Simplify and unify Q{ByteArray,String{,Ref}}::{simplify,trimmed}

As a side effect, QString::simplified() will always return a detached
copy, even if it's the same contents.

QStringRef::trimmed() can use the same calculation algorithm but can't
use the trimmed_helper() template function due to its lack of a
constructor taking begin pointer and size (std::string_view could do
it). That constructor can't be added because QStringRef always refers to
an existing QString, not to data in memory.

Change-Id: Ib966c1741819c68c6bac5fcbb00f8ac818b3ccab
Reviewed-by: Olivier Goffart <ogoffart@woboq.com>
Reviewed-by: Jędrzej Nowacki <jedrzej.nowacki@digia.com>
Reviewed-by: Marc Mutz <marc.mutz@kdab.com>

src/corelib/tools/qbytearray.cpp

@@ -1,6 +1,7 @@
 /****************************************************************************
 **
 ** Copyright (C) 2013 Digia Plc and/or its subsidiary(-ies).
+** Copyright (C) 2014 Intel Corporation.
 ** Contact: http://www.qt-project.org/legal
 **
 ** This file is part of the QtCore module of the Qt Toolkit.
@@ -46,6 +47,7 @@
 #include "qlist.h"
 #include "qlocale.h"
 #include "qlocale_p.h"
+#include "qstringalgorithms_p.h"
 #include "qscopedpointer.h"
 #include <qdatastream.h>
 #include <qmath.h>
@@ -3214,27 +3216,7 @@ QDataStream &operator>>(QDataStream &in, QByteArray &ba)
 */
 QByteArray QByteArray::simplified() const
 {
-    if (d->size == 0)
-        return *this;
-    QByteArray result(d->size, Qt::Uninitialized);
-    const char *from = d->data();
-    const char *fromend = from + d->size;
-    int outc=0;
-    char *to = result.d->data();
-    for (;;) {
-        while (from!=fromend && ascii_isspace(uchar(*from)))
-            from++;
-        while (from!=fromend && !ascii_isspace(uchar(*from)))
-            to[outc++] = *from++;
-        if (from!=fromend)
-            to[outc++] = ' ';
-        else
-            break;
-    }
-    if (outc > 0 && to[outc-1] == ' ')
-        outc--;
-    result.resize(outc);
-    return result;
+    return QStringAlgorithms<const QByteArray>::simplified_helper(*this);
 }
 
 /*!
@@ -3254,25 +3236,7 @@ QByteArray QByteArray::simplified() const
 */
 QByteArray QByteArray::trimmed() const
 {
-    if (d->size == 0)
-        return *this;
-    const char *s = d->data();
-    if (!ascii_isspace(uchar(*s)) && !ascii_isspace(uchar(s[d->size-1])))
-        return *this;
-    int start = 0;
-    int end = d->size - 1;
-    while (start<=end && ascii_isspace(uchar(s[start])))  // skip white space from start
-        start++;
-    if (start <= end) {                          // only white space
-        while (end && ascii_isspace(uchar(s[end])))           // skip white space from end
-            end--;
-    }
-    int l = end - start + 1;
-    if (l <= 0) {
-        QByteArrayDataPtr empty = { Data::allocate(0) };
-        return QByteArray(empty);
-    }
-    return QByteArray(s+start, l);
+    return QStringAlgorithms<const QByteArray>::trimmed_helper(*this);
 }
 
 /*!

src/corelib/tools/qstring.cpp

@@ -78,6 +78,7 @@
 #include "qchar.cpp"
 #include "qstringmatcher.cpp"
 #include "qstringiterator_p.h"
+#include "qstringalgorithms_p.h"
 #include "qthreadstorage.h"
 
