/**************************************************************************** ** $Id: qeuckrcodec.cpp 2 2005-11-16 15:49:26Z dmik $ ** ** Implementation of QEucKrCodec class ** ** Created : 990225 ** ** Copyright (C) 2000-2002 Trolltech AS. All rights reserved. ** ** This file is part of the tools module of the Qt GUI Toolkit. ** ** This file may be distributed under the terms of the Q Public License ** as defined by Trolltech AS of Norway and appearing in the file ** LICENSE.QPL included in the packaging of this file. ** ** This file may be distributed and/or modified under the terms of the ** GNU General Public License version 2 as published by the Free Software ** Foundation and appearing in the file LICENSE.GPL included in the ** packaging of this file. ** ** Licensees holding valid Qt Enterprise Edition or Qt Professional Edition ** licenses may use this file in accordance with the Qt Commercial License ** Agreement provided with the Software. ** ** This file is provided AS IS with NO WARRANTY OF ANY KIND, INCLUDING THE ** WARRANTY OF DESIGN, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. ** ** See http://www.trolltech.com/pricing.html or email sales@trolltech.com for ** information about Qt Commercial License Agreements. ** See http://www.trolltech.com/qpl/ for QPL licensing information. ** See http://www.trolltech.com/gpl/ for GPL licensing information. ** ** Contact info@trolltech.com if any conditions of this licensing are ** not clear to you. ** **********************************************************************/ /*! \class QEucKrCodec qeuckrcodec.h \reentrant \ingroup i18n \brief The QEucKrCodec class provides conversion to and from EUC-KR character sets. The QEucKrCodec class subclasses QTextCodec to provide support for EUC-KR, the main legacy encoding for UNIX machines in Korea. It was largely written by Mizi Research Inc. Here is the copyright statement for the code as it was at the point of contribution. Trolltech's subsequent modifications are covered by the usual copyright for Qt. \legalese Copyright (C) 1999-2000 Mizi Research Inc. All rights reserved. Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
  1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
  2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ /* these must be made \internal virtual int mibEnum() const; const char* name() const; QTextDecoder* makeDecoder() const; QCString fromUnicode(const QString& uc, int& lenInOut) const; QString toUnicode(const char* chars, int len) const; int heuristicContentMatch(const char* chars, int len) const; int heuristicNameMatch(const char* hint) const; */ #include "qeuckrcodec.h" #ifndef QT_NO_BIG_CODECS unsigned int qt_Ksc5601ToUnicode(unsigned int code); unsigned int qt_UnicodeToKsc5601(unsigned int unicode); #define IsEucChar(c) (((c) >= 0xa1) && ((c) <= 0xfe)) #define QValidChar(u) ((u) ? QChar((ushort)(u)) : QChar::replacement) /*! \reimp */ int QEucKrCodec::mibEnum() const { /* * Name: EUC-KR (preferred MIME name) [RFC1557,Choi] * MIBenum: 38 * Source: RFC-1557 (see also KS_C_5861-1992) * Alias: csEUCKR */ /* mibEnum for other codeset related with Korean. KS_C_5601-1987 36, ISO2022-KRi 37 */ return 38; } /*! \reimp */ QCString QEucKrCodec::fromUnicode(const QString& uc, int& lenInOut) const { int l = QMIN((int)uc.length(),lenInOut); int rlen = l*3+1; QCString rstr(rlen); uchar* cursor = (uchar*)rstr.data(); for (int i=0; i> 8) | 0x80; *cursor++ = (j & 0xff) | 0x80; } else { // Error *cursor++ = '?'; // unknown char } } lenInOut = cursor - (uchar*)rstr.data(); rstr.truncate(lenInOut); return rstr; } /*! \reimp */ QString QEucKrCodec::toUnicode(const char* chars, int len) const { QString result; for (int i=0; i> 8; int ch2 = code & 0x00ff; int idx; if (ch1 < 0x80 || (ch1 - 0x80) <= 0x20 || (ch1 - 0x80) >= 0x7e || (ch1 - 0x80) == 0x49) return 0; if (ch2 < 0x80 || (ch2 - 0x80) <= 0x20 || (ch2 - 0x80) >= 0x7f) return 0; idx = (ch1 - 0x80 - 0x21) * 94 + (ch2 - 0x80 - 0x21); /* Hangul : row 16 - row 40 : 1410 = 15 * 94 , 3760 = 40 * 94 */ if (idx >= 1410 && idx < 1410 + 2350) return (ksc5601_hangul_to_unicode[idx - 1410]); else if (idx >= 3854) /* Hanja : row 42 - row 93 : 3854 = 94 * (42-1) */ return (ksc5601_hanja_to_unicode[idx - 3854]); else if(idx <= 1114) return (ksc5601_symbol_to_unicode[idx]); return 0; } static unsigned short unicode2ksc(unsigned short unicode) { int lo, hi, mid, c2; unsigned char s[2]; lo = mid = c2 = 0; if (unicode >= 0xac00 && unicode <= 0xd7a3) { // Hangul hi = 2349; while (lo <= hi) { // binary search mid = (lo + hi) / 2; c2 = ksc5601_hangul_to_unicode[mid]; if(unicode < c2) hi = mid - 1; else if(unicode > c2) lo = mid + 1; else { // unicode == c2 s[0] = (mid / 94) + 0x30; s[1] = (mid % 94) + 0x21; return ( (s[0] << 8) | s[1] ); } } } else if ((unicode >= 0x4e00 && unicode <= 0x9fff) || (unicode >= 0xf900 && unicode <= 0xfa0b)) { // Hanja hi = 4887; while (lo <= hi) { // binary search mid = (lo + hi) / 2; c2 = unicode_to_ksc5601_hanja[mid].unicode; if(unicode < c2) hi = mid - 1; else if(unicode > c2) lo = mid + 1; else { // unicode == c2 return unicode_to_ksc5601_hanja[mid].kscode; } } } else { // Symbol hi = 985; while (lo <= hi) { // binary search mid = (lo + hi) / 2; c2 = unicode_to_ksc5601_symbol[mid].unicode; if(unicode < c2) hi = mid - 1; else if(unicode > c2) lo = mid + 1; else { // unicode == c2 return unicode_to_ksc5601_symbol[mid].kscode; } } } return 0; } #endif