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>
This commit is contained in:
Reece Browne
2025-07-16 17:53:50 +01:00
committed by GitHub
parent 584e2ecee7
commit 922bbc9076
66 changed files with 8728 additions and 2519 deletions

View File

@@ -0,0 +1,127 @@
/**
* File hashing utilities for cache key generation
*/
export class FileHasher {
private static readonly CHUNK_SIZE = 64 * 1024; // 64KB chunks for hashing
/**
* Generate a content-based hash for a file
* Uses first + last + middle chunks to create a reasonably unique hash
* without reading the entire file (which would be expensive for large files)
*/
static async generateContentHash(file: File): Promise<string> {
const chunks = await this.getFileChunks(file);
const combined = await this.combineChunks(chunks);
return await this.hashArrayBuffer(combined);
}
/**
* Generate a fast hash based on file metadata
* Faster but less collision-resistant than content hash
*/
static generateMetadataHash(file: File): string {
const data = `${file.name}-${file.size}-${file.lastModified}-${file.type}`;
return this.simpleHash(data);
}
/**
* Generate a hybrid hash that balances speed and uniqueness
* Uses metadata + small content sample
*/
static async generateHybridHash(file: File): Promise<string> {
const metadataHash = this.generateMetadataHash(file);
// For small files, use full content hash
if (file.size <= 1024 * 1024) { // 1MB
const contentHash = await this.generateContentHash(file);
return `${metadataHash}-${contentHash}`;
}
// For large files, use first chunk only
const firstChunk = file.slice(0, this.CHUNK_SIZE);
const firstChunkBuffer = await firstChunk.arrayBuffer();
const firstChunkHash = await this.hashArrayBuffer(firstChunkBuffer);
return `${metadataHash}-${firstChunkHash}`;
}
private static async getFileChunks(file: File): Promise<ArrayBuffer[]> {
const chunks: ArrayBuffer[] = [];
// First chunk
if (file.size > 0) {
const firstChunk = file.slice(0, Math.min(this.CHUNK_SIZE, file.size));
chunks.push(await firstChunk.arrayBuffer());
}
// Middle chunk (if file is large enough)
if (file.size > this.CHUNK_SIZE * 2) {
const middleStart = Math.floor(file.size / 2) - Math.floor(this.CHUNK_SIZE / 2);
const middleEnd = middleStart + this.CHUNK_SIZE;
const middleChunk = file.slice(middleStart, middleEnd);
chunks.push(await middleChunk.arrayBuffer());
}
// Last chunk (if file is large enough and different from first)
if (file.size > this.CHUNK_SIZE) {
const lastStart = Math.max(file.size - this.CHUNK_SIZE, this.CHUNK_SIZE);
const lastChunk = file.slice(lastStart);
chunks.push(await lastChunk.arrayBuffer());
}
return chunks;
}
private static async combineChunks(chunks: ArrayBuffer[]): Promise<ArrayBuffer> {
const totalLength = chunks.reduce((sum, chunk) => sum + chunk.byteLength, 0);
const combined = new Uint8Array(totalLength);
let offset = 0;
for (const chunk of chunks) {
combined.set(new Uint8Array(chunk), offset);
offset += chunk.byteLength;
}
return combined.buffer;
}
private static async hashArrayBuffer(buffer: ArrayBuffer): Promise<string> {
// Use Web Crypto API for proper hashing
if (crypto.subtle) {
const hashBuffer = await crypto.subtle.digest('SHA-256', buffer);
const hashArray = Array.from(new Uint8Array(hashBuffer));
return hashArray.map(b => b.toString(16).padStart(2, '0')).join('');
}
// Fallback for environments without crypto.subtle
return this.simpleHash(Array.from(new Uint8Array(buffer)).join(''));
}
private static simpleHash(str: string): string {
let hash = 0;
if (str.length === 0) return hash.toString();
for (let i = 0; i < str.length; i++) {
const char = str.charCodeAt(i);
hash = ((hash << 5) - hash) + char;
hash = hash & hash; // Convert to 32-bit integer
}
return Math.abs(hash).toString(16);
}
/**
* Validate that a file matches its expected hash
* Useful for detecting file corruption or changes
*/
static async validateFileHash(file: File, expectedHash: string): Promise<boolean> {
try {
const actualHash = await this.generateHybridHash(file);
return actualHash === expectedHash;
} catch (error) {
console.error('Hash validation failed:', error);
return false;
}
}
}

View File

@@ -1,5 +1,19 @@
import { getDocument } from "pdfjs-dist";
/**
* 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
@@ -14,6 +28,10 @@ export async function generateThumbnailForFile(file: File): Promise<string | und
try {
console.log('Generating thumbnail for', file.name);
// 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));
@@ -26,7 +44,7 @@ export async function generateThumbnailForFile(file: File): Promise<string | und
}).promise;
const page = await pdf.getPage(1);
const viewport = page.getViewport({ scale: 0.2 }); // Smaller scale for memory efficiency
const viewport = page.getViewport({ scale }); // Dynamic scale based on file size
const canvas = document.createElement("canvas");
canvas.width = viewport.width;
canvas.height = viewport.height;
@@ -45,7 +63,45 @@ export async function generateThumbnailForFile(file: File): Promise<string | und
return thumbnail;
} catch (error) {
console.warn('Failed to generate thumbnail for', file.name, error);
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;
}
}