" 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("
") ; 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 occur 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("
> 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( /Agra/g , "mangal" ) ; processed_text = processed_text.replace( /-सजय/g , "ढ" ) ; processed_text = processed_text.replace( /-ुनवजय/g , "ष्" ) ; processed_text = processed_text.replace( /-ंउचय/g , "-" ) ; processed_text = processed_text.replace( /-हजय/g , "झ" ) ; processed_text = processed_text.replace( /-दइेचय/g , "/ " ) ; processed_text = processed_text.replace( /ाॅ/g , "ॉ" ) ; // now put the processed text in the output box finally. document.getElementById(toctrl).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 string to be converted is non-blank then no need of any processing. { // first replace the two-byte nukta_varNa with corresponding one-byte nukta varNas. modified_substring = modified_substring.replace ( /क़/ , "क़" ) ; modified_substring = modified_substring.replace ( /ख़/g , "ख़" ) ; modified_substring = modified_substring.replace ( /ग़/g , "ग़" ) ; modified_substring = modified_substring.replace ( /ज़/g , "ज़" ) ; modified_substring = modified_substring.replace ( /ड़/g , "ड़" ) ; modified_substring = modified_substring.replace ( /ढ़/g , "ढ़" ) ; modified_substring = modified_substring.replace ( /ऩ/g , "ऩ" ) ; modified_substring = modified_substring.replace ( /फ़/g , "फ़" ) ; modified_substring = modified_substring.replace ( /य़/g , "य़" ) ; modified_substring = modified_substring.replace ( /ऱ/g , "ऱ" ) ; 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 Special glyph : Z (reph+anusvAr) //********************************************************************************** modified_substring = modified_substring.replace( /Z/g , "üं" ) ; // at some places ì is used eg in "कर्कंधु,पूर्णांक". //============================================================================================= // code for replacing "ç" with "ि" (chhotee ee kii maatraa) and correcting its position too. var position_of_f = modified_substring.indexOf( "ç" ) ; while ( position_of_f != -1 ) //while-02 { var charecter_right_to_f = modified_substring.charAt( position_of_f + 1 ) ; modified_substring = modified_substring.replace( "ç" + charecter_right_to_f , charecter_right_to_f + "ि" ) ; position_of_f = position_of_f + 1 ; while ( ( modified_substring.charAt( position_of_f + 1 ) == "्" ) & ( position_of_f < modified_substring.length - 1 ) ) { var string_to_be_replaced = modified_substring.charAt( position_of_f + 1 ) + modified_substring.charAt( position_of_f + 2 ) ; modified_substring = modified_substring.replace( "ि" + string_to_be_replaced , string_to_be_replaced + "ि" ) ; position_of_f = position_of_f + 2 ; } position_of_f = modified_substring.search( /ç/ , position_of_f + 1 ) ; // search for ç ahead of the current position. } // end of while-02 loop //====================================================================================== // code for moving "¨" at right place and replacing it with "ç" first; and then finally replacing "ç" with "िं" (chhotee ee kii maatraa with anuswaar) and correcting its position too. // //var position_of_f = modified_substring.indexOf( "¨" ) ; // //while ( position_of_f != -1 ) //while-02 //{ //var charecter_right_to_f = modified_substring.charAt( position_of_f + 1 ) ; // //modified_substring = modified_substring.replace( "¨" + charecter_right_to_f , charecter_right_to_f + "ç" ) ; // // //position_of_f = position_of_f + 1 ; // //while (( modified_substring.charAt( position_of_f + 1 ) == "्" ) & ( position_of_f < modified_substring.length - 1 ) ) //{ //var string_to_be_replaced = modified_substring.charAt( position_of_f + 1 ) + modified_substring.charAt( position_of_f + 2 ) ; // //modified_substring = modified_substring.replace( "ç" + string_to_be_replaced , string_to_be_replaced + "ç" ) ; // //position_of_f = position_of_f + 2 ; // //} // //position_of_f = modified_substring.search( /¨/ , position_of_f + 1 ) ; // search for "¨" ahead of the current position. // //} // end of while-02 loop // //modified_substring = modified_substring.replace( /ç/g , "िं" ) ; //====================================================================================== //Eliminating "ü"(reph) and putting 'half - r' at proper position for this. set_of_matras = "ा ि ी ु ू ृ े ै ो ौ ं ः ँ ॅ" var position_of_Z = modified_substring.indexOf( "ü" ) while( position_of_Z > 0 ) // while-04 { probable_position_of_half_r = position_of_Z - 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 ü (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_Z - probable_position_of_half_r ) ) ; new_replacement_string = "र्" + charecter_to_be_replaced ; charecter_to_be_replaced = charecter_to_be_replaced + "ü" ; modified_substring = modified_substring.replace( charecter_to_be_replaced , new_replacement_string ) ; position_of_Z = modified_substring.indexOf( "ü" ) ; }// 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