zip download of single pdfs

src/pdf/pdfZipService.test.ts

@@ -0,0 +1,86 @@
+import { describe, expect, it } from 'vitest';
+import { unzipSync } from 'fflate';
+import { createSplitResultsZip, createSplitZipFilename } from './pdfZipService';
+import type { SplitResult } from './pdfTypes';
+
+async function unzipBlob(blob: Blob): Promise<Record<string, Uint8Array>> {
+  const arrayBuffer = await blob.arrayBuffer();
+  return unzipSync(new Uint8Array(arrayBuffer));
+}
+
+describe('pdfZipService', () => {
+  it('creates a ZIP archive from split PDF blobs', async () => {
+    const results: SplitResult[] = [
+      {
+        pageIndex: 0,
+        filename: 'document_page_001.pdf',
+        blob: new Blob([new Uint8Array([1, 2, 3])], {
+          type: 'application/pdf',
+        }),
+      },
+      {
+        pageIndex: 1,
+        filename: 'document_page_002.pdf',
+        blob: new Blob([new Uint8Array([4, 5, 6])], {
+          type: 'application/pdf',
+        }),
+      },
+    ];
+
+    const zipBlob = await createSplitResultsZip(results);
+    const entries = await unzipBlob(zipBlob);
+
+    expect(zipBlob.type).toBe('application/zip');
+    expect(Object.keys(entries)).toEqual([
+      'document_page_001.pdf',
+      'document_page_002.pdf',
+    ]);
+    expect(Array.from(entries['document_page_001.pdf'])).toEqual([1, 2, 3]);
+    expect(Array.from(entries['document_page_002.pdf'])).toEqual([4, 5, 6]);
+  });
+
+  it('sanitizes and deduplicates ZIP entry names', async () => {
+    const results: SplitResult[] = [
+      {
+        pageIndex: 0,
+        filename: '../page.pdf',
+        blob: new Blob([new Uint8Array([1])], { type: 'application/pdf' }),
+      },
+      {
+        pageIndex: 1,
+        filename: '../page.pdf',
+        blob: new Blob([new Uint8Array([2])], { type: 'application/pdf' }),
+      },
+      {
+        pageIndex: 2,
+        filename: '',
+        blob: new Blob([new Uint8Array([3])], { type: 'application/pdf' }),
+      },
+    ];
+
+    const zipBlob = await createSplitResultsZip(results);
+    const entries = await unzipBlob(zipBlob);
+
+    expect(Object.keys(entries)).toEqual([
+      '.._page.pdf',
+      '.._page_2.pdf',
+      'page_003.pdf',
+    ]);
+  });
+
+  it('creates a readable ZIP filename from the source PDF name', () => {
+    expect(createSplitZipFilename('contract.pdf')).toBe(
+      'contract_split_pages.zip'
+    );
+    expect(createSplitZipFilename('contract.final.PDF')).toBe(
+      'contract.final_split_pages.zip'
+    );
+    expect(createSplitZipFilename('')).toBe('document_split_pages.zip');
+  });
+
+  it('rejects empty split results', async () => {
+    await expect(createSplitResultsZip([])).rejects.toThrow(
+      'Cannot create a ZIP archive without split results.'
+    );
+  });
+});

src/pdf/pdfZipService.ts

@@ -0,0 +1,78 @@
+import { zipSync } from 'fflate';
+import type { SplitResult } from './pdfTypes';
+
+function bytesToBlob(bytes: Uint8Array, type: string): Blob {
+  const buffer = new ArrayBuffer(bytes.byteLength);
+  new Uint8Array(buffer).set(bytes);
+  return new Blob([buffer], { type });
+}
+
+function removeControlCharacters(value: string): string {
+  return Array.from(value)
+    .filter((character) => {
+      const code = character.charCodeAt(0);
+      return code > 31 && code !== 127;
+    })
+    .join('');
+}
+
+function safeZipEntryName(filename: string, fallback: string): string {
+  const cleaned = removeControlCharacters(filename)
+    .replace(/[\\/]+/g, '_')
+    .trim();
+
+  return cleaned.length > 0 ? cleaned : fallback;
+}
+
+function uniqueZipEntryName(filename: string, usedNames: Set<string>): string {
+  if (!usedNames.has(filename)) {
+    usedNames.add(filename);
+    return filename;
+  }
+
+  const dotIndex = filename.lastIndexOf('.');
+  const hasExtension = dotIndex > 0;
+  const base = hasExtension ? filename.slice(0, dotIndex) : filename;
+  const extension = hasExtension ? filename.slice(dotIndex) : '';
+
+  let counter = 2;
+  let candidate = `${base}_${counter}${extension}`;
+
+  while (usedNames.has(candidate)) {
+    counter += 1;
+    candidate = `${base}_${counter}${extension}`;
+  }
+
+  usedNames.add(candidate);
+  return candidate;
+}
+
+export function createSplitZipFilename(pdfName: string): string {
+  const baseName = pdfName.replace(/\.pdf$/i, '').trim() || 'document';
+  return `${baseName}_split_pages.zip`;
+}
+
+export async function createSplitResultsZip(
+  results: SplitResult[]
+): Promise<Blob> {
+  if (results.length === 0) {
+    throw new Error('Cannot create a ZIP archive without split results.');
+  }
+
+  const usedNames = new Set<string>();
+  const entries: Record<string, Uint8Array> = {};
+
+  for (const result of results) {
+    const fallback = `page_${String(result.pageIndex + 1).padStart(3, '0')}.pdf`;
+    const entryName = uniqueZipEntryName(
+      safeZipEntryName(result.filename, fallback),
+      usedNames
+    );
+
+    const arrayBuffer = await result.blob.arrayBuffer();
+    entries[entryName] = new Uint8Array(arrayBuffer);
+  }
+
+  const zippedBytes = zipSync(entries, { level: 6 });
+  return bytesToBlob(zippedBytes, 'application/zip');
+}