Add wildcard-to-regexp support to QRegularExpression

This method will make QRegularExpression on par with QRegExp and
will allow to replace this class when a wildcard expression can be
set through an API (e.g. QSortFilterProxyModel::setFilterWildcard).

For other use cases, see QTBUG-34052.

[ChangeLog][QRegularExpression] Implemented support for wildcard
patterns.
Warning: QRegularExpression might not give the exact same result
as QRegExp as its implementation follows strictly the glob patterns
definition for the wildcard expressions.

Change-Id: I5ed4617ca679159430c3d46da3449f6b3100e366
Reviewed-by: Thiago Macieira <thiago.macieira@intel.com>
Reviewed-by: Oswald Buddenhagen <oswald.buddenhagen@qt.io>

src/corelib/tools/qregularexpression.cpp

@@ -798,6 +798,83 @@ Q_AUTOTEST_EXPORT unsigned int qt_qregularexpression_optimize_after_use_count =
 static const unsigned int qt_qregularexpression_optimize_after_use_count = 10;
 #endif // QT_BUILD_INTERNAL
 
+
+namespace QtPrivate {
+/*!
+    internal
+*/
+QString wildcardToRegularExpression(const QString &wildcardString)
+{
+    const int wclen = wildcardString.length();
+    QString rx;
+    int i = 0;
+    bool hasNegativeBracket = false;
+    const QChar *wc = wildcardString.unicode();
+
+    while (i < wclen) {
+        const QChar c = wc[i++];
+        switch (c.unicode()) {
+        case '*':
+            rx += QLatin1String(".*");
+            break;
+        case '?':
+            rx += QLatin1Char('.');
+            break;
+        case '$':
+        case '(':
+        case ')':
+        case '+':
+        case '.':
+        case '^':
+        case '{':
+        case '|':
+        case '}':
+            rx += QLatin1Char('\\');
+            rx += c;
+            break;
+        case '[':
+            // Support for the [!abc] or [!a-c] syntax
+            // Implements a negative look-behind for one char.
+            if (wc[i] == QLatin1Char(']')) {
+                rx += c;
+                rx += wc[i++];
+            } else if (wc[i] == QLatin1Char('!')) {
+                rx += QLatin1String(".(?<");
+                rx += wc[i++];
+                rx += c;
+                hasNegativeBracket = true;
+            } else {
+                rx += c;
+            }
+
+            if (i < wclen) {
+                if (rx[i] == QLatin1Char(']'))
+                    rx += wc[i++];
+                while (i < wclen && wc[i] != QLatin1Char(']')) {
+                    if (wc[i] == QLatin1Char('\\'))
+                        rx += QLatin1Char('\\');
+                    rx += wc[i++];
+                }
+            }
+            break;
+        case ']':
+            rx += c;
+            // Closes the negative look-behind expression.
+            if (hasNegativeBracket) {
+                rx += QLatin1Char(')');
+                hasNegativeBracket = false;
+            }
+            break;
+        default:
+            rx += c;
+            break;
+        }
+    }
+
+    return rx;
+}
+}
+
 /*!
     \internal
 */
@@ -1553,6 +1630,47 @@ void QRegularExpression::setPattern(const QString &pattern)
     d->pattern = pattern;
 }
 
+/*!
+    \since 5.12
+
+    Sets the pattern string of the regular expression to \a wildcard pattern.
+    The pattern options are left unchanged.
+
+    \warning Unlike QRegExp, this implementation follows closely the definition
+    of wildcard for glob patterns:
+    \table
+    \row \li \b{c}
+         \li Any character represents itself apart from those mentioned
+         below. Thus \b{c} matches the character \e c.
+    \row \li \b{?}
+         \li Matches any single character. It is the same as
+         \b{.} in full regexps.
+    \row \li \b{*}
+         \li Matches zero or more of any characters. It is the
+         same as \b{.*} in full regexps.
+    \row \li \b{[abc]}
+         \li Matches one character given in the bracket.
+    \row \li \b{[a-c]}
+         \li Matches one character from the range given in the bracket.
+    \row \li \b{[!abc]}
+         \li Matches one character that is not given in the bracket.
+    \row \li \b{[!a-c]}
+         \li matches one character that is not from the range given in the
+         bracket.
+    \endtable
+
+    \note This function generates a regular expression that will act following
+    the wildcard pattern given. However the content of the regular expression
+    will not be the same as the one set.
+
+    \sa pattern(), setPattern()
+*/
+void QRegularExpression::setWildcardPattern(const QString &pattern)
+{
+    setPattern(QtPrivate::wildcardToRegularExpression(pattern));
+}
+
+
 /*!
     Returns the pattern options for the regular expression.
 

src/corelib/tools/qregularexpression.h

@@ -96,6 +96,7 @@ public:
 
     QString pattern() const;
     void setPattern(const QString &pattern);
+    void setWildcardPattern(const QString &pattern);
 
     bool isValid() const;
     int patternErrorOffset() const;

