Refactor code formatting and improve error handling in htmlDocumentConverter

services/modules/convert/convert.js

@@ -1,9 +1,9 @@
-const fs = require('fs');
-const path = require('path');
-const puppeteer = require('puppeteer');
-const htmlToDocx = require('html-to-docx');
-const { execSync } = require('child_process');
-const os = require('os');
+const fs = require("fs");
+const path = require("path");
+const puppeteer = require("puppeteer");
+const htmlToDocx = require("html-to-docx");
+const { execSync } = require("child_process");
+const os = require("os");
 
 const outputDir = path.join(__dirname, "../../../storage/documents");
 
@@ -14,7 +14,7 @@ if (!fs.existsSync(outputDir)) {
 async function showSaveDialog(defaultName, format) {
   const platform = os.platform();
 
-    if (platform === 'darwin') {
+  if (platform === "darwin") {
     // macOS
     const applescript = `
             set defaultName to "${defaultName}.${format}"
@@ -23,13 +23,15 @@ async function showSaveDialog(defaultName, format) {
         `;
 
     try {
-            const result = execSync(`osascript -e '${applescript}'`, { encoding: 'utf8' });
+      const result = execSync(`osascript -e '${applescript}'`, {
+        encoding: "utf8",
+      });
       return result.trim();
     } catch (err) {
       if (err.status === 1) return null; // User canceled
       throw err;
     }
-    } else if (platform === 'win32') {
+  } else if (platform === "win32") {
     const safeName = decodeURIComponent(defaultName);
 
     const powershell = `
@@ -44,8 +46,8 @@ async function showSaveDialog(defaultName, format) {
 
     try {
       const result = execSync(
-            `powershell -NoProfile -Command "${powershell.replace(/\r?\n/g, ' ')}"`,
-            { encoding: 'utf8' }
+        `powershell -NoProfile -Command "${powershell.replace(/\r?\n/g, " ")}"`,
+        { encoding: "utf8" },
       );
       return result.trim() || null;
     } catch (err) {
@@ -57,19 +59,19 @@ async function showSaveDialog(defaultName, format) {
     try {
       const result = execSync(
         `zenity --file-selection --save --confirm-overwrite --filename="${defaultName}.${format}"`,
-                { encoding: 'utf8' }
+        { encoding: "utf8" },
       );
       return result.trim();
     } catch (err) {
       try {
         const result = execSync(
           `kdialog --getsavefilename . "${defaultName}.${format}"`,
-                    { encoding: 'utf8' }
+          { encoding: "utf8" },
         );
         return result.trim();
       } catch (err2) {
         // Fallback
-                return path.join(os.homedir(), 'Downloads', `${defaultName}.${format}`);
+        return path.join(os.homedir(), "Downloads", `${defaultName}.${format}`);
       }
     }
   }
@@ -89,11 +91,10 @@ const module_exports = {
    * @param {string} [options.outputName] - Optional output filename (without extension)
    * @param {boolean} [options.showDialog] - Show save dialog (default: false in module mode, true in CLI mode)
    */
-async convert({ inputPath, format = 'pdf', outputName, showDialog = false }) {
+  async convert({ inputPath, format = "pdf", outputName, showDialog = false }) {
+    format = format.toLowerCase().replace(".", ""); // <-- FIX
 
-    format = format.toLowerCase().replace('.', ''); // <-- FIX
-
-    if (!['pdf', 'docx', 'html', 'txt'].includes(format)) {
+    if (!["pdf", "docx", "html", "txt"].includes(format)) {
       throw new Error(`Unsupported format: ${format}`);
     }
     if (!fs.existsSync(inputPath)) {
@@ -109,7 +110,7 @@ async convert({ inputPath, format = 'pdf', outputName, showDialog = false }) {
       // Zeige nativen Dialog
       outputFile = await showSaveDialog(baseName, format);
       if (!outputFile) {
-                console.log('Speichervorgang abgebrochen.');
+        console.log("Speichervorgang abgebrochen.");
         return null;
       }
     } else {
@@ -117,23 +118,23 @@ async convert({ inputPath, format = 'pdf', outputName, showDialog = false }) {
       outputFile = path.join(outputDir, `${baseName}.${format.toLowerCase()}`);
     }
 
-        let htmlContent = fs.readFileSync(inputPath, 'utf8');
+    let htmlContent = fs.readFileSync(inputPath, "utf8");
 