 #ifdef Q_OS_WIN
@@ -4633,78 +4634,7 @@ QString& QString::setUnicode(const QChar *unicode, int size)
 */
 QString QString::simplified() const
 {
-    if (d->size == 0)
-        return *this;
-
-    const QChar * const start = reinterpret_cast<QChar *>(d->data());
-    const QChar *from = start;
-    const QChar *fromEnd = start + d->size;
-    forever {
-        QChar ch = *from;
-        if (!ch.isSpace())
-            break;
-        if (++from == fromEnd) {
-            // All-whitespace string
-            QStringDataPtr empty = { Data::allocate(0) };
-            return QString(empty);
-        }
-    }
-    // This loop needs no underflow check, as we already determined that
-    // the string contains non-whitespace. If the string has exactly one
-    // non-whitespace, it will be checked twice - we can live with that.
-    while (fromEnd[-1].isSpace())
-        fromEnd--;
-    // The rest of the function depends on the fact that we already know
-    // that the last character in the source is no whitespace.
-    const QChar *copyFrom = from;
-    int copyCount;
-    forever {
-        if (++from == fromEnd) {
-            // Only leading and/or trailing whitespace, if any at all
-            return mid(copyFrom - start, from - copyFrom);
-        }
-        QChar ch = *from;
-        if (!ch.isSpace())
-            continue;
-        if (ch != QLatin1Char(' ')) {
-            copyCount = from - copyFrom;
-            break;
-        }
-        ch = *++from;
-        if (ch.isSpace()) {
-            copyCount = from - copyFrom - 1;
-            break;
-        }
-    }
-    // 'from' now points at the non-trailing whitespace which made the
-    // string not simplified in the first place. 'copyCount' is the number
-    // of already simplified characters - at least one, obviously -
-    // without a trailing space.
-    QString result((fromEnd - from) + copyCount, Qt::Uninitialized);
-    QChar *to = reinterpret_cast<QChar *>(result.d->data());
-    ::memcpy(to, copyFrom, copyCount * 2);
-    to += copyCount;
-    fromEnd--;
-    QChar ch;
-    forever {
-        *to++ = QLatin1Char(' ');
-        do {
-            ch = *++from;
-        } while (ch.isSpace());
-        if (from == fromEnd)
-            break;
-        do {
-            *to++ = ch;
-            ch = *++from;
-            if (from == fromEnd)
-                goto done;
-        } while (!ch.isSpace());
-
-    }
-  done:
-    *to++ = ch;
-    result.truncate(to - reinterpret_cast<QChar *>(result.d->data()));
-    return result;
+    return QStringAlgorithms<const QString>::simplified_helper(*this);
 }
 
 /*!
@@ -4725,25 +4655,7 @@ QString QString::simplified() const
 */
 QString QString::trimmed() const
 {
-    if (d->size == 0)
-        return *this;
-    const QChar *s = (const QChar*)d->data();
-    if (!s->isSpace() && !s[d->size-1].isSpace())
-        return *this;
-    int start = 0;
-    int end = d->size - 1;
-    while (start<=end && s[start].isSpace())  // skip white space from start
-        start++;
-    if (start <= end) {                          // only white space
-        while (end && s[end].isSpace())           // skip white space from end
-            end--;
-    }
-    int l = end - start + 1;
-    if (l <= 0) {
-        QStringDataPtr empty = { Data::allocate(0) };
-        return QString(empty);
-    }
-    return QString(s + start, l);
+    return QStringAlgorithms<const QString>::trimmed_helper(*this);
 }
 
 /*! \fn const QChar QString::at(int position) const
@@ -9696,20 +9608,15 @@ QVector<uint> QStringRef::toUcs4() const
 */
 QStringRef QStringRef::trimmed() const
 {
-    if (m_size == 0 || m_string == 0)
+    const QChar *begin = cbegin();
+    const QChar *end = cend();
+    QStringAlgorithms<const QStringRef>::trimmed_helper_positions(begin, end);
+    if (begin == cbegin() && end == cend())
         return *this;
-    const QChar *s = m_string->constData() + m_position;
-    int start = 0;
-    int end = m_size - 1;
-    while (start <= end && s[start].isSpace())  // skip white space from start
-        start++;
-    if (start <= end) {                         // only white space
-        while (end && s[end].isSpace())         // skip white space from end
-            end--;
-    }
-    int l = end - start + 1;
-    Q_ASSERT(l >= 0);
-    return QStringRef(m_string, m_position + start, l);
+    if (begin == end)
+        return QStringRef();
+    int position = m_position + (begin - cbegin());
+    return QStringRef(m_string, position, end - begin);
 }
 
 /*!

