Compare commits
31 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
6a4aeed3e1 | ||
|
|
a4c3415838 | ||
| f535eacd97 | |||
| 9908897aa2 | |||
| 29d3cbb0b6 | |||
| babc20649a | |||
| 1188643c4b | |||
| 6b74301588 | |||
| 168527573c | |||
| 3d7bb37849 | |||
| 12a581ced9 | |||
| 857e1717a5 | |||
| 186bfb9d12 | |||
| c5bc354f65 | |||
| c48bb0428f | |||
| 46fbb615a0 | |||
| 3df4e103f9 | |||
| addff418c6 | |||
| 14d653e701 | |||
| 040bac5256 | |||
| bf44901a0a | |||
| b4d0f4e949 | |||
| b2b47b1f6a | |||
| 1b1398653b | |||
| 1f61dcb115 | |||
| 1476fc9174 | |||
| d157a3acd9 | |||
| fe6be928a9 | |||
| 8e537be454 | |||
| 6947529e02 | |||
| b6d78929b9 |
@@ -119,6 +119,6 @@ jobs:
|
||||
run: |
|
||||
npmci node install stable
|
||||
npmci npm install
|
||||
pnpm install -g @gitzone/tsdoc
|
||||
pnpm install -g @git.zone/tsdoc
|
||||
npmci command tsdoc
|
||||
continue-on-error: true
|
||||
|
||||
154
changelog.md
Normal file
154
changelog.md
Normal file
@@ -0,0 +1,154 @@
|
||||
# Changelog
|
||||
|
||||
## 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
|
||||
|
||||
- Added ISmartPdfOptions interface with port configuration options
|
||||
- Implemented automatic port allocation between 20000-30000 by default
|
||||
- Added support for custom port ranges via portRangeStart/portRangeEnd options
|
||||
- Added support for specific port assignment via port option
|
||||
- Fixed resource cleanup when port allocation fails
|
||||
- Multiple SmartPdf instances can now run simultaneously without port conflicts
|
||||
- Updated readme with comprehensive documentation for all features
|
||||
|
||||
## 2025-02-25 - 3.2.2 - fix(SmartPdf)
|
||||
Fix buffer handling for PDF conversion and text extraction
|
||||
|
||||
- Ensure Uint8Array is converted to Node Buffer for PDF conversion.
|
||||
- Correct the PDF page viewport handling by using document dimensions.
|
||||
- Fix extractTextFromPdfBuffer argument type from Uint8Array to Buffer.
|
||||
|
||||
## 2025-02-25 - 3.2.1 - fix(SmartPdf)
|
||||
Fix type for extractTextFromPdfBuffer function
|
||||
|
||||
- Corrected the parameter type from Buffer to Uint8Array for extractTextFromPdfBuffer function.
|
||||
|
||||
## 2025-02-25 - 3.2.0 - feat(smartpdf)
|
||||
Improve dependency versions and optimize PDF to PNG conversion.
|
||||
|
||||
- Update several dependencies to newer versions for better stability and performance.
|
||||
- Refactor tests to enhance readability and add directory creation validations.
|
||||
- Optimize PDF to PNG conversion by switching to a more efficient Puppeteer and PDF.js-based method.
|
||||
- Add checks for presence of required dependencies (GraphicsMagick and Ghostscript).
|
||||
- Fix media emulation issue by properly awaiting the emulateMediaType function.
|
||||
|
||||
## 2024-11-30 - 3.1.8 - fix(core)
|
||||
Fix candidate handling in PDF generation
|
||||
|
||||
- Added error handling for missing PDF candidates in server requests.
|
||||
- Updated devDependencies and dependencies to latest versions for better stability and new features.
|
||||
- Patched header retrieval logic during PDF generation for security check.
|
||||
|
||||
## 2024-09-27 - 3.1.7 - fix(dependencies)
|
||||
Update dependencies to latest versions
|
||||
|
||||
- Updated @git.zone/tsbuild to version ^2.1.84
|
||||
- Updated @git.zone/tsdoc to version ^1.3.12
|
||||
- Updated @git.zone/tsrun to version ^1.2.49
|
||||
- Updated @push.rocks/tapbundle to version ^5.3.0
|
||||
- Updated @types/node to version ^22.7.4
|
||||
- Updated @push.rocks/smartfile to version ^11.0.21
|
||||
- Updated @push.rocks/smartpromise to version ^4.0.4
|
||||
- Updated @tsclass/tsclass to version ^4.1.2
|
||||
- Updated express to version ^4.21.0
|
||||
- Updated pdf2pic to version ^3.1.3
|
||||
|
||||
## 2024-05-29 - 3.1.6 - Core
|
||||
Updated description
|
||||
|
||||
- Minor changes to documentation and internal text.
|
||||
|
||||
## 2024-04-25 to 2024-04-30 - 3.1.0 to 3.1.5 - Core
|
||||
Fix updates in core functionality
|
||||
|
||||
- Fixes and updates in core function in versions 3.1.0 to 3.1.5.
|
||||
|
||||
## 2024-04-25 - 3.0.17 - Feature
|
||||
Now supports PDF to JPG conversion
|
||||
|
||||
- Added support for converting PDF files to JPG format.
|
||||
|
||||
## 2024-03-19 to 2024-04-14 - 3.0.17 - Maintenance
|
||||
Various updates to project configuration files
|
||||
|
||||
- Updated `tsconfig`.
|
||||
- Updated `npmextra.json`.
|
||||
|
||||
## 2023-07-11 to 2024-03-19 - 3.0.15 to 3.0.16 - Organization
|
||||
Switch to new organization scheme and core updates
|
||||
|
||||
- Switched to new organization scheme.
|
||||
- Applied core updates and bug fixes.
|
||||
|
||||
## 2022-11-07 to 2023-07-10 - 3.0.13 to 3.0.14 - Core
|
||||
Fixes and updates to core functionality
|
||||
|
||||
- Various minor bug fixes and updates to core components.
|
||||
|
||||
## 2022-09-13 to 2022-11-07 - 3.0.10 to 3.0.12 - Core
|
||||
Ongoing core updates and maintenance
|
||||
|
||||
- Regular fixes and operational improvements in core functionalities.
