<html>
<head>Richa से यूनिकोड फ़ोण्ट परिवर्तित्र (28-04-2008 14:35) </title>
Last update: 10-08-2008 15:56

<script type="text/javascript">

function convert_to_unicode()
{

var array_one = new Array( 


//"Œ","","Ž","","","‘","’","“","”","•", //

"~ ",".k",

"˜","™","š","›","§",

// "¶",   "d",    "[k",  "x",  "T",  "t",   "M+", "<+", "Q",  ";",    "j",   "u", // One byte nuqtas
"M+", "<+",
"Ùk", "Ù", "ä", "–", "Ñ", "å", "ò","ó","ô","õ","ý","þ",  

"à", "Ð",  "á",    "â",   "ã",   "gª",  "º",   "í", "{k", "{", "=",  "«",   
"Nî",   "Vî",    "Bî",   "Mî",   "<î", "|", "K", "}","ð", ")",
"J",   "Vª",   "Mª",  "<ªª",  "Nª",   "Ø",  "Ý",   "æ", "ç", "Á", "xz", "#", ":",

"vkW","vks", "vkS", "vk", "v", "b±", "Ã",  "bZ", "b", "m", "Å", ",s", ",", "_",

"Ç","È","Ê","Í","Î","Ï",


"ô",  "d", "Dk", "D", "[k", "[", "x","Xk", "X", "Ä", "?k", "?",   "³", 
"p", "Pk", "P", "N", "t", "Tk", "T", ">", "Ö", "´", "×",

"ê",  "ë",   "V",  "B",   "ì",   "ï", "M+", "<+", "M",  "<", "Æ", ".",    
"r",  "Rk", "R",   "Fk", "F",  ")", "n", "/k", "èk",  "/", "Ë", "è", "u", "Uk", "U",   

"i",  "Ik", "I",   "Q",    "¶",  "c", "Ck",  "C",  "Hk",  "H", "e", "Ek",  "E",
";",  "¸",   "j",    "y", "Yk",  "Y",  "G",  "o", "Ok", "O",
"'k", "'",   "\"k",  "\"",  "l", "Lk",  "L",   "g", 

"z", 
"Ì", "Í", "Î",  "Ï",  "Ò",  "Ó",  "Ô",   "Ö",  "Ø",  "Ù", "Ü",

"ö","—","®","kW", "ks", "kS", "k",  "h", "q", "w", "`","ÿ", "¤", "s", "S","¨","©",
"a", "¡", "%", "W",  "•", "~j",  "~", "\\","+",
"^", "*",  "Þ", "ß", "(", "¼", "½", "¿", "À", "¾", "A", "-", "&", "&", "Œ", "]","ाैं",
"ñ","«","¬", "¹","º","»","¼","½","¾","¿","À",
" ः","ंु")

var array_two = new Array( 
//"०",  "१",  "२",  "३",  "४",   "५",  "६",   "७",   "८", "९",  //
"् ", "Æ", 
"×","✔","ड्क","ड्ग","्न",
// "फ़्",  "क़",  "ख़",  "ग़", "ज़्", "ज़",  "ड़",  "ढ़",   "फ़",  "य़",  "ऱ",  "ऩ",    // one-byte nukta varNas
"ड़",  "ढ़",
"त्त", "त्त्", "क्त",  "दृ",  "कृ", "द्ग","स्र","स्त्र","क्क","श्च","श्व","ढ्ढ",

"ह्व","ह्न",  "ह्य",  "हृ",  "ह्म",  "ह्र",  "ह्",   "द्द",  "क्ष", "क्ष्", "त्र", "त्र्", 
"छ्य",  "ट्य",  "ठ्य",  "ड्य",  "ढ्य", "द्य", "ज्ञ", "द्व","द्घ", "द्ध",
"श्र",  "ट्र",    "ड्र",   "ढ्र",    "छ्र",   "क्र",  "फ्र",  "द्र",   "प्र", "प्र",  "ग्र", "रु",  "रू",

"ऑ",  "ओ",  "औ",  "आ",   "अ", "ईं", "ई",  "ई",   "इ",  "उ",   "ऊ",  "ऐ",  "ए", "ऋ",
"ॠ","ऌ","ऍ","आँ","ओ","औ",

