riccardo/pdf-text-parsing
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: implementation

Browse Source
This commit is contained in:
Riccardo
2024-05-07 21:52:38 +02:00
parent 734b590482
commit f752787605
26 changed files with 6365 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.eslintrc.json Normal file
View File

@@ -0,0 +1,3 @@
{
"extends": "next/core-web-vitals"
}

4
.husky/commit-msg Executable file
View File

@@ -0,0 +1,4 @@
#!/usr/bin/env sh
. "$(dirname -- "$0")/_/husky.sh"
npx --no-install commitlint --edit $1

7
.husky/pre-commit Executable file
View File

@@ -0,0 +1,7 @@
#!/usr/bin/env sh
. "$(dirname -- "$0")/_/husky.sh"
yarn format
yarn lint-staged
yarn typecheck
yarn build

10
.prettierrc Normal file
View File

@@ -0,0 +1,10 @@
{
"semi": true,
"trailingComma": "none",
"singleQuote": true,
"printWidth": 80,
"jsxSingleQuote": true,
"tabWidth": 2,
"arrowParens": "avoid",
"plugins": ["prettier-plugin-tailwindcss"]
}

5
.yarnrc.yml Normal file
View File

@@ -0,0 +1,5 @@
compressionLevel: mixed
enableGlobalCache: false
nodeLinker: node-modules

13
README.md
View File

@@ -1 +1,12 @@
# pdf-text-parsing ## Getting Started
To ruun the development server:
```bash
yarn dev
```
## TODO
- edge cases
- tests

37
app/api/parse/route.ts Normal file
View File

@@ -0,0 +1,37 @@
import { Response } from '@/utils/data';
import { parser } from '@/utils/parser';
import { NextRequest, NextResponse } from 'next/server';
export async function POST(req: NextRequest) {
if (!req.headers.get('content-type')?.startsWith('multipart/form-data')) {
return new NextResponse('This API only accepts FormData.', {
status: 415
});
}
const data = await req.formData();
const file = data.get('File');
if (!file || !(file instanceof File)) {
return new NextResponse('No file provided', {
status: 400
});
}
try {
const parsedText = await parser(file);
const response: Response = {
text: parsedText
};
return new NextResponse(JSON.stringify(response), {
status: 200
});
} catch (err) {
return new NextResponse('Failed to parse PDF', {
status: 500
});
}
}

BIN
app/favicon.ico Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 25 KiB

73
app/globals.css Normal file
View File

@@ -0,0 +1,73 @@
@tailwind base;
@tailwind components;
@tailwind utilities;
:root {
--foreground-rgb: 0, 0, 0;
--background-start-rgb: 255, 255, 255;
--background-end-rgb: 0, 0, 255;
}
main {
display: flex;
min-height: 100vh;
flex-direction: column;
align-items: center;
justify-content: center;
}
body {
color: rgb(var(--foreground-rgb));
background: linear-gradient(
to bottom right,
transparent,
rgb(var(--background-end-rgb))
)
rgb(var(--background-start-rgb));
}
input {
border: 1px solid #ccc;
}
p {
text-align: center;
}
.dashboard {
display: flex;
flex-direction: column;
width: 60vw;
height: 80vh;
border: 1px solid #ccc;
border-radius: 15px;
padding: 20px;
box-shadow: 2px 2px 10px rgba(0, 0, 0, 5);
background-color: white;
gap: 20px;
overflow: auto;
}
.form {
display: flex;
flex-direction: column;
gap: 10px;
align-items: center;
}
.content {
flex: 1;
border: 1px solid #ccc;
overflow: auto;
padding: 10px;
}
.button {
background-color: #007bff;
color: white;
padding: 10px 20px;
border-radius: 5px;
border: none;
cursor: pointer;
max-width: 200px;
}

19
app/layout.tsx Normal file
View File

@@ -0,0 +1,19 @@
import type { Metadata } from 'next';
import './globals.css';
export const metadata: Metadata = {
title: 'PDF text parser',
description: 'Get the text content a PDF file in the browser (demo)'
};
export default function RootLayout({
children
}: Readonly<{
children: React.ReactNode;
}>) {
return (
<html lang='en'>
<body>{children}</body>
</html>
);
}