|
||||
|
||||
## 2022-06-12 to 2022-09-13 - 3.0.7 to 3.0.9 - Core
|
||||
Continued focus on high-priority bug fixes and core functionalities
|
||||
|
||||
- Regular fixes for critical bugs and enhancements.
|
||||
|
||||
## 2022-03-24 to 2022-06-29 - 3.0.3 to 3.0.6 - Core
|
||||
Further optimization and maintenance releases
|
||||
|
||||
- Further improvements and refinements of issues in core functionalities.
|
||||
|
||||
## 2022-01-05 to 2022-03-25 - 3.0.0 to 3.0.2 - Major Version Release
|
||||
Major release for version 3.0.x, including core fixes
|
||||
|
||||
- Increased version from 2.x to 3.0. New significant changes and fixes.
|
||||
|
||||
## 2022-01-05 to 2022-03-24 - 2.0.13 to 2.0.19 - Core
|
||||
Routine core updates and bug fixes
|
||||
|
||||
- Regular bug fixes in core components.
|
||||
|
||||
## 2019-11-19 to 2022-01-06 - 2.0.0 to 2.0.11 - Core
|
||||
Multiple core updates and a few performance improvements
|
||||
|
||||
- Some performance enhancements and multiple bug fixes.
|
||||
|
||||
## 2019-11-16 to 2019-11-19 - 1.0.27 to 1.0.29 - API
|
||||
Breaking change in API
|
||||
|
||||
- Naming PDF results to better represent their content.
|
||||
|
||||
## 2019-05-29 to 2019-11-15 - 1.0.13 to 1.0.26 - Core
|
||||
Core functional updates and some major restructuring
|
||||
|
||||
- Introduced multiple updates to the core, addressing bugs and improving stability.
|
||||
|
||||
## 2019-04-10 to 2019-05-28 - 1.0.4 to 1.0.12 - Core
|
||||
Fixes and updates in the core
|
||||
|
||||
- Implementation of multiple essential fixes for core components.
|
||||
|
||||
## 2018-10-06 - 1.0.1 to 1.0.3 - Core and Typings
|
||||
Initial implementation and core fixes
|
||||
|
||||
- Initial implementation of the project.
|
||||
- Fixed compilation problems in typings.
|
||||
|
||||
## 2016-01-29 - unknown - Initial
|
||||
Initial commit
|
||||
|
||||
- Initial commit for the project setup.
|
||||
@@ -6,12 +6,29 @@
|
||||
"gitzone": {
|
||||
"projectType": "npm",
|
||||
"module": {
|
||||
"githost": "gitlab.com",
|
||||
"githost": "code.foss.global",
|
||||
"gitscope": "push.rocks",
|
||||
"gitrepo": "smartpdf",
|
||||
"description": "Create PDFs fast and smoothly",
|
||||
"description": "A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.",
|
||||
"npmPackagename": "@push.rocks/smartpdf",
|
||||
"license": "MIT"
|
||||
}
|
||||
"license": "MIT",
|
||||
"keywords": [
|
||||
"PDF generation",
|
||||
"HTML to PDF",
|
||||
"website to PDF",
|
||||
"PDF manipulation",
|
||||
"puppeteer",
|
||||
"express",
|
||||
"node.js",
|
||||
"typescript",
|
||||
"automation",
|
||||
"PDF merging",
|
||||
"text extraction",
|
||||
"PDF management"
|
||||
]
|
||||
}
|
||||
},
|
||||
"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"
|
||||
}
|
||||
}
|
||||
64
package.json
64
package.json
@@ -1,39 +1,39 @@
|
||||
{
|
||||
"name": "@push.rocks/smartpdf",
|
||||
"version": "3.0.17",
|
||||
"version": "4.0.0",
|
||||
"private": false,
|
||||
"description": "create pdfs on the fly",
|
||||
"description": "A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.",
|
||||
"main": "dist_ts/index.js",
|
||||
"typings": "dist_ts/index.d.ts",
|
||||
"type": "module",
|
||||
"author": "Lossless GmbH",
|
||||
"license": "MIT",
|
||||
"scripts": {
|
||||
"test": "(tstest test/ --web)",
|
||||
"build": "(tsbuild --web --allowimplicitany)",
|
||||
"test": "(tstest test/ --verbose --timeout 60)",
|
||||
"build": "(tsbuild tsfolders --allowimplicitany)",
|
||||
"buildDocs": "tsdoc"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@gitzone/tsbuild": "^2.1.66",
|
||||
"@gitzone/tsdoc": "^1.1.12",
|
||||
"@gitzone/tsrun": "^1.2.44",
|
||||
"@gitzone/tstest": "^1.0.77",
|
||||
"@push.rocks/tapbundle": "^5.0.12",
|
||||
"@types/node": "^20.4.5"
|
||||
"@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"
|
||||
},
|
||||
"dependencies": {
|
||||
"@push.rocks/smartbuffer": "^3.0.5",
|
||||
"@push.rocks/smartdelay": "^3.0.5",
|
||||
"@push.rocks/smartfile": "^10.0.28",
|
||||
"@push.rocks/smartnetwork": "^3.0.0",
|
||||
"@push.rocks/smartpath": "^5.0.11",
|
||||
"@push.rocks/smartpromise": "^4.0.3",
|
||||
"@push.rocks/smartpuppeteer": "^2.0.2",
|
||||
"@push.rocks/smartunique": "^3.0.3",
|
||||
"@tsclass/tsclass": "^4.0.42",
|
||||
"@types/express": "^4.17.17",
|
||||
"express": "^4.18.1",
|
||||
"pdf-merger-js": "^3.4.0",
|
||||
"pdf2json": "^2.0.0"
|
||||
"@push.rocks/smartfile": "^11.2.5",
|
||||
"@push.rocks/smartnetwork": "^4.1.2",
|
||||
"@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",
|
||||
"pdf-lib": "^1.17.1",
|
||||
"pdf2json": "3.2.0"
|
||||
},
|
||||
"files": [
|
||||
"ts/**/*",
|
||||
@@ -49,5 +49,25 @@
|
||||
],
|
||||
"browserslist": [
|
||||
"last 1 chrome versions"
|
||||
]
|
||||
],
|
||||
"keywords": [
|
||||
"PDF generation",
|
||||
"HTML to PDF",
|
||||
"website to PDF",
|
||||
"PDF manipulation",
|
||||
"puppeteer",
|
||||
"express",
|
||||
"node.js",
|
||||
"typescript",
|
||||
"automation",
|
||||
"PDF merging",
|
||||
"text extraction",
|
||||
"PDF management"
|
||||
],
|
||||
"homepage": "https://code.foss.global/push.rocks/smartpdf",
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://code.foss.global/push.rocks/smartpdf.git"
|
||||
},
|
||||
"packageManager": "pnpm@10.11.0+sha512.6540583f41cc5f628eb3d9773ecee802f4f9ef9923cc45b69890fb47991d4b092964694ec3a4f738a420c918a333062c8b925d312f42e4f0c263eb603551f977"
|
||||
}
|
||||
|
||||
12649
pnpm-lock.yaml
generated
12649
pnpm-lock.yaml
generated
File diff suppressed because it is too large
Load Diff
1
readme.hints.md
Normal file
1
readme.hints.md
Normal file
@@ -0,0 +1 @@
|
||||
|
||||
451
readme.md
451
readme.md
@@ -1,39 +1,436 @@
|
||||
# @push.rocks/smartpdf
|
||||
Create PDFs fast and smoothly
|
||||
Create PDFs on the fly from HTML, websites, or existing PDFs with advanced features like text extraction, PDF merging, and PNG conversion.
