Merge 83f330348b into d22b7e56eb

public/locales/en/pdf.json

@@ -63,6 +63,18 @@
     "shortDescription": "Convert PDF into PNG images",
     "title": "PDF to PNG"
   },
+  "pdfToWord": {
+    "description": "Convert PDF documents to editable Word (.docx) format while preserving text, formatting, and layout.",
+    "longDescription": "Upload your PDF and convert it to an editable Word document directly in your browser. This tool extracts text, images, and formatting to create a .docx file that can be opened and edited in Microsoft Word or compatible applications. No data is uploaded — everything runs locally.",
+    "shortDescription": "Convert PDF files to editable Word documents",
+    "title": "PDF to Word",
+    "convertingPdf": "Converting PDF to Word...",
+    "resultTitle": "Converted Word Document",
+    "toolInfo": {
+      "description": "This tool converts PDF documents to editable Word (.docx) format. The conversion preserves text content, basic formatting, and images when possible. The resulting Word document can be opened and edited in Microsoft Word or compatible applications.",
+      "title": "PDF to Word Converter"
+    }
+  },
   "protectPdf": {
     "description": "Add password protection to your PDF files securely in your browser",
     "shortDescription": "Password protect PDF files securely",

src/pages/tools/pdf/index.ts

@@ -7,6 +7,7 @@ import { tool as compressPdfTool } from './compress-pdf/meta';
 import { tool as protectPdfTool } from './protect-pdf/meta';
 import { meta as pdfToEpub } from './pdf-to-epub/meta';
 import { tool as pdfEditor } from './editor/meta';
+import { tool as pdfToWord } from './pdf-to-word/meta';
 
 export const pdfTools: DefinedTool[] = [
   pdfEditor,
@@ -16,5 +17,6 @@ export const pdfTools: DefinedTool[] = [
   protectPdfTool,
   mergePdf,
   pdfToEpub,
-  pdfPdfToPng
+  pdfPdfToPng,
+  pdfToWord
 ];

src/pages/tools/pdf/pdf-to-word/index.tsx

@@ -0,0 +1,61 @@
+import { useState } from 'react';
+import ToolContent from '@components/ToolContent';
+import ToolPdfInput from '@components/input/ToolPdfInput';
+import ToolFileResult from '@components/result/ToolFileResult';
+import { ToolComponentProps } from '@tools/defineTool';
+import { convertPdfToWord } from './service';
+
+export default function PdfToWord({ title }: ToolComponentProps) {
+  const [input, setInput] = useState<File | null>(null);
+  const [wordFile, setWordFile] = useState<File | null>(null);
+  const [loading, setLoading] = useState(false);
+
+  const compute = async (_: {}, file: File | null) => {
+    if (!file) return;
+
+    setLoading(true);
+    setWordFile(null);
+
+    try {
+      const convertedFile = await convertPdfToWord(file);
+      setWordFile(convertedFile);
+    } catch (err) {
+      console.error('Conversion failed:', err);
+      // You could add error handling here with a snackbar or alert
+    } finally {
+      setLoading(false);
+    }
+  };
+
+  return (
+    <ToolContent
+      title={title}
+      input={input}
+      setInput={setInput}
+      initialValues={{}}
+      compute={compute}
+      inputComponent={
+        <ToolPdfInput
+          value={input}
+          onChange={setInput}
+          accept={['application/pdf']}
+          title="Upload a PDF"
+        />
+      }
+      resultComponent={
+        <ToolFileResult
+          title="Converted Word Document"
+          value={wordFile}
+          loading={loading}
+          loadingText="Converting PDF to Word..."
+        />
+      }
+      getGroups={null}
+      toolInfo={{
+        title: 'PDF to Word Converter',
+        description:
+          'This tool converts PDF documents to editable Word (.docx) format. The conversion preserves text content, basic formatting, and images when possible. The resulting Word document can be opened and edited in Microsoft Word or compatible applications.'
+      }}
+    />
+  );
+}