src/corelib/tools/qstringalgorithms_p.h

@@ -0,0 +1,135 @@
+/****************************************************************************
+**
+** Copyright (C) 2014 Intel Corporation.
+** Contact: http://www.qt-project.org/legal
+**
+** 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 Digia.  For licensing terms and
+** conditions see http://qt.digia.com/licensing.  For further information
+** use the contact form at http://qt.digia.com/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 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, Digia gives you certain additional
+** rights.  These rights are described in the Digia Qt LGPL Exception
+** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
+**
+** GNU General Public License Usage
+** Alternatively, this file may be used under the terms of the GNU
+** General Public License version 3.0 as published by the Free Software
+** Foundation and appearing in the file LICENSE.GPL included in the
+** packaging of this file.  Please review the following information to
+** ensure the GNU General Public License version 3.0 requirements will be
+** met: http://www.gnu.org/copyleft/gpl.html.
+**
+**
+** $QT_END_LICENSE$
+**
+****************************************************************************/
+
+#ifndef QSTRINGALGORITHMS_P_H
+#define QSTRINGALGORITHMS_P_H
+
+//
+//  W A R N I N G
+//  -------------
+//
+// This file is not part of the Qt API.  It exists for the convenience
+// of internal files.  This header file may change from version to version
+// without notice, or even be removed.
+//
+// We mean it.
+//
+
+#include "qstring.h"
+#include "qlocale_p.h"      // for ascii_isspace
+
+QT_BEGIN_NAMESPACE
+
+template <typename StringType> struct QStringAlgorithms
+{
+    typedef typename StringType::value_type Char;
+    typedef typename StringType::size_type size_type;
+    typedef typename QtPrivate::remove_cv<StringType>::type NakedStringType;
+    static const bool isConst = QtPrivate::is_const<StringType>::value;
+
+    static inline bool isSpace(char ch) { return ascii_isspace(ch); }
+    static inline bool isSpace(QChar ch) { return ch.isSpace(); }
+
+    // Surrogate pairs are not handled in either of the functions below. That is
+    // not a problem because there are no space characters (Zs, Zl, Zp) outside the
+    // Basic Multilingual Plane.
+
+    static inline void trimmed_helper_positions(const Char *&begin, const Char *&end)
+    {
+        // skip white space from start
+        while (begin < end && isSpace(*begin))
+            begin++;
+        // skip white space from end
+        if (begin < end) {
+            while (begin < end && isSpace(end[-1]))
+                end--;
+        }
+    }
+
+    static inline StringType trimmed_helper(StringType &str)
+    {
+        const Char *begin = str.cbegin();
+        const Char *end = str.cend();
+        trimmed_helper_positions(begin, end);
+
+        if (begin == str.cbegin() && end == str.cend())
+            return str;
+        if (begin == end)
+            return StringType();
+        return StringType(begin, end - begin);
+    }
+
+    static inline StringType simplified_helper(StringType &str)
+    {
+        if (str.isEmpty())
+            return str;
+        const Char *src = str.cbegin();
+        const Char *end = str.cend();
+        NakedStringType result(str.size(), Qt::Uninitialized);
+
+        Char *dst = const_cast<Char *>(result.cbegin());
+        Char *ptr = dst;
+        forever {
+            while (src != end && isSpace(*src))
+                ++src;
+            while (src != end && !isSpace(*src))
+                *ptr++ = *src++;
+            if (src != end)
+                *ptr++ = QChar::Space;
+            else
+                break;
+        }
+        if (ptr != dst && ptr[-1] == QChar::Space)
+            --ptr;
+
+        int newlen = ptr - dst;
+        if (newlen == str.size()) {
+            // nothing happened, return the original
+            return str;
+        }
+        result.resize(ptr - dst);
+        return qMove(result);
+    }
+};
+
+QT_END_NAMESPACE
+
+#endif // QSTRINGALGORITHMS_P_H

src/corelib/tools/tools.pri

@@ -57,6 +57,7 @@ HEADERS +=  \
         tools/qsize.h \
         tools/qstack.h \
         tools/qstring.h \
+        tools/qstringalgorithms_p.h \
         tools/qstringbuilder.h \
         tools/qstringiterator_p.h \
         tools/qstringlist.h \

tests/auto/corelib/tools/qstring/tst_qstring.cpp

@@ -2073,8 +2073,6 @@ void tst_QString::simplified()
         QVERIFY2(result.isEmpty() && !result.isNull(), qPrintable("'" + full + "' did not yield empty: " + result));
     } else {
         QCOMPARE(result, simple);
-        if (full == simple)
-            QVERIFY(result.isSharedWith(full));
     }
 }