Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 5bc84ffaa0 | |||
| 6435d0f042 | |||
| 9fbd735088 | |||
| fe05713d57 | |||
| be574df599 | |||
| 6a4aeed3e1 |
33
changelog.md
33
changelog.md
@@ -1,5 +1,38 @@
|
||||
# Changelog
|
||||
|
||||
## 2026-03-01 - 4.1.2 - fix(smartfs)
|
||||
replace smartfile with smartfs, update file reading to use SmartFs, remove GraphicsMagick/Ghostscript dependency checks, bump dev and runtime dependencies, update tests and docs, and adjust npmextra configuration
|
||||
|
||||
- Replace usage/export of @push.rocks/smartfile with @push.rocks/smartfs and update readFileToPdfObject to use SmartFs + SmartFsProviderNode
|
||||
- Remove execFile import and the GraphicsMagick/Ghostscript dependency-checking helpers from smartpdf (no more gm/gs checks)
|
||||
- Bump devDependencies: @git.zone/tsbuild ^4.1.2, @git.zone/tsdoc ^1.12.0, @git.zone/tsrun ^2.0.1, @git.zone/tstest ^3.1.8, @types/node ^25.3.2
|
||||
- Bump runtime dependencies: @push.rocks/smartfs ^1.3.1, @push.rocks/smartnetwork ^4.4.0, @tsclass/tsclass ^9.3.0, @types/express ^5.0.6, express ^5.2.1, pdf2json ^4.0.2
|
||||
- Tests updated: switched example URLs to example.com, added a third PDF generation test that writes .nogit/3.pdf, and exported tap.start() as default
|
||||
- npmextra.json reorganized to namespaced keys, added release.registries and accessLevel, and adjusted tsdoc/legal entries
|
||||
- Documentation/readme refreshed: added issue reporting/security section, feature table, and various wording/formatting updates
|
||||
|
||||
## 2025-08-02 - 4.1.0 - feat(smartpdf)
|
||||
Add progressive JPEG generation support
|
||||
|
||||
- Added new convertPDFToJpegBytes method for progressive JPEG generation
|
||||
- Integrated @push.rocks/smartjimp for true progressive JPEG encoding
|
||||
- Progressive JPEGs load in multiple passes, showing low-quality preview first
|
||||
- Supports quality and scale options like other image generation methods
|
||||
- Updated readme with comprehensive documentation and modern styling
|
||||
- Updated legal section to reflect Task Venture Capital GmbH ownership
|
||||
|
||||
## 2025-08-02 - 4.0.0 - BREAKING CHANGE(smartpdf)
|
||||
Improve image generation quality and API consistency
|
||||
|
||||
- BREAKING: Renamed `convertPDFToWebpPreviews` to `convertPDFToWebpBytes` for API consistency
|
||||
- Added configurable scale options to `convertPDFToPngBytes` method
|
||||
- Changed default scale from 1.0 to 3.0 for PNG generation (216 DPI)
|
||||
- Changed default scale from 0.5 to 3.0 for WebP generation (216 DPI)
|
||||
- Added DPI helper methods: `getScaleForDPI()` and scale constants (SCALE_SCREEN, SCALE_HIGH, SCALE_PRINT)
|
||||
- Added maxWidth/maxHeight constraints for both PNG and WebP generation
|
||||
- Improved test file organization with clear naming conventions
|
||||
- Updated documentation with DPI/scale guidance and examples
|
||||
|
||||
## 2025-08-01 - 3.3.0 - feat(smartpdf)
|
||||
Add automatic port allocation and multi-instance support
|
||||
|
||||
|
||||
@@ -1,9 +1,5 @@
|
||||
{
|
||||
"npmci": {
|
||||
"npmGlobalTools": [],
|
||||
"npmAccessLevel": "public"
|
||||
},
|
||||
"gitzone": {
|
||||
"@git.zone/cli": {
|
||||
"projectType": "npm",
|
||||
"module": {
|
||||
"githost": "code.foss.global",
|
||||
@@ -26,9 +22,19 @@
|
||||
"text extraction",
|
||||
"PDF management"
|
||||
]
|
||||
},
|
||||
"release": {
|
||||
"registries": [
|
||||
"https://verdaccio.lossless.digital",
|
||||
"https://registry.npmjs.org"
|
||||
],
|
||||
"accessLevel": "public"
|
||||
}
|
||||
},
|
||||
"tsdoc": {
|
||||
"@git.zone/tsdoc": {
|
||||
"legal": "\n## License and Legal Information\n\nThis repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository. \n\n**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.\n\n### Trademarks\n\nThis project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.\n\n### Company Information\n\nTask Venture Capital GmbH \nRegistered at District court Bremen HRB 35230 HB, Germany\n\nFor any legal inquiries or if you require further information, please contact us via email at hello@task.vc.\n\nBy using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.\n"
|
||||
},
|
||||
"@ship.zone/szci": {
|
||||
"npmGlobalTools": []
|
||||
}
|
||||
}
|
||||
27
package.json
27
package.json
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@push.rocks/smartpdf",
|
||||
"version": "3.3.0",
|
||||
"version": "4.1.2",
|
||||
"private": false,
|
||||
"description": "A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.",
|
||||
"main": "dist_ts/index.js",
|
||||
@@ -9,31 +9,32 @@
|
||||
"author": "Lossless GmbH",
|
||||
"license": "MIT",
|
||||
"scripts": {
|
||||
"test": "(tstest test/ --verbose --timeout 60)",
|
||||
"test": "(tstest test/ --verbose --timeout 120)",
|
||||
"build": "(tsbuild tsfolders --allowimplicitany)",
|
||||
"buildDocs": "tsdoc"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@git.zone/tsbuild": "^2.6.4",
|
||||
"@git.zone/tsdoc": "^1.5.0",
|
||||
"@git.zone/tsrun": "^1.3.3",
|
||||
"@git.zone/tstest": "^2.3.2",
|
||||
"@types/node": "^24.1.0"
|
||||
"@git.zone/tsbuild": "^4.1.2",
|
||||
"@git.zone/tsdoc": "^1.12.0",
|
||||
"@git.zone/tsrun": "^2.0.1",
|
||||
"@git.zone/tstest": "^3.1.8",
|
||||
"@types/node": "^25.3.2"
|
||||
},
|
||||
"dependencies": {
|
||||
"@push.rocks/smartbuffer": "^3.0.5",
|
||||
"@push.rocks/smartdelay": "^3.0.5",
|
||||
"@push.rocks/smartfile": "^11.2.5",
|
||||
"@push.rocks/smartnetwork": "^4.1.2",
|
||||
"@push.rocks/smartfs": "^1.3.1",
|
||||
"@push.rocks/smartjimp": "^1.2.0",
|
||||
"@push.rocks/smartnetwork": "^4.4.0",
|
||||
"@push.rocks/smartpath": "^6.0.0",
|
||||
"@push.rocks/smartpromise": "^4.2.3",
|
||||
"@push.rocks/smartpuppeteer": "^2.0.5",
|
||||
"@push.rocks/smartunique": "^3.0.9",
|
||||
"@tsclass/tsclass": "^9.2.0",
|
||||
"@types/express": "^5.0.3",
|
||||
"express": "^5.1.0",
|
||||
"@tsclass/tsclass": "^9.3.0",
|
||||
"@types/express": "^5.0.6",
|
||||
"express": "^5.2.1",
|
||||
"pdf-lib": "^1.17.1",
|
||||
"pdf2json": "3.2.0"
|
||||
"pdf2json": "^4.0.2"
|
||||
},
|
||||
"files": [
|
||||
"ts/**/*",
|
||||
|
||||
5356
pnpm-lock.yaml
generated
5356
pnpm-lock.yaml
generated
File diff suppressed because it is too large
Load Diff
2
pnpm-workspace.yaml
Normal file
2
pnpm-workspace.yaml
Normal file
@@ -0,0 +1,2 @@
|
||||
onlyBuiltDependencies:
|
||||
- sharp
|
||||
688
readme.md
688
readme.md
@@ -1,333 +1,423 @@
|
||||
# @push.rocks/smartpdf
|
||||
Create PDFs on the fly from HTML, websites, or existing PDFs with advanced features like text extraction, PDF merging, and PNG conversion.
