init

tuffstuff9 · tuffstuff9 · commit d2aceb2c6d54 · 2023-08-03T18:47:17.000-04:00
diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -0,0 +1,3 @@
+{
+  "workbench.colorTheme": "Abyss"
+}
diff --git a/README.md b/README.md
@@ -1,34 +1,72 @@
-This is a [Next.js](https://nextjs.org/) project bootstrapped with [`create-next-app`](https://github.com/vercel/next.js/tree/canary/packages/create-next-app).
+# Next.js PDF Parser Template 📄🔍
 
-## Getting Started
+## Introduction
 
-First, run the development server:
+I was having some trouble parsing PDFs in Next.js. I hope this template saves you some time and trouble. It's a basic `create-next-app` with PDF parsing implemented using the [pdf2json library](https://github.com/modesty/pdf2json) and file uploading facilitated by [FilePond](https://github.com/pqina/react-filepond).
 
-```bash
-npm run dev
-# or
-yarn dev
-# or
-pnpm dev
+## Installation & Setup 🚀
+
+1.  **Clone the repository**:
+2.  `git clone [repository-url]`
+3.  **Navigate to the project directory**:
+4.  `cd nextjs-pdf-parser`
+5.  **Install dependencies**:
+6.  ```bash
+    npm install
+    # or
+    yarn install
+    ```
+7.  **Run the development server**:
+
+    ```bash
+    npm run dev
+    # or
+    yarn dev
+    ```
+
+    Visit `http://localhost:3000` to view the application.
+
+## Usage 🖱
+
+Navigate to `http://localhost:3000` and use the FilePond uploader to select and upload a PDF. Once uploaded, the content of the PDF is parsed and printed to the server console (Note: it will not be printed to the browser log).
+
+## Technical Details 🛠
+
+- **nodeUtil is not defined Error**:
+
+  To bypass the `nodeUtil is not defined` error, the following configuration was added to `next.config.js`:
+
+```javascript
+const nextConfig = {
+  experimental: {
+    serverComponentsExternalPackages: ['pdf2json'],
+  },
+};
+
+module.exports = nextConfig;
 ```
 
-Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
+    See more details [here](https://github.com/modesty/pdf2json/issues/303)
+
+- **Blank output from `pdfParser.getRawTextContent()`**:
+
+  This issue might be due to incorrect type definitions. There are two potential solutions:
 
-You can start editing the page by modifying `app/page.tsx`. The page auto-updates as you edit the file.
+  1.  **Fix TypeScript definitions**: Update the type definition for PDFParser.
 
-This project uses [`next/font`](https://nextjs.org/docs/basic-features/font-optimization) to automatically optimize and load Inter, a custom Google Font.
+  2.  **Bypass type checking**: Instantiate PDFParser as shown:
 
-## Learn More
+      `const pdfParser = new (PDFParser as any)(null, 1);`
 
-To learn more about Next.js, take a look at the following resources:
+  For more details, refer to my comment on [this GitHub issue](https://github.com/modesty/pdf2json/issues/273#issuecomment-1662587255).
 
-- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API.
-- [Learn Next.js](https://nextjs.org/learn) - an interactive Next.js tutorial.
+## Acknowledgements 🙏
 
-You can check out [the Next.js GitHub repository](https://github.com/vercel/next.js/) - your feedback and contributions are welcome!
+A special thanks to the following libraries and their contributors:
 
-## Deploy on Vercel
+- **[FilePond](https://pqina.nl/filepond/)**: For providing a seamless and user-friendly file uploading experience.
+- **[pdf2json](https://www.npmjs.com/package/pdf2json)**: For its efficient and robust PDF parsing capabilities.
 
