| 1 | /**************************************************************************** | 
|---|
| 2 | ** | 
|---|
| 3 | ** Copyright (C) 2016 The Qt Company Ltd. | 
|---|
| 4 | ** Contact: https://www.qt.io/licensing/ | 
|---|
| 5 | ** | 
|---|
| 6 | ** This file is part of the QtCore module of the Qt Toolkit. | 
|---|
| 7 | ** | 
|---|
| 8 | ** $QT_BEGIN_LICENSE:LGPL$ | 
|---|
| 9 | ** Commercial License Usage | 
|---|
| 10 | ** Licensees holding valid commercial Qt licenses may use this file in | 
|---|
| 11 | ** accordance with the commercial license agreement provided with the | 
|---|
| 12 | ** Software or, alternatively, in accordance with the terms contained in | 
|---|
| 13 | ** a written agreement between you and The Qt Company. For licensing terms | 
|---|
| 14 | ** and conditions see https://www.qt.io/terms-conditions. For further | 
|---|
| 15 | ** information use the contact form at https://www.qt.io/contact-us. | 
|---|
| 16 | ** | 
|---|
| 17 | ** GNU Lesser General Public License Usage | 
|---|
| 18 | ** Alternatively, this file may be used under the terms of the GNU Lesser | 
|---|
| 19 | ** General Public License version 3 as published by the Free Software | 
|---|
| 20 | ** Foundation and appearing in the file LICENSE.LGPL3 included in the | 
|---|
| 21 | ** packaging of this file. Please review the following information to | 
|---|
| 22 | ** ensure the GNU Lesser General Public License version 3 requirements | 
|---|
| 23 | ** will be met: https://www.gnu.org/licenses/lgpl-3.0.html. | 
|---|
| 24 | ** | 
|---|
| 25 | ** GNU General Public License Usage | 
|---|
| 26 | ** Alternatively, this file may be used under the terms of the GNU | 
|---|
| 27 | ** General Public License version 2.0 or (at your option) the GNU General | 
|---|
| 28 | ** Public license version 3 or any later version approved by the KDE Free | 
|---|
| 29 | ** Qt Foundation. The licenses are as published by the Free Software | 
|---|
| 30 | ** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3 | 
|---|
| 31 | ** included in the packaging of this file. Please review the following | 
|---|
| 32 | ** information to ensure the GNU General Public License requirements will | 
|---|
| 33 | ** be met: https://www.gnu.org/licenses/gpl-2.0.html and | 
|---|
| 34 | ** https://www.gnu.org/licenses/gpl-3.0.html. | 
|---|
| 35 | ** | 
|---|
| 36 | ** $QT_END_LICENSE$ | 
|---|
| 37 | ** | 
|---|
| 38 | ****************************************************************************/ | 
|---|
| 39 |  | 
|---|
| 40 | #include <qglobal.h> | 
|---|
| 41 |  | 
|---|
| 42 | #include <QtNetwork/private/qtnetworkglobal_p.h> | 
|---|
| 43 |  | 
|---|
| 44 | #if QT_CONFIG(topleveldomain) | 
|---|
| 45 |  | 
|---|
| 46 | #include "qplatformdefs.h" | 
|---|
| 47 | #include "qurl.h" | 
|---|
| 48 | #include "private/qurltlds_p.h" | 
|---|
| 49 | #include "private/qtldurl_p.h" | 
|---|
| 50 | #include "QtCore/qlist.h" | 
|---|
| 51 | #include "QtCore/qstring.h" | 
|---|
| 52 |  | 
|---|
| 53 | QT_BEGIN_NAMESPACE | 
|---|
| 54 |  | 
|---|
| 55 | enum TLDMatchType { | 
|---|
| 56 | ExactMatch, | 
|---|
| 57 | SuffixMatch, | 
|---|
| 58 | ExceptionMatch, | 
|---|
| 59 | }; | 
|---|
| 60 |  | 
|---|
| 61 | // Scan the auto-generated table of TLDs for an entry. For more details | 
|---|
| 62 | // see comments in file:  util/corelib/qurl-generateTLDs/main.cpp | 
|---|
| 63 | static bool containsTLDEntry(QStringView entry, TLDMatchType match) | 
|---|
| 64 | { | 
|---|
| 65 | const QStringView matchSymbols[] = { | 
|---|
| 66 | u "", | 