|
||||
|
||||
## Availabililty and Links
|
||||
* [npmjs.org (npm package)](https://www.npmjs.com/package/@push.rocks/smartpdf)
|
||||
* [gitlab.com (source)](https://gitlab.com/push.rocks/smartpdf)
|
||||
* [github.com (source mirror)](https://github.com/push.rocks/smartpdf)
|
||||
* [docs (typedoc)](https://push.rocks.gitlab.io/smartpdf/)
|
||||
## Install
|
||||
To install `@push.rocks/smartpdf`, use npm or yarn:
|
||||
|
||||
## Status for master
|
||||
```bash
|
||||
npm install @push.rocks/smartpdf --save
|
||||
```
|
||||
|
||||
Status Category | Status Badge
|
||||
-- | --
|
||||
GitLab Pipelines | [](https://lossless.cloud)
|
||||
GitLab Pipline Test Coverage | [](https://lossless.cloud)
|
||||
npm | [](https://lossless.cloud)
|
||||
Snyk | [](https://lossless.cloud)
|
||||
TypeScript Support | [](https://lossless.cloud)
|
||||
node Support | [](https://nodejs.org/dist/latest-v10.x/docs/api/)
|
||||
Code Style | [](https://lossless.cloud)
|
||||
PackagePhobia (total standalone install weight) | [](https://lossless.cloud)
|
||||
PackagePhobia (package size on registry) | [](https://lossless.cloud)
|
||||
BundlePhobia (total size when bundled) | [](https://lossless.cloud)
|
||||
Or with yarn:
|
||||
|
||||
```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.
|
||||
|
||||
## Contribution
|
||||
### Getting Started
|
||||
First, import the necessary classes:
|
||||
|
||||
We are always happy for code contributions. If you are not the code contributing type that is ok. Still, maintaining Open Source repositories takes considerable time and thought. If you like the quality of what we do and our modules are useful to you we would appreciate a little monthly contribution: You can [contribute one time](https://lossless.link/contribute-onetime) or [contribute monthly](https://lossless.link/contribute). :)
|
||||
```typescript
|
||||
import { SmartPdf, IPdf } from '@push.rocks/smartpdf';
|
||||
```
|
||||
|
||||
## Contribution
|
||||
### Basic Setup with Automatic Port Allocation
|
||||
SmartPdf automatically finds an available port between 20000-30000 for its internal server:
|
||||
|
||||
We are always happy for code contributions. If you are not the code contributing type that is ok. Still, maintaining Open Source repositories takes considerable time and thought. If you like the quality of what we do and our modules are useful to you we would appreciate a little monthly contribution: You can [contribute one time](https://lossless.link/contribute-onetime) or [contribute monthly](https://lossless.link/contribute). :)
|
||||
```typescript
|
||||
async function setupSmartPdf() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
For further information read the linked docs at the top of this readme.
