* ui: import Lucide icons by path in modules that run in Node Assisted-by: Claude (Opus 5.5 Medium) * ui: register highlight.js languages once, from lowlight's modules Assisted-by: Claude (Opus 5.5 Medium) * ui: load the pdf.js worker and nerdamer as files of their own Assisted-by: Claude (Opus 5.5 Medium) * ui: draw Mermaid diagrams with Pele Assisted-by: Claude (Opus 5.5 Medium) * ui: pin dependency versions and use one Svelte across the UI packages Assisted-by: Claude (Opus 5.5 Medium) * ui: build Llama Chat as split chunks Assisted-by: Claude (Opus 5.5 Medium) * ui: load KaTeX and pdf.js on first use Assisted-by: Claude (Opus 5.5 Medium)
49 lines
1.7 KiB
TypeScript
49 lines
1.7 KiB
TypeScript
// pdf.js loads on first use, with its worker as a file of its own: extracting a PDF's text
|
|
// and drawing its pages go through that load.
|
|
import { convertPDFToImage, convertPDFToText } from '#lib/utils/pdf-processing.ts';
|
|
import { describe, expect, it } from 'vitest';
|
|
|
|
/** A one-page PDF that shows `text`, with a correct cross-reference table. */
|
|
function pdfWithText(text: string): File {
|
|
const stream = `BT /F1 24 Tf 72 720 Td (${text}) Tj ET`;
|
|
const objects = [
|
|
'<< /Type /Catalog /Pages 2 0 R >>',
|
|
'<< /Type /Pages /Kids [3 0 R] /Count 1 >>',
|
|
'<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>',
|
|
`<< /Length ${stream.length} >>\nstream\n${stream}\nendstream`,
|
|
'<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>'
|
|
];
|
|
|
|
let body = '%PDF-1.4\n';
|
|
|
|
const offsets: number[] = [];
|
|
|
|
objects.forEach((object, i) => {
|
|
offsets.push(body.length);
|
|
body += `${i + 1} 0 obj\n${object}\nendobj\n`;
|
|
});
|
|
|
|
const xref = body.length;
|
|
const entries = offsets.map((offset) => `${String(offset).padStart(10, '0')} 00000 n \n`);
|
|
|
|
body += `xref\n0 ${objects.length + 1}\n0000000000 65535 f \n${entries.join('')}`;
|
|
body += `trailer\n<< /Size ${objects.length + 1} /Root 1 0 R >>\nstartxref\n${xref}\n%%EOF\n`;
|
|
|
|
return new File([body], 'hello.pdf', { type: 'application/pdf' });
|
|
}
|
|
|
|
describe('pdf-processing', () => {
|
|
it('extracts the text of a PDF', async () => {
|
|
const text = await convertPDFToText(pdfWithText('Hello from a PDF'));
|
|
|
|
expect(text).toContain('Hello from a PDF');
|
|
});
|
|
|
|
it('draws each page of a PDF as a PNG', async () => {
|
|
const pages = await convertPDFToImage(pdfWithText('Page one'));
|
|
|
|
expect(pages).toHaveLength(1);
|
|
expect(pages[0]).toMatch(/^data:image\/png;base64,/);
|
|
});
|
|
});
|