QDom: Stop treating non-BMP characters as invalid

According to https://www.w3.org/TR/REC-xml/#NT-Char unicode characters
within the range of [#x10000-#x10FFFF] are considered to be valid, so
fix the check for valid characters accordingly. This requires changing
the loop over the input QString to iterate over code points (instead of
code units).

Fixes: QTBUG-104362
Pick-to: 6.4 6.3 6.2 5.15
Change-Id: I7dcf5cad05265a54882807a50522d28b647e06ee
Reviewed-by: Marc Mutz <marc.mutz@qt.io>

1 files changed, 5 insertions, 4 deletions

diff --git a/src/xml/dom/qdom.cpp b/src/xml/dom/qdom.cpp
index 486894019c..e0e9a465ef 100644
--- a/src/xml/dom/qdom.cpp
+++ b/src/xml/dom/qdom.cpp
@@ -22,7 +22,7 @@
 #include <qdebug.h>
 #include <qxmlstream.h>
 #include <private/qduplicatetracker_p.h>
-
+#include <private/qstringiterator_p.h>
 
 #include <stdio.h>
 #include <limits>
@@ -156,10 +156,11 @@ static QString fixedCharData(const QString &data, bool *ok)
     }
 
     QString result;
-    for (int i = 0; i < data.size(); ++i) {
-        QChar c = data.at(i);
+    QStringIterator it(data);
+    while (it.hasNext()) {
+        const char32_t c = it.next(QChar::Null);
         if (QXmlUtils::isChar(c)) {
-            result.append(c);
+            result.append(QChar::fromUcs4(c));
         } else if (QDomImplementationPrivate::invalidDataPolicy == QDomImplementation::ReturnNullNode) {
             *ok = false;
             return QString();