syntax.js

在网页上输入维文字符实例.

      } else {
	 if ( prev < 128 ) {
	    if (next < 128 ) {
	       return String.fromCharCode ( prev, next ) ;
	    } else {
	       idx2 = getIndex ( next ) ;
	       if ( beg_form[idx2] != 0 ) {
		  code2 = getUniCode ( beg_form[idx2] ) ;
	       } else {
		  code2 = next ;
	       }
	       return String.fromCharCode ( prev, code2 ) ;
	    }
	 } else if ( next < 128 || next==getUniCode(U_COMMA) || next==getUniCode(U_QUESTION) ) {
	    idx = getIndex ( prev ) ;
	    if ( end_form[idx] != 0 ) {
	        code = getUniCode ( end_form[idx] ) ;
	    } else {
	       code = prev ;
	    }
	    return String.fromCharCode ( code, next ) ;
	 }

	 idx = getIndex ( prev ) ;
	 idx2 = getIndex ( next ) ;
	 code = prev ;

         str2 = joint_special ( idx, idx2 ) ;
         if ( str2 != "" ) {
            return str2 ;
         }

	 if ( beg_tab[idx] == WD_BEG ) {
	    if ( beg_form[idx2] != 0 ) {
	       code2 = getUniCode ( beg_form[idx2] ) ;
	    } else {
	       code2 = next ;
	    }
	 } else if ( beg_tab[idx] == IN_BEG ) {
	    if ( in_beg_form[idx2] != 0 ) {
	       code2 = getUniCode ( in_beg_form[idx2] ) ;
	    } else {
	       code2 = next ;
	    }
	 } else {
	    if ( med_form[idx] != 0 ) {
	       code = getUniCode( med_form[idx] ) ;
	    } else {
	       code = prev ;
	    }

	    if ( rev_med_form[idx2] != 0 ) {
	       code2 = getUniCode ( rev_med_form[idx2] ) ;
	    } else {
	       code2 = next ;
	    }
	 }
      }
      return String.fromCharCode ( code, code2 ) ;
   }

   // a regular input key is pressed (non-backspace, non-delete)
   if ( prev == -1 ) {  // nothing in front, inserting text at the beginning of text
      if ( next == -1 ) {  // and nothing in back, the first character
	 idx1 = map_index ( cur, -1 ) ;
	 code = getUniCode ( idx1 ) ;
	 if ( end_form[idx1] != 0 ) {
	    code = getUniCode ( end_form[idx1] ) ;
	 }
         str = String.fromCharCode ( code ) ;
      } else { // inserting at the beginning of the text 
	 if ( next < 128 || next==getUniCode(U_COMMA) || next==getUniCode(U_QUESTION) ) {
	    str = getContextString ( -1, cur, -1 ) + String.fromCharCode(next) ;
	    return str ;
         }

	 idx1 = map_index ( cur, prev ) ;
         idx2 = getIndex ( next ) ;  // next charcode index
	 code1 = getUniCode ( idx1 ) ;

         if ( is_alien ( idx1 ) || is_wd_beginner(idx1) ) {
	    if ( beg_form[idx2] != 0 ) {
	       code2 = getUniCode ( beg_form[idx2] ) ;
	    } else {
	       code2 = next ; 
	    }
         } else if ( is_in_beginner ( idx1 ) ) {
	    if ( in_beg_form[idx2] != 0 ) {
	       code2 = getUniCode ( in_beg_form[idx2] ) ;
	    } else {
	       code2 = next ; 
	    }
	 } else {
            str2 = joint_special ( idx1, idx2 ) ;
            if ( str2 != "" ) {
               return str2 ;
            }

	    if ( rev_med_form[idx2] != 0 ) { // update the next letter if necessary
	       code2 = getUniCode ( rev_med_form[idx2] ) ;
	    } else {
	       code2 = next ;
	    }
         }

	 str = String.fromCharCode ( code1, code2 ) ; 
      }
   } else if ( next == -1 ) { // inserting text at the end of the text 