|---|
| 67 | u "*", | 
|---|
| 68 | u "!", | 
|---|
| 69 | }; | 
|---|
| 70 | const auto symbol = matchSymbols[match]; | 
|---|
| 71 | const int index = qt_hash(entry, qt_hash(symbol)) % tldCount; | 
|---|
| 72 |  | 
|---|
| 73 | // select the right chunk from the big table | 
|---|
| 74 | short chunk = 0; | 
|---|
| 75 | uint chunkIndex = tldIndices[index], offset = 0; | 
|---|
| 76 |  | 
|---|
| 77 | // The offset in the big string, of the group that our entry hashes into. | 
|---|
| 78 | const auto tldGroupOffset = tldIndices[index]; | 
|---|
| 79 |  | 
|---|
| 80 | // It should always be inside all chunks' total size. | 
|---|
| 81 | Q_ASSERT(tldGroupOffset < tldChunks[tldChunkCount - 1]); | 
|---|
| 82 | // All offsets are stored in non-decreasing order. | 
|---|
| 83 | // This check is within bounds as tldIndices has length tldCount+1. | 
|---|
| 84 | Q_ASSERT(tldGroupOffset <= tldIndices[index + 1]); | 
|---|
| 85 | // The last extra entry in tldIndices | 
|---|
| 86 | // should be equal to the total of all chunks' lengths. | 
|---|
| 87 | static_assert(tldIndices[tldCount] == tldChunks[tldChunkCount - 1]); | 
|---|
| 88 |  | 
|---|
| 89 | // Find which chunk contains the tldGroupOffset | 
|---|
| 90 | while (tldGroupOffset >= tldChunks[chunk]) { | 
|---|
| 91 | chunkIndex -= tldChunks[chunk]; | 
|---|
| 92 | offset += tldChunks[chunk]; | 
|---|
| 93 | chunk++; | 
|---|
| 94 |  | 
|---|
| 95 | // We can not go above the number of chunks we have, since all our | 
|---|
| 96 | // indices are less than the total chunks' size (see asserts above). | 
|---|
| 97 | Q_ASSERT(chunk < tldChunkCount); | 
|---|
| 98 | } | 
|---|
| 99 |  | 
|---|
| 100 | // check all the entries from the given offset | 
|---|
| 101 | while (chunkIndex < tldIndices[index+1] - offset) { | 
|---|
| 102 | const auto utf8 = tldData[chunk] + chunkIndex; | 
|---|
| 103 | if ((symbol.isEmpty() || QLatin1Char(*utf8) == symbol) && entry == QString::fromUtf8(utf8 + symbol.size())) | 
|---|
| 104 | return true; | 
|---|
| 105 | chunkIndex += uint(qstrlen(utf8)) + 1; // +1 for the ending \0 | 
|---|
| 106 | } | 
|---|
| 107 | return false; | 
|---|
| 108 | } | 
|---|
| 109 |  | 
|---|
| 110 | /*! | 
|---|
| 111 | \internal | 
|---|
| 112 |  | 
|---|
| 113 | Return true if \a domain is a top-level-domain per Qt's copy of the Mozilla public suffix list. | 
|---|
| 114 |  | 
|---|
| 115 | The \a domain must be in lower-case format (as per QString::toLower()). | 
|---|
| 116 | */ | 
|---|
| 117 |  | 
|---|
| 118 | Q_NETWORK_EXPORT bool qIsEffectiveTLD(QStringView domain) | 
|---|
| 119 | { | 
|---|
| 120 | // for domain 'foo.bar.com': | 
|---|
| 121 | // 1. return if TLD table contains 'foo.bar.com' | 
|---|
| 122 | // 2. else if table contains '*.bar.com', | 
|---|
| 123 | // 3. test that table does not contain '!foo.bar.com' | 
|---|
| 124 |  | 
|---|
| 125 | if (containsTLDEntry(domain, ExactMatch)) // 1 | 
|---|
| 126 | return true; | 
|---|
| 127 |  | 
|---|
| 128 | const auto dot = domain.indexOf(QLatin1Char('.')); | 
|---|
| 129 | if (dot < 0) // Actual TLD: may be effective if the subject of a wildcard rule: | 
|---|
| 130 | return containsTLDEntry(QString(QLatin1Char('.') + domain), SuffixMatch); | 
|---|
| 131 | if (containsTLDEntry(domain.mid(dot), SuffixMatch))   // 2 | 
|---|
| 132 | return !containsTLDEntry(domain, ExceptionMatch); // 3 | 
|---|
| 133 | return false; | 
|---|
| 134 | } | 
|---|
| 135 |  | 
|---|
| 136 | QT_END_NAMESPACE | 
|---|
| 137 |  | 
|---|
| 138 | #endif | 
|---|
| 139 |  | 
|---|