|
||||
// Your PDF operations here
|
||||
|
||||
## Legal
|
||||
> MIT licensed | **©** [Task Venture Capital GmbH](https://task.vc)
|
||||
| By using this npm module you agree to our [privacy policy](https://lossless.gmbH/privacy)
|
||||
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
|
||||
await smartPdf.start();
|
||||
console.log(`Server running on port: ${smartPdf.serverPort}`);
|
||||
```
|
||||
|
||||
### 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 with configurable quality:
|
||||
|
||||
```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 with default high quality (216 DPI)
|
||||
const pngImages: Uint8Array[] = await smartPdf.convertPDFToPngBytes(pdf.buffer);
|
||||
|
||||
// Or specify custom scale/DPI
|
||||
const highResPngs = await smartPdf.convertPDFToPngBytes(pdf.buffer, {
|
||||
scale: SmartPdf.SCALE_PRINT, // 6.0 scale = ~432 DPI
|
||||
maxWidth: 3000, // Optional: limit maximum width
|
||||
maxHeight: 4000 // Optional: limit maximum height
|
||||
});
|
||||
|
||||
// Save each page as a PNG
|
||||
pngImages.forEach((pngBuffer, index) => {
|
||||
fs.writeFileSync(`page-${index + 1}.png`, pngBuffer);
|
||||
});
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
#### Understanding Scale and DPI
|
||||
PDF.js renders at 72 DPI by default. Use these scale factors for different quality levels:
|
||||
- `SmartPdf.SCALE_SCREEN` (2.0): ~144 DPI - Good for screen display
|
||||
- `SmartPdf.SCALE_HIGH` (3.0): ~216 DPI - High quality (default)
|
||||
- `SmartPdf.SCALE_PRINT` (6.0): ~432 DPI - Print quality
|
||||
- Custom DPI: `scale = SmartPdf.getScaleForDPI(300)` for 300 DPI
|
||||
|
||||
### Converting PDF to WebP Images
|
||||
Generate web-optimized images using WebP format. WebP provides 25-35% better compression than PNG/JPEG while maintaining quality:
|
||||
|
||||
```typescript
|
||||
async function createWebPImages() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
// Load a PDF
|
||||
const pdf = await smartPdf.readFileToPdfObject('./document.pdf');
|
||||
|
||||
// Create high-quality WebP images (default: 3.0 scale = 216 DPI, 85% quality)
|
||||
const webpImages = await smartPdf.convertPDFToWebpBytes(pdf.buffer);
|
||||
|
||||
// Save WebP images
|
||||
webpImages.forEach((webpBuffer, index) => {
|
||||
fs.writeFileSync(`page-${index + 1}.webp`, webpBuffer);
|
||||
});
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
#### Creating Thumbnails
|
||||
Generate small thumbnail images for PDF galleries or document lists:
|
||||
|
||||
```typescript
|
||||
async function createThumbnails() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
const pdf = await smartPdf.readFileToPdfObject('./document.pdf');
|
||||
|
||||
// Create small thumbnails (0.5 scale = ~36 DPI, 70% quality)
|
||||
const thumbnails = await smartPdf.convertPDFToWebpBytes(pdf.buffer, {
|
||||
scale: 0.5, // Small readable thumbnails
|
||||
quality: 70 // Lower quality for smaller files
|
||||
});
|
||||
|
||||
// Save thumbnails
|
||||
thumbnails.forEach((thumb, index) => {
|
||||
fs.writeFileSync(`thumb-${index + 1}.webp`, thumb);
|
||||
});
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
#### Constrained Dimensions
|
||||
Create previews with maximum width/height constraints, useful for responsive layouts:
|
||||
|
||||
```typescript
|
||||
async function createConstrainedPreviews() {
|
||||
const smartPdf = await SmartPdf.create();
|
||||
await smartPdf.start();
|
||||
|
||||
const pdf = await smartPdf.readFileToPdfObject('./document.pdf');
|
||||
|
||||
// Create previews that fit within 800x600 pixels
|
||||
const previews = await smartPdf.convertPDFToWebpBytes(pdf.buffer, {
|
||||
scale: 1.0, // Start with full size
|
||||
quality: 90, // High quality
|
||||
maxWidth: 800, // Maximum 800px wide
|
||||
maxHeight: 600 // Maximum 600px tall
|
||||
});
|
||||
|
||||
// The method automatically scales down to fit within constraints
|
||||
previews.forEach((preview, index) => {
|
||||
fs.writeFileSync(`preview-constrained-${index + 1}.webp`, preview);
|
||||
});
|
||||
|
||||
await smartPdf.stop();
|
||||
}
|
||||
```
|
||||
|
||||
#### WebP Options
|
||||
The `convertPDFToWebpBytes` method accepts these options:
|
||||
|
||||
- `scale`: Scale factor for preview size (default: 3.0 for ~216 DPI)
|
||||
- `quality`: WebP compression quality (default: 85, range: 0-100)
|
||||
- `maxWidth`: Maximum width in pixels (optional)
|
||||
- `maxHeight`: Maximum height in pixels (optional)
|
||||
|
||||
Common scale values:
|
||||
- `0.5`: Thumbnails (~36 DPI)
|
||||
- `2.0`: Screen display (~144 DPI)
|
||||
- `3.0`: High quality (~216 DPI, default)
|
||||
- `6.0`: Print quality (~432 DPI)
|
||||
|
||||
### 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:
|
||||
|
||||
```typescript
|
||||
interface IPdf {
|
||||
name: string; // Filename of the PDF
|
||||
buffer: Buffer; // PDF content as buffer
|
||||
id: string | null; // Unique identifier
|
||||
metadata?: {
|
||||
textExtraction?: string; // Extracted text content
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
## Best Practices
|
||||
|
||||
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.
|
||||
|
||||
## 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.
|
||||
|
||||
**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.
|
||||
|
||||
### Company Information
|
||||
|
||||
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.
|
||||
|
||||
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.