"क्क", "क", "क", "क्", "ख", "ख्", "ग", "ग", "ग्", "घ", "घ", "घ्", "ङ",
"च", "च", "च्", "छ", "ज", "ज", "ज्", "झ", "झ्", "ञ", "ञ्",

"ट्ट",   "ट्ठ",   "ट",   "ठ",   "ड्ड",   "ड्ढ",  "ड़", "ढ़", "ड",   "ढ", "ण", "ण्",   
"त", "त", "त्", "थ", "थ्",  "द्ध",  "द", "ध", "ध", "ध्", "ध्", "ध्", "न", "न", "न्",    

"प", "प", "प्",  "फ", "फ्",  "ब", "ब", "ब्",  "भ", "भ्",  "म",  "म", "म्",  
"य", "य्",  "र", "ल", "ल", "ल्",  "ळ",  "व", "व", "व्",   
"श", "श्",  "ष", "ष्", "स", "स", "स्", "ह", 

"्र",    
"द्द", "ट्ट","ट्ठ","ड्ड","भ","्य","ड्ढ","झ्","क्र","त्त्","श्",

"ीं","ें","ैं","ॉ",  "ो",   "ौ",   "ा",   "ी",   "ु",   "ू",   "ृ", "ृ","ॄ",  "े",   "ै", "े","ौ",
"ं",   "ँ",   "ः",   "ॅ",  "ऽ", "्र",  "्", "?", "़",
"‘",   "’",   "“",   "”",  ";",  "(",    ")",   "{",    "}",   "=", "।", ".", "-",  "µ", "॰", ",", "ौं",
"॰","॥","ॐ","*","ह्","÷","(",")","=","{","}",
":","ुं" )

// The following two characters are to be replaced through proper checking of locations:
// "Z" )
// "र्" (reph) 

// "f" )
// "ि"  


var array_one_length = array_one.length ;

if (  (document.getElementById("text_or_html")).selectedIndex == 0 )  // if the input is plain text
{ 
    document.getElementById("unicode_text").value = "You have chosen SIMPLE TEXT in Richa to convert into Unicode."  ;  

    var modified_substring = document.getElementById("legacy_text").value  ;

//****************************************************************************************
//  Break the long text into small bunches of max. max_text_size  characters each.
//****************************************************************************************
    var text_size = document.getElementById("legacy_text").value.length ;

    var processed_text = '' ;  //blank

    var sthiti1 = 0 ;  var sthiti2 = 0 ;  var chale_chalo = 1 ;
 
    var max_text_size = 6000;

    while ( chale_chalo == 1 ) 
    {
     sthiti1 = sthiti2 ;

     if ( sthiti2 < ( text_size - max_text_size ) )  
     { 
      sthiti2 +=  max_text_size ;
      while (document.getElementById("legacy_text").value.charAt ( sthiti2 ) != ' ') {sthiti2--;}
     } 
     else  { sthiti2 = text_size  ;  chale_chalo = 0 }

     var modified_substring = document.getElementById("legacy_text").value.substring ( sthiti1, sthiti2 )  ;

    Replace_Symbols( ) ;

    processed_text += modified_substring ;

//****************************************************************************************
//  Breaking part code over
//****************************************************************************************
//  processed_text = processed_text.replace( /mangal/g , "Richa" ) ;   

    document.getElementById("unicode_text").value = processed_text  ;
   }

}

else    // if input is HTML then

{

document.getElementById("unicode_text").value = "You have chosen HTML TEXT in Richa to convert into Unicode."  ;  

var remaining_text = document.getElementById("legacy_text").value ;
var processed_text = "" ;  //blank initially

var position_of_current_opening_bracket = 0 ;
var position_of_next_closing_bracket = 1 ;

var idx = remaining_text.indexOf( "<p " )  // search starting from paragraphs. then search for sanskrit 99.
idx = remaining_text.indexOf( "Sanskrit 99" , idx )
var idx2 = 0  //  position_of_current_opening_bracket  ">"
var idx3 = 0  //  position of "/span"
var idx4 = 0  //  postion of "span" only , ie span without "/"

while ( idx != -1 )    // while-01 loop     ;  while "Sanskrit 99"  is found..

