qtextcodec.cpp

奇趣公司比较新的qt/emd版本

  \link http://www.iana.org/assignments/character-sets
  IANA character-sets encoding file\endlink.
*/
QList<QByteArray> QTextCodec::aliases() const
{
    return QList<QByteArray>();
}

/*!
    \fn QString QTextCodec::convertToUnicode(const char *chars, int len,
                                             ConverterState *state) const

    QTextCodec subclasses must reimplement this function.

    Converts the first \a len characters of \a chars from the
    encoding of the subclass to Unicode, and returns the result in a
    QString.

    \a state can be 0, in which case the conversion is stateless and
    default conversion rules should be used. If state is not 0, the
    codec should save the state after the conversion in \a state, and
    adjust the remainingChars and invalidChars members of the struct.
*/

/*!
    \fn QByteArray QTextCodec::convertFromUnicode(const QChar *input, int number,
                                                  ConverterState *state) const

    QTextCodec subclasses must reimplement this function.

    Converts the first \a number of characters from the \a input array
    from Unicode to the encoding of the subclass, and returns the result
    in a QByteArray.

    \a state can be 0 in which case the conversion is stateless and
    default conversion rules should be used. If state is not 0, the
    codec should save the state after the conversion in \a state, and
    adjust the remainingChars and invalidChars members of the struct.
*/

/*!
    Creates a QTextDecoder which stores enough state to decode chunks
    of \c{char *} data to create chunks of Unicode data.

    The caller is responsible for deleting the returned object.
*/
QTextDecoder* QTextCodec::makeDecoder() const
{
    return new QTextDecoder(this);
}


/*!
    Creates a QTextEncoder which stores enough state to encode chunks
    of Unicode data as \c{char *} data.

    The caller is responsible for deleting the returned object.
*/
QTextEncoder* QTextCodec::makeEncoder() const
{
    return new QTextEncoder(this);
}

/*!
    \fn QByteArray QTextCodec::fromUnicode(const QChar *input, int number,
                                           ConverterState *state) const

    Converts the first \a number of characters from the \a input array
    from Unicode to the encoding of this codec, and returns the result
    in a QByteArray.

    The \a state of the convertor used is updated.
*/

/*!
    Converts \a str from Unicode to the encoding of this codec, and
    returns the result in a QByteArray.
*/
QByteArray QTextCodec::fromUnicode(const QString& str) const
{
    return convertFromUnicode(str.constData(), str.length(), 0);
}

/*!
    \fn QString QTextCodec::toUnicode(const char *input, int size,
                                      ConverterState *state) const

    Converts the first \a size characters from the \a input from the
    encoding of this codec to Unicode, and returns the result in a
    QString.

    The \a state of the convertor used is updated.
*/

/*!
    Converts \a a from the encoding of this codec to Unicode, and
    returns the result in a QString.
*/
QString QTextCodec::toUnicode(const QByteArray& a) const
{
    return convertToUnicode(a.constData(), a.length(), 0);
}

/*!
    Returns true if the Unicode character \a ch can be fully encoded
    with this codec; otherwise returns false.
*/
bool QTextCodec::canEncode(QChar ch) const
{
    ConverterState state;
    state.flags = ConvertInvalidToNull;
    convertFromUnicode(&ch, 1, &state);
    return (state.invalidChars == 0);
}

/*!
    \overload

    \a s contains the string being tested for encode-ability.
*/
bool QTextCodec::canEncode(const QString& s) const
{
    ConverterState state;
    state.flags = ConvertInvalidToNull;
    convertFromUnicode(s.constData(), s.length(), &state);
    return (state.invalidChars == 0);
}

#ifdef QT3_SUPPORT
/*!
    Returns a string representing the current language and
    sublanguage, e.g. "pt" for Portuguese, or "pt_br" for Portuguese/Brazil.