|
||||
# @push.rocks/smartpdf 📄✨
|
||||
|
||||
## Install
|
||||
To install `@push.rocks/smartpdf`, use npm or yarn:
|
||||
> **Transform HTML, websites, and PDFs into beautiful documents and images with just a few lines of code.**
|
||||
|
||||
[](https://www.npmjs.com/package/@push.rocks/smartpdf)
|
||||
[](https://www.typescriptlang.org/)
|
||||
[](./license)
|
||||
|
||||
## Issue Reporting and Security
|
||||
|
||||
For reporting bugs, issues, or security vulnerabilities, please visit [community.foss.global/](https://community.foss.global/). This is the central community hub for all issue reporting. Developers who sign and comply with our contribution agreement and go through identification can also get a [code.foss.global/](https://code.foss.global/) account to submit Pull Requests directly.
|
||||
|
||||
## 🚀 Why SmartPDF?
|
||||
|
||||
SmartPDF is your Swiss Army knife for PDF operations in Node.js. Whether you're generating invoices from HTML, snapshotting web pages, merging documents, or converting PDF pages to images — SmartPDF handles it all through a clean, async-first TypeScript API backed by headless Chromium.
|
||||
|
||||
### ✨ Features at a Glance
|
||||
|
||||
| Feature | Description |
|
||||
|---------|-------------|
|
||||
| 📝 **HTML → PDF** | Render any HTML string (with full CSS) into an A4-sized PDF |
|
||||
| 🌐 **Website → PDF** | Capture a live URL as a PDF — either A4 or full-page scroll |
|
||||
| 🔀 **PDF Merging** | Combine multiple PDF buffers into a single document |
|
||||
| 🖼️ **PDF → Images** | Convert PDF pages to **PNG**, **WebP**, or progressive **JPEG** |
|
||||
| 📑 **Text Extraction** | Pull raw text content from any PDF buffer |
|
||||
| 🔌 **Smart Port Management** | Automatic port allocation so multiple instances never collide |
|
||||
| 🎛️ **DPI Control** | Built-in scale constants for screen, high-quality, and print resolutions |
|
||||
| 🌐 **BYO Browser** | Optionally pass your own Puppeteer `Browser` instance |
|
||||
|
||||
## 📦 Installation
|
||||
|
||||
```bash
|
||||
npm install @push.rocks/smartpdf --save
|
||||
pnpm add @push.rocks/smartpdf
|
||||
```
|
||||
|
||||
Or with yarn:
|
||||
> **Prerequisites:** SmartPDF uses headless Chromium via Puppeteer under the hood. On most systems this is handled automatically. If you run into browser-launch issues (CI, Docker, etc.), make sure the required system libraries are installed — see the [Puppeteer troubleshooting guide](https://pptr.dev/troubleshooting).
|
||||
|
||||
```bash
|
||||
yarn add @push.rocks/smartpdf
|
||||
```
|
||||
|
||||
## Requirements
|
||||
This package requires a Chrome or Chromium installation to be available on the system, as it uses Puppeteer for rendering. The package will automatically detect and use the appropriate executable.
|
||||
|
||||
## Usage
|
||||
`@push.rocks/smartpdf` provides a powerful interface for PDF generation and manipulation. All examples use ESM syntax and TypeScript.
|
||||
|
||||
### Getting Started
|
||||
First, import the necessary classes:
|
||||
## 🎯 Quick Start
|
||||
|
||||
```typescript
|
||||
import { SmartPdf, IPdf } from '@push.rocks/smartpdf';
|
||||
```
|
||||
import { SmartPdf } from '@push.rocks/smartpdf';
|
||||
import * as fs from 'fs';
|
||||
|
||||
### Basic Setup with Automatic Port Allocation
|
||||
SmartPdf automatically finds an available port between 20000-30000 for its internal server:
|
||||
|
||||
```typescript
|
||||
async function setupSmartPdf() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
// Your PDF operations here
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
### Advanced Setup with Custom Port Configuration
|
||||
You can specify custom port settings to avoid conflicts or meet specific requirements:
|
||||
|
||||
```typescript
|
||||
// Use a specific port
|
||||
const smartPdf = await SmartPdf.create({ port: 3000 });
|
||||
|
||||
// Use a custom port range
|
||||
const smartPdf = await SmartPdf.create({
|
||||
portRangeStart: 4000,
|
||||
portRangeEnd: 5000
|
||||
});
|
||||
|
||||
// The server will find an available port in your specified range
|
||||
// 1. Create and start
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
console.log(`Server running on port: ${smartPdf.serverPort}`);
|
||||
|
||||
// 2. Generate a PDF from HTML
|
||||
const pdf = await smartPdf.getA4PdfResultForHtmlString(`
|
||||
<h1>Hello, PDF World! 🌍</h1>
|
||||
<p>Generated with SmartPDF.</p>
|
||||
`);
|
||||
|
||||
// 3. Write to disk
|
||||
fs.writeFileSync('my-first.pdf', pdf.buffer);
|
||||
|
||||
// 4. Clean up
|
||||
await smartPdf.stop();
|
||||
```
|
||||
|
||||
### Creating PDFs from HTML Strings
|
||||
Generate PDFs from HTML content with full CSS support:
|
||||
|
||||
```typescript
|
||||
async function createPdfFromHtml() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
const htmlString = `
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<style>
|
||||
body { font-family: Arial, sans-serif; margin: 40px; }
|
||||
h1 { color: #333; }
|
||||
.highlight { background-color: yellow; }
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<h1>Professional PDF Document</h1>
|
||||
<p>This PDF was generated from <span class="highlight">HTML content</span>.</p>
|
||||
</body>
|
||||
</html>
|
||||
`;
|
||||
|
||||
const pdf: IPdf = await smartPdf.getA4PdfResultForHtmlString(htmlString);
|
||||
|
||||
// pdf.buffer contains the PDF data
|
||||
// pdf.id contains a unique identifier
|
||||
// pdf.name contains the filename
|
||||
// pdf.metadata contains additional information like extracted text
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
### Generating PDFs from Websites
|
||||
Capture web pages as PDFs with two different approaches:
|
||||
|
||||
#### A4 Format PDF from Website
|
||||
Captures the viewable area formatted for A4 paper:
|
||||
|
||||
```typescript
|
||||
async function createA4PdfFromWebsite() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
const pdf: IPdf = await smartPdf.getPdfResultForWebsite('https://example.com');
|
||||
|
||||
// Save to file
|
||||
await fs.writeFile('website-a4.pdf', pdf.buffer);
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
#### Full Webpage as Single PDF
|
||||
Captures the entire webpage in a single PDF, regardless of length:
|
||||
|
||||
```typescript
|
||||
async function createFullPdfFromWebsite() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
const pdf: IPdf = await smartPdf.getFullWebsiteAsSinglePdf('https://example.com');
|
||||
|
||||
// This captures the entire scrollable area
|
||||
await fs.writeFile('website-full.pdf', pdf.buffer);
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
### Merging Multiple PDFs
|
||||
Combine multiple PDF files into a single document:
|
||||
|
||||
```typescript
|
||||
async function mergePdfs() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
// Create or load your PDFs
|
||||
const pdf1 = await smartPdf.getA4PdfResultForHtmlString('<h1>Document 1</h1>');
|
||||
const pdf2 = await smartPdf.getA4PdfResultForHtmlString('<h1>Document 2</h1>');
|
||||
const pdf3 = await smartPdf.readFileToPdfObject('./existing-document.pdf');
|
||||
|
||||
// Merge PDFs - order matters!
