QXmlStreamReader: Raise error on unexpected tokens

QXmlStreamReader accepted multiple DOCTYPE elements, containing DTD
fragments in the XML prolog, and in the XML body.
Well-formed but invalid XML files - with multiple DTD fragments in
prolog and body, combined with recursive entity expansions - have
caused infinite loops in QXmlStreamReader.

This patch implements a token check in QXmlStreamReader.
A stream is allowed to start with an XML prolog. StartDocument
and DOCTYPE elements are only allowed in this prolog, which
may also contain ProcessingInstruction and Comment elements.
As soon as anything else is seen, the prolog ends.
After that, the prolog-specific elements are treated as unexpected.
Furthermore, the prolog can contain at most one DOCTYPE element.

Update the documentation to reflect the new behavior.
Add an autotest that checks the new error cases are correctly detected,
and no error is raised for legitimate input.

The original OSS-Fuzz files (see bug reports) are not included in this
patch for file size reasons. They have been tested manually. Each of
them has more than one DOCTYPE element, causing infinite loops in
recursive entity expansions. The newly implemented functionality
detects those invalid DTD fragments. By raising an error, it aborts
stream reading before an infinite loop occurs.

Thanks to OSS-Fuzz for finding this.

Fixes: QTBUG-92113
Fixes: QTBUG-95188
Pick-to: 6.6 6.5 6.2 5.15
Change-Id: I0a082b9188b2eee50b396c4d5b1c9e1fd237bbdd
Reviewed-by: Volker Hilsheimer <volker.hilsheimer@qt.io>

src/corelib/serialization/qxmlstream.cpp

@@ -185,7 +185,7 @@ WRAP(indexOf, QLatin1StringView)
     addData() or by waiting for it to arrive on the device().
 
     \value UnexpectedElementError The parser encountered an element
-    that was different to those it expected.
+    or token that was different to those it expected.
 
 */
 
@@ -322,13 +322,34 @@ QXmlStreamEntityResolver *QXmlStreamReader::entityResolver() const
 
   QXmlStreamReader is a well-formed XML 1.0 parser that does \e not
   include external parsed entities. As long as no error occurs, the
-  application code can thus be assured that the data provided by the
+  application code can thus be assured, that
-  stream reader satisfies the W3C's criteria for well-formed XML. For
+  \list
-  example, you can be certain that all tags are indeed nested and
+  \li the data provided by the stream reader satisfies the W3C's
-  closed properly, that references to internal entities have been
+      criteria for well-formed XML,
-  replaced with the correct replacement text, and that attributes have
+  \li tokens are provided in a valid order.
-  been normalized or added according to the internal subset of the
+  \endlist
-  DTD.
+
+  Unless QXmlStreamReader raises an error, it guarantees the following:
+  \list
+  \li All tags are nested and closed properly.
+  \li References to internal entities have been replaced with the
+      correct replacement text.
+  \li Attributes have been normalized or added according to the
+      internal subset of the \l DTD.
+  \li Tokens of type \l StartDocument happen before all others,
+      aside from comments and processing instructions.
+  \li At most one DOCTYPE element (a token of type \l DTD) is present.
+  \li If present, the DOCTYPE appears before all other elements,
+      aside from StartDocument, comments and processing instructions.
+  \endlist
+
+  In particular, once any token of type \l StartElement, \l EndElement,
+  \l Characters, \l EntityReference or \l EndDocument is seen, no
+  tokens of type StartDocument or DTD will be seen. If one is present in
+  the input stream, out of order, an error is raised.
+
+  \note The token types \l Comment and \l ProcessingInstruction may appear
+  anywhere in the stream.
 
   If an error occurs while parsing, atEnd() and hasError() return
   true, and error() returns the error that occurred. The functions
@@ -659,6 +680,7 @@ QXmlStreamReader::TokenType QXmlStreamReader::readNext()
         d->token = -1;
         return readNext();
     }
+    d->checkToken();
     return d->type;
 }
 
@@ -743,6 +765,11 @@ static constexpr auto QXmlStreamReader_tokenTypeString = qOffsetStringArray(
     "ProcessingInstruction"
 );
 
+static constexpr auto QXmlStreamReader_XmlContextString = qOffsetStringArray(
+    "Prolog",
+    "Body"
+);
+
 /*!
     \property  QXmlStreamReader::namespaceProcessing
     \brief the namespace-processing flag of the stream reader.
@@ -777,6 +804,15 @@ QString QXmlStreamReader::tokenString() const
     return QLatin1StringView(QXmlStreamReader_tokenTypeString.at(d->type));
 }
 
