require('path');
+const { marked } = require('marked');
+const puppeteer = require('puppeteer');
+
+const inputFile = process.argv[2];
+
+if (!inputFile) {
+  console.error('Usage: node md-to-pdf.js <input.md> [output/custom.pdf]');
+  process.exit(1);
+}
+
+if (!fs.existsSync(inputFile)) {
+  console.error(`File not found: ${inputFile}`);
+  process.exit(1);
+}
+
+const outputDir = path.resolve(path.dirname(inputFile), 'output');
+if (!fs.existsSync(outputDir)) fs.mkdirSync(outputDir, { recursive: true });
+
+const baseName = path.basename(inputFile, path.extname(inputFile)) + '.pdf';
+const outputFile = process.argv[3]
+  ? path.resolve(process.argv[3])
+  : path.join(outputDir, baseName);
+
+const rawMarkdown = fs.readFileSync(inputFile, 'utf8');
+// Remove a thematic break (---) when it is immediately followed by a heading
+// (with only blank lines in between), so it doesn't render as <hr>.
+const markdown = rawMarkdown.replace(/^---[ \t]*$(\n[ \t]*)*(?=^#{1,6}\s)/gm, '');
+const body = marked(markdown);
+
+const html = `<!DOCTYPE html>
+<html lang="fr">
+<head>
+  <meta charset="UTF-8">
+  <style>
+    *, *::before, *::after {
+      box-sizing: border-box;
+    }
+
+    html, body {
+      margin: 0;
+      padding: 0;
+      background: #ffffff;
+      color: #1a1a1a;
+      font-family: 'Segoe UI', system-ui, -apple-system, sans-serif;
+      font-size: 14px;
+      line-height: 1.7;
+    }
+
+    .page {
+      max-width: 860px;
+      margin: 0 auto;
+      padding: 40px 50px;
+    }
+
+    /* ---------- Headings ---------- */
+    h1, h2, h3, h4, h5, h6 {
+      font-weight: 700;
+      line-height: 1.3;
+      margin-top: 2em;
+      margin-bottom: 0.5em;
+      break-after: avoid;
+    }
+    .page > h1:first-child,
+    .page > h2:first-child,
+    .page > h3:first-child {
+      margin-top: 0;
+    }
+    h1 { font-size: 2em;   border-bottom: 2px solid #e0e0e0; padding-bottom: 0.3em; }
+    h2 { font-size: 1.5em; border-bottom: 1px solid #e0e0e0; padding-bottom: 0.2em; }
+    h3 { font-size: 1.2em; }
+    h4 { font-size: 1em; }
+
+    /* ---------- Paragraphs & text ---------- */
+    p { margin: 0.6em 0; }
+
+    a { color: #0969da; text-decoration: none; }
+    a:hover { text-decoration: underline; }
+
+    strong { font-weight: 700; }
+    em     { font-style: italic; }
+
+    /* ---------- Code ---------- */
+    code {
+      font-family: 'JetBrains Mono', 'Fira Code', 'Cascadia Code', Consolas, monospace;
+      font-size: 0.88em;
+      background: #f3f4f6;
+      border: 1px solid #e5e7eb;
+      border-radius: 4px;
+      padding: 0.15em 0.4em;
+    }
+
+    pre {
+      background: #f6f8fa;
+      border: 1px solid #d1d5db;
+      border-radius: 6px;
+      padding: 1em 1.2em;
+      overflow-x: auto;
+      break-inside: avoid;
+      margin: 1em 0;
+    }
+
+    pre code {
+      background: none;
+      border: none;
+      padding: 0;
+      font-size: 0.85em;
+      line-height: 1.6;
+    }
+
+    /* ---------- Blockquote ---------- */
+    blockquote {
+      margin: 1em 0;
+      padding: 0.6em 1.2em;
+      border-left: 4px solid #0969da;
+      background: #f0f6ff;
+      border-radius: 0 6px 6px 0;
+      break-inside: avoid;
+      color: #444;
+    }
+    blockquote p { margin: 0; }
+
+    /* ---------- Lists ---------- */
+    ul, ol {
+      margin: 0.6em 0;
+      padding-left: 1.8em;
+    }
+    li { margin: 0.25em 0; }
+
+    /* ---------- Horizontal rule ---------- */
+    hr {
+      border: none;
+      border-top: 1px solid #e0e0e0;
