Added QStringRef::toLatin1 and QStringRef::toUtf8

These helper functions make it convenient to avoid making an unnecessary
copy of the string before converting it to a QByteArray. The current
most obvious way to do this would be:

  // QStringRef text
  QByteArray latin1 = text.toString().toLatin1();

Though the copy can also be avoided by doing:

  const QString textData =
      QString::fromRawData(text.unicode(), text.size());
  QByteArray latin1 = textData.toLatin1();

Now the faster method can be achieved using the new obvious way:

  QByteArray latin1 = text.toLatin1();

Reviewed-by: Thiago Macieira
Reviewed-by: Robin Burchell
(cherry picked from commit feabda665de62a0f6a82d831b45926697f30b45b)

2 files changed, 43 insertions, 0 deletions

diff --git a/src/corelib/tools/qstring.cpp b/src/corelib/tools/qstring.cpp
index 5493ba915b..75695558ba 100644
--- a/src/corelib/tools/qstring.cpp
+++ b/src/corelib/tools/qstring.cpp
@@ -8014,6 +8014,47 @@ QString QStringRef::toString() const {
     return QString(m_string->unicode() + m_position, m_size);
 }
 
+/*!
+    Returns a Latin-1 representation of the string reference as a QByteArray.
+
+    The returned byte array is undefined if the string reference contains
+    non-Latin1 characters. Those characters may be suppressed or replaced with a
+    question mark.
+
+    \sa QString::toLatin1(), toUtf8()
+    \since 4.8
+*/
+QByteArray QStringRef::toLatin1() const
+{
+    if (!m_string)
+        return QByteArray();
+    return toLatin1_helper(m_string->unicode() + m_position, m_size);
+}
+
+/*!
+    Returns a UTF-8 representation of the string reference as a QByteArray.
+
+    UTF-8 is a Unicode codec and can represent all characters in a Unicode
+    string like QString.
+
+    However, in the Unicode range, there are certain codepoints that are not
+    considered characters. The Unicode standard reserves the last two
+    codepoints in each Unicode Plane (U+FFFE, U+FFFF, U+1FFFE, U+1FFFF,
+    U+2FFFE, etc.), as well as 16 codepoints in the range U+FDD0..U+FDDF,
+    inclusive, as non-characters. If any of those appear in the string, they
+    may be discarded and will not appear in the UTF-8 representation, or they
+    may be replaced by one or more replacement characters.
+
+    \sa QString::toUtf8(), toLatin1(), QTextCodec
+    \since 4.8
+*/
+QByteArray QStringRef::toUtf8() const
+{
+    if (isNull())
+        return QByteArray();
+    return QUtf8::convertFromUnicode(m_string->unicode() + m_position, m_size, 0);
+}
+
 
 /*! \relates QStringRef
 
diff --git a/src/corelib/tools/qstring.h b/src/corelib/tools/qstring.h
index 66cfa744df..2b3026cd31 100644
--- a/src/corelib/tools/qstring.h
+++ b/src/corelib/tools/qstring.h
@@ -1167,6 +1167,8 @@ public:
 
     inline void clear() { m_string = 0; m_position = m_size = 0; }
     QString toString() const;
+    QByteArray toLatin1() const;
+    QByteArray toUtf8() const;
     inline bool isEmpty() const { return m_size == 0; }
     inline bool isNull() const { return m_string == 0 || m_string->isNull(); }