Stirling-PDF/frontend/src/utils/thumbnailUtils.ts

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

112 lines
4.0 KiB
TypeScript
Raw Normal View History

import { getDocument } from "pdfjs-dist";
Stirling 2.0 (#3928) # Description of Changes <!-- File context for managing files between tools and views Optimisation for large files Updated Split to work with new file system and match Matts stepped design closer --> --- ## Checklist ### General - [ ] I have read the [Contribution Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md) - [ ] I have read the [Stirling-PDF Developer Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md) (if applicable) - [ ] I have read the [How to add new languages to Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md) (if applicable) - [ ] I have performed a self-review of my own code - [ ] My changes generate no new warnings ### Documentation - [ ] I have updated relevant docs on [Stirling-PDF's doc repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/) (if functionality has heavily changed) - [ ] I have read the section [Add New Translation Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags) (for new translation tags only) ### UI Changes (if applicable) - [ ] Screenshots or videos demonstrating the UI changes are attached (e.g., as comments or direct attachments in the PR) ### Testing (if applicable) - [ ] I have tested my changes locally. Refer to the [Testing Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing) for more details. --------- Co-authored-by: Anthony Stirling <77850077+Frooodle@users.noreply.github.com>
2025-07-16 17:53:50 +01:00
/**
* Calculate thumbnail scale based on file size
* Smaller files get higher quality, larger files get lower quality
*/
export function calculateScaleFromFileSize(fileSize: number): number {
const MB = 1024 * 1024;
if (fileSize < 1 * MB) return 0.6; // < 1MB: High quality
if (fileSize < 5 * MB) return 0.4; // 1-5MB: Medium-high quality
if (fileSize < 15 * MB) return 0.3; // 5-15MB: Medium quality
if (fileSize < 30 * MB) return 0.2; // 15-30MB: Low-medium quality
return 0.15; // 30MB+: Low quality
}
/**
* Generate thumbnail for a PDF file during upload
* Returns base64 data URL or undefined if generation fails
*/
export async function generateThumbnailForFile(file: File): Promise<string | undefined> {
// Skip thumbnail generation for large files to avoid memory issues
if (file.size >= 50 * 1024 * 1024) { // 50MB limit
console.log('Skipping thumbnail generation for large file:', file.name);
return undefined;
}
V2: Convert Tool (#3828) 🔄 Dynamic Processing Strategies - Adaptive routing: Same tool uses different backend endpoints based on file analysis - Combined vs separate processing: Intelligently chooses between merge operations and individual file processing - Cross-format workflows: Enable complex conversions like "mixed files → PDF" that other tools can't handle ⚙️ Format-Specific Intelligence Each conversion type gets tailored options: - HTML/ZIP → PDF: Zoom controls (0.1-3.0 increments) with live preview - Email → PDF: Attachment handling, size limits, recipient control - PDF → PDF/A: Digital signature detection with warnings - Images → PDF: Smart combining vs individual file options File Architecture Core Implementation: ├── Convert.tsx # Main stepped workflow UI ├── ConvertSettings.tsx # Centralized settings with smart detection ├── GroupedFormatDropdown.tsx # Enhanced format selector with grouping ├── useConvertParameters.ts # Smart detection & parameter management ├── useConvertOperation.ts # Multi-strategy processing logic └── Settings Components: ├── ConvertFromWebSettings.tsx # HTML zoom controls ├── ConvertFromEmailSettings.tsx # Email attachment options ├── ConvertToPdfaSettings.tsx # PDF/A with signature detection ├── ConvertFromImageSettings.tsx # Image PDF options └── ConvertToImageSettings.tsx # PDF to image options Utility Layer Utils & Services: ├── convertUtils.ts # Format detection & endpoint routing ├── fileResponseUtils.ts # Generic API response handling └── setupTests.ts # Enhanced test environment with crypto mocks Testing & Quality Comprehensive Test Coverage Test Suite: ├── useConvertParameters.test.ts # Parameter logic & smart detection ├── useConvertParametersAutoDetection.test.ts # File type analysis ├── ConvertIntegration.test.tsx # End-to-end conversion workflows ├── ConvertSmartDetectionIntegration.test.tsx # Mixed file scenarios ├── ConvertE2E.spec.ts # Playwright browser tests ├── convertUtils.test.ts # Utility function validation └── fileResponseUtils.test.ts # API response handling Advanced Test Features - Crypto API mocking: Proper test environment for file hashing - File.arrayBuffer() polyfills: Complete browser API simulation - Multi-file scenario testing: Complex batch processing validation - CI/CD integration: Vitest runs in GitHub Actions with proper artifacts --------- Co-authored-by: Connor Yoh <connor@stirlingpdf.com> Co-authored-by: Anthony Stirling <77850077+Frooodle@users.noreply.github.com>
2025-08-01 16:08:04 +01:00
if (!file.type.startsWith('application/pdf')) {
console.warn('File is not a PDF, skipping thumbnail generation:', file.name);
return undefined;
}
try {
console.log('Generating thumbnail for', file.name);