+/*!
+   \internal
+   \return \param loc (Prolog/Body) as a string.
+ */
+static constexpr QLatin1StringView contextString(QXmlStreamReaderPrivate::XmlContext ctxt)
+{
+    return QLatin1StringView(QXmlStreamReader_XmlContextString.at(static_cast<int>(ctxt)));
+}
+
 #endif // feature xmlstreamreader
 
 QXmlStreamPrivateTagStack::QXmlStreamPrivateTagStack()
@@ -864,6 +900,8 @@ void QXmlStreamReaderPrivate::init()
 
     type = QXmlStreamReader::NoToken;
     error = QXmlStreamReader::NoError;
+    currentContext = XmlContext::Prolog;
+    foundDTD = false;
 }
 
 /*
@@ -3814,6 +3852,97 @@ void QXmlStreamWriter::writeCurrentToken(const QXmlStreamReader &reader)
     }
 }
 
+static constexpr bool isTokenAllowedInContext(QXmlStreamReader::TokenType type,
+                                               QXmlStreamReaderPrivate::XmlContext loc)
+{
+    switch (type) {
+    case QXmlStreamReader::StartDocument:
+    case QXmlStreamReader::DTD:
+        return loc == QXmlStreamReaderPrivate::XmlContext::Prolog;
+
+    case QXmlStreamReader::StartElement:
+    case QXmlStreamReader::EndElement:
+    case QXmlStreamReader::Characters:
+    case QXmlStreamReader::EntityReference:
+    case QXmlStreamReader::EndDocument:
+        return loc == QXmlStreamReaderPrivate::XmlContext::Body;
+
+    case QXmlStreamReader::Comment:
+    case QXmlStreamReader::ProcessingInstruction:
+        return true;
+
+    case QXmlStreamReader::NoToken:
+    case QXmlStreamReader::Invalid:
+        return false;
+    }
+
+    // GCC 8.x does not treat __builtin_unreachable() as constexpr
+#if !defined(Q_CC_GNU_ONLY) || (Q_CC_GNU >= 900)
+    Q_UNREACHABLE_RETURN(false);
+#else
+    return false;
+#endif
+}
+
+/*!
+   \internal
+   \brief QXmlStreamReader::isValidToken
+   \return \c true if \param type is a valid token type.
+   \return \c false if \param type is an unexpected token,
+   which indicates a non-well-formed or invalid XML stream.
+ */
+bool QXmlStreamReaderPrivate::isValidToken(QXmlStreamReader::TokenType type)
+{
+    // Don't change currentContext, if Invalid or NoToken occur in the prolog
+    if (type == QXmlStreamReader::Invalid || type == QXmlStreamReader::NoToken)
+        return false;
+
+    // If a token type gets rejected in the body, there is no recovery
+    const bool result = isTokenAllowedInContext(type, currentContext);
+    if (result || currentContext == XmlContext::Body)
+        return result;
+
+    // First non-Prolog token observed => switch context to body and check again.
+    currentContext = XmlContext::Body;
+    return isTokenAllowedInContext(type, currentContext);
+}
+
+/*!
+   \internal
+   Checks token type and raises an error, if it is invalid
+   in the current context (prolog/body).
+ */
+void QXmlStreamReaderPrivate::checkToken()
+{
+    Q_Q(QXmlStreamReader);
+
+    // The token type must be consumed, to keep track if the body has been reached.
+    const XmlContext context = currentContext;
+    const bool ok = isValidToken(type);
+
+    // Do nothing if an error has been raised already (going along with an unexpected token)
+    if (error != QXmlStreamReader::Error::NoError)
+        return;
+
+    if (!ok) {
+        raiseError(QXmlStreamReader::UnexpectedElementError,
+                   QObject::tr("Unexpected token type %1 in %2.")
+                   .arg(q->tokenString(), contextString(context)));
+        return;
+    }
+
+    if (type != QXmlStreamReader::DTD)
+        return;
+
+    // Raise error on multiple DTD tokens
+    if (foundDTD) {
+        raiseError(QXmlStreamReader::UnexpectedElementError,
+                   QObject::tr("Found second DTD token in %1.").arg(contextString(context)));
+    } else {
+        foundDTD = true;
+    }
+}
+
 /*!
  \fn bool QXmlStreamAttributes::hasAttribute(QAnyStringView qualifiedName) const
 

src/corelib/serialization/qxmlstream_p.h

@@ -297,6 +297,17 @@ public:
     QStringDecoder decoder;
     bool atEnd;
 
