Fix Arabic text rendering in generated PDFs

Add Arabic text shaping functionality to convert base characters to their contextual presentation forms before bidi reordering and PDF rendering. Includes a new regression test to verify correct shaping by asserting the presence of presentation form codepoints in the PDF's embedded ToUnicode CMap. Replit-Commit-Author: Agent Replit-Commit-Session-Id: 77cfe984-2c65-4152-bb7a-0df28274fe66 Replit-Commit-Checkpoint-Type: full_checkpoint Replit-Commit-Event-Id: 18d38e3a-cfe8-4b69-a02c-380283320b78 Replit-Commit-Screenshot-Url: https://storage.googleapis.com/screenshot-production-us-central1/c3c252e4-c83d-40ca-9fff-99a3ea60701e/77cfe984-2c65-4152-bb7a-0df28274fe66/Ow4s0aa Replit-Helium-Checkpoint-Created: true
2026-05-03 15:26:38 +00:00
parent 62ee62e6fa
commit 627a8fe7b1
6 changed files with 132 additions and 10 deletions
@@ -1024,6 +1024,73 @@ test("PDF content: title label, rowColor tint, dropped isHighlighted, fontColor"
  void ascii;
 });

+test("PDF Arabic shaping: title renders in connected presentation forms (not isolated)", async () => {
+  // Regression for the bug where Arabic in the printed PDF appeared as
+  // disconnected, visually-reversed letters (e.g. "الاجتماعات" →
+  // "تاعامتجالا"). PDFKit has no built-in HarfBuzz, so we now run a
+  // pre-shaping pass that converts base Arabic letters (U+0600..U+06FF)
+  // to their contextual presentation forms (FE80..FEFF, plus FEFB
+  // lam-alef ligature) BEFORE handing text to bidi + PDFKit. We assert
+  // the rendered PDF contains presentation-form codepoints in its
+  // embedded ToUnicode CMap (proves shaped glyphs were drawn).
+
+  // End-to-end: render a real PDF and assert the inflated streams
+  // (which include the embedded ToUnicode CMap) reference at least one
+  // Arabic Presentation Forms-B codepoint. Without shaping the CMap
+  // would only contain base U+06xx hex values.
+  const shapedDate = "2099-05-04";
+  const shapedMeeting = await api(adminCookie, "POST", "/api/executive-meetings", {
+    titleAr: "اجتماع الاختبار",
+    titleEn: "Shaping Smoke Test",
+    meetingDate: shapedDate,
+    attendees: [
+      { name: "محمد عبدالله", attendanceType: "internal", sortOrder: 0 },
+    ],
+  });
+  assert.equal(shapedMeeting.status, 201);
+  created.meetingIds.push((await shapedMeeting.json()).id);
+
+  const res = await api(
+    adminCookie,
+    "GET",
+    `/api/executive-meetings/pdf?date=${shapedDate}&lang=ar`,
+  );
+  assert.equal(res.status, 200);
+  const buf = Buffer.from(await res.arrayBuffer());
+
+  // Inflate every FlateDecode stream and concat — same trick as the
+  // existing PDF content test. ToUnicode CMaps are inflate-able and
+  // contain pairs like `<XX> <FE8D>`, so a regex over the joined
+  // payload is enough.
+  let cursor = 0;
+  const decoded = [];
+  while (true) {
+    const start = buf.indexOf("stream\n", cursor);
+    if (start < 0) break;
+    const end = buf.indexOf("\nendstream", start);
+    if (end < 0) break;
+    try {
+      decoded.push(
+        zlib
+          .inflateSync(buf.slice(start + "stream\n".length, end))
+          .toString("latin1"),
+      );
+    } catch {
+      // not a deflate stream
+    }
+    cursor = end + "\nendstream".length;
+  }
+  const allDecoded = decoded.join("\n");
+  // Match any FE80..FEFF or FB50..FDFF hex literal — these are the
+  // Arabic Presentation Forms ranges. Without shaping none would appear.
+  const presFormsRegex = /<(?:FE[89A-F][0-9A-F]|FEF[0-9A-F]|FE[7][0-9A-F]|FB[5-9A-F][0-9A-F]|FC[0-9A-F]{2}|FD[0-9A-F]{2})>/i;
+  assert.match(
+    allDecoded,
+    presFormsRegex,
+    "rendered PDF must reference Arabic Presentation Forms codepoints (proves shaping ran before PDFKit)",
+  );
+});
+
 test("PDF embeds the brand logo when set in global font settings", async () => {
  // Build a real 1x1 RGB PNG (png-js rejects most base64 fixtures).
  const u32 = (n) => {