saulteafarmer/Stirling-PDF
1
0
Fork 0
mirror of https://github.com/Stirling-Tools/Stirling-PDF.git synced 2025-09-18 01:19:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Properly type PDFs

Browse Source
This commit is contained in:
James Brunton 2025-09-12 12:14:54 +01:00
parent e31e6461e4
commit 6a1caf0904
2 changed files with 31 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
frontend/src/services/pdfMetadataService.ts
View File

@ -1,6 +1,7 @@
import { pdfWorkerManager } from './pdfWorkerManager';
import { FileAnalyzer } from './fileAnalyzer';
import { TrappedStatus, CustomMetadataEntry, ExtractedPDFMetadata } from '../types/metadata';
import { PDFDocumentProxy } from 'pdfjs-dist/types/src/display/api';
export interface MetadataExtractionResult {
success: true;
@ -18,8 +19,8 @@ export type MetadataExtractionResponse = MetadataExtractionResult | MetadataExtr
* Utility to format PDF date strings to required format (yyyy/MM/dd HH:mm:ss)
* Handles PDF date format: "D:YYYYMMDDHHmmSSOHH'mm'" or standard date strings
*/
function formatPDFDate(dateString: unknown): string {
if (!dateString || typeof dateString !== 'string') {
function formatPDFDate(dateString: string): string {
if (!dateString) {
return '';
}
@ -80,14 +81,14 @@ function convertTrappedStatus(trapped: unknown): TrappedStatus {
* Extract custom metadata fields from PDF.js info object
* Custom metadata is nested under the "Custom" key
*/
function extractCustomMetadata(info: Record<string, unknown>): CustomMetadataEntry[] {
function extractCustomMetadata(custom: unknown): CustomMetadataEntry[] {
const customMetadata: CustomMetadataEntry[] = [];
let customIdCounter = 1;
// Check if there's a Custom object containing the custom metadata
if (info.Custom && typeof info.Custom === 'object' && info.Custom !== null) {
const customObj = info.Custom as Record<string, unknown>;
if (typeof custom === 'object' && custom !== null) {
const customObj = custom as Record<string, unknown>;
Object.entries(customObj).forEach(([key, value]) => {
if (value != null && value !== '') {
@ -107,7 +108,7 @@ function extractCustomMetadata(info: Record<string, unknown>): CustomMetadataEnt
/**
* Safely cleanup PDF document with error handling
*/
function cleanupPdfDocument(pdfDoc: any): void {
function cleanupPdfDocument(pdfDoc: PDFDocumentProxy | null): void {
if (pdfDoc) {
try {
pdfWorkerManager.destroyDocument(pdfDoc);
@ -117,6 +118,14 @@ function cleanupPdfDocument(pdfDoc: any): void {
}
}
function getStringMetadata(info: Record<string, unknown>, key: string): string {
if (typeof info[key] === 'string') {
return info[key];
} else {
return '';
}
}
/**
* Extract all metadata from a PDF file
* Returns a result object with success/error state
@ -131,9 +140,9 @@ export async function extractPDFMetadata(file: File): Promise<MetadataExtraction
};
}
let pdfDoc: any = null;
let pdfDoc: PDFDocumentProxy | null = null;
let arrayBuffer: ArrayBuffer;
let metadata: any;
let metadata;
try {
arrayBuffer = await file.arrayBuffer();
@ -151,20 +160,20 @@ export async function extractPDFMetadata(file: File): Promise<MetadataExtraction
};
}
const info = metadata.info || {};
const info = metadata.info as Record<string, unknown>;
// Safely extract metadata with proper type checking
const extractedMetadata: ExtractedPDFMetadata = {
title: typeof info.Title === 'string' ? info.Title : '',
author: typeof info.Author === 'string' ? info.Author : '',
subject: typeof info.Subject === 'string' ? info.Subject : '',
keywords: typeof info.Keywords === 'string' ? info.Keywords : '',
creator: typeof info.Creator === 'string' ? info.Creator : '',
producer: typeof info.Producer === 'string' ? info.Producer : '',
creationDate: formatPDFDate(info.CreationDate),
modificationDate: formatPDFDate(info.ModDate),
title: getStringMetadata(info, 'Title'),
author: getStringMetadata(info, 'Author'),
subject: getStringMetadata(info, 'Subject'),
keywords: getStringMetadata(info, 'Keywords'),
creator: getStringMetadata(info, 'Creator'),
producer: getStringMetadata(info, 'Producer'),
creationDate: formatPDFDate(getStringMetadata(info, 'CreationDate')),
modificationDate: formatPDFDate(getStringMetadata(info, 'ModDate')),
trapped: convertTrappedStatus(info.Trapped),
customMetadata: extractCustomMetadata(info)
customMetadata: extractCustomMetadata(info.Custom),
};
cleanupPdfDocument(pdfDoc);

7
frontend/src/services/pdfWorkerManager.ts
View File

@ -6,11 +6,12 @@
*/
import * as pdfjsLib from 'pdfjs-dist';
import { PDFDocumentProxy } from 'pdfjs-dist/types/src/display/api';
const { getDocument, GlobalWorkerOptions } = pdfjsLib;
class PDFWorkerManager {
private static instance: PDFWorkerManager;
private activeDocuments = new Set<any>();
private activeDocuments = new Set<PDFDocumentProxy>();
private workerCount = 0;
private maxWorkers = 10; // Limit concurrent workers
private isInitialized = false;
@ -48,7 +49,7 @@ class PDFWorkerManager {
stopAtErrors?: boolean;
verbosity?: number;
} = {}
): Promise<any> {
): Promise<PDFDocumentProxy> {
// Wait if we've hit the worker limit
if (this.activeDocuments.size >= this.maxWorkers) {
await this.waitForAvailableWorker();
@ -104,7 +105,7 @@ class PDFWorkerManager {
/**
* Properly destroy a PDF document and clean up resources
*/
destroyDocument(pdf: any): void {
destroyDocument(pdf: PDFDocumentProxy): void {
if (this.activeDocuments.has(pdf)) {
try {
pdf.destroy();