feat: add PDF to EPUB conversion tool

- Updated package.json to include new dependencies for PDF to EPUB conversion.
- Implemented PdfToEpub component for converting PDF files to EPUB format.
- Added meta information for the new PDF to EPUB tool.
- Created service to handle PDF processing and EPUB file generation.
- Integrated the new tool into the existing PDF tools list.

package.json

@@ -41,11 +41,16 @@
     "@types/morsee": "^1.0.2",
     "@types/omggif": "^1.0.5",
     "browser-image-compression": "^2.0.2",
+    "buffer": "^6.0.3",
     "color": "^4.2.3",
     "dayjs": "^1.11.13",
+    "epub-gen-memory": "^1.1.2",
+    "epubconventer": "^1.0.2",
+    "file-saver": "^2.0.5",
     "formik": "^2.4.6",
     "jimp": "^0.22.12",
     "js-quantities": "^1.8.0",
+    "jszip": "^3.10.1",
     "lint-staged": "^15.4.3",
     "lodash": "^4.17.21",
     "mime": "^4.0.6",
@@ -53,17 +58,22 @@
     "nerdamer-prime": "^1.2.4",
     "notistack": "^3.0.1",
     "omggif": "^1.0.10",
+    "path-browserify": "^1.0.1",
     "pdf-lib": "^1.17.1",
+    "pdfjs-dist": "^5.2.133",
     "playwright": "^1.45.0",
+    "process": "^0.11.10",
     "rc-slider": "^11.1.8",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-helmet": "^6.1.0",
     "react-image-crop": "^11.0.7",
     "react-router-dom": "^6.23.1",
+    "stream-browserify": "^3.0.0",
     "tesseract.js": "^6.0.0",
     "type-fest": "^4.35.0",
     "use-deep-compare-effect": "^1.8.1",
+    "util": "^0.12.5",
     "yup": "^1.4.0"
   },
   "devDependencies": {
@@ -77,6 +87,7 @@
     "@types/node": "^20.12.12",
     "@types/react": "^18.3.3",
     "@types/react-dom": "^18.3.0",
+    "@types/jszip": "^3.10.1",
     "@types/react-helmet": "^6.1.11",
     "@typescript-eslint/eslint-plugin": "^6.21.0",
     "@typescript-eslint/parser": "^6.21.0",

src/pages/tools/pdf/index.ts

@@ -4,11 +4,13 @@ import { meta as mergePdf } from './merge-pdf/meta';
 import { DefinedTool } from '@tools/defineTool';
 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';
 
 export const pdfTools: DefinedTool[] = [
   splitPdfMeta,
   pdfRotatePdf,
   compressPdfTool,
   protectPdfTool,
-  mergePdf
+  mergePdf,
+  pdfToEpub
 ];

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

@@ -0,0 +1,67 @@
+import { useState, useEffect } from 'react';
+import ToolFileResult from '@components/result/ToolFileResult';
+import ToolContent from '@components/ToolContent';
+import { ToolComponentProps } from '@tools/defineTool';
+import ToolPdfInput from '@components/input/ToolPdfInput';
+import { convertPdfToEpub } from './service';
+
+export default function PdfToEpub({ title }: ToolComponentProps) {
+  const [input, setInput] = useState<File | null>(null);
+  const [result, setResult] = useState<File | null>(null);
+  const [isProcessing, setIsProcessing] = useState<boolean>(false);
+
+  const compute = async (files: File[]) => {
+    if (!files?.[0]) return;
+
+    try {
+      setIsProcessing(true);
+      setResult(null); // Clear previous result
+      const epub = await convertPdfToEpub(files[0]);
+      setResult(epub);
+    } catch (error) {
+      console.error('Failed to convert PDF to EPUB:', error);
+      // Handle error appropriately - maybe set an error state
+    } finally {
+      setIsProcessing(false);
+    }
+  };
+
+  // Auto-trigger conversion when file is uploaded
+  useEffect(() => {
+    if (input) {
+      compute([input]);
+    }
+  }, [input]);
+
+  return (
+    <ToolContent
+      title={title}
+      input={input}
+      setInput={setInput}
+      initialValues={input ? [input] : []}
+      compute={compute}
+      inputComponent={
+        <ToolPdfInput
+          value={input}
+          onChange={(file) => setInput(file)}
+          accept={['application/pdf']}
+          title={'Input PDF'}
+        />
+      }
+      getGroups={null}
+      resultComponent={
+        <ToolFileResult
+          title={'EPUB Output'}
+          value={result}
+          extension={'epub'}
+          loading={isProcessing}
+          loadingText={'Converting PDF to EPUB...'}
+        />
+      }
+      toolInfo={{
+        title: 'How to Use PDF to EPUB?',
+        description: `Upload a PDF file and this tool will convert it into an EPUB format, suitable for most e-reader devices.`
+      }}
+    />
+  );
+}

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

@@ -0,0 +1,13 @@
+import { defineTool } from '@tools/defineTool';
+import { lazy } from 'react';
+
+export const meta = defineTool('pdf', {
+  name: 'PDF to EPUB',
+  shortDescription: 'Convert PDF files to EPUB format',
+  description:
+    'Transform PDF documents into EPUB files for better e-reader compatibility.',
+  icon: 'material-symbols:import-contacts',
+  component: lazy(() => import('./index')),
+  keywords: ['pdf', 'epub', 'convert', 'ebook'],
+  path: 'pdf-to-epub'
+});