|
||||
const mergedPdf: Uint8Array = await smartPdf.mergePdfs([
|
||||
pdf1.buffer,
|
||||
pdf2.buffer,
|
||||
pdf3.buffer
|
||||
]);
|
||||
|
||||
// Save the merged PDF
|
||||
await fs.writeFile('merged-document.pdf', mergedPdf);
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
### Reading PDFs and Extracting Text
|
||||
Extract text content from existing PDFs:
|
||||
|
||||
```typescript
|
||||
async function extractTextFromPdf() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
|
||||
// Read PDF from disk
|
||||
const pdf: IPdf = await smartPdf.readFileToPdfObject('/path/to/document.pdf');
|
||||
|
||||
// Extract all text
|
||||
const extractedText = await smartPdf.extractTextFromPdfBuffer(pdf.buffer);
|
||||
console.log('Extracted text:', extractedText);
|
||||
|
||||
// The pdf object also contains metadata with text extraction
|
||||
console.log('Metadata:', pdf.metadata);
|
||||
}
|
||||
```
|
||||
|
||||
### Converting PDF to PNG Images
|
||||
Convert each page of a PDF into PNG images:
|
||||
|
||||
```typescript
|
||||
async function convertPdfToPng() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
// Load a PDF
|
||||
const pdf = await smartPdf.readFileToPdfObject('./document.pdf');
|
||||
|
||||
// Convert to PNG images (one per page)
|
||||
const pngImages: Uint8Array[] = await smartPdf.convertPDFToPngBytes(pdf.buffer);
|
||||
|
||||
// Save each page as a PNG
|
||||
pngImages.forEach((pngBuffer, index) => {
|
||||
fs.writeFileSync(`page-${index + 1}.png`, pngBuffer);
|
||||
});
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
### Using External Browser Instance
|
||||
For advanced use cases, you can provide your own Puppeteer browser instance:
|
||||
|
||||
```typescript
|
||||
import puppeteer from 'puppeteer';
|
||||
|
||||
async function useExternalBrowser() {
|
||||
// Create your own browser instance with custom options
|
||||
const browser = await puppeteer.launch({
|
||||
headless: true,
|
||||
args: ['--no-sandbox', '--disable-setuid-sandbox']
|
||||
});
|
||||
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start(browser);
|
||||
|
||||
// Use SmartPdf normally
|
||||
const pdf = await smartPdf.getA4PdfResultForHtmlString('<h1>Hello</h1>');
|
||||
|
||||
// SmartPdf will not close the browser when stopping
|
||||
await smartPdf.stop();
|
||||
|
||||
// You control the browser lifecycle
|
||||
await browser.close();
|
||||
}
|
||||
```
|
||||
|
||||
### Running Multiple Instances
|
||||
Thanks to automatic port allocation, you can run multiple SmartPdf instances simultaneously:
|
||||
|
||||
```typescript
|
||||
async function runMultipleInstances() {
|
||||
// Each instance automatically finds its own free port
|
||||
const instance1 = await SmartPdf.create();
|
||||
const instance2 = await SmartPdf.create();
|
||||
const instance3 = await SmartPdf.create();
|
||||
|
||||
// Start all instances
|
||||
await Promise.all([
|
||||
instance1.start(),
|
||||
instance2.start(),
|
||||
instance3.start()
|
||||
]);
|
||||
|
||||
console.log(`Instance 1 running on port: ${instance1.serverPort}`);
|
||||
console.log(`Instance 2 running on port: ${instance2.serverPort}`);
|
||||
console.log(`Instance 3 running on port: ${instance3.serverPort}`);
|
||||
|
||||
// Use instances independently
|
||||
const pdfs = await Promise.all([
|
||||
instance1.getA4PdfResultForHtmlString('<h1>PDF 1</h1>'),
|
||||
instance2.getA4PdfResultForHtmlString('<h1>PDF 2</h1>'),
|
||||
instance3.getA4PdfResultForHtmlString('<h1>PDF 3</h1>')
|
||||
]);
|
||||
|
||||
// Clean up all instances
|
||||
await Promise.all([
|
||||
instance1.stop(),
|
||||
instance2.stop(),
|
||||
instance3.stop()
|
||||
]);
|
||||
}
|
||||
```
|
||||
|
||||
### Error Handling
|
||||
Always wrap SmartPdf operations in try-catch blocks and ensure proper cleanup:
|
||||
|
||||
```typescript
|
||||
async function safePdfGeneration() {
|
||||
let smartPdf: SmartPdf;
|
||||
|
||||
try {
|
||||
smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
const pdf = await smartPdf.getA4PdfResultForHtmlString('<h1>Hello</h1>');
|
||||
// Process PDF...
|
||||
|
||||
} catch (error) {
|
||||
console.error('PDF generation failed:', error);
|
||||
// Handle error appropriately
|
||||
} finally {
|
||||
// Always cleanup
|
||||
if (smartPdf) {
|
||||
await smartPdf.stop();
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### IPdf Interface
|
||||
The `IPdf` interface represents a PDF with its metadata:
|
||||
Every method returns an `IPdf` object:
|
||||
|
||||
```typescript
|
||||
interface IPdf {
|
||||
name: string; // Filename of the PDF
|
||||
buffer: Buffer; // PDF content as buffer
|
||||
id: string | null; // Unique identifier
|
||||
id: string | null; // Unique identifier
|
||||
name: string; // Filename
|
||||
buffer: Buffer; // Raw PDF bytes
|
||||
metadata?: {
|
||||
textExtraction?: string; // Extracted text content
|
||||
textExtraction?: string; // Extracted text (when available)
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
## Best Practices
|
||||
## 📚 How It Works
|
||||
|
||||
1. **Always start and stop**: Initialize with `start()` and cleanup with `stop()` to properly manage resources.
|
||||
2. **Port management**: Use the automatic port allocation feature to avoid conflicts when running multiple instances.
|
||||
3. **Error handling**: Always implement proper error handling as PDF generation can fail due to various reasons.
|
||||
4. **Resource cleanup**: Ensure `stop()` is called even if an error occurs to prevent memory leaks.
|
||||
5. **HTML optimization**: When creating PDFs from HTML, ensure your HTML is well-formed and CSS is embedded or inlined.
|
||||
SmartPDF spins up a lightweight Express server bound to `localhost` and a headless Chromium browser. When you call a generation method:
|
||||
|
||||
1. Your HTML is registered internally and served at `http://localhost:{port}/{id}`
|
||||
2. Puppeteer navigates to that URL, waits for the page to fully render, and captures a PDF
|
||||
3. A header-based security check ensures only the correct content is captured
|
||||
4. The server and browser are torn down when you call `stop()`
|
||||
|
||||
This architecture means you get **pixel-perfect CSS rendering**, **web font support**, and **full JavaScript execution** — the same rendering engine that powers Chrome.
|
||||
|
||||
## 🏗️ Instance Management
|
||||
|
||||
```typescript
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
// ... your operations ...
|
||||
|
||||
await smartPdf.stop();
|
||||
```
|
||||
|
||||
For production use, wrap in try/finally:
|
||||
|
||||
```typescript
|
||||
const smartPdf = await SmartPdf.create();
|
||||
try {
|
||||
await smartPdf.start();
|
||||
// ... generate PDFs ...
|
||||
} finally {
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
### 🔌 Smart Port Allocation
|
||||
|
||||
Run multiple instances without conflicts:
|
||||
|
||||
```typescript
|
||||
// Each instance auto-selects a free port (default range: 20000–30000)
|
||||
const instance1 = new SmartPdf();
|
||||
const instance2 = new SmartPdf();
|
||||
await instance1.start(); // e.g. port 20000
|
||||
await instance2.start(); // e.g. port 20001
|
||||
|
||||
console.log(instance1.serverPort); // 20000
|
||||
console.log(instance2.serverPort); // 20001
|
||||
|
||||
// Custom range
|
||||
const custom = new SmartPdf({ portRangeStart: 4000, portRangeEnd: 5000 });
|
||||
|
||||
// Or pin a specific port
|
||||
const pinned = new SmartPdf({ port: 3000 });
|
||||
```
|
||||
|
||||
If a specific port is already in use, `start()` throws an error immediately instead of silently failing.
