feat: extract text from fetched PDFs

server/tests/pdf-text.test.ts

@@ -0,0 +1,63 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import { extractPdfText, hasPdfMagic } from "../src/llm/pdf-text.js";
+import { createPdf } from "./pdf-fixture.js";
+
+test("extracts selectable text with page markers and selected-page support", async () => {
+  const bytes = createPdf(["Quarterly revenue was 42.", "Costs were 18."]);
+  const result = await extractPdfText(bytes, [2]);
+  assert.equal(result.status, "ok");
+  assert.equal(result.pageCount, 2);
+  assert.deepEqual(result.pages, [2]);
+  assert.match(result.text, /--- Page 2 ---/);
+  assert.match(result.text, /Costs were 18\./);
+  assert.doesNotMatch(result.text, /Quarterly revenue/);
+});
+
+test("reports PDFs with no selectable text clearly", async () => {
+  const result = await extractPdfText(createPdf([""]));
+  assert.equal(result.status, "no_text");
+  assert.match(result.text, /No extractable text/);
+});
+
+test("reports encrypted PDFs clearly", async () => {
+  const result = await extractPdfText(createPdf(["Secret"], true));
+  assert.equal(result.status, "encrypted");
+  assert.match(result.text, /encrypted and requires a password/);
+});
+
+test("reports page-free PDFs and rejects invalid requested pages", async () => {
+  const empty = await extractPdfText(createPdf([]));
+  assert.equal(empty.status, "no_pages");
+  assert.match(empty.text, /no pages/);
+  const outOfRange = await extractPdfText(createPdf(["Only page"]), [2]);
+  assert.equal(outOfRange.status, "error");
+  assert.match(outOfRange.text, /has 1 pages/);
+});
+
+test("limits each extraction to 30 pages and preserves the full page count", async () => {
+  const result = await extractPdfText(createPdf(Array.from({ length: 31 }, (_, index) => `Text on page ${index + 1}.`)));
+  assert.equal(result.status, "ok");
+  assert.equal(result.pageCount, 31);
+  assert.equal(result.pages.length, 30);
+  assert.equal(result.pages.at(-1), 30);
+});
+
+test("caps accumulated extracted text at the caller limit", async () => {
+  const result = await extractPdfText(createPdf(["Long sentence. ".repeat(200)]), undefined, 50);
+  assert.equal(result.status, "ok");
+  assert.equal(result.truncated, true);
+  assert.ok(result.text.length <= 50);
+});
+
+test("terminates an over-time worker and returns an explicit timeout result", async () => {
+  const result = await extractPdfText(createPdf(["Small document"]), undefined, 12_000, 1);
+  assert.equal(result.status, "error");
+  assert.match(result.text, /time limit/);
+});
+
+test("recognizes PDF magic in a mislabeled or prefixed response", () => {
+  assert.equal(hasPdfMagic(new TextEncoder().encode("%PDF-1.4")), true);
+  assert.equal(hasPdfMagic(new TextEncoder().encode(`${" ".repeat(500)}%PDF-1.7`)), true);
+  assert.equal(hasPdfMagic(new TextEncoder().encode("<html>not a PDF</html>")), false);
+});