      if ( prev < 128 ) {
	 str = String.fromCharCode(prev) + getContextString ( -1, cur, -1 ) ;
	 return str ;
      }

      idx = getIndex ( prev ) ;
      code = getUniCode ( map_index ( cur, idx ) ) ; // ucode for cur

      idx1 = getIndex ( code ) ;  // current code index

      str2 = joint_special ( idx, idx1 ) ;
      if ( str2 != "" ) {
         return str2 ;
      }

      if ( is_alien (idx1) == true ) { // if cur is not regular char
	 if ( end_form[ idx ] != 0 ) { // check for end form
	    code1 = getUniCode ( end_form[idx] ) ;

	    str = String.fromCharCode ( code1, getUniCode(idx1) ) ;
	 } else {
	    str = String.fromCharCode ( prev, code ) ;
	 }
      } else {
	 if ( med_form[idx] != 0 ) {  // see if to use medial form
	    code1 = getUniCode ( med_form[idx] ) ;
	 } else {
	    code1 = prev ;
	 }

	 if ( end_form[idx1] != 0 ) {
	    code = getUniCode ( end_form[idx1] ) ;
	 }

         str = String.fromCharCode ( code1, code ) ;
      }
   } else { // inserting a letter in the middle of the text
      idx = getIndex ( prev ) ;  // previous charcode index
      code = getUniCode ( map_index ( cur, idx ) ) ; // ucode for cur

      idx1 = getIndex ( code ) ;  // current code index
      idx2 = getIndex ( next ) ;  // next charcode index

      /*
      if ( next == String("\r").charCodeAt(0) ) {
	 str = getContextString ( prev, cur, -1 ) + String.fromCharCode(next) ;
	 return str ;
      }
      */

      if ( next < 128 || next==getUniCode(U_COMMA) || next==getUniCode(U_QUESTION) ) {
	 if ( prev < 128 ) {
	    str=String.fromCharCode(prev)+getContextString(-1,cur,-1)+String.fromCharCode(next);
	 } else {
	    str= getContextString(prev,cur, -1) + String.fromCharCode(next) ;
	 }
	 return str ;
      }

      if ( is_alien ( idx1 ) ) {
	 if ( end_form[ idx ] != 0 ) { // check for end form
	    code1 = getUniCode ( end_form[idx] ) ;

	    str1 = String.fromCharCode ( code1, getUniCode(idx1) ) ;
	 } else {
	    str1 = String.fromCharCode ( prev, code ) ;
	 }

	 if ( beg_form[idx2] != 0 ) {
	    str2 = String.fromCharCode ( getUniCode ( beg_form[idx2] ) ) ;
	 } else {
	    str2 = String.fromCharCode(next) ; 
	 }
	 
	 str = str1.concat ( str2 ) ;
      } else if ( is_wd_beginner ( idx1 ) ) {
	 if ( beg_form[idx2] != 0 ) {
	    str2 = String.fromCharCode ( getUniCode ( beg_form[idx2] ) ) ;
	 } else {
	    str2 = String.fromCharCode(next) ; 
	 }


         str1 = joint_special ( idx, idx1 ) ;
         if ( str1 != "" ) {
	    return str1.concat ( str2 ) ;
         }

	 if ( med_form[idx] != 0 ) {  // see if to use medial form
	    code1 = getUniCode ( med_form[idx] ) ;
	 } else {
	    code1 = prev ;
	 }

	 str1 = String.fromCharCode ( code1, code ) ; 

	 str = str1.concat ( str2 ) ;
      } else if ( is_in_beginner(idx1) ) {
	 if ( in_beg_form[idx2] != 0 ) {
	    str2 = String.fromCharCode ( getUniCode ( in_beg_form[idx2] ) ) ;
	 } else {
	    str2 = String.fromCharCode ( next ) ;
	 }

         str1 = joint_special ( idx, idx1 ) ;
         if ( str1 != "" ) {
	    return str1.concat ( str2 ) ;
         }