11
app/page.tsx Normal file
View File

@@ -0,0 +1,11 @@
'use client';
import Dashboard from '@/components/Dashboard';
export default function Home() {
return (
<main>
<Dashboard />
</main>
);
}

3
commitlint.config.ts Normal file
View File

@@ -0,0 +1,3 @@
module.exports = {
extends: ['@commitlint/config-conventional']
};

13
components/Button.tsx Normal file
View File

@@ -0,0 +1,13 @@
interface ButtonProps {
label: string;
disabled?: boolean;
onClick: () => void;
}
export function Button({ onClick, disabled = false, label }: ButtonProps) {
return (
<button onClick={onClick} disabled={disabled} className='button'>
{label}
</button>
);
}

13
components/Content.tsx Normal file
View File

@@ -0,0 +1,13 @@
interface ContentProps {
loading: boolean;
error?: string;
text: string;
}
export function Content({ loading, error, text }: ContentProps) {
return (
<div className='content'>
{loading ? 'Parsing file...' : <>{error ? <p>{error}</p> : text}</>}
</div>
);
}

116
components/Dashboard.tsx Normal file
View File

@@ -0,0 +1,116 @@
import { responseSchema } from '@/utils/data';
import axios from 'axios';
import { useCallback, useState } from 'react';
import { Button } from './Button';
import { Content } from './Content';
export default function Dashboard() {
const [clearing, setClearing] = useState(false);
const [file, setFile] = useState<File>();
const [loading, setLoading] = useState(false);
const [error, setError] = useState<string>();
const [parsedText, setParsedText] = useState<string>('');
const handleFileChange = useCallback(
(e: React.ChangeEvent<HTMLInputElement>) => {
if (e.target.files) {
setFile(e.target.files[0]);
} else {
setFile(undefined);
}
},
[]
);
const handleClear = useCallback(() => {
setClearing(false);
setFile(undefined);
setParsedText('');
}, []);
const validateFile = useCallback((file: File) => {
if (file.type !== 'application/pdf') {
setError(
"The file you've selected is not a PDF file. Please select a PDF file."
);
setLoading(false);
return false;
}
// This limit is caused by the project being deployed on Vercel using a free tier, with limited resources
if (file.size > 1024 * 1024) {
setError('The file must be smaller than 1MB.');
setLoading(false);
return false;
}
return true;
}, []);
const uploadFile = useCallback(async () => {
if (!file) return;
if (!validateFile(file)) return;
const formData = new FormData();
formData.append('File', file);
try {
const response = await axios.post('/api/parse', formData);
const validatedData = responseSchema.safeParse(response.data);
if (!validatedData.success) {
setError('There was an error parsing the file. Please try again.');
return;
}
setParsedText(validatedData.data.text);
setClearing(true);
} catch {
setError('Internal server error. Please try again later.');
} finally {
setLoading(false);
}
}, [file, validateFile]);
const handleUpload = useCallback(() => {
setLoading(true);
setError(undefined);
setParsedText('');
uploadFile();
}, [uploadFile]);
function renderForm() {
if (clearing) {
return (
<>
<p>File: {file?.name}</p>
<Button label='Use a different file' onClick={handleClear} />
</>
);
}
return (
<>
<input type='file' accept='.pdf' onChange={handleFileChange} />
<Button
label='Upload and parse'
onClick={handleUpload}
disabled={!file}
/>
</>
);
}
return (
<div className='dashboard'>
<p>This is a tool to extract the text from a PDF file</p>
<div className='form'> {renderForm()}</div>
<Content loading={loading} error={error} text={parsedText} />
</div>
);
}

5
next-env.d.ts vendored Normal file
View File

@@ -0,0 +1,5 @@
/// <reference types="next" />
/// <reference types="next/image-types/global" />
// NOTE: This file should not be edited
// see https://nextjs.org/docs/basic-features/typescript for more information.