Stirling 2.0 (#3928) # Description of Changes <!-- File context for managing files between tools and views Optimisation for large files Updated Split to work with new file system and match Matts stepped design closer --> --- ## Checklist ### General - [ ] I have read the [Contribution Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md) - [ ] I have read the [Stirling-PDF Developer Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md) (if applicable) - [ ] I have read the [How to add new languages to Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md) (if applicable) - [ ] I have performed a self-review of my own code - [ ] My changes generate no new warnings ### Documentation - [ ] I have updated relevant docs on [Stirling-PDF's doc repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/) (if functionality has heavily changed) - [ ] I have read the section [Add New Translation Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags) (for new translation tags only) ### UI Changes (if applicable) - [ ] Screenshots or videos demonstrating the UI changes are attached (e.g., as comments or direct attachments in the PR) ### Testing (if applicable) - [ ] I have tested my changes locally. Refer to the [Testing Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing) for more details. --------- Co-authored-by: Anthony Stirling <77850077+Frooodle@users.noreply.github.com>
2025-07-16 17:53:50 +01:00
// Calculate quality scale based on file size
const scale = calculateScaleFromFileSize(file.size);
console.log(`Using scale ${scale} for ${file.name} (${(file.size / 1024 / 1024).toFixed(1)}MB)`);
// Only read first 2MB for thumbnail generation to save memory
const chunkSize = 2 * 1024 * 1024; // 2MB
const chunk = file.slice(0, Math.min(chunkSize, file.size));
const arrayBuffer = await chunk.arrayBuffer();
const pdf = await getDocument({
data: arrayBuffer,
disableAutoFetch: true,
disableStream: true
}).promise;
const page = await pdf.getPage(1);
Stirling 2.0 (#3928) # Description of Changes <!-- File context for managing files between tools and views Optimisation for large files Updated Split to work with new file system and match Matts stepped design closer --> --- ## Checklist ### General - [ ] I have read the [Contribution Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md) - [ ] I have read the [Stirling-PDF Developer Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md) (if applicable) - [ ] I have read the [How to add new languages to Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md) (if applicable) - [ ] I have performed a self-review of my own code - [ ] My changes generate no new warnings ### Documentation - [ ] I have updated relevant docs on [Stirling-PDF's doc repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/) (if functionality has heavily changed) - [ ] I have read the section [Add New Translation Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags) (for new translation tags only) ### UI Changes (if applicable) - [ ] Screenshots or videos demonstrating the UI changes are attached (e.g., as comments or direct attachments in the PR) ### Testing (if applicable) - [ ] I have tested my changes locally. Refer to the [Testing Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing) for more details. --------- Co-authored-by: Anthony Stirling <77850077+Frooodle@users.noreply.github.com>
2025-07-16 17:53:50 +01:00
const viewport = page.getViewport({ scale }); // Dynamic scale based on file size
const canvas = document.createElement("canvas");
canvas.width = viewport.width;
canvas.height = viewport.height;
const context = canvas.getContext("2d");
if (!context) {
throw new Error('Could not get canvas context');
}
await page.render({ canvasContext: context, viewport }).promise;
const thumbnail = canvas.toDataURL();
// Immediately clean up memory after thumbnail generation
pdf.destroy();
console.log('Thumbnail generated and PDF destroyed for', file.name);
return thumbnail;
} catch (error) {
Stirling 2.0 (#3928) # Description of Changes <!-- File context for managing files between tools and views Optimisation for large files Updated Split to work with new file system and match Matts stepped design closer --> --- ## Checklist ### General - [ ] I have read the [Contribution Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md) - [ ] I have read the [Stirling-PDF Developer Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md) (if applicable) - [ ] I have read the [How to add new languages to Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md) (if applicable) - [ ] I have performed a self-review of my own code - [ ] My changes generate no new warnings ### Documentation - [ ] I have updated relevant docs on [Stirling-PDF's doc repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/) (if functionality has heavily changed) - [ ] I have read the section [Add New Translation Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags) (for new translation tags only) ### UI Changes (if applicable) - [ ] Screenshots or videos demonstrating the UI changes are attached (e.g., as comments or direct attachments in the PR) ### Testing (if applicable) - [ ] I have tested my changes locally. Refer to the [Testing Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing) for more details. --------- Co-authored-by: Anthony Stirling <77850077+Frooodle@users.noreply.github.com>
2025-07-16 17:53:50 +01:00
if (error instanceof Error) {
if (error.name === 'InvalidPDFException') {
console.warn(`PDF structure issue for ${file.name} - using fallback thumbnail`);
// Return a placeholder or try with full file instead of chunk
try {
const fullArrayBuffer = await file.arrayBuffer();
const pdf = await getDocument({
data: fullArrayBuffer,
disableAutoFetch: true,
disableStream: true,
verbosity: 0 // Reduce PDF.js warnings
}).promise;
const page = await pdf.getPage(1);
const viewport = page.getViewport({ scale });
const canvas = document.createElement("canvas");
canvas.width = viewport.width;
canvas.height = viewport.height;
const context = canvas.getContext("2d");
if (!context) {
throw new Error('Could not get canvas context');
}
await page.render({ canvasContext: context, viewport }).promise;
const thumbnail = canvas.toDataURL();
pdf.destroy();
return thumbnail;
} catch (fallbackError) {
console.warn('Fallback thumbnail generation also failed for', file.name, fallbackError);
return undefined;
}
} else {
console.warn('Failed to generate thumbnail for', file.name, error);
return undefined;
}
}
console.warn('Unknown error generating thumbnail for', file.name, error);
return undefined;
}
}