{  
idx2 = remaining_text.indexOf( ">" , idx )  
idx3 = remaining_text.indexOf( "/span" , idx2 )
idx4 = remaining_text.indexOf( "span" , idx2 )


while ( idx4 < idx3 )     // this loop to take care of  nested span.
{
idx4 = remaining_text.indexOf( "span" , idx3+4 ) ;
idx3 = remaining_text.indexOf( "/span" , idx3+4 ) ;
}


var modified_substring = remaining_text.substring( idx2 , idx3 ) ;
modified_substring = modified_substring.replace( />/g , ">>" ) ; 
processed_text = processed_text + remaining_text.substring( 0 , idx2 ) + modified_substring + "/span" ;   

remaining_text = remaining_text.substring( idx3 + 5 ) ;  //remaining_text excludes "/span"
idx = remaining_text.indexOf( "Sanskrit 99" ) ;

} //end of outermost while-01


processed_text = processed_text + remaining_text ;




// -----------------------------

//  This section for taking care of paragraphs marked class = MsoBodyText  or class = MsoBodyText

remaining_text = processed_text ;
processed_text = "" ;  //blank initially

var position_of_start_of_paragraph = 0 ;
var position_of_end_of_paragraph = 1 ;

position_of_start_of_paragraph = remaining_text.indexOf("<p ")   ;


while ( position_of_start_of_paragraph != -1 )  //search for <p  in the remaining_text
{

position_of_start_of_paragraph = remaining_text.indexOf("<p ")   ;
position_of_end_of_paragraph = remaining_text.indexOf("/p>")   ;

modified_substring = remaining_text.substring( position_of_start_of_paragraph + 3 ,  position_of_end_of_paragraph ) ;


if ( modified_substring.indexOf( "MsoBodyText" ) != -1 )
{ 
  modified_substring = modified_substring.replace( />/g , ">>" )  ;    // repace all ">" with ">>" in this paragraph

idx = modified_substring.indexOf("font-family")  ;  // in Mybodytext, whereever font-family is found, it means it is roman text.
idx2 = 0 ;  // position of ">>"
idx3 = 0 ;  // position of "/span"
idx4 = 0 ;  // position of "span" only without "/"

while ( idx != -1 )     // again change ">>" to ">" only those which occure immediately after font-family:"Times new Roman"
{

idx2 = modified_substring.indexOf( ">>" , idx ) ;
idx3 = modified_substring.indexOf( "/span" , idx2 ) ;
idx4 = modified_substring.indexOf( "span" , idx2 ) ;


while ( idx4 < idx3 )
 {
   idx4 = modified_substring.indexOf( "span" , idx3+4 )  ;
   idx3 = modified_substring.indexOf( "/span" , idx3+4 )  ;
 }

modified_substring = modified_substring.substring( 0, idx2 ) + (modified_substring.substring( idx2 , idx3 )).replace( />>/g , ">" ) + modified_substring.substring( idx3 ) ; 
idx = modified_substring.indexOf( "font-family" , idx3 ) ;

} // end of while inner loop
} // end of if statement

processed_text = processed_text + remaining_text.substring( 0 , position_of_start_of_paragraph + 3 ) +  modified_substring + "/p>" ;   
remaining_text = remaining_text.substring( position_of_end_of_paragraph + 3 ) ; 
position_of_start_of_paragraph = remaining_text.indexOf("<p ")   ;

} // end of outer while loop

processed_text = processed_text + remaining_text ;





// ------------------------

// Now do actual font conversion  of text occuring between  all the  pairs  >>  and  <

remaining_text = processed_text ;     processed_text = "" ; 

idx2 = remaining_text.indexOf( ">>" )  ;



while ( idx2 != -1 )    // while-01 loop (checks if ">>" is still present

{  

position_of_current_opening_bracket = remaining_text.indexOf( ">>" , idx2 )  
position_of_next_closing_bracket = remaining_text.indexOf( "<" , position_of_current_opening_bracket )

modified_substring = remaining_text.substring( position_of_current_opening_bracket + 2 , position_of_next_closing_bracket ) ;

processed_text = processed_text + remaining_text.substring( 0 , position_of_current_opening_bracket + 1 ) ;   // ">" included by using +1 here
remaining_text = remaining_text.substring( position_of_next_closing_bracket + 1 ) ;  //remaining_text excludes the closing bracket


