qjpunicode.cpp

qt-embedded-2.3.8.tar.gz源码

/****************************************************************************
** $Id: qt/src/3rdparty/tools/qjpunicode.cpp   2.3.8   edited 2004-08-05 $
**
** Implementation of QJpUnicodeConv class
**
** Created : 990225
**
** 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.
**
**********************************************************************/

/*! \class QJpUnicodeConv qjpunicode.h

  \brief The QJpUnicodeConv class provides implementation support for
  QJisCodec, QSjisCodec, and QEucJpCodec.

  You should not need to use this class directly.  If you do, keep in
  mind that the function names will change in Qt 3.0: Every function
  name will get a lower-case first letter: Jisx0212ToUnicode becomes
  jisx0212ToUnicode, and so on.  We apologize for the upheaval.

  The environment variable \c UNICODEMAP_JP can be used to fine-tune how
  QJpUnicodeConv, QEucJpCodec, QJisCodec and QSjisCodec do their work.
  The mapping names are as for the Japanese XML working group's <a
  href="http://www.y-adagio.com/public/standards/tr_xml_jpf/toc.htm">
  XML Japanese Profile</a>, as it names and explains all the widely
  used mappings. Here are brief descriptions, written by Serika
  Kurusugawa: <ul>

  <li> "unicode-0.9" or "unicode-0201" for Unicode style. This assume
  JISX0201 for 0x00-0x7f. (0.9 is a table version of jisx02xx mapping
  used for Uniocde spec version 1.1)

  <li> "unicode-ascii" This assume US-ASCII for 0x00-0x7f, and some
  chars (JISX0208 0x2140 and JISX0212 0x2237) are different from
  Unicode 1.1 to avoid conflict.

  <li> "open-19970715-0201" ("open-0201" for convenience) or
  "jisx0221-1995" for JISX0221-JISX0201 style. JIS X 0221 is JIS
  version of Unicode, but a few chars (0x5c, 0x7e, 0x2140, 0x216f,
  0x2131) are different from Unicode 1.1. This is used when 0x5c is
  treated as YEN SIGN.

  <li> "open-19970715-ascii" ("open-ascii" for convenience) for
  JISX0221-ASCII style. This is used when 0x5c is treated as REVERSE
  SOLIDUS.

  <li> "open-19970715-ms" ("open-ms" for convenience) or "cp932" for
  Microsoft Windows style. Windows Code Page 932. Some chars (0x2140,
  0x2141, 0x2142, 0x215d, 0x2171, 0x2172) are different from Unicode
  1.1.

  <li> "jdk1.1.7" for Sun's JDK style Same as Unicode 1.1, except that
  JIS 0x2140 is mapped to UFF3C. Either ASCII or JISX0201 can be used
  for 0x00-0x7f.

  </ul> In addition, QJpUnicodeConv supports some extensions:
  "nec-vdc", "ibm-vdc" or "udc".

  For example, if you want to use Unicode style conversion, but with
  NEC's extension, set \c UNICODEMAP_JP to
  <nobr><code>unicode-0.9, nec-vdc</code>.</nobr> (You will probably
  need to quote that in the shell command.)

  Most of the code here was originally written by Serika Kurusugawa
  a.k.a. Junji Takagi, and is includes in Qt with the author's
  permission, and the grateful thanks of the Trolltech team. Here is
  the copyright statement for that code:

  \mustquote

  Copyright (c) 1999 Serika Kurusugawa, All rights reserved.

  Redistribution and use in source and binary forms, with or without
  modification, are permitted provided that the following conditions
  are met: <ol>
  <li> Redistributions of source code must retain the above copyright
     notice, this list of conditions and the following disclaimer.
  <li> 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.
  </ol>

  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.

*/

#include "qcstring.h"

#ifndef QT_NO_JPUNICODE

#include <stdlib.h>
#include <ctype.h>

#include "qjpunicode.h"

#define	USE_JISX0212

#define	STRICT

#define	IsLatin(c)	(/*((c) >= 0x00) &&*/ ((c) <= 0x7f))
#define	IsKana(c)	(((c) >= 0xa1) && ((c) <= 0xdf))
#define	IsJisChar(c)	(((c) >= 0x21) && ((c) <= 0x7e))
#define	IsSjisChar1(c)	((((c) >= 0x81) && ((c) <= 0x9f)) ||	\
			 (((c) >= 0xe0) && ((c) <= 0xfc)))
#define	IsSjisUDC1(c)	(((c) >= 0xf0) && ((c) <= 0xfc))
#define	IsSjisChar2(c)	(((c) >= 0x40) && ((c) != 0x7f) && ((c) <= 0xfc))

static uint Jisx0208ToSjis(uint h, uint l);
static
inline uint Jisx0208ToSjis(uint jis)
{
    return Jisx0208ToSjis((jis & 0xff00) >> 8, (jis & 0x00ff));
}

static uint SjisToJisx0208(uint h, uint l);
#if 0
static
inline uint SjisToJisx0208(uint sjis)
{
    return SjisToJisx0208((sjis & 0xff00) >> 8, (sjis & 0x00ff));
}
#endif
static uint Jisx0201ToUnicode11(uint h, uint l);
static uint Jisx0208ToUnicode11(uint h, uint l);
static uint Jisx0212ToUnicode11(uint h, uint l);

static uint Unicode11ToJisx0201(uint h, uint l);
static uint Unicode11ToJisx0208(uint h, uint l);
static uint Unicode11ToJisx0212(uint h, uint l);