|
||||
|
||||
### 🌐 Bring Your Own Browser
|
||||
|
||||
Pass an existing Puppeteer `Browser` instance — SmartPDF won't close it when you call `stop()`:
|
||||
|
||||
```typescript
|
||||
import puppeteer from 'puppeteer';
|
||||
|
||||
const browser = await puppeteer.launch({
|
||||
headless: 'new',
|
||||
args: ['--no-sandbox'],
|
||||
});
|
||||
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start(browser); // uses your browser
|
||||
|
||||
await smartPdf.stop(); // server stops, browser stays open
|
||||
await browser.close(); // you manage browser lifecycle
|
||||
```
|
||||
|
||||
## 🎨 PDF Generation
|
||||
|
||||
### 📝 HTML → A4 PDF
|
||||
|
||||
Renders at a 794×1122 viewport (A4 at 96 DPI) with full CSS support:
|
||||
|
||||
```typescript
|
||||
const pdf = await smartPdf.getA4PdfResultForHtmlString(`
|
||||
<style>
|
||||
body { font-family: 'Helvetica', sans-serif; margin: 40px; }
|
||||
.header {
|
||||
background: linear-gradient(135deg, #667eea, #764ba2);
|
||||
color: white; padding: 30px; border-radius: 10px; text-align: center;
|
||||
}
|
||||
table { width: 100%; border-collapse: collapse; margin-top: 20px; }
|
||||
th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
|
||||
th { background: #f5f5f5; }
|
||||
</style>
|
||||
|
||||
<div class="header">
|
||||
<h1>Invoice #2024-001</h1>
|
||||
</div>
|
||||
|
||||
<table>
|
||||
<tr><th>Item</th><th>Qty</th><th>Price</th></tr>
|
||||
<tr><td>Widget Pro</td><td>5</td><td>$49.99</td></tr>
|
||||
<tr><td>Gizmo Ultra</td><td>2</td><td>$129.99</td></tr>
|
||||
</table>
|
||||
`);
|
||||
|
||||
fs.writeFileSync('invoice.pdf', pdf.buffer);
|
||||
```
|
||||
|
||||
### 🌐 Website → PDF
|
||||
|
||||
Two methods depending on your needs:
|
||||
|
||||
```typescript
|
||||
// Standard capture — uses the document's own dimensions
|
||||
const pdf = await smartPdf.getPdfResultForWebsite('https://example.com');
|
||||
|
||||
// Full-page capture — scrolls to bottom, captures everything as a single page
|
||||
const fullPdf = await smartPdf.getFullWebsiteAsSinglePdf('https://example.com');
|
||||
```
|
||||
|
||||
`getPdfResultForWebsite` uses a 1980×1200 viewport and respects the page's own width/height. `getFullWebsiteAsSinglePdf` uses a 1920px-wide viewport and measures the full scroll height, producing a single tall page.
|
||||
|
||||
### 🔀 Merge Multiple PDFs
|
||||
|
||||
Combine any number of PDF buffers into one document using `pdf-lib`:
|
||||
|
||||
```typescript
|
||||
const invoice = await smartPdf.readFileToPdfObject('./invoice.pdf');
|
||||
const terms = await smartPdf.readFileToPdfObject('./terms.pdf');
|
||||
const appendix = await smartPdf.getA4PdfResultForHtmlString('<h1>Appendix</h1>...');
|
||||
|
||||
const merged = await smartPdf.mergePdfs([
|
||||
invoice.buffer,
|
||||
terms.buffer,
|
||||
appendix.buffer,
|
||||
]);
|
||||
|
||||
fs.writeFileSync('complete-package.pdf', merged);
|
||||
```
|
||||
|
||||
### 📑 Read a PDF from Disk
|
||||
|
||||
```typescript
|
||||
const pdfObject = await smartPdf.readFileToPdfObject('./document.pdf');
|
||||
console.log(pdfObject.name); // "document.pdf"
|
||||
console.log(pdfObject.buffer); // <Buffer ...>
|
||||
```
|
||||
|
||||
### 📖 Extract Text
|
||||
|
||||
Pull raw text from any PDF buffer:
|
||||
|
||||
```typescript
|
||||
const text = await smartPdf.extractTextFromPdfBuffer(pdf.buffer);
|
||||
console.log(text);
|
||||
```
|
||||
|
||||
> Uses [pdf2json](https://github.com/modesty/pdf2json) under the hood. Works best with text-based PDFs; scanned documents may return limited results.
|
||||
|
||||
## 🖼️ PDF → Image Conversion
|
||||
|
||||
Convert PDF pages to raster images using Puppeteer + PDF.js. Each page becomes a separate image buffer.
|
||||
|
||||
### PNG — Lossless Quality
|
||||
|
||||
```typescript
|
||||
const pngPages = await smartPdf.convertPDFToPngBytes(pdf.buffer, {
|
||||
scale: SmartPdf.SCALE_HIGH, // 3.0 = ~216 DPI (default)
|
||||
});
|
||||
|
||||
pngPages.forEach((png, i) => {
|
||||
fs.writeFileSync(`page-${i + 1}.png`, Buffer.from(png));
|
||||
});
|
||||
```
|
||||
|
||||
### WebP — Modern & Efficient
|
||||
|
||||
25–60% smaller than PNG at similar visual quality:
|
||||
|
||||
```typescript
|
||||
const webpPages = await smartPdf.convertPDFToWebpBytes(pdf.buffer, {
|
||||
scale: 2.0, // ~144 DPI
|
||||
quality: 90, // 0–100 (default: 85)
|
||||
});
|
||||
```
|
||||
|
||||
### JPEG — Progressive Loading
|
||||
|
||||
Generates true progressive JPEGs (multi-pass rendering) via sharp:
|
||||
|
||||
```typescript
|
||||
const jpegPages = await smartPdf.convertPDFToJpegBytes(pdf.buffer, {
|
||||
scale: SmartPdf.SCALE_HIGH,
|
||||
quality: 85, // 0–100 (default: 85)
|
||||
maxWidth: 1920, // optional dimension constraints
|
||||
maxHeight: 1080,
|
||||
});
|
||||
```
|
||||
|
||||
### 📏 DPI & Scale Reference
|
||||
|
||||
All image methods accept a `scale` parameter. PDF.js renders at 72 DPI by default, so `scale` is a multiplier:
|
||||
|
||||
| Constant | Value | DPI | Use Case |
|
||||
|----------|-------|-----|----------|
|
||||
| `SmartPdf.SCALE_SCREEN` | 2.0 | ~144 | Web display, thumbnails |
|
||||
| `SmartPdf.SCALE_HIGH` | 3.0 | ~216 | General purpose (default) |
|
||||
| `SmartPdf.SCALE_PRINT` | 6.0 | ~432 | Print-quality output |
|
||||
|
||||
Or calculate a custom scale:
|
||||
|
||||
```typescript
|
||||
const scale = SmartPdf.getScaleForDPI(300); // → 4.167
|
||||
```
|
||||
|
||||
### 🖼️ Dimension Constraints
|
||||
|
||||
All image methods support `maxWidth` and `maxHeight` to cap output size while preserving aspect ratio:
|
||||
|
||||
```typescript
|
||||
// High-res render, but capped at 800×1000 px
|
||||
const constrained = await smartPdf.convertPDFToWebpBytes(pdf.buffer, {
|
||||
scale: SmartPdf.SCALE_HIGH,
|
||||
quality: 90,
|
||||
maxWidth: 800,
|
||||
maxHeight: 1000,
|
||||
});
|
||||
```
|
||||
|
||||
### 📊 Format Comparison
|
||||
|
||||
| Format | Typical Size vs PNG | Lossy? | Transparency | Progressive | Best For |
|
||||
|--------|-------------------|--------|--------------|-------------|----------|
|
||||
| **PNG** | baseline | No | ✅ | — | Screenshots, diagrams, text-heavy docs |
|
||||
| **WebP** | 40–75% | Yes | ✅ | — | Modern web apps, thumbnails |
|
||||
| **JPEG** | 50–70% | Yes | ❌ | ✅ | Photos, complex graphics, email |
|
||||
|
||||
## ⚡ Parallel Processing
|
||||
|
||||
Process multiple URLs concurrently with separate instances:
|
||||
|
||||
```typescript
|
||||
const urls = [
|
||||
'https://example.com/page1',
|
||||
'https://example.com/page2',
|
||||
'https://example.com/page3',
|
||||
];
|
||||
|
||||
// Spin up parallel instances
|
||||
const instances = await Promise.all(
|
||||
urls.map(() => SmartPdf.create())
|
||||
);
|
||||
await Promise.all(instances.map(i => i.start()));
|
||||
|
||||
// Generate in parallel
|
||||
const pdfs = await Promise.all(
|
||||
urls.map((url, i) => instances[i].getFullWebsiteAsSinglePdf(url))
|
||||
);
|
||||
|
||||
// Merge all results
|
||||
const merged = await instances[0].mergePdfs(pdfs.map(p => p.buffer));
|
||||
fs.writeFileSync('all-pages.pdf', merged);
|
||||
|
||||
// Clean up
|
||||
await Promise.all(instances.map(i => i.stop()));
|
||||
```
|
||||
|
||||
## 📝 Full API Reference
|
||||
|
||||
### `SmartPdf` Class
|
||||
|
||||
#### Static Properties
|
||||
|
||||
| Property | Type | Value | Description |
|
||||
|----------|------|-------|-------------|
|
||||
| `SCALE_SCREEN` | `number` | `2.0` | ~144 DPI scale factor |
|
||||
| `SCALE_HIGH` | `number` | `3.0` | ~216 DPI scale factor (default) |
|
||||
| `SCALE_PRINT` | `number` | `6.0` | ~432 DPI scale factor |
|
||||
|
||||
#### Static Methods
|
||||
|
||||
| Method | Returns | Description |
|
||||
|--------|---------|-------------|
|
||||
