Add QUrl::topLevelDomain() and move TLD table from QtNetwork to QtCore

Move Qt's copy of the Mozilla public suffix list from QtNetwork
to QtCore and use it to expose a new API function QUrl::topLevelDomain().
This function returns the section of the url that is a registrar-controlled
top level domain.

QtCore now exports a couple of functions to the other Qt modules: qTopLevelDomain,
a helper function for QUrl::topLevelDomain(); and qIsEffectiveTLD(), a helper
function for QNetworkCookeieJar.

The motivation for this new API is to allow QtWebKit implement a Third-Party
Cookie blocking policy. For this QtWebKit needs to know the element of the url
that is the registry-controlled TLD. Without this knowledge it would end up
blocking third-party cookies per host rather than per registry-controlled domain.

See also https://bugs.webkit.org/show_bug.cgi?id=45455

Merge-request: 1205
Task-number: QTBUG-13601
Reviewed-by: Peter Hartmann <peter.hartmann@nokia.com>
(cherry picked from commit 154402f56dcf8303a6ce601a52215226af8d31ba)

1 files changed, 117 insertions, 0 deletions

diff --git a/src/corelib/io/qtldurl.cpp b/src/corelib/io/qtldurl.cpp
new file mode 100644
index 0000000000..7db4bbddd5
--- /dev/null
+++ b/src/corelib/io/qtldurl.cpp
@@ -0,0 +1,117 @@
+/****************************************************************************
+**
+** Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies).
+** All rights reserved.
+** Contact: Nokia Corporation (qt-info@nokia.com)
+**
+** This file is part of the QtCore module of the Qt Toolkit.
+**
+** $QT_BEGIN_LICENSE:LGPL$
+** No Commercial Usage
+** This file contains pre-release code and may not be distributed.
+** You may use this file in accordance with the terms and conditions
+** contained in the Technology Preview License Agreement accompanying
+** this package.
+**
+** GNU Lesser General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU Lesser
+** General Public License version 2.1 as published by the Free Software
+** Foundation and appearing in the file LICENSE.LGPL included in the
+** packaging of this file.  Please review the following information to
+** ensure the GNU Lesser General Public License version 2.1 requirements
+** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
+**
+** In addition, as a special exception, Nokia gives you certain additional
+** rights.  These rights are described in the Nokia Qt LGPL Exception
+** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
+**
+** If you have questions regarding the use of this file, please contact
+** Nokia at qt-info@nokia.com.
+**
+**
+**
+**
+**
+**
+**
+**
+** $QT_END_LICENSE$
+**
+****************************************************************************/
+
+#include "qplatformdefs.h"
+#include "qurl.h"
+#include "private/qurltlds_p.h"
+#include "private/qtldurl_p.h"
+#include "QtCore/qstringlist.h"
+
+QT_BEGIN_NAMESPACE
+
+static bool containsTLDEntry(const QString &entry)
+{
+    int index = qHash(entry) % tldCount;
+    int currentDomainIndex = tldIndices[index];
+    while (currentDomainIndex < tldIndices[index+1]) {
+        QString currentEntry = QString::fromUtf8(tldData + currentDomainIndex);
+        if (currentEntry == entry)
+            return true;
+        currentDomainIndex += qstrlen(tldData + currentDomainIndex) + 1; // +1 for the ending \0
+    }
+    return false;
+}
+
+/*!
+    \internal
+
+    Return the top-level-domain per Qt's copy of the Mozilla public suffix list of
+    \a domain.
+*/
+
+Q_CORE_EXPORT QString qTopLevelDomain(const QString &domain)
+{
+    QStringList sections = domain.toLower().split(QLatin1Char('.'), QString::SkipEmptyParts);
+    if (sections.isEmpty())
+        return QString();
+
+    QString level, tld;
+    for (int j = sections.count() - 1; j >= 0; --j) {
+        level.prepend(QLatin1Char('.') + sections.at(j));
+        if (qIsEffectiveTLD(level.right(level.size() - 1)))
+            tld = level;
+    }
+    return tld;
+}
+
+/*!
+    \internal
+
+    Return true if \a domain is a top-level-domain per Qt's copy of the Mozilla public suffix list.
+*/
+
+Q_CORE_EXPORT bool qIsEffectiveTLD(const QString &domain)
+{
+    // for domain 'foo.bar.com':
+    // 1. return if TLD table contains 'foo.bar.com'
+    if (containsTLDEntry(domain))
+        return true;
+
+    if (domain.contains(QLatin1Char('.'))) {
+        int count = domain.size() - domain.indexOf(QLatin1Char('.'));
+        QString wildCardDomain;
+        wildCardDomain.reserve(count + 1);
+        wildCardDomain.append(QLatin1Char('*'));
+        wildCardDomain.append(domain.right(count));
+        // 2. if table contains '*.bar.com',
+        // test if table contains '!foo.bar.com'
+        if (containsTLDEntry(wildCardDomain)) {
+            QString exceptionDomain;
+            exceptionDomain.reserve(domain.size() + 1);
+            exceptionDomain.append(QLatin1Char('!'));
+            exceptionDomain.append(domain);
+            return (! containsTLDEntry(exceptionDomain));
+        }
+    }
+    return false;
+}
+
+QT_END_NAMESPACE