|
||||
97
test/test.port.ts
Normal file
97
test/test.port.ts
Normal file
@@ -0,0 +1,97 @@
|
||||
import { expect, tap } from '@git.zone/tstest/tapbundle';
|
||||
import * as smartpdf from '../ts/index.js';
|
||||
|
||||
tap.test('should create multiple SmartPdf instances with automatic port allocation', async () => {
|
||||
const instance1 = new smartpdf.SmartPdf();
|
||||
const instance2 = new smartpdf.SmartPdf();
|
||||
const instance3 = new smartpdf.SmartPdf();
|
||||
|
||||
// Start all instances
|
||||
await instance1.start();
|
||||
await instance2.start();
|
||||
await instance3.start();
|
||||
|
||||
// Verify all instances have different ports
|
||||
expect(instance1.serverPort).toBeGreaterThanOrEqual(20000);
|
||||
expect(instance1.serverPort).toBeLessThanOrEqual(30000);
|
||||
expect(instance2.serverPort).toBeGreaterThanOrEqual(20000);
|
||||
expect(instance2.serverPort).toBeLessThanOrEqual(30000);
|
||||
expect(instance3.serverPort).toBeGreaterThanOrEqual(20000);
|
||||
expect(instance3.serverPort).toBeLessThanOrEqual(30000);
|
||||
|
||||
// Ensure all ports are different
|
||||
expect(instance1.serverPort).not.toEqual(instance2.serverPort);
|
||||
expect(instance1.serverPort).not.toEqual(instance3.serverPort);
|
||||
expect(instance2.serverPort).not.toEqual(instance3.serverPort);
|
||||
|
||||
console.log(`Instance 1 port: ${instance1.serverPort}`);
|
||||
console.log(`Instance 2 port: ${instance2.serverPort}`);
|
||||
console.log(`Instance 3 port: ${instance3.serverPort}`);
|
||||
|
||||
// Test that all instances work correctly
|
||||
const pdf1 = await instance1.getA4PdfResultForHtmlString('<h1>Instance 1</h1>');
|
||||
const pdf2 = await instance2.getA4PdfResultForHtmlString('<h1>Instance 2</h1>');
|
||||
const pdf3 = await instance3.getA4PdfResultForHtmlString('<h1>Instance 3</h1>');
|
||||
|
||||
expect(pdf1.buffer).toBeInstanceOf(Buffer);
|
||||
expect(pdf2.buffer).toBeInstanceOf(Buffer);
|
||||
expect(pdf3.buffer).toBeInstanceOf(Buffer);
|
||||
|
||||
// Clean up
|
||||
await instance1.stop();
|
||||
await instance2.stop();
|
||||
await instance3.stop();
|
||||
});
|
||||
|
||||
tap.test('should create SmartPdf instance with custom port range', async () => {
|
||||
const customInstance = new smartpdf.SmartPdf({
|
||||
portRangeStart: 25000,
|
||||
portRangeEnd: 26000
|
||||
});
|
||||
|
||||
await customInstance.start();
|
||||
|
||||
expect(customInstance.serverPort).toBeGreaterThanOrEqual(25000);
|
||||
expect(customInstance.serverPort).toBeLessThanOrEqual(26000);
|
||||
|
||||
console.log(`Custom range instance port: ${customInstance.serverPort}`);
|
||||
|
||||
await customInstance.stop();
|
||||
});
|
||||
|
||||
tap.test('should create SmartPdf instance with specific port', async () => {
|
||||
const specificPortInstance = new smartpdf.SmartPdf({
|
||||
port: 28888
|
||||
});
|
||||
|
||||
await specificPortInstance.start();
|
||||
|
||||
expect(specificPortInstance.serverPort).toEqual(28888);
|
||||
|
||||
console.log(`Specific port instance: ${specificPortInstance.serverPort}`);
|
||||
|
||||
await specificPortInstance.stop();
|
||||
});
|
||||
|
||||
tap.test('should throw error when specific port is already in use', async () => {
|
||||
const instance1 = new smartpdf.SmartPdf({ port: 29999 });
|
||||
await instance1.start();
|
||||
|
||||
const instance2 = new smartpdf.SmartPdf({ port: 29999 });
|
||||
|
||||
let errorThrown = false;
|
||||
try {
|
||||
await instance2.start();
|
||||
} catch (error) {
|
||||
errorThrown = true;
|
||||
expect(error.message).toInclude('already in use');
|
||||
}
|
||||
|
||||
expect(errorThrown).toBeTrue();
|
||||
|
||||
await instance1.stop();
|
||||
});
|
||||
|
||||
|
||||
|
||||
export default tap.start();
|
||||
185
test/test.ts
185
test/test.ts
@@ -1,59 +1,180 @@
|
||||
import { expect, tap } from '@push.rocks/tapbundle';
|
||||
import { expect, tap } from '@git.zone/tstest/tapbundle';
|
||||
import * as smartpdf from '../ts/index.js';
|
||||
import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
|
||||
let testSmartPdf: smartpdf.SmartPdf;
|
||||
|
||||
tap.test('should create a valid instance of smartpdf', async () => {
|
||||
/**
|
||||
* Ensures that a directory exists.
|
||||
* @param dirPath - The directory path to ensure.
|
||||
*/
|
||||
function ensureDir(dirPath: string): void {
|
||||
if (!fs.existsSync(dirPath)) {
|
||||
fs.mkdirSync(dirPath, { recursive: true });
|
||||
}
|
||||
}
|
||||
|
||||
// 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);
|
||||
});
|
||||
|
||||
tap.test('should start the instance', async () => {
|
||||
tap.test('should start the SmartPdf instance', async () => {
|
||||
await testSmartPdf.start();
|
||||
});
|
||||
|
||||
tap.test('should create a pdf from html string', async () => {
|
||||
await testSmartPdf.getA4PdfResultForHtmlString('hi');
|
||||
tap.test('should create PDFs from HTML string', async () => {
|
||||
const pdf1 = await testSmartPdf.getA4PdfResultForHtmlString('hi');
|
||||
const pdf2 = await testSmartPdf.getA4PdfResultForHtmlString('hello');
|
||||
expect(pdf1.buffer).toBeInstanceOf(Buffer);
|
||||
expect(pdf2.buffer).toBeInstanceOf(Buffer);
|
||||
});
|
||||
|
||||
tap.test('should create a pdf from html string', async () => {
