Fix captions with non-BMP characters

KWin replaces any non-printable character with a space. This check does not
handle surrogate pairs correctly. Additionally, translators sometimes insert
non-printable soft-hyphens into titles, which also cause KWin to display a
space instead.

This code adds the missing surrogate handling, and (to fix both issues), also
removes non-printable characters instead of replacing them with a space.

Also moved the changed test after these changes, so that changes in non-
printable characters do not cause unneeded redraws.

Unit tests adapted by Vlad Zagorodniy.

Test Plan:

kwrite /tmp/Test😣.txt shows correct title. I also tested actual non-printable
characters, such as 0x1A, and these are correctly omitted.

BUG: 376813
FIXED-IN: 5.15.5

Reviewers: #kwin, zzag

Reviewed By: #kwin, zzag

Subscribers: zzag, grasslin, kwin

Tags: #kwin

Differential Revision: https://phabricator.kde.org/D19052

autotests/integration/x11_client_test.cpp

@@ -49,7 +49,8 @@ private Q_SLOTS:
     void init();
     void cleanup();
 
-    void testCaptionSimplified();
+    void testTrimCaption_data();
+    void testTrimCaption();
     void testFullscreenLayerWithActiveWaylandWindow();
     void testFocusInWithWaylandLastActiveWindow();
     void testX11WindowId();
@@ -94,13 +95,23 @@ struct XcbConnectionDeleter
     }
 };
 
+void X11ClientTest::testTrimCaption_data()
+{
+    QTest::addColumn<QByteArray>("originalTitle");
+    QTest::addColumn<QByteArray>("expectedTitle");
 
-void X11ClientTest::testCaptionSimplified()
+    QTest::newRow("simplified")
+        << QByteArrayLiteral("Was tun, wenn Schüler Autismus haben?\342\200\250\342\200\250\342\200\250 – Marlies Hübner - Mozilla Firefox")
+        << QByteArrayLiteral("Was tun, wenn Schüler Autismus haben? – Marlies Hübner - Mozilla Firefox");
+
+    QTest::newRow("with emojis")
+        << QByteArrayLiteral("\bTesting non\302\255printable:\177, emoij:\360\237\230\203, non-characters:\357\277\276")
+        << QByteArrayLiteral("Testing nonprintable:, emoij:\360\237\230\203, non-characters:");
+}
+
+void X11ClientTest::testTrimCaption()
 {
     // this test verifies that caption is properly trimmed
-    // see BUG 323798 comment #12
-    QSignalSpy windowAddedSpy(effects, &EffectsHandler::windowAdded);
-    QVERIFY(windowAddedSpy.isValid());
 
     // create an xcb window
     QScopedPointer<xcb_connection_t, XcbConnectionDeleter> c(xcb_connect(nullptr, nullptr));
@@ -119,8 +130,8 @@ void X11ClientTest::testCaptionSimplified()
     xcb_icccm_size_hints_set_size(&hints, 1, windowGeometry.width(), windowGeometry.height());
     xcb_icccm_set_wm_normal_hints(c.data(), w, &hints);
     NETWinInfo winInfo(c.data(), w, rootWindow(), NET::Properties(), NET::Properties2());
-    const QByteArray origTitle = QByteArrayLiteral("Was tun, wenn Schüler Autismus haben?\342\200\250\342\200\250\342\200\250 – Marlies Hübner - Mozilla Firefox");
+    QFETCH(QByteArray, originalTitle);
-    winInfo.setName(origTitle.constData());
+    winInfo.setName(originalTitle);
     xcb_map_window(c.data(), w);
     xcb_flush(c.data());
 
@@ -131,8 +142,8 @@ void X11ClientTest::testCaptionSimplified()
     Client *client = windowCreatedSpy.first().first().value<Client*>();
     QVERIFY(client);
     QCOMPARE(client->window(), w);
-    QVERIFY(client->caption() != QString::fromUtf8(origTitle));
+    QFETCH(QByteArray, expectedTitle);
-    QCOMPARE(client->caption(), QString::fromUtf8(origTitle).simplified());
+    QCOMPARE(client->caption(), QString::fromUtf8(expectedTitle));
 
     // and destroy the window again
     xcb_unmap_window(c.data(), w);

client.cpp

@@ -1463,13 +1463,27 @@ static const QChar LRM(0x200E);
 
 void Client::setCaption(const QString& _s, bool force)
 {
-    if (!force && _s == cap_normal)
-        return;
     QString s(_s);
-    for (int i = 0; i < s.length(); ++i)
+    for (int i = 0; i < s.length(); ) {
-        if (!s[i].isPrint())
+        if (!s[i].isPrint()) {
-            s[i] = QChar(u' ');
+            if (QChar(s[i]).isHighSurrogate() && i + 1 < s.length() && QChar(s[i + 1]).isLowSurrogate()) {
+                const uint uc = QChar::surrogateToUcs4(s[i], s[i + 1]);
+                if (!QChar::isPrint(uc)) {
+                    s.remove(i, 2);
+                } else {
+                    i += 2;
+                }
+                continue;
+            }
+            s.remove(i, 1);
+            continue;
+        }
+        ++i;
+    }
     const bool changed = (s != cap_normal);
+    if (!force && !changed) {
+        return;
+    }
     cap_normal = s;
     if (!force && !changed) {
         emit captionChanged();