qtextcodec.cpp

奇趣公司比较新的qt/emd版本

                localeMapper = ru_RU_hack(lang);
        }

        delete [] ctype;
        delete [] lang;
    }

    // If everything failed, we default to 8859-1
    // We could perhaps default to 8859-15.
    if (!localeMapper)
        localeMapper = QTextCodec::codecForName("ISO 8859-1");
#endif
}


static void setup()
{
#ifndef QT_NO_THREAD
    QMutexLocker locker(QMutexPool::globalInstanceGet(&all));
#endif

    if (all)
        return;

    if (destroying_is_ok)
        qWarning("QTextCodec: Creating new codec during codec cleanup");
    all = new QList<QTextCodec*>;
    // create the cleanup object to cleanup all codecs on exit
    (void) createQTextCodecCleanup();

#ifndef QT_NO_CODECS
#  if defined(Q_WS_X11) && !defined(QT_BOOTSTRAPPED)
    // no font codecs when bootstrapping
    (void)new QFontLaoCodec;
#    if defined(QT_NO_ICONV)
    // no iconv(3) support, must build all codecs into the library
    (void)new QFontGb2312Codec;
    (void)new QFontGbkCodec;
    (void)new QFontGb18030_0Codec;
    (void)new QFontJis0208Codec;
    (void)new QFontJis0201Codec;
    (void)new QFontKsc5601Codec;
    (void)new QFontBig5hkscsCodec;
    (void)new QFontBig5Codec;
#    endif // QT_NO_ICONV && !QT_BOOTSTRAPPED
#  endif // Q_WS_X11

    (void)new QTsciiCodec;

    for (int i = 0; i < 9; ++i)
        (void)new QIsciiCodec(i);

    for (int i = 0; i < QSimpleTextCodec::numSimpleCodecs; ++i)
        (void)new QSimpleTextCodec(i);

#  if defined(QT_NO_ICONV) && !defined(QT_BOOTSTRAPPED)
    // no asian codecs when bootstrapping, sorry
    (void)new QGb18030Codec;
    (void)new QGbkCodec;
    (void)new QGb2312Codec;
    (void)new QEucJpCodec;
    (void)new QJisCodec;
    (void)new QSjisCodec;
    (void)new QEucKrCodec;
    (void)new QBig5Codec;
    (void)new QBig5hkscsCodec;
#  endif // QT_NO_ICONV && !QT_BOOTSTRAPPED
#endif // QT_NO_CODECS

#ifdef Q_OS_WIN32
    (void) new QWindowsLocalCodec;
#endif // Q_OS_WIN32

    (void)new QUtf16Codec;
    (void)new QUtf16BECodec;
    (void)new QUtf16LECodec;
    (void)new QLatin15Codec;
    (void)new QLatin1Codec;
    (void)new QUtf8Codec;

#if defined(Q_OS_UNIX) && !defined(QT_NO_ICONV) && !defined(QT_BOOTSTRAPPED)
    // QIconvCodec depends on the UTF-16 codec, so it needs to be created last
    (void) new QIconvCodec();
#endif

    if (!localeMapper)
        setupLocaleMapper();
}



/*!
    \class QTextCodec
    \brief The QTextCodec class provides conversions between text encodings.
    \reentrant
    \ingroup i18n

    Qt uses Unicode to store, draw and manipulate strings. In many
    situations you may wish to deal with data that uses a different
    encoding. For example, most Japanese documents are still stored
    in Shift-JIS or ISO 2022-JP, while Russian users often have their
    documents in KOI8-R or Windows-1251.

    Qt provides a set of QTextCodec classes to help with converting
    non-Unicode formats to and from Unicode. You can also create your
    own codec classes.

    The supported encodings are:

    \list
    \o Apple Roman
    \o \l{Big5 Text Codec}{Big5}
    \o \l{Big5-HKSCS Text Codec}{Big5-HKSCS}
    \o \l{EUC-JP Text Codec}{EUC-JP}
    \o \l{EUC-KR Text Codec}{EUC-KR}
    \o \l{GBK Text Codec}{GB18030-0}
    \o IBM 850
    \o IBM 866
    \o IBM 874
    \o \l{ISO 2022-JP (JIS) Text Codec}{ISO 2022-JP}
    \o ISO 8859-1 to 10
    \o ISO 8859-13 to 16
    \o Iscii-Bng, Dev, Gjr, Knd, Mlm, Ori, Pnj, Tlg, and Tml
    \o JIS X 0201
    \o JIS X 0208
    \o KOI8-R
    \o KOI8-U
    \o MuleLao-1
    \o ROMAN8
    \o \l{Shift-JIS Text Codec}{Shift-JIS}
    \o TIS-620
    \o \l{TSCII Text Codec}{TSCII}
    \o UTF-8
    \o UTF-16
    \o UTF-16BE
    \o UTF-16LE
    \o Windows-1250 to 1258
    \o WINSAMI2
    \endlist