8
next.config.mjs Normal file
View File

@@ -0,0 +1,8 @@
/** @type {import('next').NextConfig} */
const nextConfig = {
experimental: {
serverComponentsExternalPackages: ["pdf-parse"],
},
};
export default nextConfig;

50
package.json Normal file
View File

@@ -0,0 +1,50 @@
{
"name": "pdf-parser",
"version": "0.1.0",
"private": true,
"scripts": {
"dev": "next dev",
"build": "next build",
"start": "next start",
"lint": "next lint",
"format": "prettier --config .prettierrc 'app/' --write",
"typecheck": "tsc --noEmit",
"prepare": "husky install"
},
"dependencies": {
"axios": "^1.6.8",
"next": "14.2.3",
"pdf-parse": "^1.1.1",
"react": "^18",
"react-dom": "^18",
"zod": "^3.23.6"
},
"devDependencies": {
"@commitlint/cli": "^18.4.3",
"@commitlint/config-conventional": "^18.4.3",
"@types/node": "^20",
"@types/pdf-parse": "^1.1.4",
"@types/react": "^18",
"@types/react-dom": "^18",
"@typescript-eslint/eslint-plugin": "^6.12.0",
"@typescript-eslint/parser": "^6.12.0",
"eslint": "^8",
"eslint-config-next": "14.2.3",
"eslint-config-prettier": "^9.0.0",
"husky": "^8.0.3",
"lint-staged": "^15.1.0",
"postcss": "^8",
"prettier": "^3.1.0",
"prettier-plugin-tailwindcss": "^0.5.7",
"tailwindcss": "^3.4.1",
"typescript": "^5"
},
"lint-staged": {
"*.ts": [
"eslint --quiet --fix"
],
"*.{json,ts}": [
"prettier --write --ignore-unknown"
]
}
}

8
postcss.config.mjs Normal file
View File

@@ -0,0 +1,8 @@
/** @type {import('postcss-load-config').Config} */
const config = {
plugins: {
tailwindcss: {},
},
};
export default config;

1
public/next.svg Normal file
View File

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 394 80"><path fill="#000" d="M262 0h68.5v12.7h-27.2v66.6h-13.6V12.7H262V0ZM149 0v12.7H94v20.4h44.3v12.6H94v21h55v12.6H80.5V0h68.7zm34.3 0h-17.8l63.8 79.4h17.9l-32-39.7 32-39.6h-17.9l-23 28.6-23-28.6zm18.3 56.7-9-11-27.1 33.7h17.8l18.3-22.7z"/><path fill="#000" d="M81 79.3 17 0H0v79.3h13.6V17l50.2 62.3H81Zm252.6-.4c-1 0-1.8-.4-2.5-1s-1.1-1.6-1.1-2.6.3-1.8 1-2.5 1.6-1 2.6-1 1.8.3 2.5 1a3.4 3.4 0 0 1 .6 4.3 3.7 3.7 0 0 1-3 1.8zm23.2-33.5h6v23.3c0 2.1-.4 4-1.3 5.5a9.1 9.1 0 0 1-3.8 3.5c-1.6.8-3.5 1.3-5.7 1.3-2 0-3.7-.4-5.3-1s-2.8-1.8-3.7-3.2c-.9-1.3-1.4-3-1.4-5h6c.1.8.3 1.6.7 2.2s1 1.2 1.6 1.5c.7.4 1.5.5 2.4.5 1 0 1.8-.2 2.4-.6a4 4 0 0 0 1.6-1.8c.3-.8.5-1.8.5-3V45.5zm30.9 9.1a4.4 4.4 0 0 0-2-3.3 7.5 7.5 0 0 0-4.3-1.1c-1.3 0-2.4.2-3.3.5-.9.4-1.6 1-2 1.6a3.5 3.5 0 0 0-.3 4c.3.5.7.9 1.3 1.2l1.8 1 2 .5 3.2.8c1.3.3 2.5.7 3.7 1.2a13 13 0 0 1 3.2 1.8 8.1 8.1 0 0 1 3 6.5c0 2-.5 3.7-1.5 5.1a10 10 0 0 1-4.4 3.5c-1.8.8-4.1 1.2-6.8 1.2-2.6 0-4.9-.4-6.8-1.2-2-.8-3.4-2-4.5-3.5a10 10 0 0 1-1.7-5.6h6a5 5 0 0 0 3.5 4.6c1 .4 2.2.6 3.4.6 1.3 0 2.5-.2 3.5-.6 1-.4 1.8-1 2.4-1.7a4 4 0 0 0 .8-2.4c0-.9-.2-1.6-.7-2.2a11 11 0 0 0-2.1-1.4l-3.2-1-3.8-1c-2.8-.7-5-1.7-6.6-3.2a7.2 7.2 0 0 1-2.4-5.7 8 8 0 0 1 1.7-5 10 10 0 0 1 4.3-3.5c2-.8 4-1.2 6.4-1.2 2.3 0 4.4.4 6.2 1.2 1.8.8 3.2 2 4.3 3.4 1 1.4 1.5 3 1.5 5h-5.8z"/></svg>
Side by Side