| `create(options?)` | `Promise<SmartPdf>` | Factory method to create an instance |
|
||||
| `getScaleForDPI(dpi)` | `number` | Converts a DPI value to a scale factor (`dpi / 72`) |
|
||||
|
||||
#### Instance Properties
|
||||
|
||||
| Property | Type | Description |
|
||||
|----------|------|-------------|
|
||||
| `serverPort` | `number` | The port the internal Express server is listening on |
|
||||
|
||||
#### Instance Methods
|
||||
|
||||
| Method | Returns | Description |
|
||||
|--------|---------|-------------|
|
||||
| `start(browser?)` | `Promise<void>` | Starts internal server + browser. Optionally accepts an existing Puppeteer `Browser`. |
|
||||
| `stop()` | `Promise<void>` | Shuts down server and browser (unless external browser was provided). |
|
||||
| `getA4PdfResultForHtmlString(html)` | `Promise<IPdf>` | Renders HTML at 794×1122 viewport → A4 PDF |
|
||||
| `getPdfResultForWebsite(url)` | `Promise<IPdf>` | Captures website at 1980×1200 viewport → PDF |
|
||||
| `getFullWebsiteAsSinglePdf(url)` | `Promise<IPdf>` | Captures full scrollable page at 1920px wide → single-page PDF |
|
||||
| `mergePdfs(buffers)` | `Promise<Uint8Array>` | Merges an array of PDF `Uint8Array` buffers |
|
||||
| `readFileToPdfObject(path)` | `Promise<IPdf>` | Reads a PDF file from disk into an `IPdf` object |
|
||||
| `extractTextFromPdfBuffer(buffer)` | `Promise<string>` | Extracts raw text from a PDF buffer |
|
||||
| `convertPDFToPngBytes(buffer, opts?)` | `Promise<Uint8Array[]>` | Converts each PDF page to a PNG buffer |
|
||||
| `convertPDFToWebpBytes(buffer, opts?)` | `Promise<Uint8Array[]>` | Converts each PDF page to a WebP buffer |
|
||||
| `convertPDFToJpegBytes(buffer, opts?)` | `Promise<Uint8Array[]>` | Converts each PDF page to a progressive JPEG buffer |
|
||||
|
||||
#### Image Conversion Options
|
||||
|
||||
```typescript
|
||||
{
|
||||
scale?: number; // DPI multiplier (default: 3.0)
|
||||
quality?: number; // 0–100, WebP/JPEG only (default: 85)
|
||||
maxWidth?: number; // Max output width in pixels
|
||||
maxHeight?: number; // Max output height in pixels
|
||||
}
|
||||
```
|
||||
|
||||
### `ISmartPdfOptions` Interface
|
||||
|
||||
```typescript
|
||||
{
|
||||
port?: number; // Use a specific port
|
||||
portRangeStart?: number; // Auto-allocation range start (default: 20000)
|
||||
portRangeEnd?: number; // Auto-allocation range end (default: 30000)
|
||||
}
|
||||
```
|
||||
|
||||
## License and Legal Information
|
||||
|
||||
This repository contains open-source code that is licensed under the MIT License. A copy of the MIT License can be found in the [license](license) file within this repository.
|
||||
This repository contains open-source code licensed under the MIT License. A copy of the license can be found in the [LICENSE](./LICENSE) file.
|
||||
|
||||
**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.
|
||||
|
||||
### Trademarks
|
||||
|
||||
This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH and are not included within the scope of the MIT license granted herein. Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines, and any usage must be approved in writing by Task Venture Capital GmbH.
|
||||
This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH or third parties, and are not included within the scope of the MIT license granted herein.
|
||||
|
||||
Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines or the guidelines of the respective third-party owners, and any usage must be approved in writing. Third-party trademarks used herein are the property of their respective owners and used only in a descriptive manner, e.g. for an implementation of an API or similar.
|
||||
|
||||
### Company Information
|
||||
|
||||
Task Venture Capital GmbH
|
||||
Registered at District court Bremen HRB 35230 HB, Germany
|
||||
Task Venture Capital GmbH
|
||||
Registered at District Court Bremen HRB 35230 HB, Germany
|
||||
|
||||
For any legal inquiries or if you require further information, please contact us via email at hello@task.vc.
|
||||
For any legal inquiries or further information, please contact us via email at hello@task.vc.
|
||||
|
||||
By using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.
|
||||
By using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.
|
||||
|
||||
224
test/test.ts
224
test/test.ts
@@ -15,6 +15,13 @@ function ensureDir(dirPath: string): void {
|
||||
}
|
||||
}
|
||||
|
||||
// Clean test results directory at start
|
||||
const testResultsDir = path.join('.nogit', 'testresults');
|
||||
if (fs.existsSync(testResultsDir)) {
|
||||
fs.rmSync(testResultsDir, { recursive: true, force: true });
|
||||
}
|
||||
ensureDir(testResultsDir);
|
||||
|
||||
tap.test('should create a valid instance of SmartPdf', async () => {
|
||||
testSmartPdf = new smartpdf.SmartPdf();
|
||||
expect(testSmartPdf).toBeInstanceOf(smartpdf.SmartPdf);
|
||||
@@ -32,8 +39,8 @@ tap.test('should create PDFs from HTML string', async () => {
|
||||
});
|
||||
|
||||
tap.test('should create PDFs from websites', async () => {
|
||||
const pdfA4 = await testSmartPdf.getPdfResultForWebsite('https://www.wikipedia.org');
|
||||
const pdfSingle = await testSmartPdf.getFullWebsiteAsSinglePdf('https://www.wikipedia.org');
|
||||
const pdfA4 = await testSmartPdf.getPdfResultForWebsite('https://example.com');
|
||||
const pdfSingle = await testSmartPdf.getFullWebsiteAsSinglePdf('https://example.com');
|
||||
expect(pdfA4.buffer).toBeInstanceOf(Buffer);
|
||||
expect(pdfSingle.buffer).toBeInstanceOf(Buffer);
|
||||
});
|
||||
@@ -65,21 +72,224 @@ tap.test('should create PNG images from combined PDF using Puppeteer conversion'
|
||||
});
|
||||
|
||||
tap.test('should store PNG results from both conversion functions in .nogit/testresults', async () => {
|
||||
const testResultsDir = path.join('.nogit', 'testresults');
|
||||
ensureDir(testResultsDir);
|
||||
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/combined.pdf');
|
||||
|
||||
// Convert using Puppeteer-based function and store images
|
||||
const imagesPuppeteer = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
|
||||
imagesPuppeteer.forEach((img, index) => {
|
||||
const filePath = path.join(testResultsDir, `puppeteer_method_page_${index + 1}.png`);
|
||||
const filePath = path.join(testResultsDir, `png_combined_page${index + 1}.png`);
|
||||
fs.writeFileSync(filePath, Buffer.from(img));
|
||||
});
|
||||
});
|
||||
|
||||
tap.test('should create a third PDF for image conversion tests', async () => {
|
||||
const pdfResult = await testSmartPdf.getFullWebsiteAsSinglePdf('https://www.wikipedia.org');
|
||||
expect(pdfResult.buffer).toBeInstanceOf(Buffer);
|
||||
ensureDir('.nogit');
|
||||
fs.writeFileSync(path.join('.nogit', '3.pdf'), pdfResult.buffer as Buffer);
|
||||
});
|
||||
|
||||
tap.test('should create WebP preview images from PDF', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
const webpPreviews = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer);
|
||||
expect(webpPreviews.length).toBeGreaterThan(0);
|
||||
console.log('WebP preview sizes:', webpPreviews.map(img => img.length));
|
||||
|
||||
// Also create PNG previews for comparison
|
||||
const pngPreviews = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
|
||||
console.log('PNG preview sizes:', pngPreviews.map(img => img.length));
|
||||
|
||||
// Save the first page as both WebP and PNG preview
|
||||
fs.writeFileSync(path.join(testResultsDir, 'webp_default_page1.webp'), Buffer.from(webpPreviews[0]));
|
||||
fs.writeFileSync(path.join(testResultsDir, 'png_default_page1.png'), Buffer.from(pngPreviews[0]));
|
||||
});
|
||||
|
||||
tap.test('should create WebP previews with custom scale and quality', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
|
||||