    QTextCodecs can be used as follows to convert some locally encoded
    string to Unicode. Suppose you have some string encoded in Russian
    KOI8-R encoding, and want to convert it to Unicode. The simple way
    to do it is like this:

    \code
        QByteArray encodedString = "...";
        QTextCodec *codec = QTextCodec::codecForName("KOI8-R");
        QString string = codec->toUnicode(encodedString);
    \endcode

    After this, \c string holds the text converted to Unicode.
    Converting a string from Unicode to the local encoding is just as
    easy:

    \code
        QString string = "...";
        QTextCodec *codec = QTextCodec::codecForName("KOI8-R");
        QByteArray encodedString = codec->fromUnicode(string);
    \endcode

    To read or write files in various encodings, use QTextStream and
    its \l{QTextStream::setCodec()}{setCodec()} function. See the
    \l{tools/codecs}{Codecs} example for an application of QTextCodec
    to file I/O.

    Some care must be taken when trying to convert the data in chunks,
    for example, when receiving it over a network. In such cases it is
    possible that a multi-byte character will be split over two
    chunks. At best this might result in the loss of a character and
    at worst cause the entire conversion to fail.

    The approach to use in these situations is to create a QTextDecoder
    object for the codec and use this QTextDecoder for the whole
    decoding process, as shown below:

    \code
        QTextCodec *codec = QTextCodec::codecForName("Shift-JIS");
        QTextDecoder *decoder = codec->makeDecoder();

        QString string;
        while (new_data_available()) {
            QByteArray chunk = get_new_data();
            string += decoder->toUnicode(chunk);
        }
    \endcode

    The QTextDecoder object maintains state between chunks and therefore
    works correctly even if a multi-byte character is split between
    chunks.

    \section1 Creating Your Own Codec Class

    Support for new text encodings can be added to Qt by creating
    QTextCodec subclasses.

    The pure virtual functions describe the encoder to the system and
    the coder is used as required in the different text file formats
    supported by QTextStream, and under X11, for the locale-specific
    character input and output.

    To add support for another encoding to Qt, make a subclass of
    QTextCodec and implement the functions listed in the table below.

    \table
    \header \o Function \o Description

    \row \o name()
         \o Returns the official name for the encoding. If the
            ncoding is listed in the
            \l{http://www.iana.org/assignments/character-sets}{IANA
            character-sets encoding file}, the name should be the
            preferred MIME name for the encoding.

    \row \o aliases()
         \o Returns a list of alternative names for the encoding.
            QTextCodec provides a default implementation that returns
            an empty list. For example, "ISO-8859-1" has "latin1",
	    "CP819", "IBM819", and "iso-ir-100" as aliases.

    \row \o mibEnum()
         \o Return the MIB enum for the encoding if it is listed in
            the \l{http://www.iana.org/assignments/character-sets}{IANA
            character-sets encoding file}.

    \row \o convertToUnicode()
         \o Converts an 8-bit character string to Unicode.

    \row \o convertFromUnicode()
         \o Converts a Unicode string to an 8-bit character string.
    \endtable

    You may find it more convenient to make your codec class
    available as a plugin; see \l{How to Create Qt Plugins} for
    details.

    \sa QTextStream, QTextDecoder, QTextEncoder, {Codecs Example}
*/

/*!
    \enum QTextCodec::ConversionFlag

    \value DefaultConversion  No flag is set.
    \value ConvertInvalidToNull  If this flag is set, invalid input results in
           an empty string.
    \value IgnoreHeader  Ignore any Unicode byte-order mark and don't generate any.
*/

/*!
    \fn QTextCodec::ConverterState::ConverterState(ConversionFlags flags)

    Constructs a ConverterState object initialized with the given \a flags.
*/

/*!
    \fn QTextCodec::ConverterState::~ConverterState()

    Destroys the ConverterState object.
*/

/*!
    \nonreentrant

    Constructs a QTextCodec, and gives it the highest precedence. The
    QTextCodec should always be constructed on the heap (i.e. with \c
    new). Qt takes ownership and will delete it when the application
    terminates.
*/
QTextCodec::QTextCodec()
{
    setup();
    all->prepend(this);
}


/*!
    \nonreentrant

    Destroys the QTextCodec. Note that you should not delete codecs
    yourself: once created they become Qt's responsibility.
*/
QTextCodec::~QTextCodec()
{
    if (!destroying_is_ok)
        qWarning("QTextCodec::~QTextCodec: Called by application");
    if (all)
        all->removeAll(this);
}

/*!
    \fn QTextCodec *QTextCodec::codecForName(const char *name)

    Searches all installed QTextCodec objects and returns the one
    which best matches \a name; the match is case-insensitive. Returns
    0 if no codec matching the name \a name could be found.
*/