Replace_Symbols() ;   // call the subroutine and replace the legacy symbols  with corresponding Unicode.


processed_text = processed_text + modified_substring + "<"  ;

idx2 = remaining_text.indexOf( ">>" ) ;


} //end of outermost while-01



processed_text = processed_text + remaining_text ; 



// do follwing conversions which are still left  or  were done incorrectly due to unavoidable reasons.
 
// processed_text = processed_text.replace( /Sanskrit 99/g , "mangal" ) ;   

// processed_text = processed_text.replace( /ृलतष/g , "ं" )   ;  
// processed_text = processed_text.replace( /ृटुखतष/g , "घ" )  ;
// processed_text = processed_text.replace( /ृामपष/g , "ृ" )  ;
// processed_text = processed_text.replace( /ृगतष/g , ":" )  ;
// processed_text = processed_text.replace( /ृनबसपष/g , "/&nbsp" )  ; 
// processed_text = processed_text.replace( /ाॅ/g , "ॉ" )  ; 


// now put the processed text in the output box finally.

document.getElementById("unicode_text").value = processed_text  


} // end of else loop for HTML case


// --------------------------------------------------


function Replace_Symbols( )

{

//substitute array_two elements in place of corresponding array_one elements

if ( modified_substring != "" )  // if stringto be converted is non-blank then no need of any processing.
{
for ( input_symbol_idx = 0;   input_symbol_idx < array_one_length;    input_symbol_idx++ )

{

idx = 0  ;  // index of the symbol being searched for replacement

while (idx != -1 ) //whie-00
{

modified_substring = modified_substring.replace( array_one[ input_symbol_idx ] , array_two[input_symbol_idx] )
idx = modified_substring.indexOf( array_one[input_symbol_idx] )

} // end of while-00 loop
} // end of for loop

//**********************************************************************************
// Code for Replacing five Special glyphs
//**********************************************************************************

//**********************************************************************************
// Code for Glyph1 : ± (reph+anusvAr)
//**********************************************************************************
   modified_substring = modified_substring.replace( /±/g , "Zं" ) ; // at some places  ì  is  used eg  in "कर्कंधु,पूर्णांक".
  
//
//**********************************************************************************
// code for replacing "f" with "ि" and correcting its position too. (moving it one position forward)
//**********************************************************************************

var position_of_i = modified_substring.indexOf( "f" )

while ( position_of_i != -1 )  //while-02
{
var charecter_next_to_i = modified_substring.charAt( position_of_i + 1 )
var charecter_to_be_replaced = "f" + charecter_next_to_i
modified_substring = modified_substring.replace( charecter_to_be_replaced , charecter_next_to_i + "ि" ) 
position_of_i = modified_substring.search( /f/ , position_of_i + 1 ) // search for i ahead of the current position.

} // end of while-02 loop

//**********************************************************************************
// Glyph3 & Glyph4: Ç  É
// code for replacing "fa" with "िं"  and correcting its position too.(moving it two positions forward)
//**********************************************************************************

modified_substring = modified_substring.replace( /Ç/g , "fa" ) ; // at some places  Ç  is  used eg  in "किंकर".
modified_substring = modified_substring.replace( /É/g , "र्fa" ) ; // at some places  É  is  used eg  in "शर्मिंदा"

var position_of_i = modified_substring.indexOf( "fa" )

while ( position_of_i != -1 )  //while-02
{
var charecter_next_to_ip2 = modified_substring.charAt( position_of_i + 2 )
var charecter_to_be_replaced = "fa" + charecter_next_to_ip2
modified_substring = modified_substring.replace( charecter_to_be_replaced , charecter_next_to_ip2 + "िं" ) 
position_of_i = modified_substring.search( /fa/ , position_of_i + 2 ) // search for i ahead of the current position.