	 if ( med_form[idx] != 0 ) {  // see if to use medial form
	    code1 = getUniCode ( med_form[idx] ) ;
	 } else {
	    code1 = prev ;
	 }

	 str1 = String.fromCharCode ( code1, code ) ; 

	 str = str1.concat ( str2 ) ;
      } else {
	 if ( med_form[idx] != 0 ) {  // see if to use medial form
	    code1 = getUniCode ( med_form[idx] ) ;
	 } else {
	    code1 = prev ;
	 }

         str2 = joint_special ( idx1, idx2 ) ;
         if ( str2 != "" ) {
	    str1 = String.fromCharCode ( code1 ) ;
	    return str1.concat ( str2 ) ;
         }

	 if ( rev_med_form[idx2] != 0 ) { // update the next letter if necessary
	    code2 = getUniCode ( rev_med_form[idx2] ) ;
	 } else {
	    code2 = getUniCode ( idx2 ) ;
	 }

	 str = String.fromCharCode ( code1, code, code2 ) ; 
      }
   }

   return str ;
};

/*
 * joint_special ( idx1, idx2 ) -- return a single character string if idx1 and
 *  idx2 forms a special joint letter such as LA, _LA, __AA, etc.
 */
function joint_special ( idx1, idx2 ) {
   var i = -1 ;

   if ( idx1 == LEE || idx1 == LEE_ ) { // for LA
      if ( idx2 == AA || idx2 == _AA || idx2 == _AA_ || idx2 == __AA ) {
         i = LA ;
      }
   } else if ( idx1 == _LEE || idx1 == _LEE_ ) { // for _LA
      if ( idx2 == AA || idx2 == _AA || idx2 == _AA_ || idx2 == __AA ) {
         i = _LA ;
      }
   } else if ( idx1 == I_ ) { // for I_ + _AA = AA, _I_ + _AA = __AA, etc.
      if ( idx2 == AA || idx2 == _AA || idx2 == _AA_ ) {
         i = AA ;
      } else if ( idx2 == AE || idx2 == _AE || idx2 == _AE_ ) {
         i = AE ;
      } else if ( idx2 == OO || idx2 == _OO || idx2 == S_OO ) {
         i = OO ;
      } else if ( idx2 == OE || idx2 == _OE || idx2 == S_OE ) {
         i = OE ;
      } else if ( idx2 == UU || idx2 == _UU || idx2 == S_UU ) {
         i = UU ;
      } else if ( idx2 == UE || idx2 == _UE || idx2 == S_UE ) {
         i = UE ;
      } else if ( idx2 == DSH ) {
         //i = II ;
      } else if ( idx2 == _E_ ) {
         //i = EE ;
      }
   } else if ( idx1 == _I_ ) {
      if ( idx2 == AA || idx2 == _AA || idx2 == _AA_ ) {
         i = __AA ;
      } else if ( idx2 == AE || idx2 == _AE || idx2 == _AE_ ) {
         i = __AE ;
      } else if ( idx2 == OO || idx2 == _OO || idx2 == S_OO ) {
         i = __OO ;
      } else if ( idx2 == OE || idx2 == _OE || idx2 == S_OE ) {
         i = __OE ;
      } else if ( idx2 == UU || idx2 == _UU || idx2 == S_UU ) {
         i = __UU ;
      } else if ( idx2 == UE || idx2 == _UE || idx2 == S_UE ) {
         i = __UE ;
      } else if ( idx2 == DSH ) {
         //i = _II ;
      } else if ( idx2 == _E_ ) {
         //i = _EE ;
      }
   }