// Create smaller previews with lower quality for thumbnails
|
||||
const thumbnails = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
|
||||
scale: 0.5, // Create readable thumbnails at ~36 DPI
|
||||
quality: 70
|
||||
});
|
||||
|
||||
expect(thumbnails.length).toBeGreaterThan(0);
|
||||
console.log('Thumbnail sizes:', thumbnails.map(img => img.length));
|
||||
|
||||
// Save thumbnails
|
||||
thumbnails.forEach((thumb, index) => {
|
||||
fs.writeFileSync(path.join(testResultsDir, `webp_thumbnail_page${index + 1}.webp`), Buffer.from(thumb));
|
||||
});
|
||||
});
|
||||
|
||||
tap.test('should create WebP previews with max dimensions', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
|
||||
// Create previews with maximum dimensions (will use high scale but constrain to max size)
|
||||
const constrainedPreviews = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
|
||||
scale: smartpdf.SmartPdf.SCALE_HIGH, // Start with high quality
|
||||
quality: 90,
|
||||
maxWidth: 800,
|
||||
maxHeight: 1000
|
||||
});
|
||||
|
||||
expect(constrainedPreviews.length).toBeGreaterThan(0);
|
||||
console.log('Constrained preview sizes:', constrainedPreviews.map(img => img.length));
|
||||
|
||||
// Save constrained preview
|
||||
fs.writeFileSync(path.join(testResultsDir, 'webp_constrained_page1.webp'), Buffer.from(constrainedPreviews[0]));
|
||||
});
|
||||
|
||||
tap.test('should verify WebP files are smaller than PNG', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
|
||||
// Generate both PNG and WebP versions at the same scale for fair comparison
|
||||
const comparisonScale = smartpdf.SmartPdf.SCALE_HIGH; // Both use 3.0 scale
|
||||
|
||||
const pngImages = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer, {
|
||||
scale: comparisonScale
|
||||
});
|
||||
const webpImages = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
|
||||
scale: comparisonScale,
|
||||
quality: 85
|
||||
});
|
||||
|
||||
expect(pngImages.length).toEqual(webpImages.length);
|
||||
|
||||
// Compare sizes
|
||||
let totalPngSize = 0;
|
||||
let totalWebpSize = 0;
|
||||
|
||||
pngImages.forEach((png, index) => {
|
||||
const pngSize = png.length;
|
||||
const webpSize = webpImages[index].length;
|
||||
totalPngSize += pngSize;
|
||||
totalWebpSize += webpSize;
|
||||
|
||||
const reduction = ((pngSize - webpSize) / pngSize * 100).toFixed(1);
|
||||
console.log(`Page ${index + 1}: PNG=${pngSize} bytes, WebP=${webpSize} bytes, Reduction=${reduction}%`);
|
||||
|
||||
// Save comparison files
|
||||
fs.writeFileSync(path.join(testResultsDir, `comparison_png_page${index + 1}.png`), Buffer.from(png));
|
||||
fs.writeFileSync(path.join(testResultsDir, `comparison_webp_page${index + 1}.webp`), Buffer.from(webpImages[index]));
|
||||
});
|
||||
|
||||
const totalReduction = ((totalPngSize - totalWebpSize) / totalPngSize * 100).toFixed(1);
|
||||
console.log(`Total size reduction: ${totalReduction}% (PNG: ${totalPngSize} bytes, WebP: ${totalWebpSize} bytes)`);
|
||||
|
||||
// WebP should be smaller
|
||||
expect(totalWebpSize).toBeLessThan(totalPngSize);
|
||||
});
|
||||
|
||||
tap.test('should create JPEG images from PDF', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
const jpegImages = await testSmartPdf.convertPDFToJpegBytes(pdfObject.buffer);
|
||||
expect(jpegImages.length).toBeGreaterThan(0);
|
||||
console.log('JPEG image sizes:', jpegImages.map(img => img.length));
|
||||
|
||||
// Save the first page as JPEG
|
||||
fs.writeFileSync(path.join(testResultsDir, 'jpeg_default_page1.jpg'), Buffer.from(jpegImages[0]));
|
||||
});
|
||||
|
||||
tap.test('should create JPEG images with different quality levels', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
|
||||
// Test different quality levels
|
||||
const qualityLevels = [50, 70, 85, 95];
|
||||
|
||||
for (const quality of qualityLevels) {
|
||||
const jpegImages = await testSmartPdf.convertPDFToJpegBytes(pdfObject.buffer, {
|
||||
scale: smartpdf.SmartPdf.SCALE_HIGH,
|
||||
quality: quality
|
||||
});
|
||||
|
||||
console.log(`JPEG quality ${quality}: ${jpegImages[0].length} bytes`);
|
||||
|
||||
// Save first page at each quality level
|
||||
fs.writeFileSync(
|
||||
path.join(testResultsDir, `jpeg_quality_${quality}_page1.jpg`),
|
||||
Buffer.from(jpegImages[0])
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
tap.test('should create JPEG images with max dimensions', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
|
||||
// Create constrained JPEG images
|
||||
const constrainedJpegs = await testSmartPdf.convertPDFToJpegBytes(pdfObject.buffer, {
|
||||
scale: smartpdf.SmartPdf.SCALE_HIGH,
|
||||
quality: 85,
|
||||
maxWidth: 1200,
|
||||
maxHeight: 1200
|
||||
});
|
||||
|
||||
expect(constrainedJpegs.length).toBeGreaterThan(0);
|
||||
console.log('Constrained JPEG sizes:', constrainedJpegs.map(img => img.length));
|
||||
|
||||
// Save constrained JPEG
|
||||
fs.writeFileSync(path.join(testResultsDir, 'jpeg_constrained_page1.jpg'), Buffer.from(constrainedJpegs[0]));
|
||||
});
|
||||
|
||||
tap.test('should compare file sizes between PNG, WebP, and JPEG', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
|
||||
// Generate all three formats at the same scale
|
||||
const comparisonScale = smartpdf.SmartPdf.SCALE_HIGH; // 3.0 scale
|
||||
|
||||
const pngImages = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer, {
|
||||
scale: comparisonScale
|
||||
});
|
||||
const webpImages = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
|
||||
scale: comparisonScale,
|
||||
quality: 85
|
||||
});
|
||||
const jpegImages = await testSmartPdf.convertPDFToJpegBytes(pdfObject.buffer, {
|
||||
scale: comparisonScale,
|
||||
quality: 85
|
||||
});
|
||||
|
||||
expect(pngImages.length).toEqual(webpImages.length);
|
||||
expect(pngImages.length).toEqual(jpegImages.length);
|
||||
|
||||
// Compare sizes
|
||||
let totalPngSize = 0;
|
||||
let totalWebpSize = 0;
|
||||
let totalJpegSize = 0;
|
||||
|
||||
pngImages.forEach((png, index) => {
|
||||
const pngSize = png.length;
|
||||
const webpSize = webpImages[index].length;
|
||||
const jpegSize = jpegImages[index].length;
|
||||
|
||||
totalPngSize += pngSize;
|
||||
totalWebpSize += webpSize;
|
||||
totalJpegSize += jpegSize;
|
||||
|
||||
const webpReduction = ((pngSize - webpSize) / pngSize * 100).toFixed(1);
|
||||
const jpegReduction = ((pngSize - jpegSize) / pngSize * 100).toFixed(1);
|
||||
|
||||
console.log(`Page ${index + 1}:`);
|
||||
console.log(` PNG: ${pngSize} bytes`);
|
||||
console.log(` WebP: ${webpSize} bytes (${webpReduction}% smaller than PNG)`);
|
||||
console.log(` JPEG: ${jpegSize} bytes (${jpegReduction}% smaller than PNG)`);
|
||||
});
|
||||
|
||||
const totalWebpReduction = ((totalPngSize - totalWebpSize) / totalPngSize * 100).toFixed(1);
|
||||
const totalJpegReduction = ((totalPngSize - totalJpegSize) / totalPngSize * 100).toFixed(1);
|
||||
|
||||
console.log('\nTotal size comparison:');
|
||||
console.log(`PNG: ${totalPngSize} bytes`);
|
||||
console.log(`WebP: ${totalWebpSize} bytes (${totalWebpReduction}% reduction)`);
|
||||
console.log(`JPEG: ${totalJpegSize} bytes (${totalJpegReduction}% reduction)`);
|
||||
|
||||
// JPEG and WebP should both be smaller than PNG
|
||||
expect(totalJpegSize).toBeLessThan(totalPngSize);
|
||||
expect(totalWebpSize).toBeLessThan(totalPngSize);
|
||||
});
|
||||
|
||||
tap.test('should close the SmartPdf instance properly', async () => {
|
||||
await testSmartPdf.stop();
|
||||
});
|
||||
|
||||
tap.start();
|
||||
export default tap.start();
|
||||
@@ -3,6 +3,6 @@
|
||||
*/
|
||||
export const commitinfo = {
|
||||
name: '@push.rocks/smartpdf',
|
||||
version: '3.2.2',
|
||||
version: '4.1.2',
|
||||
description: 'A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.'