+      margin: 2em 0;
+    }
+
+    /* ---------- Tables ---------- */
+    table {
+      width: 100%;
+      border-collapse: collapse;
+      margin: 1em 0;
+      font-size: 0.92em;
+      break-inside: avoid;
+    }
+
+    thead {
+      background: #f0f1f3;
+    }
+
+    th, td {
+      border: 1px solid #d1d5db;
+      padding: 0.55em 0.9em;
+      text-align: left;
+      vertical-align: top;
+    }
+
+    th {
+      font-weight: 600;
+      color: #374151;
+    }
+
+    tbody tr:nth-child(even) {
+      background: #f9fafb;
+    }
+
+    /* ---------- Images ---------- */
+    img {
+      max-width: 100%;
+      height: auto;
+      border-radius: 6px;
+      break-inside: avoid;
+    }
+
+    /* ---------- Page-break hints ---------- */
+    p, li, blockquote, pre, img {
+      break-inside: avoid;
+    }
+
+    /* Avoid orphan headings at the bottom of a page */
+    h1 + *, h2 + *, h3 + *, h4 + *, h5 + *, h6 + * {
+      break-before: avoid;
+    }
+  </style>
+</head>
+<body>
+  <div class="page">
+    ${body}
+  </div>
+</body>
+</html>`;
+
+(async () => {
+  const browser = await puppeteer.launch({ args: ['--no-sandbox'] });
+  const page = await browser.newPage();
+
+  // Viewport très haut pour que getBoundingClientRect() retourne des coords absolues
+  await page.setViewport({ width: 794, height: 100000 });
+  await page.setContent(html, { waitUntil: 'networkidle0' });
+
+  // Si un h2 tombe dans la moitié basse d'une page A4, on le pousse à la page suivante.
+  // On simule la pagination avec un décalage cumulatif : chaque saut de page forcé
+  // avance les positions de tous les titres suivants, évitant l'effet cascade.
+  await page.evaluate(() => {
+    const MM_TO_PX   = 96 / 25.4;
+    const PAGE_H     = Math.round(297 * MM_TO_PX);  // 1123px — hauteur brute A4
+    const MARGIN_TOP = Math.round(15  * MM_TO_PX);  //   57px
+    const MARGIN_BOT = Math.round(15  * MM_TO_PX);  //   57px
+    const CONTENT_H  = PAGE_H - MARGIN_TOP - MARGIN_BOT; // ~1009px par page
+
+    let cumulativeShift = 0;
+
+    document.querySelectorAll('h2').forEach(h => {
+      // Position originale (layout écran, sans sauts de page CSS)
+      const originalY  = h.getBoundingClientRect().top;
+      // Position effective après les sauts de page déjà décidés avant ce titre
+      const effectiveY = originalY + cumulativeShift;
+      const pageNum    = Math.floor(effectiveY / CONTENT_H);
+      const posInPage  = effectiveY % CONTENT_H;
+
+      if (posInPage > CONTENT_H / 2) {
+        h.style.pageBreakBefore = 'always';
+        // Ce titre est repoussé au début de la page suivante :
+        // on calcule le décalage ajouté et on l'accumule pour les titres suivants
+        const newEffectiveY  = (pageNum + 1) * CONTENT_H;
+        cumulativeShift     += newEffectiveY - effectiveY;
+      }
+    });
+  });
+
+  await page.pdf({
+    path: outputFile,
+    format: 'A4',
+    printBackground: true,
+    margin: { top: '15mm', bottom: '15mm', left: '10mm', right: '10mm' },
+  });
+
+  await browser.close();
+
+  console.log(`PDF generated: ${outputFile}`);
+})();
@@ -0,0 +1,21 @@
+{
+  "name": "markdown-to-pdf",
+  "version": "1.0.0",
+  "description": "",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "repository": {
+    "type": "git",
+    "url": "ssh://gitea@192.168.1.62/hykocx/markdown-to-pdf.git"
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "type": "commonjs",
+  "dependencies": {
+    "marked": "^18.0.0",
+    "puppeteer": "^24.40.0"
+  }
+}