} // end of while-02 loop

//**********************************************************************************
// Glyph5: Ê
// code for replacing "h" with "ी"  and correcting its position too.(moving it one positions forward)
//**********************************************************************************

modified_substring = modified_substring.replace( /Ê/g , "ीZ" ) ; // at some places  Ê  is  used eg  in "किंकर".


/*
var position_of_i = modified_substring.indexOf( "h" )

while ( position_of_i != -1 )  //while-02
{
var charecter_next_to_i = modified_substring.charAt( position_of_i + 1 )
var charecter_to_be_replaced = "h" + charecter_next_to_i
modified_substring = modified_substring.replace( charecter_to_be_replaced , charecter_next_to_i + "ी" ) 
position_of_i = modified_substring.search( /h/ , position_of_i + 1 ) // search for i ahead of the current position.

} // end of while-02 loop
*/


//**********************************************************************************
// End of Code for Replacing four Special glyphs
//**********************************************************************************

// following loop to eliminate 'chhotee ee kee maatraa' on half-letters as a result of above transformation.

var position_of_wrong_ee = modified_substring.indexOf( "ि्" ) 

while ( position_of_wrong_ee != -1 )  //while-03

{
var consonent_next_to_wrong_ee = modified_substring.charAt( position_of_wrong_ee + 2 )
var charecter_to_be_replaced = "ि्" + consonent_next_to_wrong_ee 
modified_substring = modified_substring.replace( charecter_to_be_replaced , "्" + consonent_next_to_wrong_ee + "ि" ) 
position_of_wrong_ee = modified_substring.search( /ि्/ , position_of_wrong_ee + 2 ) // search for 'wrong ee' ahead of the current position. 

} // end of while-03 loop


// Eliminating reph "Z" and putting 'half - r' at proper position for this.
set_of_matras = "ा ि ी ु ू ृ े ै ो ौ ं : ँ ॅ" 
var position_of_R = modified_substring.indexOf( "Z" )

while ( position_of_R > 0 )  // while-04
{
probable_position_of_half_r = position_of_R - 1 ;
var charecter_at_probable_position_of_half_r = modified_substring.charAt( probable_position_of_half_r )


// trying to find non-maatra position left to current O (ie, half -r).

while ( set_of_matras.match( charecter_at_probable_position_of_half_r ) != null )  // while-05

{
probable_position_of_half_r = probable_position_of_half_r - 1 ;
charecter_at_probable_position_of_half_r = modified_substring.charAt( probable_position_of_half_r ) ;

} // end of while-05


charecter_to_be_replaced = modified_substring.substr ( probable_position_of_half_r , ( position_of_R - probable_position_of_half_r ) ) ;
new_replacement_string = "र्" + charecter_to_be_replaced ; 
charecter_to_be_replaced = charecter_to_be_replaced + "Z" ;
modified_substring = modified_substring.replace( charecter_to_be_replaced , new_replacement_string ) ;
position_of_R = modified_substring.indexOf( "Z" ) ;

} // end of while-04

} // end of IF  statement  meant to  supress processing of  blank  string.


} // end of the function  Replace_Symbols


} // end of legacy_to_unicode function


</script>
</head>





<!-- ----------------------------------------------------------------------------------
      body of the HTML starts here. one text box is provided each for input and output. 
-->


<body>
<form name="form1">

Paste the text in Richa font in the box below : <br/><br/>

<textarea name="TextToConvert" id="legacy_text" cols="80" rows="7"></textarea> <br><br>

The input given in the above box is : 
<div > <select id="text_or_html">
<option>Plain TEXT</option>
<option>HTML TEXT</option>
</select> </div> 

<div align="middle">
<input  type="button" id="converter" name="converter" value=" Convert to Unicode >> " onClick="convert_to_unicode();" accesskey="c" title="शॉर्टकट alt+c"> 
</div>  <br><br>

This is Unicode equivalent of the above : <br/><br>
<textarea name="ConvertedText" id="unicode_text" cols="80" rows="13"></textarea>
<br /><br />

</form>
</body>

</html>