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

@@ -0,0 +1,149 @@
+import * as pdfjsLib from 'pdfjs-dist';
+import pdfjsWorker from 'pdfjs-dist/build/pdf.worker.min?url';
+import JSZip from 'jszip';
+
+// Set worker source for PDF.js
+pdfjsLib.GlobalWorkerOptions.workerSrc = pdfjsWorker;
+
+/**
+ * Helper to convert raw text into clean paragraphs
+ */
+function formatTextToParagraphs(raw: string): string {
+  return raw
+    .split(/\n{2,}|\r{2,}/g) // Split on double line breaks
+    .map((p) => p.trim())
+    .filter((p) => p.length > 0)
+    .map((p) => `<p>${p.replace(/\n/g, ' ')}</p>`)
+    .join('\n');
+}
+
+export async function convertPdfToEpub(pdfFile: File): Promise<File> {
+  const arrayBuffer = await pdfFile.arrayBuffer();
+
+  // Load PDF document
+  const loadingTask = pdfjsLib.getDocument({ data: arrayBuffer });
+  const pdfDoc = await loadingTask.promise;
+  const numPages = pdfDoc.numPages;
+
+  // Extract text from all pages
+  const pages: string[] = [];
+  for (let i = 1; i <= numPages; i++) {
+    const page = await pdfDoc.getPage(i);
+    const textContent = await page.getTextContent();
+
+    const pageText = textContent.items.map((item: any) => item.str).join('\n'); // Preserve line breaks better
+
+    pages.push(pageText);
+  }
+
+  // Create EPUB structure using JSZip
+  const zip = new JSZip();
+
+  zip.file('mimetype', 'application/epub+zip', { compression: 'STORE' });
+
+  const metaInf = zip.folder('META-INF');
+  metaInf!.file(
+    'container.xml',
+    `<?xml version="1.0" encoding="UTF-8"?>
+<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
+  <rootfiles>
+    <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>
+  </rootfiles>
+</container>`
+  );
+
+  const oebps = zip.folder('OEBPS');
+  const bookTitle = pdfFile.name.replace(/\.pdf$/i, '');
+
+  const contentOpf = `<?xml version="1.0" encoding="UTF-8"?>
+<package xmlns="http://www.idpf.org/2007/opf" unique-identifier="bookid" version="2.0">
+  <metadata xmlns:dc="http://purl.org/dc/elements/1.1/">
+    <dc:title>${bookTitle}</dc:title>
+    <dc:creator>Converted by omni-tools</dc:creator>
+    <dc:identifier id="bookid">${Date.now()}</dc:identifier>
+    <dc:language>en</dc:language>
+  </metadata>
+  <manifest>
+    <item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml"/>
+    ${pages
+      .map(
+        (_, index) =>
+          `<item id="chapter${index + 1}" href="chapter${
+            index + 1
+          }.xhtml" media-type="application/xhtml+xml"/>`
+      )
+      .join('\n    ')}
+  </manifest>
+  <spine toc="ncx">
+    ${pages
+      .map((_, index) => `<itemref idref="chapter${index + 1}"/>`)
+      .join('\n    ')}
+  </spine>
+</package>`;
+
+  oebps!.file('content.opf', contentOpf);
+
+  const tocNcx = `<?xml version="1.0" encoding="UTF-8"?>
+<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1">
+  <head>
+    <meta name="dtb:uid" content="${Date.now()}"/>
+    <meta name="dtb:depth" content="1"/>
+    <meta name="dtb:totalPageCount" content="0"/>
+    <meta name="dtb:maxPageNumber" content="0"/>
+  </head>
+  <docTitle>
+    <text>${bookTitle}</text>
+  </docTitle>
+  <navMap>
+    ${pages
+      .map(
+        (_, index) =>
+          `<navPoint id="navpoint-${index + 1}" playOrder="${index + 1}">
+        <navLabel>
+          <text>Page ${index + 1}</text>
+        </navLabel>
+        <content src="chapter${index + 1}.xhtml"/>
+      </navPoint>`
+      )
+      .join('\n    ')}
+  </navMap>
+</ncx>`;
+
+  oebps!.file('toc.ncx', tocNcx);
+
+  pages.forEach((pageText, index) => {
+    const formattedBody = formatTextToParagraphs(pageText);
+
+    const chapterXhtml = `<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+  <title>Page ${index + 1}</title>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+  <style>
+    body {
+      font-family: serif;
+      line-height: 1.6;
+      margin: 1em;
+    }
+    p {
+      margin-bottom: 1em;
+      text-align: justify;
+    }
+  </style>
+</head>
+<body>
+  <h1>Page ${index + 1}</h1>
+  ${formattedBody}
+</body>
+</html>`;
+
+    oebps!.file(`chapter${index + 1}.xhtml`, chapterXhtml);
+  });
+
+  const epubBuffer = await zip.generateAsync({ type: 'arraybuffer' });
+
+  return new File([epubBuffer], pdfFile.name.replace(/\.pdf$/i, '.epub'), {
+    type: 'application/epub+zip'
+  });
+}