/*
 * Unicode 1.1 conversion.
 */

/*!
  \fn QJpUnicodeConv::QJpUnicodeConv (int r)
  \internal
*/


/*! \internal */
uint QJpUnicodeConv::AsciiToUnicode(uint h, uint l) const
{
    if ((h == 0) && (l < 0x80)) {
	return l;
    }
    return 0x0000;
}

/*! \internal */
uint QJpUnicodeConv::Jisx0201ToUnicode(uint h, uint l) const
{
    if (h == 0) {
	if (IsLatin(l)) {
	    return Jisx0201LatinToUnicode(h, l);
	} else if (IsKana(l)) {
	    return Jisx0201KanaToUnicode(h, l);
	}
    }
    return 0x0000;
}

/*! \internal */
uint QJpUnicodeConv::Jisx0201LatinToUnicode(uint h, uint l) const
{
    if ((h == 0) && IsLatin(l)) {
	return Jisx0201ToUnicode11(h, l);
    }
    return 0x0000;
}

/*! \internal */
uint QJpUnicodeConv::Jisx0201KanaToUnicode(uint h, uint l) const
{
    if ((h == 0) && IsKana(l)) {
	return Jisx0201ToUnicode11(h, l);
    }
    return 0x0000;
}

/*! \internal */
uint QJpUnicodeConv::Jisx0208ToUnicode(uint h, uint l) const
{
    if (rule & JU_UDC){
	if ((0x75 <= h) && (h <= 0x7e) && IsJisChar(l)/*0x21 - 0x7e*/) {
	    // User Defined Char (mapped to Private Use Area)
	    return 0xe000 + (h - 0x75) * 0x5e + (l - 0x21);
	}
    }
    if ((rule & JU_NEC_VDC) == 0) {
	if ((h == 0x2d) && (IsJisChar(l)/*0x21 - 0x7c*/)) {
	    // NEC Vendor Defined Char
	    return 0x0000;
	}
    }
    return Jisx0208ToUnicode11(h, l);
}

/*! \internal */
uint QJpUnicodeConv::Jisx0212ToUnicode(uint h, uint l) const
{
    if (rule & JU_UDC){
	if ((0x75 <= h) && (h <= 0x7e) && IsJisChar(l)/*0x21 - 0x7e*/) {
	    // User Defined Char (mapped to Private Use Area)
	    return 0xe3ac + (h - 0x75) * 0x5e + (l - 0x21);
	}
    }
    if ((rule & JU_IBM_VDC) == 0){
	if (((h == 0x73) && (0x73 <= l) && (l <= 0x7e)) ||
	    ((h == 0x74) && (IsJisChar(l)/*0x21 - 0x7e*/))) {
	    // IBM Vendor Defined Char
	    return 0x0000;
	}
    }
    return Jisx0212ToUnicode11(h, l);
}

/*! \internal */
uint QJpUnicodeConv::UnicodeToAscii(uint h, uint l) const
{
    if ((h == 0) && (l < 0x80)) {
	return l;
    }
    return 0x0000;
}

/*! \internal */
uint QJpUnicodeConv::UnicodeToJisx0201(uint h, uint l) const
{
    uint jis;
    if ((jis = UnicodeToJisx0201Latin(h, l)) != 0) {
	return jis;
    } else if ((jis = UnicodeToJisx0201Kana(h, l)) != 0) {
	return jis;
    }
    return 0x0000;
}

/*! \internal */
uint QJpUnicodeConv::UnicodeToJisx0201Latin(uint h, uint l) const
{
    uint jis = Unicode11ToJisx0201(h, l);
    if (IsLatin(jis)) {
	return jis;
    }
    return 0x0000;
}

/*! \internal */
uint QJpUnicodeConv::UnicodeToJisx0201Kana(uint h, uint l) const
{
    uint jis = Unicode11ToJisx0201(h, l);
    if (IsKana(jis)) {
	return jis;
    }
    return 0x0000;
}

/*! \internal */
uint QJpUnicodeConv::UnicodeToJisx0208(uint h, uint l) const
{
    if (rule & JU_UDC){
	uint unicode = (h << 8) | l;
	if ((0xe000 <= unicode) && (unicode <= 0xe3ab)) {
	    // User Defined Char (mapped to Private Use Area)
	    unicode -= 0xe000;
	    return ((0x75 + unicode / 0x5e ) << 8) | (0x21 + unicode % 0x5e);
	}
    }
    uint jis = Unicode11ToJisx0208(h, l);
    if ((rule & JU_NEC_VDC) == 0) {
	if ((0x2d21 <= jis) && (jis <= 0x2d7c)) {
	    // NEC Vendor Defined Char
	    return 0x0000;
	}
    }
    return jis;
}

/*! \internal */
uint QJpUnicodeConv::UnicodeToJisx0212(uint h, uint l) const
{
    if (rule & JU_UDC){