src/corelib/tools/qregularexpression_p.h

@@ -0,0 +1,70 @@
+/****************************************************************************
+**
+** Copyright (C) 2018 Samuel Gaist <samuel.gaist@edeltech.ch>
+** Copyright (C) 2018 The Qt Company Ltd.
+** Contact: https://www.qt.io/licensing/
+**
+** This file is part of the QtCore module of the Qt Toolkit.
+**
+** $QT_BEGIN_LICENSE:LGPL$
+** Commercial License Usage
+** Licensees holding valid commercial Qt licenses may use this file in
+** accordance with the commercial license agreement provided with the
+** Software or, alternatively, in accordance with the terms contained in
+** a written agreement between you and The Qt Company. For licensing terms
+** and conditions see https://www.qt.io/terms-conditions. For further
+** information use the contact form at https://www.qt.io/contact-us.
+**
+** GNU Lesser General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU Lesser
+** General Public License version 3 as published by the Free Software
+** Foundation and appearing in the file LICENSE.LGPL3 included in the
+** packaging of this file. Please review the following information to
+** ensure the GNU Lesser General Public License version 3 requirements
+** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
+**
+** GNU General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU
+** General Public License version 2.0 or (at your option) the GNU General
+** Public license version 3 or any later version approved by the KDE Free
+** Qt Foundation. The licenses are as published by the Free Software
+** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
+** included in the packaging of this file. Please review the following
+** information to ensure the GNU General Public License requirements will
+** be met: https://www.gnu.org/licenses/gpl-2.0.html and
+** https://www.gnu.org/licenses/gpl-3.0.html.
+**
+** $QT_END_LICENSE$
+**
+****************************************************************************/
+
+#ifndef QREGULAREXPRESSION_P_H
+#define QREGULAREXPRESSION_P_H
+
+//
+//  W A R N I N G
+//  -------------
+//
+// This file is not part of the Qt API.  It exists purely as an
+// implementation detail.  This header file may change from version to
+// version without notice, or even be removed.
+//
+// We mean it.
+//
+
+#include <private/qglobal_p.h>
+
+#include <qregularexpression.h>
+#include <qstring.h>
+
+QT_REQUIRE_CONFIG(regularexpression);
+
+QT_BEGIN_NAMESPACE
+
+namespace QtPrivate {
+QString wildcardToRegularExpression(const QString &expression);
+}
+
+QT_END_NAMESPACE
+
+#endif

src/corelib/tools/tools.pri

@@ -181,7 +181,9 @@ qtConfig(datetimeparser) {
 qtConfig(regularexpression) {
     QMAKE_USE_PRIVATE += pcre2
 
-    HEADERS += tools/qregularexpression.h
+    HEADERS += \
+        tools/qregularexpression.h \
+        tools/qregularexpression_p.h
     SOURCES += tools/qregularexpression.cpp
 }
 

tests/auto/corelib/tools/qregularexpression/tst_qregularexpression.cpp

@@ -2066,3 +2066,80 @@ void tst_QRegularExpression::QStringAndQStringRefEquivalence()
         }
     }
 }
+
+void tst_QRegularExpression::wildcard_data()
+{
+    QTest::addColumn<QString>("pattern");
+    QTest::addColumn<QString>("string");
+    QTest::addColumn<int>("foundIndex");
+
+    auto addRow = [](const char *pattern, const char *string, int foundIndex) {
+        QTest::addRow(pattern) << pattern << string << foundIndex;
+    };
+
+    addRow("*.html", "test.html", 0);
+    addRow("*.html", "test.htm", -1);
+    addRow("bar*", "foobarbaz", 3);
+    addRow("*", "Qt Rocks!", 0);
+    addRow(".html", "test.html", 4);
+    addRow(".h", "test.cpp", -1);
+    addRow(".???l", "test.html", 4);
+    addRow("?", "test.html", 0);
+    addRow("?m", "test.html", 6);
+    addRow(".h[a-z]ml", "test.html", 4);
+    addRow(".h[A-Z]ml", "test.html", -1);
+    addRow(".h[A-Z]ml", "test.hTml", 4);
+    addRow(".h[!A-Z]ml", "test.hTml", -1);
+    addRow(".h[!A-Z]ml", "test.html", 4);
+    addRow(".h[!T]ml", "test.hTml", -1);
+    addRow(".h[!T]ml", "test.html", 4);
+    addRow(".h[!T]m[!L]", "test.htmL", -1);
+    addRow(".h[!T]m[!L]", "test.html", 4);
+    addRow(".h[][!]", "test.h]ml", 4);
+    addRow(".h[][!]", "test.h[ml", 4);
+    addRow(".h[][!]", "test.h!ml", 4);
+}
+
+void tst_QRegularExpression::wildcard()
+{
+    QFETCH(QString, pattern);
+    QFETCH(QString, string);
+    QFETCH(int, foundIndex);
+
+    QRegularExpression re;
+    re.setWildcardPattern(pattern);
+    if (forceOptimize)
+        re.optimize();
+
+    QRegularExpressionMatch match = re.match(string);
+
+    QCOMPARE(match.capturedStart(), foundIndex);
+}
+
+void tst_QRegularExpression::testInvalidWildcard_data()
+{
+    QTest::addColumn<QString>("pattern");
+    QTest::addColumn<bool>("isValid");
+
+    QTest::newRow("valid []") << "[abc]" << true;
+    QTest::newRow("valid ending ]") << "abc]" << true;
+    QTest::newRow("invalid [") << "[abc" << false;
+    QTest::newRow("ending [") << "abc[" << false;
+    QTest::newRow("ending [^") << "abc[^" << false;
+    QTest::newRow("ending [\\") << "abc[\\" << false;
+    QTest::newRow("ending []") << "abc[]" << false;
+    QTest::newRow("ending [[") << "abc[[" << false;
+}
+
+void tst_QRegularExpression::testInvalidWildcard()
+{
+    QFETCH(QString, pattern);
+
+    QRegularExpression re;
+    re.setWildcardPattern(pattern);
+    if (forceOptimize)
+        re.optimize();
+
+    QFETCH(bool, isValid);
+    QCOMPARE(re.isValid(), isValid);
+}

tests/auto/corelib/tools/qregularexpression/tst_qregularexpression.h

@@ -69,6 +69,11 @@ private slots:
     void JOptionUsage();
     void QStringAndQStringRefEquivalence();
 
+    void wildcard_data();
+    void wildcard();
+    void testInvalidWildcard_data();
+    void testInvalidWildcard();
+
 private:
     void provideRegularExpressions();
 };