diff options
Diffstat (limited to 'src/corelib/codecs/qsjiscodec.cpp')
| -rw-r--r-- | src/corelib/codecs/qsjiscodec.cpp | 229 |
1 files changed, 229 insertions, 0 deletions
diff --git a/src/corelib/codecs/qsjiscodec.cpp b/src/corelib/codecs/qsjiscodec.cpp new file mode 100644 index 0000000000..ac89b333c4 --- /dev/null +++ b/src/corelib/codecs/qsjiscodec.cpp @@ -0,0 +1,229 @@ +/**************************************************************************** +** +** Copyright (C) 2012 Nokia Corporation and/or its subsidiary(-ies). +** All rights reserved. +** Contact: Nokia Corporation (qt-info@nokia.com) +** +** This file is part of the plugins of the Qt Toolkit. +** +** $QT_BEGIN_LICENSE:LGPL$ +** GNU Lesser General Public License Usage +** 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, Nokia gives you certain additional +** rights. These rights are described in the Nokia 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. +** +** Other Usage +** Alternatively, this file may be used in accordance with the terms and +** conditions contained in a signed written agreement between you and Nokia. +** +** +** +** +** +** $QT_END_LICENSE$ +** +****************************************************************************/ + +// Most of the code here was originally written by Serika Kurusugawa +// a.k.a. Junji Takagi, and is included in Qt with the author's permission, +// and the grateful thanks of the Qt team. + +/*! \class QSjisCodec + \reentrant + \internal +*/ + +#include "qsjiscodec.h" +#include "qlist.h" + +QT_BEGIN_NAMESPACE + +#ifndef QT_NO_TEXTCODEC +enum { + Esc = 0x1b +}; + +#define IsKana(c) (((c) >= 0xa1) && ((c) <= 0xdf)) +#define IsSjisChar1(c) ((((c) >= 0x81) && ((c) <= 0x9f)) || \ + (((c) >= 0xe0) && ((c) <= 0xfc))) +#define IsSjisChar2(c) (((c) >= 0x40) && ((c) != 0x7f) && ((c) <= 0xfc)) +#define IsUserDefinedChar1(c) (((c) >= 0xf0) && ((c) <= 0xfc)) + +#define QValidChar(u) ((u) ? QChar((ushort)(u)) : QChar(QChar::ReplacementCharacter)) + +/*! + Creates a Shift-JIS codec. Note that this is done automatically by + the QApplication, you do not need construct your own. +*/ +QSjisCodec::QSjisCodec() : conv(QJpUnicodeConv::newConverter(QJpUnicodeConv::Default)) +{ +} + + +/*! + Destroys the Shift-JIS codec. +*/ +QSjisCodec::~QSjisCodec() +{ + delete (QJpUnicodeConv*)conv; + conv = 0; +} + + +QByteArray QSjisCodec::convertFromUnicode(const QChar *uc, int len, ConverterState *state) const +{ + char replacement = '?'; + if (state) { + if (state->flags & ConvertInvalidToNull) + replacement = 0; + } + int invalid = 0; + + int rlen = 2*len + 1; + QByteArray rstr; + rstr.resize(rlen); + uchar* cursor = (uchar*)rstr.data(); + for (int i = 0; i < len; i++) { + QChar ch = uc[i]; + uint j; + if (ch.row() == 0x00 && ch.cell() < 0x80) { + // ASCII + *cursor++ = ch.cell(); + } else if ((j = conv->unicodeToJisx0201(ch.row(), ch.cell())) != 0) { + // JIS X 0201 Latin or JIS X 0201 Kana + *cursor++ = j; + } else if ((j = conv->unicodeToSjis(ch.row(), ch.cell())) != 0) { + // JIS X 0208 + *cursor++ = (j >> 8); + *cursor++ = (j & 0xff); + } else if ((j = conv->unicodeToSjisibmvdc(ch.row(), ch.cell())) != 0) { + // JIS X 0208 IBM VDC + *cursor++ = (j >> 8); + *cursor++ = (j & 0xff); + } else if ((j = conv->unicodeToCp932(ch.row(), ch.cell())) != 0) { + // CP932 (for lead bytes 87, ee & ed) + *cursor++ = (j >> 8); + *cursor++ = (j & 0xff); + } else if ((j = conv->unicodeToJisx0212(ch.row(), ch.cell())) != 0) { + // JIS X 0212 (can't be encoded in ShiftJIS !) + *cursor++ = 0x81; // white square + *cursor++ = 0xa0; // white square + } else { + // Error + *cursor++ = replacement; + ++invalid; + } + } + rstr.resize(cursor - (const uchar*)rstr.constData()); + + if (state) { + state->invalidChars += invalid; + } + return rstr; +} + +QString QSjisCodec::convertToUnicode(const char* chars, int len, ConverterState *state) const +{ + uchar buf[1] = {0}; + int nbuf = 0; + QChar replacement = QChar::ReplacementCharacter; + if (state) { + if (state->flags & ConvertInvalidToNull) + replacement = QChar::Null; + nbuf = state->remainingChars; + buf[0] = state->state_data[0]; + } + int invalid = 0; + uint u= 0; + QString result; + for (int i=0; i<len; i++) { + uchar ch = chars[i]; + switch (nbuf) { + case 0: + if (ch < 0x80) { + result += QValidChar(ch); + } else if (IsKana(ch)) { + // JIS X 0201 Latin or JIS X 0201 Kana + u = conv->jisx0201ToUnicode(ch); + result += QValidChar(u); + } else if (IsSjisChar1(ch)) { + // JIS X 0208 + buf[0] = ch; + nbuf = 1; + } else { + // Invalid + result += replacement; + ++invalid; + } + break; + case 1: + // JIS X 0208 + if (IsSjisChar2(ch)) { + if ((u = conv->sjisibmvdcToUnicode(buf[0], ch))) { + result += QValidChar(u); + } else if ((u = conv->cp932ToUnicode(buf[0], ch))) { + result += QValidChar(u); + } + else if (IsUserDefinedChar1(buf[0])) { + result += QChar::ReplacementCharacter; + } else { + u = conv->sjisToUnicode(buf[0], ch); + result += QValidChar(u); + } + } else { + // Invalid + result += replacement; + ++invalid; + } + nbuf = 0; + break; + } + } + + if (state) { + state->remainingChars = nbuf; + state->state_data[0] = buf[0]; + state->invalidChars += invalid; + } + return result; +} + + +int QSjisCodec::_mibEnum() +{ + return 17; +} + +QByteArray QSjisCodec::_name() +{ + return "Shift_JIS"; +} + +/*! + Returns the codec's mime name. +*/ +QList<QByteArray> QSjisCodec::_aliases() +{ + QList<QByteArray> list; + list << "SJIS" // Qt 3 compat + << "MS_Kanji"; + return list; +} +#endif // QT_NO_TEXTCODEC + +QT_END_NAMESPACE |