-The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new?utm_medium=default-template&filter=next.js&utm_source=create-next-app&utm_campaign=create-next-app-readme) from the creators of Next.js.
+## License 📜
 
-Check out our [Next.js deployment documentation](https://nextjs.org/docs/deployment) for more details.
+MIT License
diff --git a/app/api/upload/route.ts b/app/api/upload/route.ts
@@ -0,0 +1,60 @@
+import { NextRequest, NextResponse } from 'next/server'; // To handle the request and response
+import { promises as fs } from 'fs'; // To save the file temporarily
+import { v4 as uuidv4 } from 'uuid'; // To generate a unique filename
+import PDFParser from 'pdf2json'; // To parse the pdf
+
+export async function POST(req: NextRequest) {
+  const formData: FormData = await req.formData();
+  const uploadedFiles = formData.getAll('filepond');
+  let fileName = '';
+  let parsedText = '';
+
+  if (uploadedFiles && uploadedFiles.length > 0) {
+    const uploadedFile = uploadedFiles[1];
+    console.log('Uploaded file:', uploadedFile);
+
+    // Check if uploadedFile is of type File
+    if (uploadedFile instanceof File) {
+      // Generate a unique filename
+      fileName = uuidv4();
+
+      // Convert the uploaded file into a temporary file
+      const tempFilePath = `/tmp/${fileName}.pdf`;
+
+      // Convert ArrayBuffer to Buffer
+      const fileBuffer = Buffer.from(await uploadedFile.arrayBuffer());
+
+      // Save the buffer as a file
+      await fs.writeFile(tempFilePath, fileBuffer);
+
+      // Parse the pdf using pdf2json. See pdf2json docs for more info.
+
+      // The reason I am bypassing type checks is because
+      // the default type definitions for pdf2json in the npm install
+      // do not allow for any constructor arguments.
+      // You can either modify the type definitions or bypass the type checks.
+      // I chose to bypass the type checks.
+      const pdfParser = new (PDFParser as any)(null, 1);
+
+      // See pdf2json docs for more info on how the below works.
+      pdfParser.on('pdfParser_dataError', (errData: any) =>
+        console.log(errData.parserError)
+      );
+
+      pdfParser.on('pdfParser_dataReady', () => {
+        console.log((pdfParser as any).getRawTextContent());
+        parsedText = (pdfParser as any).getRawTextContent();
+      });
+
+      pdfParser.loadPDF(tempFilePath);
+    } else {
+      console.log('Uploaded file is not in the expected format.');
+    }
+  } else {
+    console.log('No files found.');
+  }
+
+  const response = new NextResponse(parsedText);
+  response.headers.set('FileName', fileName);
+  return response;
+}
diff --git a/app/layout.tsx b/app/layout.tsx
@@ -1,22 +1,22 @@
-import './globals.css'
-import type { Metadata } from 'next'
-import { Inter } from 'next/font/google'
+import './globals.css';
+import type { Metadata } from 'next';
+import { Inter } from 'next/font/google';
 
-const inter = Inter({ subsets: ['latin'] })
+const inter = Inter({ subsets: ['latin'] });
 
 export const metadata: Metadata = {
-  title: 'Create Next App',
-  description: 'Generated by create next app',
-}
+  title: 'Next.js PDF Parser',
+  description: 'Created by tuffstuff9 // github.com/tuffstuff9',
+};
 
 export default function RootLayout({
   children,
 }: {
-  children: React.ReactNode
+  children: React.ReactNode;
 }) {
   return (
-    <html lang="en">
+    <html lang='en'>
       <body className={inter.className}>{children}</body>
     </html>
-  )
+  );
 }
diff --git a/app/page.tsx b/app/page.tsx
@@ -1,113 +1,11 @@
-import Image from 'next/image'
+import FileUpload from '@/components/file-upload';
 