|
||||
}
|
||||
|
||||
@@ -3,8 +3,6 @@ import * as paths from './smartpdf.paths.js';
|
||||
import { Server } from 'http';
|
||||
import { PdfCandidate } from './smartpdf.classes.pdfcandidate.js';
|
||||
import { type IPdf } from '@tsclass/tsclass/dist_ts/business/pdf.js';
|
||||
import { execFile } from 'child_process';
|
||||
|
||||
declare const document: any;
|
||||
|
||||
export interface ISmartPdfOptions {
|
||||
@@ -14,6 +12,19 @@ export interface ISmartPdfOptions {
|
||||
}
|
||||
|
||||
export class SmartPdf {
|
||||
// STATIC SCALE CONSTANTS
|
||||
public static readonly SCALE_SCREEN = 2.0; // ~144 DPI - Good for screen display
|
||||
public static readonly SCALE_HIGH = 3.0; // ~216 DPI - High quality (default)
|
||||
public static readonly SCALE_PRINT = 6.0; // ~432 DPI - Print quality
|
||||
|
||||
/**
|
||||
* Calculate scale factor for desired DPI
|
||||
* PDF.js default is 72 DPI, so scale = desiredDPI / 72
|
||||
*/
|
||||
public static getScaleForDPI(dpi: number): number {
|
||||
return dpi / 72;
|
||||
}
|
||||
|
||||
// STATIC
|
||||
public static async create(optionsArg?: ISmartPdfOptions) {
|
||||
const smartpdfInstance = new SmartPdf(optionsArg);
|
||||
@@ -259,7 +270,9 @@ export class SmartPdf {
|
||||
public async readFileToPdfObject(pathArg: string): Promise<plugins.tsclass.business.IPdf> {
|
||||
const absolutePath = plugins.smartpath.transform.makeAbsolute(pathArg);
|
||||
const parsedPath = plugins.path.parse(absolutePath);
|
||||
const buffer = await plugins.smartfile.fs.toBuffer(absolutePath);
|
||||
const smartfsInstance = new plugins.smartfs.SmartFs(new plugins.smartfs.SmartFsProviderNode());
|
||||
const fileContent = await smartfsInstance.file(absolutePath).read();
|
||||
const buffer = Buffer.from(fileContent);
|
||||
return {
|
||||
name: parsedPath.base,
|
||||
buffer,
|
||||
@@ -286,31 +299,6 @@ export class SmartPdf {
|
||||
return deferred.promise;
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks for the presence of required dependencies: GraphicsMagick and Ghostscript.
|
||||
*/
|
||||
private async checkDependencies(): Promise<void> {
|
||||
await Promise.all([
|
||||
this.checkCommandExists('gm', ['version']),
|
||||
this.checkCommandExists('gs', ['--version']),
|
||||
]);
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if a given command exists by trying to execute it.
|
||||
*/
|
||||
private checkCommandExists(command: string, args: string[]): Promise<void> {
|
||||
return new Promise((resolve, reject) => {
|
||||
execFile(command, args, (error, stdout, stderr) => {
|
||||
if (error) {
|
||||
reject(new Error(`Dependency check failed: ${command} is not installed or not in the PATH. ${error.message}`));
|
||||
} else {
|
||||
resolve();
|
||||
}
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Converts a PDF to PNG bytes for each page using Puppeteer and PDF.js.
|
||||
* This method creates a temporary HTML page that loads PDF.js from a CDN,
|
||||
@@ -318,10 +306,14 @@ export class SmartPdf {
|
||||
*/
|
||||
public async convertPDFToPngBytes(
|
||||
pdfBytes: Uint8Array,
|
||||
options: { width?: number; height?: number; quality?: number } = {}
|
||||
options: {
|
||||
scale?: number; // Scale factor for output size (default: 3.0 for 216 DPI)
|
||||
maxWidth?: number; // Maximum width in pixels (optional)
|
||||
maxHeight?: number; // Maximum height in pixels (optional)
|
||||
} = {}
|
||||
): Promise<Uint8Array[]> {
|
||||
// Note: options.width, options.height, and options.quality are not applied here,
|
||||
// as the rendered canvas size is determined by the PDF page dimensions.
|
||||
// Set default scale for higher quality output (3.0 = ~216 DPI)
|
||||
const scale = options.scale || 3.0;
|
||||
|
||||
// Create a new page using the headless browser.
|
||||
const page = await this.headlessBrowser.newPage();
|
||||
@@ -354,12 +346,31 @@ export class SmartPdf {
|
||||
const numPages = pdf.numPages;
|
||||
for (let pageNum = 1; pageNum <= numPages; pageNum++) {
|
||||
const page = await pdf.getPage(pageNum);
|
||||
const viewport = page.getViewport({ scale: 1.0 });
|
||||
// Apply scale factor to viewport
|
||||
const viewport = page.getViewport({ scale: ${scale} });
|
||||
|
||||
// Apply max width/height constraints if specified
|
||||
let finalScale = ${scale};
|
||||
${options.maxWidth ? `
|
||||
if (viewport.width > ${options.maxWidth}) {
|
||||
finalScale = ${options.maxWidth} / (viewport.width / ${scale});
|
||||
}` : ''}
|
||||
${options.maxHeight ? `
|
||||
if (viewport.height > ${options.maxHeight}) {
|
||||
const heightScale = ${options.maxHeight} / (viewport.height / ${scale});
|
||||
finalScale = Math.min(finalScale, heightScale);
|
||||
}` : ''}
|
||||
|
||||
// Get final viewport with adjusted scale
|
||||
const finalViewport = page.getViewport({ scale: finalScale });
|
||||
|
||||
const canvas = document.createElement('canvas');
|
||||
const context = canvas.getContext('2d');
|
||||
canvas.width = viewport.width;
|
||||
canvas.height = viewport.height;
|
||||
await page.render({ canvasContext: context, viewport: viewport }).promise;
|
||||
canvas.width = finalViewport.width;
|
||||
canvas.height = finalViewport.height;
|
||||
canvas.setAttribute('data-page', pageNum);
|
||||
|
||||
await page.render({ canvasContext: context, viewport: finalViewport }).promise;
|
||||
document.body.appendChild(canvas);
|
||||
}
|
||||
window.renderComplete = true;
|
||||
@@ -391,4 +402,163 @@ export class SmartPdf {
|
||||
await page.close();
|
||||
return pngBuffers;
|
||||
}
|
||||
|
||||
/**
|
||||
* Converts a PDF to WebP bytes for each page.
|
||||
* This method creates web-optimized images using WebP format.