src/pages/tools/pdf/pdf-to-word/meta.ts

@@ -0,0 +1,18 @@
+import { defineTool } from '@tools/defineTool';
+import { lazy } from 'react';
+
+export const tool = defineTool('pdf', {
+  i18n: {
+    name: 'pdf:pdfToWord.title',
+    description: 'pdf:pdfToWord.description',
+    shortDescription: 'pdf:pdfToWord.shortDescription',
+    longDescription: 'pdf:pdfToWord.longDescription',
+    userTypes: ['generalUsers']
+  },
+
+  path: 'pdf-to-word',
+  icon: 'material-symbols:description', // Word document icon
+
+  keywords: ['pdf', 'word', 'docx', 'convert', 'document', 'text', 'office'],
+  component: lazy(() => import('./index'))
+});

src/pages/tools/pdf/pdf-to-word/service.ts

@@ -0,0 +1,90 @@
+import * as pdfjsLib from 'pdfjs-dist';
+import pdfjsWorker from 'pdfjs-dist/build/pdf.worker.min?url';
+
+pdfjsLib.GlobalWorkerOptions.workerSrc = pdfjsWorker;
+
+interface TextItem {
+  str: string;
+  dir: string;
+  width: number;
+  height: number;
+  transform: number[];
+  fontName: string;
+  hasEOL: boolean;
+}
+
+interface TextContent {
+  items: TextItem[];
+  styles: Record<string, any>;
+}
+
+export async function convertPdfToWord(pdfFile: File): Promise<File> {
+  const arrayBuffer = await pdfFile.arrayBuffer();
+  const pdf = await pdfjsLib.getDocument({ data: arrayBuffer }).promise;
+
+  let fullText = '';
+  let documentTitle = pdfFile.name.replace(/\.pdf$/i, '');
+
+  // Extract text from all pages
+  for (let i = 1; i <= pdf.numPages; i++) {
+    const page = await pdf.getPage(i);
+    const textContent = (await page.getTextContent()) as TextContent;
+
+    // Process text items and maintain basic formatting
+    let pageText = '';
+    let lastY = -1;
+
+    textContent.items.forEach((item) => {
+      const currentY = item.transform[5];
+
+      // If Y position changed significantly, it's likely a new line
+      if (lastY !== -1 && Math.abs(lastY - currentY) > 5) {
+        pageText += '\n';
+      }
+
+      pageText += item.str;
+
+      // Add space if the item doesn't end with space and next item doesn't start with space
+      if (item.hasEOL) {
+        pageText += '\n';
+      } else {
+        pageText += ' ';
+      }
+
+      lastY = currentY;
+    });
+
+    fullText += pageText.trim() + '\n\n';
+  }
+
+  // Create a basic Word document structure using RTF format
+  // RTF is simpler to generate than DOCX and is supported by Word
+  const rtfContent = createRTFDocument(fullText.trim(), documentTitle);
+
+  // Create the file
+  const wordBlob = new Blob([rtfContent], {
+    type: 'application/rtf'
+  });
+
+  const wordFile = new File(
+    [wordBlob],
+    pdfFile.name.replace(/\.pdf$/i, '.rtf'),
+    { type: 'application/rtf' }
+  );
+
+  return wordFile;
+}
+
+function createRTFDocument(text: string, title: string): string {
+  // Basic RTF structure
+  const rtfHeader = `{\\rtf1\\ansi\\deff0 {\\fonttbl {\\f0 Times New Roman;}}`;
+  const rtfTitle = `\\f0\\fs24\\b ${escapeRTF(title)}\\b0\\par\\par`;
+  const rtfBody = escapeRTF(text).replace(/\n/g, '\\par ');
+  const rtfFooter = `}`;
+
+  return rtfHeader + rtfTitle + rtfBody + rtfFooter;
+}
+
+function escapeRTF(text: string): string {
+  return text.replace(/\\/g, '\\\\').replace(/{/g, '\\{').replace(/}/g, '\\}');
+}