 export default function Home() {
   return (
-    <main className="flex min-h-screen flex-col items-center justify-between p-24">
-      <div className="z-10 w-full max-w-5xl items-center justify-between font-mono text-sm lg:flex">
-        <p className="fixed left-0 top-0 flex w-full justify-center border-b border-gray-300 bg-gradient-to-b from-zinc-200 pb-6 pt-8 backdrop-blur-2xl dark:border-neutral-800 dark:bg-zinc-800/30 dark:from-inherit lg:static lg:w-auto  lg:rounded-xl lg:border lg:bg-gray-200 lg:p-4 lg:dark:bg-zinc-800/30">
-          Get started by editing&nbsp;
-          <code className="font-mono font-bold">app/page.tsx</code>
-        </p>
-        <div className="fixed bottom-0 left-0 flex h-48 w-full items-end justify-center bg-gradient-to-t from-white via-white dark:from-black dark:via-black lg:static lg:h-auto lg:w-auto lg:bg-none">
-          <a
-            className="pointer-events-none flex place-items-center gap-2 p-8 lg:pointer-events-auto lg:p-0"
-            href="https://vercel.com?utm_source=create-next-app&utm_medium=appdir-template&utm_campaign=create-next-app"
-            target="_blank"
-            rel="noopener noreferrer"
-          >
-            By{' '}
-            <Image
-              src="/vercel.svg"
-              alt="Vercel Logo"
-              className="dark:invert"
-              width={100}
-              height={24}
-              priority
-            />
-          </a>
-        </div>
-      </div>
-
-      <div className="relative flex place-items-center before:absolute before:h-[300px] before:w-[480px] before:-translate-x-1/2 before:rounded-full before:bg-gradient-radial before:from-white before:to-transparent before:blur-2xl before:content-[''] after:absolute after:-z-20 after:h-[180px] after:w-[240px] after:translate-x-1/3 after:bg-gradient-conic after:from-sky-200 after:via-blue-200 after:blur-2xl after:content-[''] before:dark:bg-gradient-to-br before:dark:from-transparent before:dark:to-blue-700 before:dark:opacity-10 after:dark:from-sky-900 after:dark:via-[#0141ff] after:dark:opacity-40 before:lg:h-[360px] z-[-1]">
-        <Image
-          className="relative dark:drop-shadow-[0_0_0.3rem_#ffffff70] dark:invert"
-          src="/next.svg"
-          alt="Next.js Logo"
-          width={180}
-          height={37}
-          priority
-        />
-      </div>
-
-      <div className="mb-32 grid text-center lg:mb-0 lg:grid-cols-4 lg:text-left">
-        <a
-          href="https://nextjs.org/docs?utm_source=create-next-app&utm_medium=appdir-template&utm_campaign=create-next-app"
-          className="group rounded-lg border border-transparent px-5 py-4 transition-colors hover:border-gray-300 hover:bg-gray-100 hover:dark:border-neutral-700 hover:dark:bg-neutral-800/30"
-          target="_blank"
-          rel="noopener noreferrer"
-        >
-          <h2 className={`mb-3 text-2xl font-semibold`}>
-            Docs{' '}
-            <span className="inline-block transition-transform group-hover:translate-x-1 motion-reduce:transform-none">
-              -&gt;
-            </span>
-          </h2>
-          <p className={`m-0 max-w-[30ch] text-sm opacity-50`}>
-            Find in-depth information about Next.js features and API.
-          </p>
-        </a>
-
-        <a
-          href="https://nextjs.org/learn?utm_source=create-next-app&utm_medium=appdir-template-tw&utm_campaign=create-next-app"
-          className="group rounded-lg border border-transparent px-5 py-4 transition-colors hover:border-gray-300 hover:bg-gray-100 hover:dark:border-neutral-700 hover:dark:bg-neutral-800/30"
-          target="_blank"
-          rel="noopener noreferrer"
-        >
-          <h2 className={`mb-3 text-2xl font-semibold`}>
