qbig5codec.cpp

qt-embedded-2.3.8.tar.gz源码

/****************************************************************************
** $Id: qt/src/3rdparty/tools/qbig5codec.cpp   2.3.8   edited 2004-08-05 $
**
** Implementation of QBig5Codec class
**
** Created : 990713
**
** Copyright (C) 1992-2000 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 [e-mail] 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 [e-mail] if any conditions of this licensing are
** not clear to you.
**
**********************************************************************/

// Most of the code here was originally written by Ming-Che Chuang and
// is included in Qt with the author's permission, and the grateful
// thanks of the Trolltech team.

// (Note: Ming-Che's code is also QPL'd, ref mail to [e-mail])

#include "qbig5codec.h"

#ifndef QT_NO_BIG5CODEC

unsigned int qt_UnicodeToBig5(unsigned int unicode);
static unsigned int qt_Big5ToUnicode(unsigned int code);
static bool big5ucs(unsigned char *s,unsigned char *t);
static bool ucsbig5(unsigned char *s,unsigned char *t);

#define IsBig5Char(c)	(((c) >= 0x81) && ((c) <= 0xfe))
#define	QValidChar(u)	((u) ? QChar((ushort)(u)) : QChar::replacement)


int QBig5Codec::mibEnum() const
{
  return 2026;
}


QCString QBig5Codec::fromUnicode(const QString& uc, int& len_in_out) const
{
  int l = QMIN((int)uc.length(),len_in_out);
  int rlen = l*3+1;
  QCString rstr(rlen);
  uchar* cursor = (uchar*)rstr.data();
  for (int i=0; i<l; i++) {
    QChar ch = uc[i];
    uint j;
    if ( ch.row() == 0x00 && ch.cell() < 0x80 ) {
      // ASCII
      *cursor++ = ch.cell();
    } else if ((j = qt_UnicodeToBig5((ch.row() << 8) | ch.cell())) ) {
      //Big5 1984
      *cursor++ = (j >> 8);
      *cursor++ = (j & 0xff);
    } else if ( ch.unicode() == 0xa0 ) {
	*cursor++ = ' ';
    } else {
      // Error
      *cursor++ = '?';	// unknown char
    }
  }
  len_in_out = cursor - (uchar*)rstr.data();
  rstr.truncate(len_in_out);
  return rstr;
}

QString QBig5Codec::toUnicode(const char* chars, int len) const
{
  QString result;
  for (int i=0; i<len; i++) {
    uchar ch = chars[i];
    if ( ch < 0x80 ) {
      // ASCII
      result += QChar(ch);
    } else if ( IsBig5Char(ch) ) {
      // Big5 1984
      if ( i < len-1 ) {
	uchar c2 = chars[++i];
	if ( (c2 >=0x40) && (c2 <=0xfe) ) {
	  uint u = qt_Big5ToUnicode((ch << 8) | c2);
	  result += QValidChar(u);
	} else {
	  i--;
	  result += QChar::replacement;
	}
      } else {
	result += QChar::replacement;
      }
    } else {
      // Invalid
      result += QChar::replacement;
    }
  }
  return result;
}

const char* QBig5Codec::name() const
{
  return "Big5";
}

int QBig5Codec::heuristicNameMatch(const char* hint) const
{
  if (qstrnicmp(hint, "Big5", 4) == 0 ) return 4;
  else if (qstrnicmp(hint, "zh_TW.Big5", 10) == 0) return 10;
  else  return QTextCodec::heuristicNameMatch(hint);
}

int QBig5Codec::heuristicContentMatch(const char* chars, int len) const
{
  int score = 0;
  for (int i=0; i<len; i++) {
    uchar ch = chars[i];
    // No nulls allowed.
    if ( !ch )
      return -1;
    if ( ch < 32 && ch != '\t' && ch != '\n' && ch != '\r' ) {
      // Suspicious
      if ( score )
	score--;
    } else if ( ch < 0x80 ) {
      // Inconclusive
      score++;
    } else if ( IsBig5Char(ch) ) {
      // Big5 1984
      if ( i < len-1 ) {
	uchar c2 = chars[++i];
	if ( !((c2 >=0x40) &&  (c2<=0xfe) ))
	  return -1;
	score+=2;
      }
      score++;
    } else {
      // Invalid
      return -1;
    }
  }
  return score;
}

unsigned int qt_UnicodeToBig5(unsigned int unicode)
{
  unsigned char source[2],target[2];
  source[0]=(unicode>>8);
  source[1]=(unicode & 0xff);
  ucsbig5(source,target);
  return ( (target[0]<<8) | target[1]);

}

static unsigned int qt_Big5ToUnicode(unsigned int code)
{
  unsigned char source[2],target[2];
  source[0]=(code >> 8);
  source[1]=(code & 0xff);
  big5ucs(source,target);
  return ((target[0]<<8) | target[1]);

}

class QBig5Decoder : public QTextDecoder {
  uchar buf[2];
  int nbuf;
public:
  QBig5Decoder() : nbuf(0)
  {
  }

  QString toUnicode(const char* chars, int len)
  {
    QString result;
    for (int i=0; i<len; i++) {
      uchar ch = chars[i];
      switch (nbuf) {