kanjiinfo.cxx

Displays the Japanese text

#include "KanjiInfo.h"
  
// Main symbol group, corresponds to JIS codes 0x2100
KanjiInfo::KANJI KanjiInfo::misc_unicode[] = {   
  #include "codepage/jwp_umis.dat"
};

KanjiInfo::KANJI KanjiInfo::ext_unicode[] = {   
  #include "codepage/jwp_uext.dat"
};

// Kanji unicode
KanjiInfo::KANJI KanjiInfo::kanji_unicode[] = {   
  #include "codepage/jwp_ukan.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1250[128] = {      // Eastern Europe code page  
  #include "codepage/jwp_cp1250.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1251[128] = {      // Cyrillic code page
  #include "codepage/jwp_cp1251.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1252[128] = {      // USA, West Europe code page
  #include "codepage/jwp_cp1252.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1253[128] = {      // Greek code page
  #include "codepage/jwp_cp1253.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1254[128] = {      // Turkish code page
  #include "codepage/jwp_cp1254.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1255[128] = {      // Hebrew code page
  #include "codepage/jwp_cp1255.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1256[128] = {      // Arabic code page
  #include "codepage/jwp_cp1256.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1257[128] = {      // Baltic code page
  #include "codepage/jwp_cp1257.dat"
};

KanjiInfo::KANJI KanjiInfo::cp1258[128] = {      // Vietnamese code page
  #include "codepage/jwp_cp1258.dat"
};

unsigned short KanjiInfo::countKanjiUnicode() {
	
	static unsigned short _kanji_unicode_count = 
		(sizeof(kanji_unicode)/sizeof(KANJI));

	return _kanji_unicode_count;

}

unsigned short KanjiInfo::countMiscUnicode() {
	
	static unsigned short _misc_unicode_count = 
		(sizeof(misc_unicode)/sizeof(KANJI));

	return _misc_unicode_count;

}

unsigned short KanjiInfo::countExtUnicode() {
	
	static unsigned short _ext_unicode_count = 
		(sizeof(ext_unicode)/sizeof(KANJI));

	return _ext_unicode_count;

}


unsigned short KanjiInfo::jis2sjis(unsigned short ch) {

	unsigned c1,c2;
	c1  = (ch >> 8);
	c2  = (ch & 0xff);
	c2 += (c1 % 2) ? ((c2 > 95) ? 32 : 31) : 126;    // jis code -> sjis code [jis2sjis() from jconv.c]
	c1  = ((c1+1) >> 1) + ((c1 < 95) ? 112 : 176);   // jis code -> sjis code [jis2sjis() from jconv.c]

	return ((c1 << 8) | (c2));
}

unsigned short KanjiInfo::jis2unicode (unsigned short ch) {
  if ((ch <= 0x7e)) return (ch);                    // ASCII
	if ((ch >= 0x0080) && (ch <= 0x00ff)) return (ext_unicode[ch-0x80]);  // Extended ASCII
	if ((ch >= 0x2330) && (ch <= 0x237a)) return (ch-0x2330+0xff10);      // Japanese ASCII
	if ((ch >= 0x2421) && (ch <= 0x2473)) return (ch-0x2421+0x3041);      // Hiragana
	if ((ch >= 0x2521) && (ch <= 0x2576)) return (ch-0x2521+0x30a1);      // Katakana
	if ((ch >= 0x2621) && (ch <= 0x2658)) return (ch-0x2621+0x0391);      // Greek
	if ((ch >= 0x2721) && (ch <= 0x2771)) return (ch-0x2721+0x0410);      // Cyrillic
	if ((ch >= 0x3021) && (ch <= 0x7426)) {                               // Kanji    
    ch -= 0x3021;
	  ch  = (ch >> 8)*94+(ch&0x00ff);
    return (kanji_unicode[ch]);
	}
	if ((ch >= 0x2121) && (ch <= 0x217e)) return (misc_unicode[ch-0x2121]);       // Main symbol group
	if ((ch >= 0x2221) && (ch <= 0x227f)) return (misc_unicode[ch-0x2221+94]);    // Secondary symbol group
		return 0;
	}

unsigned short KanjiInfo::sjis2jis (unsigned short ch) {
	unsigned short p1,p2;
	p1 = ch >> 8;
	p2 = ch & 0xff;
	sjis2jis (&p1,&p2);

	return ((p1 << 8) | p2);
}

unsigned short KanjiInfo::unicode2jis (unsigned short ch) {
  int i;
	if ((ch <= 0x007e)                  ) return (ch);                // ASCII
	if ((ch >= 0x3041) && (ch <= 0x3093)) return (ch-0x3041+0x2421);  // Hiragana
	if ((ch >= 0x30a1) && (ch <= 0x30f6)) return (ch-0x30a1+0x2521);  // Katakana
	if ((ch >= 0x0391) && (ch <= 0x03c9)) return (ch-0x0391+0x2621);  // Greek
	if ((ch >= 0x0410) && (ch <= 0x044f)) return (ch-0x0410+0x2721);  // Cyrillic
	for (i = 0; i < countKanjiUnicode(); i++) {                       // The kanji
		if (kanji_unicode[i] == ch) {
			ch = i/94;
			return (((ch+0x30) << 8) | (i-ch*94)+0x21);
		}
	}
	for (i = 0; i < countMiscUnicode(); i++) {
                        // Symbol and pucntuation (main group)
		if (misc_unicode[i] == ch) return ((i >= 94) ? 0x2221+i-94 : 0x2121+i);
	}
	for (i = 0; i < countExtUnicode(); i++) {
		// Extneded ascii codes.
    if (ext_unicode[i] == ch) return (i+0x80);
	}
	if ((ch >= 0xff10) && (ch <= 0xff5a)) return (ch-0xff10+0x2330);  // Japanese ASCII.
	return (0);           // The Japanese ASCII needs to be here because some puncutation is stored within gaps
}                       //   in the JASCII table, and if we move this before the misc codes they will not be found!    

void KanjiInfo::sjis2jis (unsigned short *p1,unsigned short *p2) {
  unsigned short c1 = *p1;
  unsigned short c2 = *p2;
  unsigned short adjust     = c2 < 159;
  unsigned short rowOffset  = (c1 < 160) ? 112 : 176;
  unsigned short cellOffset = adjust ? ((c2 > 127) ? 32 : 31) : 126;
  *p1  = ((c1 - rowOffset) << 1) - adjust;
  *p2 -= cellOffset;
}