After

Width:  |  Height:  |  Size: 1.3 KiB

1
public/vercel.svg Normal file
View File

@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 283 64"><path fill="black" d="M141 16c-11 0-19 7-19 18s9 18 20 18c7 0 13-3 16-7l-7-5c-2 3-6 4-9 4-5 0-9-3-10-7h28v-3c0-11-8-18-19-18zm-9 15c1-4 4-7 9-7s8 3 9 7h-18zm117-15c-11 0-19 7-19 18s9 18 20 18c6 0 12-3 16-7l-8-5c-2 3-5 4-8 4-5 0-9-3-11-7h28l1-3c0-11-8-18-19-18zm-10 15c2-4 5-7 10-7s8 3 9 7h-19zm-39 3c0 6 4 10 10 10 4 0 7-2 9-5l8 5c-3 5-9 8-17 8-11 0-19-7-19-18s8-18 19-18c8 0 14 3 17 8l-8 5c-2-3-5-5-9-5-6 0-10 4-10 10zm83-29v46h-9V5h9zM37 0l37 64H0L37 0zm92 5-27 48L74 5h10l18 30 17-30h10zm59 12v10l-3-1c-6 0-10 4-10 10v15h-9V17h9v9c0-5 6-9 13-9z"/></svg>
Side by Side

After

Width:  |  Height:  |  Size: 629 B

20
tailwind.config.ts Normal file
View File

@@ -0,0 +1,20 @@
import type { Config } from "tailwindcss";
const config: Config = {
content: [
"./pages/**/*.{js,ts,jsx,tsx,mdx}",
"./components/**/*.{js,ts,jsx,tsx,mdx}",
"./app/**/*.{js,ts,jsx,tsx,mdx}",
],
theme: {
extend: {
backgroundImage: {
"gradient-radial": "radial-gradient(var(--tw-gradient-stops))",
"gradient-conic":
"conic-gradient(from 180deg at 50% 50%, var(--tw-gradient-stops))",
},
},
},
plugins: [],
};
export default config;

26
tsconfig.json Normal file
View File

@@ -0,0 +1,26 @@
{
"compilerOptions": {
"lib": ["dom", "dom.iterable", "esnext"],
"allowJs": true,
"skipLibCheck": true,
"strict": true,
"noEmit": true,
"esModuleInterop": true,
"module": "esnext",
"moduleResolution": "bundler",
"resolveJsonModule": true,
"isolatedModules": true,
"jsx": "preserve",
"incremental": true,
"plugins": [
{
"name": "next"
}
],
"paths": {
"@/*": ["./*"]
}
},
"include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", ".next/types/**/*.ts"],
"exclude": ["node_modules", ".next", ".vercel"]
}

7
utils/data.ts Normal file
View File

@@ -0,0 +1,7 @@
import { z } from 'zod';
export const responseSchema = z.object({
text: z.string()
});
export type Response = z.infer<typeof responseSchema>;

12
utils/parser.ts Normal file
View File

@@ -0,0 +1,12 @@
import PdfParse from 'pdf-parse';
export async function parser(file: File) {
const chunks = [];
for await (const chunk of file.stream() as any) {
chunks.push(chunk);
}
const parsedContent = await PdfParse(Buffer.concat(chunks));
return parsedContent.text;
}

5901
yarn.lock Normal file
View File

File diff suppressed because it is too large Load Diff