metadata

src/lib/components/ui/card/index.ts

@@ -1,10 +1,10 @@
-import Root from "./card.svelte";
-import Content from "./card-content.svelte";
-import Description from "./card-description.svelte";
-import Footer from "./card-footer.svelte";
-import Header from "./card-header.svelte";
-import Title from "./card-title.svelte";
-import Action from "./card-action.svelte";
+import Root from './card.svelte';
+import Content from './card-content.svelte';
+import Description from './card-description.svelte';
+import Footer from './card-footer.svelte';
+import Header from './card-header.svelte';
+import Title from './card-title.svelte';
+import Action from './card-action.svelte';
 
 export {
 	Root,
@@ -21,5 +21,5 @@ export {
 	Footer as CardFooter,
 	Header as CardHeader,
 	Title as CardTitle,
-	Action as CardAction,
+	Action as CardAction
 };

src/lib/pdf-metadata.ts

@@ -0,0 +1,108 @@
+import { PDFDocument } from 'pdf-lib';
+
+export type PdfMetadataInfo = {
+	title: string;
+	author: string;
+	subject: string;
+	keywords: string[];
+	creator: string;
+	producer: string;
+	creationDate: Date | null;
+	modificationDate: Date | null;
+	pageCount: number;
+	embeddedFileSuspected: boolean;
+};
+
+export type PdfMetadataResult =
+	| { status: 'ok'; metadata: PdfMetadataInfo }
+	| { status: 'encrypted' };
+
+// The pdf-lib error class for encrypted documents is not exported from the
+// package root, so we identify it by its message instead.
+const isEncryptedPdfError = (error: unknown) =>
+	error instanceof Error && error.message.includes('is encrypted');
+
+const safeRead = <T>(read: () => T | undefined): T | undefined => {
+	try {
+		return read();
+	} catch {
+		return undefined;
+	}
+};
+
+const toDateOrNull = (value: Date | undefined): Date | null =>
+	value && !Number.isNaN(value.getTime()) ? value : null;
+
+// Finds an ASCII marker in raw bytes without decoding the whole file. The
+// search for '/EmbeddedFile' also matches '/EmbeddedFiles' as a prefix.
+const containsAsciiMarker = (bytes: Uint8Array, marker: string): boolean => {
+	const firstByte = marker.charCodeAt(0);
+	for (let index = 0; index <= bytes.length - marker.length; index += 1) {
+		if (bytes[index] !== firstByte) continue;
+		let matched = true;
+		for (let offset = 1; offset < marker.length; offset += 1) {
+			if (bytes[index + offset] !== marker.charCodeAt(offset)) {
+				matched = false;
+				break;
+			}
+		}
+		if (matched) return true;
+	}
+	return false;
+};
+
+export const hasEmbeddedFileMarkers = (bytes: Uint8Array): boolean =>
+	containsAsciiMarker(bytes, '/EmbeddedFile');
+
+export const readPdfMetadata = async (bytes: Uint8Array): Promise<PdfMetadataResult> => {
+	const embeddedFileSuspected = hasEmbeddedFileMarkers(bytes);
+
+	let document: PDFDocument;
+	try {
+		document = await PDFDocument.load(bytes, { updateMetadata: false });
+	} catch (error) {
+		if (isEncryptedPdfError(error)) return { status: 'encrypted' };
+		throw error;
+	}
+
+	const keywords = safeRead(() => document.getKeywords());
+
+	return {
+		status: 'ok',
+		metadata: {
+			title: safeRead(() => document.getTitle()) ?? '',
+			author: safeRead(() => document.getAuthor()) ?? '',
+			subject: safeRead(() => document.getSubject()) ?? '',
+			// PDF keyword lists have no canonical separator; split only on
+			// explicit punctuation so multi-word keywords survive.
+			keywords: keywords
+				? keywords
+						.split(/[;,]/)
+						.map((keyword) => keyword.trim())
+						.filter(Boolean)
+				: [],
+			creator: safeRead(() => document.getCreator()) ?? '',
+			producer: safeRead(() => document.getProducer()) ?? '',
+			creationDate: toDateOrNull(safeRead(() => document.getCreationDate())),
+			modificationDate: toDateOrNull(safeRead(() => document.getModificationDate())),
+			pageCount: document.getPageCount(),
+			embeddedFileSuspected
+		}
+	};
+};
+
+export const stripPdfMetadata = async (bytes: Uint8Array): Promise<Uint8Array> => {
+	const document = await PDFDocument.load(bytes, { updateMetadata: false });
+	const now = new Date();
+
+	document.setTitle('');
+	document.setAuthor('');
+	document.setSubject('');
+	document.setKeywords([]);
+	document.setCreator('');
+	document.setProducer('beA-Edit');
+	document.setCreationDate(now);
+	document.setModificationDate(now);
+
+	return document.save();
+};

src/lib/tools.ts

@@ -59,5 +59,11 @@ export const tools: Tool[] = [
 		title: 'PDFs zusammenfügen',
 		description: 'Fügen Sie mehrere PDFs zu einer Datei zusammen.',
 		icon: 'merge'
+	},
+	{
+		slug: 'metadata',
+		title: 'Metadaten',
+		description: 'Zeigen Sie Metadaten eines PDFs an und entfernen Sie sie.',
+		icon: 'info'
 	}
 ];