     // Remove <think> tags if present
-        htmlContent = htmlContent.replace(/<think>[\s\S]*?<\/think>/gi, '');
+    htmlContent = htmlContent.replace(/<think>[\s\S]*?<\/think>/gi, "");
 
     switch (format.toLowerCase()) {
-            case 'html':
-                fs.writeFileSync(outputFile, htmlContent, 'utf8');
+      case "html":
+        fs.writeFileSync(outputFile, htmlContent, "utf8");
         break;
-            case 'pdf':
+      case "pdf":
         await this.htmlToPDF(htmlContent, outputFile);
         break;
-            case 'docx':
+      case "docx":
         await this.htmlToDOCX(htmlContent, outputFile);
         break;
-            case 'txt':
-                fs.writeFileSync(outputFile, this.htmlToTXT(htmlContent), 'utf8');
+      case "txt":
+        fs.writeFileSync(outputFile, this.htmlToTXT(htmlContent), "utf8");
         break;
       default:
         throw new Error(`Unsupported format: ${format}`);
@@ -145,31 +146,61 @@ async convert({ inputPath, format = 'pdf', outputName, showDialog = false }) {
 
   // HTML → PDF
   async htmlToPDF(html, outputPath) {
-        const browser = await puppeteer.launch({ 
+    let browser;
+    try {
+      browser = await puppeteer.launch({
         headless: true,
-            args: ['--no-sandbox', '--disable-setuid-sandbox']
+        args: ["--no-sandbox", "--disable-setuid-sandbox"],
       });
+
       const page = await browser.newPage();
-        await page.setContent(html, { waitUntil: 'networkidle0' });
+      await page.setContent(html, { waitUntil: "networkidle0" });
       await page.pdf({
         path: outputPath,
-            format: 'A4', 
+        format: "A4",
         printBackground: true,
-            margin: { top: '20mm', right: '20mm', bottom: '20mm', left: '20mm' }
+        margin: {
+          top: "20mm",
+          right: "20mm",
+          bottom: "20mm",
+          left: "20mm",
+        },
       });
+    } finally {
+      if (browser) {
         await browser.close();
+      }
+    }
   },
 
   // HTML → DOCX
   async htmlToDOCX(html, outputPath) {
-        const buffer = await htmlToDocx(html);
+    try {
+      // html‑to‑docx library converts HTML string into a Word .docx buffer
+      // Usage from html‑to‑docx docs:
+      // await HTMLtoDOCX(htmlString, headerHTMLString, documentOptions, footerHTMLString)  [oai_citation:0‡GitHub](https://github.com/privateOmega/html-to-docx?utm_source=chatgpt.com)
+      const buffer = await htmlToDocx(html, null, {
+        table: { row: { cantSplit: true } },
+      });
       fs.writeFileSync(outputPath, buffer);
+    } catch (err) {
+      throw new Error(`DOCX conversion failed: ${err.message}`);
+    }
   },
 
-    // HTML → TXT (rudimentär)
+  // HTML → TXT
   htmlToTXT(html) {
-        return html.replace(/<[^>]*>/g, '').replace(/\s+\n/g, '\n').trim();
-    }
+    // A decent plain text conversion: strip tags and collapse whitespace
+    // If you want more advanced extraction consider using a library like `html-to-text` or `strip-html`  [oai_citation:1‡GitHub](https://github.com/html-to-text/node-html-to-text?utm_source=chatgpt.com)
+    return (
+      html
+        // Remove all tags
+        .replace(/<[^>]+>/g, "")
+        // Convert multiple whitespace into single spaces
+        .replace(/\s+/g, " ")
+        .trim()
+    );
+  },
 };
 
 module.exports = module_exports;
@@ -179,24 +210,26 @@ if (require.main === module) {
   (async () => {
     const args = process.argv.slice(2);
     if (args.length < 1) {
-            console.log('Usage: node htmlDocumentConverter.js <input.html> [format]');
-            console.log('Formats: pdf (default), docx, html, txt');
-            console.log('');
-            console.log('Ein nativer "Speichern unter" Dialog wird automatisch geöffnet.');
+      console.log("Usage: node htmlDocumentConverter.js <input.html> [format]");
+      console.log("Formats: pdf (default), docx, html, txt");
+      console.log("");
+      console.log(
+        'Ein nativer "Speichern unter" Dialog wird automatisch geöffnet.',
+      );
       process.exit(1);
     }
 
     const inputPath = args[0];
-        const format = args[1] || 'pdf';
+    const format = args[1] || "pdf";
 
     try {
       await module_exports.convert({
         inputPath,
         format,
-                showDialog: true  
+        showDialog: true,
       });
     } catch (err) {
-            console.error('Konvertierung fehlgeschlagen:', err.message);
+      console.error("Konvertierung fehlgeschlagen:", err.message);
       process.exit(1);
     }
   })();