    \sa QLocale
*/
const char *QTextCodec::locale()
{
    static char locale[6];
    QByteArray l = QLocale::system().name().toLatin1();
    int len = qMin(l.length(), 5);
    memcpy(locale, l.constData(), len);
    locale[len] = '\0';

    return locale;
}

/*!
    \overload
*/

QByteArray QTextCodec::fromUnicode(const QString& uc, int& lenInOut) const
{
    QByteArray result = convertFromUnicode(uc.constData(), lenInOut, 0);
    lenInOut = result.length();
    return result;
}

/*!
    \overload

    \a a contains the source characters; \a len contains the number of
    characters in \a a to use.
*/
QString QTextCodec::toUnicode(const QByteArray& a, int len) const
{
    len = qMin(a.size(), len);
    return convertToUnicode(a.constData(), len, 0);
}
#endif

/*!
    \overload

    \a chars contains the source characters.
*/
QString QTextCodec::toUnicode(const char *chars) const
{
    int len = qstrlen(chars);
    return convertToUnicode(chars, len, 0);
}


/*!
    \class QTextEncoder
    \brief The QTextEncoder class provides a state-based encoder.
    \reentrant
    \ingroup i18n

    A text encoder converts text from Unicode into an encoded text format
    using a specific codec.

    The encoder converts Unicode into another format, remembering any
    state that is required between calls.

    \sa QTextCodec::makeEncoder(), QTextDecoder
*/

/*!
    \fn QTextEncoder::QTextEncoder(const QTextCodec *codec)

    Constructs a text encoder for the given \a codec.
*/

/*!
    Destroys the encoder.
*/
QTextEncoder::~QTextEncoder()
{
}

/*!
    Converts the Unicode string \a str into an encoded QByteArray.
*/
QByteArray QTextEncoder::fromUnicode(const QString& str)
{
    QByteArray result = c->fromUnicode(str.constData(), str.length(), &state);
    return result;
}

/*!
    \overload

    Converts \a len characters (not bytes) from \a uc, and returns the
    result in a QByteArray.
*/
QByteArray QTextEncoder::fromUnicode(const QChar *uc, int len)
{
    QByteArray result = c->fromUnicode(uc, len, &state);
    return result;
}

#ifdef QT3_SUPPORT
/*!
  \overload

  Converts \a lenInOut characters (not bytes) from \a uc, and returns the
  result in a QByteArray. The number of characters read is returned in
  the \a lenInOut parameter.
*/
QByteArray QTextEncoder::fromUnicode(const QString& uc, int& lenInOut)
{
    QByteArray result = c->fromUnicode(uc.constData(), lenInOut, &state);
    lenInOut = result.length();
    return result;
}
#endif

/*!
    \class QTextDecoder
    \brief The QTextDecoder class provides a state-based decoder.
    \reentrant
    \ingroup i18n

    A text decoder converts text from an encoded text format into Unicode
    using a specific codec.

    The decoder converts text in this format into Unicode, remembering any
    state that is required between calls.

    \sa QTextCodec::makeDecoder(), QTextEncoder
*/

/*!
    \fn QTextDecoder::QTextDecoder(const QTextCodec *codec)

    Constructs a text decoder for the given \a codec.
*/

/*!
    Destroys the decoder.
*/
QTextDecoder::~QTextDecoder()
{
}

/*!
    \fn QString QTextDecoder::toUnicode(const char *chars, int len)

    Converts the first \a len bytes in \a chars to Unicode, returning
    the result.

    If not all characters are used (e.g. if only part of a multi-byte
    encoding is at the end of the characters), the decoder remembers
    enough state to continue with the next call to this function.
*/
QString QTextDecoder::toUnicode(const char *chars, int len)
{
    return c->toUnicode(chars, len, &state);
}


/*! \overload

    The converted string is returned in \a target.
 */
void QTextDecoder::toUnicode(QString *target, const char *chars, int len)
{
    Q_ASSERT(target);
    switch (c->mibEnum()) {
    case 106: // utf8
        static_cast<const QUtf8Codec*>(c)->convertToUnicode(target, chars, len, &state);
        break;
    case 4: { // latin1
        target->resize(len);
        ushort *data = (ushort*)target->data();
        for (int i = len; i >=0; --i)
            data[i] = (uchar) chars[i];
    } break;
    default:
        *target = c->toUnicode(chars, len, &state);
    }
}


/*!
    \overload

    Converts the bytes in the byte array specified by \a ba to Unicode
    and returns the result.
*/
QString QTextDecoder::toUnicode(const QByteArray &ba)
{
    return c->toUnicode(ba.constData(), ba.length(), &state);
}


/*!
    \fn QTextCodec* QTextCodec::codecForTr()

    Returns the codec used by QObject::tr() on its argument. If this
    function returns 0 (the default), tr() assumes Latin-1.

