" 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 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("
> 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 , "/ " ) ; // 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 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++ ) { //*********************************************************** // if (input_symbol_idx==106) // { alert(" input_symbol_idx = "+input_symbol_idx); // alert(" character = "+string.fromCharCode(input_symbol_idx)) // } // if (input_symbol_idx == 107) // { alert(" input_symbol_idx = "+input_symbol_idx); // alert(" character = ",+string.fromCharCode(input_symbol_idx)) // } //*********************************************************** idx = 0 ; // index of the symbol being searched for replacement while (idx != -1 ) //while-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 //alert(" modified substring = "+modified_substring) //********************************************************************************** // Code for Replacing five Special glyphs //********************************************************************************** //"æ","ç","ê","ë", //"र्ä","र्å","र्è","र्é", //********************************************************************************** // Code for Glyph1 : È (reph+anusvAr) //********************************************************************************** modified_substring = modified_substring.replace( /È/g , "Çं" ) ; // at some places ì is used eg in "कर्कंधु,पूर्णांक". //********************************************************************************** // Code for Glyph2 : ç (ekAr+reph+anusvAr) //********************************************************************************** modified_substring = modified_substring.replace( /ç/g , "Çें") ; //********************************************************************************** // Code for Glyph3 : æ (ekAr+reph) //********************************************************************************** modified_substring = modified_substring.replace( /æ/g , "Çे") ; //********************************************************************************** // Code for Glyph4 : ë (aikAr+reph+anusvAr) //********************************************************************************** modified_substring = modified_substring.replace( /ë/g , "Çैं") ; //********************************************************************************** // Code for Glyph5 : ê (aikAr+reph) //********************************************************************************** modified_substring = modified_substring.replace( /ê/g , "Çै") ; //********************************************************************************** // Code for Glyph6 : Ô ( reph + ी ) //********************************************************************************** modified_substring = modified_substring.replace( /Ô/g , "Çी" ) ; //********************************************************************************** // Code for Glyph7 : Ó ( ी + anusvAr ) //********************************************************************************** modified_substring = modified_substring.replace( /Ó/g , "ीं" ) ; //********************************************************************************** // Code for Glyph8 : Õ ( reph + ी + anusvAr ) //********************************************************************************** modified_substring = modified_substring.replace( /Õ/g , "Çीं" ) ; //********************************************************************************** // Code for Glyph09 : Ì ( reph + ि ) // Code for Glyph10 : Î (ि) [ikAr mAtrA before a संयुक्ताक्षर as in क्लिष्ट, स्थित etc) // replace "Ê" and "Î" with "ि" and correcting its position too(moving it one position forward) //********************************************************************************** modified_substring = modified_substring.replace( /Ì/g , "र्Ê" ) ; // at some places Ì is used eg in "धार्मिक". modified_substring = modified_substring.replace( /Î/g , "Ê" ) ; var position_of_i = modified_substring.indexOf( "Ê" ) while ( position_of_i != -1 ) //while-02 { var charecter_next_to_i = modified_substring.charAt( position_of_i + 1 ) var charecter_to_be_replaced = "Ê" + charecter_next_to_i modified_substring = modified_substring.replace( charecter_to_be_replaced , charecter_next_to_i + "ि" ) position_of_i = modified_substring.search( /Ê/ , position_of_i + 1 ) // search for i ahead of the current position. } // end of while-02 loop //********************************************************************************** // Code for Glyph8 : Ë ("िं") // Code for Glyph9 : Í ("र्िं") // replace Ë with "िं" and correcting its position too(moving it two positions forward) //********************************************************************************** modified_substring = modified_substring.replace( /Í/g , "र्Ë" ) ; // at some places Í is used eg in "शर्मिंदा" modified_substring = modified_substring.replace( /Ë/g , "ÊÆ" ) ; // at some places Ë is used eg in "किंकर". var position_of_i = modified_substring.indexOf( "ÊÆ" ) while ( position_of_i != -1 ) //while-02 { var charecter_next_to_ip2 = modified_substring.charAt( position_of_i + 2 ) var charecter_to_be_replaced = "ÊÆ" + charecter_next_to_ip2 modified_substring = modified_substring.replace( charecter_to_be_replaced , charecter_next_to_ip2 + "िं" ) position_of_i = modified_substring.search( /ÊÆ/ , position_of_i + 2 ) // 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 "Ç" and putting 'half - r' at proper position for this. set_of_matras = "ा ि ी ु ू ृ े ै ो ौ ं : ँ ॅ" var position_of_R = modified_substring.indexOf( "Ç" ) 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 + "Ç" ; modified_substring = modified_substring.replace( charecter_to_be_replaced , new_replacement_string ) ; position_of_R = modified_substring.indexOf( "Ç" ) ; } // end of while-04 } // end of IF statement meant to supress processing of blank string. modified_substring = modified_substring.replace( /ाे/g , "ो") ; modified_substring = modified_substring.replace( /ाै/g , "ौ") ; } // end of the function Replace_Symbols } // end of legacy_to_unicode function