|
||||
await testSmartPdf.getA4PdfResultForHtmlString('hi');
|
||||
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');
|
||||
expect(pdfA4.buffer).toBeInstanceOf(Buffer);
|
||||
expect(pdfSingle.buffer).toBeInstanceOf(Buffer);
|
||||
});
|
||||
|
||||
tap.test('should create a pdf from website as A4', async () => {
|
||||
await testSmartPdf.getPdfResultForWebsite('https://www.wikipedia.org');
|
||||
});
|
||||
|
||||
tap.test('should create a pdf from website as single page PDF', async () => {
|
||||
await testSmartPdf.getFullWebsiteAsSinglePdf('https://www.wikipedia.org');
|
||||
});
|
||||
|
||||
tap.test('should create a valid PDFResult', async () => {
|
||||
const writePDfToDisk = async (urlArg: string, fileName: string) => {
|
||||
tap.test('should create valid PDF results and write them to disk', async () => {
|
||||
const writePdfToDisk = async (urlArg: string, fileName: string) => {
|
||||
const pdfResult = await testSmartPdf.getFullWebsiteAsSinglePdf(urlArg);
|
||||
expect(pdfResult.buffer).toBeInstanceOf(Buffer);
|
||||
const fs = await import('fs');
|
||||
|
||||
if (!fs.existsSync('.nogit/')) {
|
||||
fs.mkdirSync('.nogit/');
|
||||
}
|
||||
fs.writeFileSync(`.nogit/${fileName}`, pdfResult.buffer as Buffer);
|
||||
ensureDir('.nogit');
|
||||
fs.writeFileSync(path.join('.nogit', fileName), pdfResult.buffer as Buffer);
|
||||
};
|
||||
await writePDfToDisk('https://lossless.com/', '1.pdf');
|
||||
await writePDfToDisk('https://layer.io', '2.pdf');
|
||||
await writePdfToDisk('https://lossless.com/', '1.pdf');
|
||||
await writePdfToDisk('https://layer.io', '2.pdf');
|
||||
});
|
||||
|
||||
tap.test('should combine pdfs', async () => {
|
||||
const fs = await import('fs');
|
||||
tap.test('should merge PDFs into a combined PDF', async () => {
|
||||
const pdf1 = await testSmartPdf.readFileToPdfObject('.nogit/1.pdf');
|
||||
const pdf2 = await testSmartPdf.readFileToPdfObject('.nogit/2.pdf');
|
||||
fs.writeFileSync(
|
||||
`.nogit/combined.pdf`,
|
||||
(await testSmartPdf.mergePdfs([pdf1, pdf2])).buffer as Buffer
|
||||
);
|
||||
const mergedBuffer = await testSmartPdf.mergePdfs([pdf1.buffer, pdf2.buffer]);
|
||||
ensureDir('.nogit');
|
||||
fs.writeFileSync(path.join('.nogit', 'combined.pdf'), mergedBuffer);
|
||||
});
|
||||
|
||||
tap.test('should be able to close properly', async () => {
|
||||
tap.test('should create PNG images from combined PDF using Puppeteer conversion', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/combined.pdf');
|
||||
const images = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
|
||||
expect(images.length).toBeGreaterThan(0);
|
||||
console.log('Puppeteer-based conversion image sizes:', images.map(img => img.length));
|
||||
});
|
||||
|
||||
tap.test('should store PNG results from both conversion functions in .nogit/testresults', async () => {
|
||||
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, `png_combined_page${index + 1}.png`);
|
||||
fs.writeFileSync(filePath, Buffer.from(img));
|
||||
});
|
||||
});
|
||||
|
||||
tap.test('should create WebP preview images from PDF', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
const webpPreviews = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer);
|
||||
expect(webpPreviews.length).toBeGreaterThan(0);
|
||||
console.log('WebP preview sizes:', webpPreviews.map(img => img.length));
|
||||
|
||||
// Also create PNG previews for comparison
|
||||
const pngPreviews = await testSmartPdf.convertPDFToPngBytes(pdfObject.buffer);
|
||||
console.log('PNG preview sizes:', pngPreviews.map(img => img.length));
|
||||
|
||||
// Save the first page as both WebP and PNG preview
|
||||
fs.writeFileSync(path.join(testResultsDir, 'webp_default_page1.webp'), Buffer.from(webpPreviews[0]));
|
||||
fs.writeFileSync(path.join(testResultsDir, 'png_default_page1.png'), Buffer.from(pngPreviews[0]));
|
||||
});
|
||||
|
||||
tap.test('should create WebP previews with custom scale and quality', async () => {
|
||||
const pdfObject = await testSmartPdf.readFileToPdfObject('.nogit/3.pdf');
|
||||
|
||||
// Create smaller previews with lower quality for thumbnails
|
||||
const thumbnails = await testSmartPdf.convertPDFToWebpBytes(pdfObject.buffer, {
|
||||
scale: 0.5, // Create readable thumbnails at ~36 DPI
|
||||
quality: 70
|
||||
});
|
||||
|
||||
expect(thumbnails.length).toBeGreaterThan(0);
|
||||
console.log('Thumbnail sizes:', thumbnails.map(img => img.length));
|
||||
|
||||
// Save thumbnails
|
||||
thumbnails.forEach((thumb, index) => {
|
||||
fs.writeFileSync(path.join(testResultsDir, `webp_thumbnail_page${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 close the SmartPdf instance properly', async () => {
|
||||
await testSmartPdf.stop();
|
||||
});
|
||||
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
/**
|
||||
* autocreated commitinfo by @pushrocks/commitinfo
|
||||
* autocreated commitinfo by @push.rocks/commitinfo
|
||||
*/
|
||||
export const commitinfo = {
|
||||
name: '@push.rocks/smartpdf',
|
||||
version: '3.0.17',
|
||||
description: 'create pdfs on the fly'
|
||||
version: '3.2.2',
|
||||
description: 'A library for creating PDFs dynamically from HTML or websites with additional features like merging PDFs.'
