summaryrefslogtreecommitdiffstats
path: root/src/corelib/serialization/qxmlutils.cpp
diff options
context:
space:
mode:
authorSona Kurazyan <sona.kurazyan@qt.io>2022-06-17 14:43:17 +0200
committerMarc Mutz <marc.mutz@qt.io>2022-06-20 21:29:04 +0000
commitda0d7f61c851431d14430684c62345bc23dbf001 (patch)
tree3e7bf228e48edc2ef9972806b46c83be78a585fa /src/corelib/serialization/qxmlutils.cpp
parent3d73aa660b5e1af5758ae7207ce1c05d7a0458e1 (diff)
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>
Diffstat (limited to 'src/corelib/serialization/qxmlutils.cpp')
-rw-r--r--src/corelib/serialization/qxmlutils.cpp15
1 files changed, 9 insertions, 6 deletions
diff --git a/src/corelib/serialization/qxmlutils.cpp b/src/corelib/serialization/qxmlutils.cpp
index 74a0cf0c23..778e8de72d 100644
--- a/src/corelib/serialization/qxmlutils.cpp
+++ b/src/corelib/serialization/qxmlutils.cpp
@@ -235,13 +235,16 @@ bool QXmlUtils::isLetter(const QChar c)
\sa {http://www.w3.org/TR/REC-xml/#NT-Char},
{Extensible Markup Language (XML) 1.0 (Fourth Edition), [2] Char}
*/
-bool QXmlUtils::isChar(const QChar c)
+bool QXmlUtils::isChar(const char32_t c)
{
- return (c.unicode() >= 0x0020 && c.unicode() <= 0xD7FF)
- || c.unicode() == 0x0009
- || c.unicode() == 0x000A
- || c.unicode() == 0x000D
- || (c.unicode() >= 0xE000 && c.unicode() <= 0xFFFD);
+ // The valid range is defined by https://www.w3.org/TR/REC-xml/#NT-Char as following:
+ // Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
+ return (c >= 0x0020 && c <= 0xD7FF)
+ || c == 0x0009
+ || c == 0x000A
+ || c == 0x000D
+ || (c >= 0xE000 && c <= 0xFFFD)
+ || (c >= 0x10000 && c <= 0x10FFFF);
}
/*!