-            Learn{' '}
-            <span className="inline-block transition-transform group-hover:translate-x-1 motion-reduce:transform-none">
-              -&gt;
-            </span>
-          </h2>
-          <p className={`m-0 max-w-[30ch] text-sm opacity-50`}>
-            Learn about Next.js in an interactive course with&nbsp;quizzes!
-          </p>
-        </a>
-
-        <a
-          href="https://vercel.com/templates?framework=next.js&utm_source=create-next-app&utm_medium=appdir-template&utm_campaign=create-next-app"
-          className="group rounded-lg border border-transparent px-5 py-4 transition-colors hover:border-gray-300 hover:bg-gray-100 hover:dark:border-neutral-700 hover:dark:bg-neutral-800/30"
-          target="_blank"
-          rel="noopener noreferrer"
-        >
-          <h2 className={`mb-3 text-2xl font-semibold`}>
-            Templates{' '}
-            <span className="inline-block transition-transform group-hover:translate-x-1 motion-reduce:transform-none">
-              -&gt;
-            </span>
-          </h2>
-          <p className={`m-0 max-w-[30ch] text-sm opacity-50`}>
-            Explore the Next.js 13 playground.
-          </p>
-        </a>
-
-        <a
-          href="https://vercel.com/new?utm_source=create-next-app&utm_medium=appdir-template&utm_campaign=create-next-app"
-          className="group rounded-lg border border-transparent px-5 py-4 transition-colors hover:border-gray-300 hover:bg-gray-100 hover:dark:border-neutral-700 hover:dark:bg-neutral-800/30"
-          target="_blank"
-          rel="noopener noreferrer"
-        >
-          <h2 className={`mb-3 text-2xl font-semibold`}>
-            Deploy{' '}
-            <span className="inline-block transition-transform group-hover:translate-x-1 motion-reduce:transform-none">
-              -&gt;
-            </span>
-          </h2>
-          <p className={`m-0 max-w-[30ch] text-sm opacity-50`}>
-            Instantly deploy your Next.js site to a shareable URL with Vercel.
-          </p>
-        </a>
+    <main className='flex min-h-screen flex-col items-center justify-between p-24'>
+      <div className='w-96'>
+        <FileUpload />
       </div>
     </main>
-  )
+  );
 }
diff --git a/components/file-upload.tsx b/components/file-upload.tsx
@@ -0,0 +1,16 @@
+'use client';
+import { FilePond } from 'react-filepond';
+import 'filepond/dist/filepond.min.css';
+import { useState } from 'react';
+
+export default function FileUpload() {
+  return (
+    <FilePond
+      server={{
+        process: '/api/upload',
+        fetch: null,
+        revert: null,
+      }}
+    />
+  );
+}
diff --git a/next.config.js b/next.config.js
@@ -1,4 +1,8 @@
 /** @type {import('next').NextConfig} */
-const nextConfig = {}
+const nextConfig = {
+  experimental: {
+    serverComponentsExternalPackages: ['pdf2json'],
+  },
+};
 
-module.exports = nextConfig
+module.exports = nextConfig;
diff --git a/package.json b/package.json
@@ -12,12 +12,17 @@
     "@types/node": "20.4.5",
     "@types/react": "18.2.18",
     "@types/react-dom": "18.2.7",
+    "@types/uuid": "^9.0.2",
     "autoprefixer": "10.4.14",
+    "filepond": "^4.30.4",
     "next": "13.4.12",
+    "pdf2json": "^3.0.4",
     "postcss": "8.4.27",
     "react": "18.2.0",
     "react-dom": "18.2.0",
+    "react-filepond": "^7.1.2",
     "tailwindcss": "3.3.3",
-    "typescript": "5.1.6"
+    "typescript": "5.1.6",
+    "uuid": "^9.0.0"
   }
 }
diff --git a/public/next.svg b/public/next.svg
diff --git a/public/vercel.svg b/public/vercel.svg
diff --git a/yarn.lock b/yarn.lock

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+{`
	`2`	`+ "workbench.colorTheme": "Abyss"`
	`3`	`+}`