|
||||
}
|
||||
|
||||
@@ -3,13 +3,33 @@ 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 {
|
||||
port?: number;
|
||||
portRangeStart?: number;
|
||||
portRangeEnd?: number;
|
||||
}
|
||||
|
||||
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() {
|
||||
const smartpdfInstance = new SmartPdf();
|
||||
public static async create(optionsArg?: ISmartPdfOptions) {
|
||||
const smartpdfInstance = new SmartPdf(optionsArg);
|
||||
return smartpdfInstance;
|
||||
}
|
||||
|
||||
@@ -20,9 +40,15 @@ export class SmartPdf {
|
||||
externalBrowserBool: boolean = false;
|
||||
private _readyDeferred: plugins.smartpromise.Deferred<void>;
|
||||
private _candidates: { [key: string]: PdfCandidate } = {};
|
||||
private _options: ISmartPdfOptions;
|
||||
|
||||
constructor() {
|
||||
constructor(optionsArg?: ISmartPdfOptions) {
|
||||
this._readyDeferred = new plugins.smartpromise.Deferred();
|
||||
this._options = {
|
||||
portRangeStart: 20000,
|
||||
portRangeEnd: 30000,
|
||||
...optionsArg
|
||||
};
|
||||
}
|
||||
|
||||
async start(headlessBrowserArg?: plugins.smartpuppeteer.puppeteer.Browser) {
|
||||
@@ -34,21 +60,56 @@ export class SmartPdf {
|
||||
this.externalBrowserBool = true;
|
||||
} else {
|
||||
this.headlessBrowser = await plugins.smartpuppeteer.getEnvAwareBrowserInstance({
|
||||
forceNoSandbox: true,
|
||||
forceNoSandbox: false,
|
||||
});
|
||||
}
|
||||
|
||||
// setup server
|
||||
// Find an available port BEFORE creating server
|
||||
const smartnetworkInstance = new plugins.smartnetwork.SmartNetwork();
|
||||
|
||||
if (this._options.port) {
|
||||
// If a specific port is requested, check if it's available
|
||||
const isPortAvailable = await smartnetworkInstance.isLocalPortUnused(this._options.port);
|
||||
if (isPortAvailable) {
|
||||
this.serverPort = this._options.port;
|
||||
} else {
|
||||
// Clean up browser if we created one
|
||||
if (!this.externalBrowserBool && this.headlessBrowser) {
|
||||
await this.headlessBrowser.close();
|
||||
}
|
||||
throw new Error(`Requested port ${this._options.port} is already in use`);
|
||||
}
|
||||
} else {
|
||||
// Find a free port in the specified range
|
||||
this.serverPort = await smartnetworkInstance.findFreePort(
|
||||
this._options.portRangeStart,
|
||||
this._options.portRangeEnd
|
||||
);
|
||||
if (!this.serverPort) {
|
||||
// Clean up browser if we created one
|
||||
if (!this.externalBrowserBool && this.headlessBrowser) {
|
||||
await this.headlessBrowser.close();
|
||||
}
|
||||
throw new Error(`No free ports available in range ${this._options.portRangeStart}-${this._options.portRangeEnd}`);
|
||||
}
|
||||
}
|
||||
|
||||
// Now setup server after we know we have a valid port
|
||||
const app = plugins.express();
|
||||
app.get('/:pdfId', (req, res) => {
|
||||
res.setHeader('PDF-ID', this._candidates[req.params.pdfId].pdfId);
|
||||
res.send(this._candidates[req.params.pdfId].htmlString);
|
||||
const wantedCandidate = this._candidates[req.params.pdfId];
|
||||
if (!wantedCandidate) {
|
||||
console.log(`${req.url} not attached to a candidate`);
|
||||
return;
|
||||
}
|
||||
res.setHeader('pdf-id', wantedCandidate.pdfId);
|
||||
res.send(wantedCandidate.htmlString);
|
||||
});
|
||||
this.htmlServerInstance = plugins.http.createServer(app);
|
||||
const smartnetworkInstance = new plugins.smartnetwork.SmartNetwork();
|
||||
const portAvailable = smartnetworkInstance.isLocalPortUnused(3210);
|
||||
this.htmlServerInstance.listen(3210, 'localhost');
|
||||
|
||||
this.htmlServerInstance.listen(this.serverPort, 'localhost');
|
||||
this.htmlServerInstance.on('listening', () => {
|
||||
console.log(`SmartPdf server listening on port ${this.serverPort}`);
|
||||
this._readyDeferred.resolve();
|
||||
done.resolve();
|
||||
});
|
||||
@@ -70,7 +131,7 @@ export class SmartPdf {
|
||||
}
|
||||
|
||||
/**
|
||||
* returns a pdf for a given html string;
|
||||
* Returns a PDF for a given HTML string.
|
||||
*/
|
||||
async getA4PdfResultForHtmlString(htmlStringArg: string): Promise<plugins.tsclass.business.IPdf> {
|
||||
await this._readyDeferred.promise;
|
||||
@@ -81,10 +142,9 @@ export class SmartPdf {
|
||||
width: 794,
|
||||
height: 1122,
|
||||
});
|
||||
const response = await page.goto(`http://localhost:3210/${pdfCandidate.pdfId}`, {
|
||||
const response = await page.goto(`http://localhost:${this.serverPort}/${pdfCandidate.pdfId}`, {
|
||||
waitUntil: 'networkidle2',
|
||||
});
|
||||
// await plugins.smartdelay.delayFor(1000);
|
||||
const headers = response.headers();
|
||||
if (headers['pdf-id'] !== pdfCandidate.pdfId) {
|
||||
console.log('Error! Headers do not match. For security reasons no pdf is being emitted!');
|
||||
@@ -99,6 +159,8 @@ export class SmartPdf {
|
||||
printBackground: true,
|
||||
displayHeaderFooter: false,
|
||||
});
|
||||
// Convert Uint8Array to Node Buffer
|
||||
const nodePdfBuffer = Buffer.from(pdfBuffer);
|
||||
await page.close();
|
||||
delete this._candidates[pdfCandidate.pdfId];
|
||||
pdfCandidate.doneDeferred.resolve();
|
||||
@@ -107,9 +169,9 @@ export class SmartPdf {
|
||||
id: pdfCandidate.pdfId,
|
||||
name: `${pdfCandidate.pdfId}.js`,
|
||||
metadata: {
|
||||
textExtraction: await this.extractTextFromPdfBuffer(pdfBuffer),
|
||||
textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
|
||||
},
|
||||
buffer: pdfBuffer,
|
||||
buffer: nodePdfBuffer,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -134,14 +196,16 @@ export class SmartPdf {
|
||||
printBackground: true,
|
||||
displayHeaderFooter: false,
|
||||
});
|
||||
// Convert Uint8Array to Node Buffer
|
||||
const nodePdfBuffer = Buffer.from(pdfBuffer);
|
||||
await page.close();
|
||||
return {
|
||||
id: pdfId,
|
||||
name: `${pdfId}.js`,
|
||||
metadata: {
|
||||
textExtraction: await this.extractTextFromPdfBuffer(pdfBuffer),
|
||||
textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
|
||||
},
|
||||
buffer: pdfBuffer,
|
||||
buffer: nodePdfBuffer,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -151,15 +215,23 @@ export class SmartPdf {
|
||||
width: 1920,
|
||||
height: 1200,
|
||||
});
|
||||
page.emulateMediaType('screen');
|
||||
await page.emulateMediaType('screen');
|
||||
const response = await page.goto(websiteUrl, { waitUntil: 'networkidle2' });
|
||||
const pdfId = plugins.smartunique.shortId();
|
||||
// Use both document.body and document.documentElement to ensure we have a valid height and width.