   if ( i != -1 ) {
      return String.fromCharCode ( getUniCode ( i ) ) ;
   }

   return "" ;
}

function is_alien ( code ) 
{
   if ( code == SPACE || code == DOT || code == EXCLAMATION || code == U_QUESTION ||
	 code == U_SEMICOLON || code == U_COMMA || code == MINUS || code == ONE ||
	 code == TWO || code == THREE || code == FOUR || code == FIVE ||
         code == SIX || code == SEVEN || code == EIGHT || code == NINE ||
         code == ZERO || code == ASTERISC || code == PERCENT || code == DOLLAR ||
         code == POUND || code == AT || code == WEDGE || code == AND ||
         code == LPAREN || code == RPAREN || code == PLUS || code == EQUAL ||
         code == TILDE || code == UNDERSCORE || code == COLON || code == LFEED ||
         code == DQUOTE || code == SQUOTE || code == RBRACK || code == LBRACK ||
         code == LBRACE || code == RBRACE || code == LTHAN || code == GTHAN ||
         code == FSLASH || code == PIPE || code == PRIM ) {
      return true ;
   } 

   return false ;
};

/*
 * is_wd_beginner ( idx ) -- returns true if idx represents an Uyghur character that
 * mandates the next character be in the beginning form.
 */
function is_wd_beginner ( idx ) // should next character be in beginning form
{
   if ( idx == AA || idx == _AA_ || idx == _AA || idx == __AA ||
	 idx == AE || idx == _AE_ || idx == _AE || idx == __AE ||
         idx == LA || idx == _LA ) {
      return true ;
   }

   return false ;
};

/*
 * is_wd_beginner ( idx ) -- returns true if idx represents an Uyghur character that
 * mandates the next character be in the in-word beginning form.
 */
function is_in_beginner ( idx )//should next character be in in-word beginning form
{
   return beg_tab[idx] == IN_BEG ;
};


function getUniCode ( charCode ) 
{
   var ucode ;

   ucode = char_code[charCode] ;

   return ucode ;
};

/*
 * getIndex ( uniChar ) -- reverse lookup the index from code_char table
 */
function getIndex ( uniChar )
{
   var i ;

   for ( i = AA ; i <= LFEED ; i++ ) {
      if ( char_code[i] == uniChar ) {
	 return i ;
      } 
   }
};

/*
 * map_index ( input, prev ) -- returns the index for input according to the previous character
 */
function map_index ( input, prev )
{
   var wd_beg, in_beg ;

   var str = String.fromCharCode ( input ) ;
   cur = str.charAt(0) ; 

   wd_beg = beg_tab [prev] ;

   if ( wd_beg != WD_BEG ) {
      in_beg = beg_tab[prev] ;
   }

   if ( wd_beg == WD_BEG || prev == -1 ) {
      switch ( cur )
      {
         case 'a' :
            return EHE_ ;
         case 'A' :
            return EHE_ ;
         case 'b' :
         case 'B' :
            return BEE_ ;
         case 'c' :
         case 'C' :
            return GHEE_ ;
         case 'd' :
            return DEE ;
         case 'D' :
            return SZEE ;
         case 'e' :
            return EE_ ;
         case 'E' :
            return EE_ ;
         case 'f' :
            return AA ;
         case 'F' :
            return FEE_ ;
         case 'g' :
            return AE ;
         case 'G' :
            return GEE_ ;
         case 'h' :
            return II_ ;
         case 'H' :
            return HEE_ ;
         case 'i' :
         case 'I' :
            return NGEE_ ;
         case 'j' :
            return QEE_ ;
         case 'J' :
            return JEE_ ;
         case 'k' :
            return KEE_ ;
         case 'K' :
            return OE ;
         case 'l' :
            return LEE_ ;
         case 'L' :
            return LA ;
         case 'm' :
         case 'M' :
            return MEE_ ;
         case 'n' :
         case 'N' :
            return NEE_ ;
         case 'o' :
         case 'O' : // capital 'Oh'
            return OO ;
         case 'p' : 
         case 'P' : 
            return PEE_ ;
         case 'q' :
         case 'Q' :
            return CHEE_ ;
         case 'r' :
         case 'R' :
            return REE ;
         case 's' :
         case 'S' :
            return SEE_ ;
         case 't' :
            return TEE_ ;
         case 'u' :
         case 'U' :
            return UU ;
         case 'v' :
         case 'V' :
            return UE ;
         case 'w' :
         case 'W' :
            return VEE ;
         case 'x' :
         case 'X' :
            return SHEE_ ;