From 2d8dfb0b6280210a59d97c5926c628b322c7b453 Mon Sep 17 00:00:00 2001
From: maettuu <mangori41@bluewin.ch>
Date: Wed, 6 Aug 2025 12:35:49 +0200
Subject: [PATCH] Add regression test for Unicode mapping

Verifies that ToUnicodeMap correctly maps Extension B characters to their full Unicode code points using codePointAt

See PR https://github.com/mozilla/pdf.js/pull/19184
---
 test/unit/clitests.json          |  1 +
 test/unit/to_unicode_map_spec.js | 33 ++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+)
 create mode 100644 test/unit/to_unicode_map_spec.js

diff --git a/test/unit/clitests.json b/test/unit/clitests.json
index 1328b612461bc..1440845f8e8c7 100644
--- a/test/unit/clitests.json
+++ b/test/unit/clitests.json
@@ -46,6 +46,7 @@
     "struct_tree_spec.js",
     "svg_factory_spec.js",
     "text_layer_spec.js",
+    "to_unicode_map_spec.js",
     "type1_parser_spec.js",
     "ui_utils_spec.js",
     "unicode_spec.js",
diff --git a/test/unit/to_unicode_map_spec.js b/test/unit/to_unicode_map_spec.js
new file mode 100644
index 0000000000000..706718bdda6c2
--- /dev/null
+++ b/test/unit/to_unicode_map_spec.js
@@ -0,0 +1,33 @@
+/* Copyright 2025 Mozilla Foundation
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import { ToUnicodeMap } from "../../src/core/to_unicode_map.js";
+
+describe("ToUnicodeMap", () => {
+  it("should correctly map Extension B characters using codePointAt", () => {
+    const cmap = { 0x20: "\uD840\uDC00" }; // Example Extension B character
+    const toUnicodeMap = new ToUnicodeMap(cmap);
+
+    const expected = 0x20000; // Unicode code point for the character
+    let actual;
+    toUnicodeMap.forEach((charCode, unicode) => {
+      if (charCode === (0x20).toString()) {
+        actual = unicode;
+      }
+    });
+
+    expect(actual).toBe(expected);
+  });
+});