/*!
    Searches all installed QTextCodec objects and returns the one
    which best matches \a name; the match is case-insensitive. Returns
    0 if no codec matching the name \a name could be found.
*/
QTextCodec *QTextCodec::codecForName(const QByteArray &name)
{
    if (name.isEmpty())
        return 0;

    setup();

    for (int i = 0; i < all->size(); ++i) {
        QTextCodec *cursor = all->at(i);
        if (nameMatch(cursor->name(), name))
            return cursor;
        QList<QByteArray> aliases = cursor->aliases();
        for (int i = 0; i < aliases.size(); ++i)
            if (nameMatch(aliases.at(i), name))
                return cursor;
    }

    return createForName(name);
}


/*!
    Returns the QTextCodec which matches the \link
    QTextCodec::mibEnum() MIBenum\endlink \a mib.
*/
QTextCodec* QTextCodec::codecForMib(int mib)
{
    setup();

    // Qt 3 used 1000 (mib for UCS2) as it's identifier for the utf16 codec. Map
    // this correctly for compatibility.
    if (mib == 1000)
        mib = 1015;

    QList<QTextCodec*>::ConstIterator i;
    for (int i = 0; i < all->size(); ++i) {
        QTextCodec *cursor = all->at(i);
        if (cursor->mibEnum() == mib)
            return cursor;
    }

    return createForMib(mib);
}

/*!
    Returns the list of all available codecs, by name. Call
    QTextCodec::codecForName() to obtain the QTextCodec for the name.

    The list may contain many mentions of the same codec
    if the codec has aliases.

    \sa availableMibs(), name(), aliases()
*/
QList<QByteArray> QTextCodec::availableCodecs()
{
    setup();

    QList<QByteArray> codecs;
    for (int i = 0; i < all->size(); ++i) {
        codecs += all->at(i)->name();
        codecs += all->at(i)->aliases();
    }
#ifndef QT_NO_TEXTCODECPLUGIN
    QFactoryLoader *l = loader();
    QStringList keys = l->keys();
    for (int i = 0; i < keys.size(); ++i) {
        if (!keys.at(i).startsWith(QLatin1String("MIB: "))) {
            QByteArray name = keys.at(i).toLatin1();
            if (!codecs.contains(name))
                codecs += name;
        }
    }
#endif

    return codecs;
}

/*!
    Returns the list of MIBs for all available codecs. Call
    QTextCodec::codecForMib() to obtain the QTextCodec for the MIB.

    \sa availableCodecs(), mibEnum()
*/
QList<int> QTextCodec::availableMibs()
{
    setup();

    QList<int> codecs;
    for (int i = 0; i < all->size(); ++i)
        codecs += all->at(i)->mibEnum();
#ifndef QT_NO_TEXTCODECPLUGIN
    QFactoryLoader *l = loader();
    QStringList keys = l->keys();
    for (int i = 0; i < keys.size(); ++i) {
        if (keys.at(i).startsWith(QLatin1String("MIB: "))) {
            int mib = keys.at(i).mid(5).toInt();
            if (!codecs.contains(mib))
                codecs += mib;
        }
    }
#endif

    return codecs;
}

/*!
    Set the codec to \a c; this will be returned by codecForLocale().
    This might be needed for some applications that want to use their
    own mechanism for setting the locale.

    Setting this codec is not supported on DOS based Windows.

    \sa codecForLocale()
*/
void QTextCodec::setCodecForLocale(QTextCodec *c)
{
#ifdef Q_WS_WIN
    if (QSysInfo::WindowsVersion& QSysInfo::WV_DOS_based)
	return;
#endif
    localeMapper = c;
}

/*!
    Returns a pointer to the codec most suitable for this locale.

    On Windows, the codec will be based on a system locale. On Unix
    systems, starting with Qt 4.2, the codec will be using the \e
    iconv library. Note that in both cases the codec's name will be
    "System".
*/

QTextCodec* QTextCodec::codecForLocale()
{
    if (localeMapper)
        return localeMapper;

    setup();

    return localeMapper;
}


/*!
    \fn QByteArray QTextCodec::name() const

    QTextCodec subclasses must reimplement this function. It returns
    the name of the encoding supported by the subclass.

    If the codec is registered as a character set in the
    \link http://www.iana.org/assignments/character-sets
    IANA character-sets encoding file\endlink this method should return
    the preferred mime name for the codec if defined, otherwise its name.
*/

/*!
    \fn int QTextCodec::mibEnum() const

    Subclasses of QTextCodec must reimplement this function. It
    returns the MIBenum (see \link
    http://www.iana.org/assignments/character-sets the
    IANA character-sets encoding file\endlink for more information).
    It is important that each QTextCodec subclass returns the correct
    unique value for this function.
*/

/*!
  Subclasses can return a number of aliases for the codec in question.

  Standard aliases for codecs can be found in the