+    enum class XmlContext
+    {
+        Prolog,
+        Body,
+    };
+
+    XmlContext currentContext = XmlContext::Prolog;
+    bool foundDTD = false;
+    bool isValidToken(QXmlStreamReader::TokenType type);
+    void checkToken();
+
     /*!
       \sa setType()
      */

tests/auto/corelib/serialization/qxmlstream/tokenError/dtdInBody.xml

@@ -0,0 +1,20 @@
+<!DOCTYPE TEST [
+   <!ELEMENT TESTATTRIBUTE (CASE+)>
+   <!ELEMENT CASE (CLASS, FUNCTION)>
+   <!ELEMENT CLASS (#PCDATA)>
+
+   <!-- adding random ENTITY statement, as this is typical DTD content -->
+   <!ENTITY unite "&#x222a;">
+
+   <!ATTLIST CASE CLASS CDATA #REQUIRED>
+]>
+<TEST>
+  <CASE>
+    <CLASS>tst_QXmlStream</CLASS>
+  </CASE>
+  <!-- invalid DTD in XML body follows -->
+  <!DOCTYPE DTDTEST [
+    <!ELEMENT RESULT (CASE+)>
+    <!ATTLIST RESULT OUTPUT CDATA #REQUIRED>
+  ]>
+</TEST>

tests/auto/corelib/serialization/qxmlstream/tokenError/multipleDtd.xml

@@ -0,0 +1,20 @@
+<!DOCTYPE TEST [
+   <!ELEMENT TESTATTRIBUTE (CASE+)>
+   <!ELEMENT CASE (CLASS, FUNCTION, DATASET, COMMENTS)>
+   <!ELEMENT CLASS (#PCDATA)>
+
+   <!-- adding random ENTITY statements, as this is typical DTD content -->
+   <!ENTITY iff "&hArr;">
+
+   <!ATTLIST CASE CLASS CDATA #REQUIRED>
+]>
+<!-- invalid second DTD follows -->
+<!DOCTYPE SECOND [
+   <!ELEMENT SECONDATTRIBUTE (#PCDATA)>
+   <!ENTITY on "&#8728;">
+]>
+<TEST>
+  <CASE>
+    <CLASS>tst_QXmlStream</CLASS>
+  </CASE>
+</TEST>

tests/auto/corelib/serialization/qxmlstream/tokenError/wellFormed.xml

@@ -0,0 +1,15 @@
+<!DOCTYPE TEST [
+   <!ELEMENT TESTATTRIBUTE (CASE+)>
+   <!ELEMENT CASE (CLASS, FUNCTION, DATASET, COMMENTS)>
+   <!ELEMENT CLASS (#PCDATA)>
+
+   <!-- adding random ENTITY statements, as this is typical DTD content -->
+   <!ENTITY unite "&#x222a;">
+
+   <!ATTLIST CASE CLASS CDATA #REQUIRED>
+]>
+<TEST>
+  <CASE>
+    <CLASS>tst_QXmlStream</CLASS>
+  </CASE>
+</TEST>

tests/auto/corelib/serialization/qxmlstream/tst_qxmlstream.cpp

@@ -591,6 +591,9 @@ private slots:
 
     void entityExpansionLimit() const;
 
+    void tokenErrorHandling_data() const;
+    void tokenErrorHandling() const;
+
 private:
     static QByteArray readFile(const QString &filename);
 
@@ -1867,5 +1870,41 @@ void tst_QXmlStream::test_fastScanName() const
     QCOMPARE(reader.error(), errorType);
 }
 
+void tst_QXmlStream::tokenErrorHandling_data() const
+{
+    QTest::addColumn<QString>("fileName");
+    QTest::addColumn<QXmlStreamReader::Error>("expectedError");
+    QTest::addColumn<QString>("errorKeyWord");
+
+    constexpr auto invalid = QXmlStreamReader::Error::UnexpectedElementError;
+    constexpr auto valid = QXmlStreamReader::Error::NoError;
+    QTest::newRow("DtdInBody") << "dtdInBody.xml" << invalid << "DTD";
+    QTest::newRow("multipleDTD") << "multipleDtd.xml" << invalid << "second DTD";
+    QTest::newRow("wellFormed") << "wellFormed.xml" << valid << "";
+}
+
+void tst_QXmlStream::tokenErrorHandling() const
+{
+    QFETCH(const QString, fileName);
+    QFETCH(const QXmlStreamReader::Error, expectedError);
+    QFETCH(const QString, errorKeyWord);
+
+    const QDir dir(QFINDTESTDATA("tokenError"));
+    QFile file(dir.absoluteFilePath(fileName));
+
+    // Cross-compiling: File will be on host only
+    if (!file.exists())
+        QSKIP("Testfile not found.");
+
+    file.open(QIODevice::ReadOnly);
+    QXmlStreamReader reader(&file);
+    while (!reader.atEnd())
+        reader.readNext();
+
+    QCOMPARE(reader.error(), expectedError);
+    if (expectedError != QXmlStreamReader::Error::NoError)
+        QVERIFY(reader.errorString().contains(errorKeyWord));
+}
+
 #include "tst_qxmlstream.moc"
 // vim: et:ts=4:sw=4:sts=4