|
||||
const { documentHeight, documentWidth } = await page.evaluate(() => {
|
||||
return {
|
||||
documentHeight: document.body.scrollHeight,
|
||||
documentWidth: document.body.clientWidth,
|
||||
documentHeight: Math.max(
|
||||
document.body.scrollHeight,
|
||||
document.documentElement.scrollHeight
|
||||
) || 1200,
|
||||
documentWidth: Math.max(
|
||||
document.body.clientWidth,
|
||||
document.documentElement.clientWidth
|
||||
) || 1920,
|
||||
};
|
||||
});
|
||||
// Update viewport height to the full document height.
|
||||
await page.setViewport({
|
||||
width: 1920,
|
||||
height: documentHeight,
|
||||
@@ -172,35 +244,35 @@ export class SmartPdf {
|
||||
scale: 1,
|
||||
pageRanges: '1',
|
||||
});
|
||||
// Convert Uint8Array to Node Buffer
|
||||
const nodePdfBuffer = Buffer.from(pdfBuffer);
|
||||
await page.close();
|
||||
return {
|
||||
id: pdfId,
|
||||
name: `${pdfId}.js`,
|
||||
metadata: {
|
||||
textExtraction: await this.extractTextFromPdfBuffer(pdfBuffer),
|
||||
textExtraction: await this.extractTextFromPdfBuffer(nodePdfBuffer),
|
||||
},
|
||||
buffer: pdfBuffer,
|
||||
buffer: nodePdfBuffer,
|
||||
};
|
||||
}
|
||||
|
||||
public async mergePdfs(pdfArrayArg: plugins.tsclass.business.IPdf[]): Promise<IPdf> {
|
||||
const merger = new plugins.pdfMerger();
|
||||
for (const pdf of pdfArrayArg) {
|
||||
merger.add(Buffer.from(pdf.buffer));
|
||||
public async mergePdfs(inputPdfBuffers: Uint8Array[]): Promise<Uint8Array> {
|
||||
const mergedPdf = await plugins.pdfLib.PDFDocument.create();
|
||||
for (const pdfBytes of inputPdfBuffers) {
|
||||
const pdfDoc = await plugins.pdfLib.PDFDocument.load(pdfBytes);
|
||||
const pages = await mergedPdf.copyPages(pdfDoc, pdfDoc.getPageIndices());
|
||||
pages.forEach((page) => mergedPdf.addPage(page));
|
||||
}
|
||||
const resultBuffer = await merger.saveAsBuffer();
|
||||
return {
|
||||
name: 'mergedPdf',
|
||||
buffer: resultBuffer,
|
||||
id: null,
|
||||
metadata: null,
|
||||
};
|
||||
|
||||
const mergedPdfBytes = await mergedPdf.save();
|
||||
return mergedPdfBytes;
|
||||
}
|
||||
|
||||
public async readFileToPdfObject(pathArg: string): Promise<plugins.tsclass.business.IPdf> {
|
||||
const path = plugins.smartpath.transform.makeAbsolute(pathArg);
|
||||
const parsedPath = plugins.path.parse(path);
|
||||
const buffer = await plugins.smartfile.fs.toBuffer(path);
|
||||
const absolutePath = plugins.smartpath.transform.makeAbsolute(pathArg);
|
||||
const parsedPath = plugins.path.parse(absolutePath);
|
||||
const buffer = await plugins.smartfile.fs.toBuffer(absolutePath);
|
||||
return {
|
||||
name: parsedPath.base,
|
||||
buffer,
|
||||
@@ -226,4 +298,244 @@ export class SmartPdf {
|
||||
pdfParser.parseBuffer(pdfBufferArg);
|
||||
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,
|
||||
* renders each PDF page to a canvas, and then screenshots each canvas element.
|
||||
*/
|
||||
public async convertPDFToPngBytes(
|
||||
pdfBytes: Uint8Array,
|
||||
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[]> {
|
||||
// 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();
|
||||
|
||||
// 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.
|
||||
const htmlTemplate: string = `
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
<title>PDF to PNG 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 pngBuffers: Uint8Array[] = [];
|
||||
|
||||
for (const canvasElement of canvasElements) {
|
||||
// Screenshot the canvas element. The screenshot will be a PNG buffer.
|
||||
const screenshotBuffer = (await canvasElement.screenshot({ encoding: 'binary' })) as Buffer;
|
||||
pngBuffers.push(new Uint8Array(screenshotBuffer));
|
||||
}
|
||||
|
||||
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;
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ import * as path from 'path';
|
||||
export { http, path };
|
||||
|
||||
// @pushrocks
|
||||
import * as smartbuffer from '@push.rocks/smartbuffer';
|
||||
import * as smartfile from '@push.rocks/smartfile';
|
||||
import * as smartdelay from '@push.rocks/smartdelay';
|
||||
import * as smartpromise from '@push.rocks/smartpromise';
|
||||
@@ -14,6 +15,7 @@ import * as smartnetwork from '@push.rocks/smartnetwork';
|
||||
import * as smartunique from '@push.rocks/smartunique';
|
||||
|
||||
export {
|
||||
smartbuffer,
|
||||
smartfile,
|
||||
smartdelay,
|
||||
smartpromise,
|
||||
@@ -29,9 +31,8 @@ import * as tsclass from '@tsclass/tsclass';
|
||||
export { tsclass };
|
||||
|
||||
// thirdparty
|
||||
import pdfMerger from 'pdf-merger-js';
|
||||
// @ts-ignore
|
||||
import pdf2json from 'pdf2json';
|
||||
import express from 'express';
|
||||
import pdf2json from 'pdf2json';
|
||||
import pdfLib from 'pdf-lib';
|
||||
|
||||
export { pdfMerger, pdf2json, express };
|
||||
export { express, pdf2json, pdfLib, };
|
||||
|
||||
Reference in New Issue
Block a user