    \sa setCodecForTr()
*/

/*!
    \fn void QTextCodec::setCodecForTr(QTextCodec *c)
    \nonreentrant

    Sets the codec used by QObject::tr() on its argument to \a c. If
    \a c is 0 (the default), tr() assumes Latin-1.

    If the literal quoted text in the program is not in the Latin-1
    encoding, this function can be used to set the appropriate
    encoding. For example, software developed by Korean programmers
    might use eucKR for all the text in the program, in which case the
    main() function might look like this:

    \code
        int main(int argc, char *argv[])
        {
            QApplication app(argc, argv);
            QTextCodec::setCodecForTr(QTextCodec::codecForName("eucKR"));
            ...
        }
    \endcode

    Note that this is not the way to select the encoding that the \e
    user has chosen. For example, to convert an application containing
    literal English strings to Korean, all that is needed is for the
    English strings to be passed through tr() and for translation
    files to be loaded. For details of internationalization, see
    \l{Internationalization with Qt}.

    \sa codecForTr(), setCodecForCStrings()
*/


/*!
    \fn QTextCodec* QTextCodec::codecForCStrings()

    Returns the codec used by QString to convert to and from \c{const
    char *} and QByteArrays. If this function returns 0 (the default),
    QString assumes Latin-1.

    \sa setCodecForCStrings()
*/

/*!
    \fn void QTextCodec::setCodecForCStrings(QTextCodec *codec)
    \nonreentrant

    Sets the codec used by QString to convert to and from \c{const
    char *} and QByteArrays. If the \a codec is 0 (the default),
    QString assumes Latin-1.

    \warning Some codecs do not preserve the characters in the ASCII
    range (0x00 to 0x7F). For example, the Japanese Shift-JIS
    encoding maps the backslash character (0x5A) to the Yen
    character. To avoid undesirable side-effects, we recommend
    avoiding such codecs with setCodecsForCString().

    \sa codecForCStrings(), setCodecForTr()
*/

/*!
  \internal
*/
QTextCodec *QTextCodec::codecForHtml(const QByteArray &ba)
{
    // determine charset
    int mib = 4; // Latin-1
    int pos;
    QTextCodec *c = 0;

    if (ba.size() > 1 && (((uchar)ba[0] == 0xfe && (uchar)ba[1] == 0xff)
                          || ((uchar)ba[0] == 0xff && (uchar)ba[1] == 0xfe))) {
        mib = 1015; // utf16
    } else if (ba.size() > 2
             && (uchar)ba[0] == 0xef
             && (uchar)ba[1] == 0xbb
             && (uchar)ba[2] == 0xbf) {
        mib = 106; // utf-8
    } else {
        QByteArray header = ba.left(512).toLower();
        if ((pos = header.indexOf("http-equiv=")) != -1) {
            pos = header.indexOf("charset=", pos) + int(strlen("charset="));
            if (pos != -1) {
                int pos2 = header.indexOf('\"', pos+1);
                QByteArray cs = header.mid(pos, pos2-pos);
                //            qDebug("found charset: %s", cs.data());
                c = QTextCodec::codecForName(cs);
            }
        }
    }
    if (!c)
        c = QTextCodec::codecForMib(mib);

    return c;
}

/*! \internal
    \since 4.3
    Determines whether the decoder encountered a failure while decoding the input. If
    an error was encountered, the produced result is undefined, and gets converted as according
    to the conversion flags.
 */
bool QTextDecoder::hasFailure() const
{
    return state.invalidChars != 0;
}

/*!
    \fn QTextCodec *QTextCodec::codecForContent(const char *str, int size)

    This functionality is no longer provided by Qt. This
    compatibility function always returns a null pointer.
*/

/*!
    \fn QTextCodec *QTextCodec::codecForName(const char *hint, int accuracy)

    Use the codecForName(const QByteArray &) overload instead.
*/

/*!
    \fn QTextCodec *QTextCodec::codecForIndex(int i)

    Use availableCodecs() or availableMibs() instead and iterate
    through the resulting list.
*/


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

    Use name() instead.
*/

#endif // QT_NO_TEXTCODEC