|
||||
* WebP provides 25-35% better compression than JPEG/PNG while maintaining quality.
|
||||
*/
|
||||
public async convertPDFToWebpBytes(
|
||||
pdfBytes: Uint8Array,
|
||||
options: {
|
||||
scale?: number; // Scale factor for preview size (default: 3.0 for 216 DPI)
|
||||
quality?: number; // WebP quality 0-100 (default: 85)
|
||||
maxWidth?: number; // Maximum width in pixels (optional)
|
||||
maxHeight?: number; // Maximum height in pixels (optional)
|
||||
} = {}
|
||||
): Promise<Uint8Array[]> {
|
||||
// Set default options for higher quality output (3.0 = ~216 DPI)
|
||||
const scale = options.scale || 3.0;
|
||||
const quality = options.quality || 85;
|
||||
|
||||
// Create a new page using the headless browser
|
||||
const page = await this.headlessBrowser.newPage();
|
||||
|
||||
// Prepare PDF data as a base64 string
|
||||
const base64Pdf: string = Buffer.from(pdfBytes).toString('base64');
|
||||
|
||||
// HTML template that loads PDF.js and renders the PDF with scaling
|
||||
const htmlTemplate: string = `
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<title>PDF to WebP Preview Converter</title>
|
||||
<style>
|
||||
body { margin: 0; }
|
||||
canvas { display: block; margin: 10px auto; }
|
||||
</style>
|
||||
<script src="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.min.js"></script>
|
||||
</head>
|
||||
<body>
|
||||
<script>
|
||||
(async function() {
|
||||
pdfjsLib.GlobalWorkerOptions.workerSrc = 'https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.worker.min.js';
|
||||
const pdfData = "__PDF_DATA__";
|
||||
const raw = atob(pdfData);
|
||||
const pdfArray = new Uint8Array([...raw].map(c => c.charCodeAt(0)));
|
||||
const loadingTask = pdfjsLib.getDocument({data: pdfArray});
|
||||
const pdf = await loadingTask.promise;
|
||||
const numPages = pdf.numPages;
|
||||
|
||||
for (let pageNum = 1; pageNum <= numPages; pageNum++) {
|
||||
const page = await pdf.getPage(pageNum);
|
||||
// Apply scale factor to viewport
|
||||
const viewport = page.getViewport({ scale: ${scale} });
|
||||
|
||||
// Apply max width/height constraints if specified
|
||||
let finalScale = ${scale};
|
||||
${options.maxWidth ? `
|
||||
if (viewport.width > ${options.maxWidth}) {
|
||||
finalScale = ${options.maxWidth} / (viewport.width / ${scale});
|
||||
}` : ''}
|
||||
${options.maxHeight ? `
|
||||
if (viewport.height > ${options.maxHeight}) {
|
||||
const heightScale = ${options.maxHeight} / (viewport.height / ${scale});
|
||||
finalScale = Math.min(finalScale, heightScale);
|
||||
}` : ''}
|
||||
|
||||
// Get final viewport with adjusted scale
|
||||
const finalViewport = page.getViewport({ scale: finalScale });
|
||||
|
||||
const canvas = document.createElement('canvas');
|
||||
const context = canvas.getContext('2d');
|
||||
canvas.width = finalViewport.width;
|
||||
canvas.height = finalViewport.height;
|
||||
canvas.setAttribute('data-page', pageNum);
|
||||
|
||||
await page.render({ canvasContext: context, viewport: finalViewport }).promise;
|
||||
document.body.appendChild(canvas);
|
||||
}
|
||||
window.renderComplete = true;
|
||||
})();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
`;
|
||||
|
||||
// Replace the placeholder with the actual base64 PDF data
|
||||
const htmlContent: string = htmlTemplate.replace("__PDF_DATA__", base64Pdf);
|
||||
|
||||
// Set the page content
|
||||
await page.setContent(htmlContent, { waitUntil: 'networkidle0' });
|
||||
|
||||
// Wait until the PDF.js rendering is complete
|
||||
await page.waitForFunction(() => (window as any).renderComplete === true, { timeout: 30000 });
|
||||
|
||||
// Query all canvas elements (each representing a rendered PDF page)
|
||||
const canvasElements = await page.$$('canvas');
|
||||
const webpBuffers: Uint8Array[] = [];
|
||||
|
||||
for (const canvasElement of canvasElements) {
|
||||
// Screenshot the canvas element as WebP
|
||||
const screenshotBuffer = (await canvasElement.screenshot({
|
||||
type: 'webp',
|
||||
quality: quality,
|
||||
encoding: 'binary'
|
||||
})) as Buffer;
|
||||
webpBuffers.push(new Uint8Array(screenshotBuffer));
|
||||
}
|
||||
|
||||
await page.close();
|
||||
return webpBuffers;
|
||||
}
|
||||
|
||||
/**
|
||||
* Converts a PDF to progressive JPEG bytes for each page.
|
||||
* This method creates progressive JPEG images that load in multiple passes,
|
||||
* showing a low-quality preview first, then progressively improving.
|
||||
* Uses SmartJimp for true progressive JPEG encoding.
|
||||
*/
|
||||
public async convertPDFToJpegBytes(
|
||||
pdfBytes: Uint8Array,
|
||||
options: {
|
||||
scale?: number; // Scale factor for output size (default: 3.0 for 216 DPI)
|
||||
quality?: number; // JPEG quality 0-100 (default: 85)
|
||||
maxWidth?: number; // Maximum width in pixels (optional)
|
||||
maxHeight?: number; // Maximum height in pixels (optional)
|
||||
} = {}
|
||||
): Promise<Uint8Array[]> {
|
||||
// First, convert PDF to PNG using our existing method
|
||||
const pngBuffers = await this.convertPDFToPngBytes(pdfBytes, {
|
||||
scale: options.scale,
|
||||
maxWidth: options.maxWidth,
|
||||
maxHeight: options.maxHeight
|
||||
});
|
||||
|
||||
// Initialize SmartJimp in sharp mode for progressive JPEG support
|
||||
const smartJimpInstance = new plugins.smartjimp.SmartJimp({ mode: 'sharp' });
|
||||
|
||||
// Convert each PNG to progressive JPEG
|
||||
const jpegBuffers: Uint8Array[] = [];
|
||||
const quality = options.quality || 85;
|
||||
|
||||
for (const pngBuffer of pngBuffers) {
|
||||
// Convert PNG buffer to progressive JPEG
|
||||
const jpegBuffer = await smartJimpInstance.computeAssetVariation(
|
||||
Buffer.from(pngBuffer),
|
||||
{
|
||||
format: 'jpeg',
|
||||
progressive: true,
|
||||
// SmartJimp uses a different quality scale, need to check if adjustment is needed
|
||||
// For now, pass through the quality value
|
||||
quality
|
||||
}
|
||||
);
|
||||
|
||||
jpegBuffers.push(new Uint8Array(jpegBuffer));
|
||||
}
|
||||
|
||||
return jpegBuffers;
|
||||
}
|
||||
}
|
||||
@@ -6,23 +6,25 @@ export { http, path };
|
||||
|
||||
// @pushrocks
|
||||
import * as smartbuffer from '@push.rocks/smartbuffer';
|
||||
import * as smartfile from '@push.rocks/smartfile';
|
||||
import * as smartfs from '@push.rocks/smartfs';
|
||||
import * as smartdelay from '@push.rocks/smartdelay';
|
||||
import * as smartpromise from '@push.rocks/smartpromise';
|
||||
import * as smartpath from '@push.rocks/smartpath';
|
||||
import * as smartpuppeteer from '@push.rocks/smartpuppeteer';
|
||||
import * as smartnetwork from '@push.rocks/smartnetwork';
|
||||
import * as smartunique from '@push.rocks/smartunique';
|
||||
import * as smartjimp from '@push.rocks/smartjimp';
|
||||
|
||||
export {
|
||||
smartbuffer,
|
||||
smartfile,
|
||||
smartfs,
|
||||
smartdelay,
|
||||
smartpromise,
|
||||
smartpath,
|
||||
smartpuppeteer,
|
||||
smartunique,
|
||||
smartnetwork,
|
||||
smartjimp,
|
||||
};
|
||||
|
||||
// tsclass scope
|
||||
|
||||
Reference in New Issue
Block a user