Comparing strings with symbols from different alphabets

Question

I want to compare two strings which contains symbols from different alphabets (e.g. Russian and English). I want that symbols which looks similarly is considered as equal to each other.

E.g. in the word "Mom" letter "o" is from English alphabet (code 043E in Unicode), and in the world "Mоm" letter "о" is from Russian alphabet (code 006F in Unicode). So ("Mom" = "Mоm") => false, but I want it would be true. Is there some standard SAS function or I should wright a macro to do it.

Thanks!

score 1 · Accepted Answer · answered Feb 13 '16 at 15:42

I would do like that:

First I would make map. I mean which letter in Russian language corresponds to what letter in English language. Example:
б = b
в = v
...

I would store this map in a separate table or as macroVars. Then I would create a macro loop, with tranwrd function, which loops throug the map, which was created.

Example here could be like that.

data _null_;
    stringBefore = "без";
    stringAfter = tranwrd(stringBefore,"а","a");
    stringAfter = tranwrd(stringAfter,"б","b");
    stringAfter = tranwrd(stringAfter,"в","v");
...
run;

After this transformation I think You can compare your strings.

score 0 · Answer 2 · answered Feb 16 '16 at 10:31

I also coded some functions to deal with keybord layout misprints. Here is code:

/***************************************************************************/
/* FUNCTION count_rus_letters RETURNS NUMBER OF CYRILLIC LETTERS IN STRING */
/***************************************************************************/ 
proc fcmp outlib=sasuser.userfuncs.mystring;
FUNCTION count_rus_letters(string $);
length letter $2;

rus_count=0;

len=klength(string);

do i=1 to len;
  letter=ksubstr(string,i,1);
  if letter in ("А","а","Б","б","В","в","Г","г","Д","д","Е","е","Ё","ё","Ж","ж"
      "З","з","И","и","Й","й","К","к","Л","л","М","м","Н","н","О","о","П","п","Р","р",
      "С","с","Т","т","У","у","Ф","ф","Х","х","Ц","ц","Ч","ч","Ш","ш","Щ","щ","Ъ","ъ"
      "Ы","ы","Ь","ь","Э","э","Ю","ю","Я","я") 
  then rus_count+1;
end;

return(rus_count);
endsub;
run;

/**************************************************************************/
/* FUNCTION count_eng_letters RETURNS NUMBER OF ENGLISH LETTERS IN STRING */
/**************************************************************************/ 
proc fcmp outlib=sasuser.userfuncs.mystring;
FUNCTION count_eng_letters(string $);
length letter $2;

eng_count=0;

len=klength(string);

do i=1 to len;
  letter=ksubstr(string,i,1);
  if rank('A') <= rank(letter) <=rank('z') 
  then eng_count+1;
end;

return(eng_count);
endsub;
run;

/**************************************************************************/
/* FUNCTION is_string_russian RETURNS 1 IF NUMBER OF RUSSIAN SYMBOLS IN   */
/* STRING >= NUMBER OF ENGLISH SYMBOLS                                    */
/**************************************************************************/ 
proc fcmp outlib=sasuser.userfuncs.mystring;
FUNCTION is_string_russian(string $);
length letter $2 result 8;

eng_count=0;
rus_count=0;

len=klength(string);

do i=1 to len;
  letter=ksubstr(string,i,1);
  if letter in ("А","а","Б","б","В","в","Г","г","Д","д","Е","е","Ё","ё","Ж","ж"
      "З","з","И","и","Й","й","К","к","Л","л","М","м","Н","н","О","о","П","п","Р","р",
      "С","с","Т","т","У","у","Ф","ф","Х","х","Ц","ц","Ч","ч","Ш","ш","Щ","щ","Ъ","ъ"
      "Ы","ы","Ь","ь","Э","э","Ю","ю","Я","я") 
  then rus_count+1;
  if rank('A') <= rank(letter) <=rank('z') 
  then eng_count+1;
end;

if rus_count>=eng_count
then result=1;
else result=0;

return(result);
endsub;
run;

/**************************************************************************/
/* FUNCTION fix_layout_misprints REPLACES MISPRINTED SYMBOLS BY ANALYSING */
/* LANGUAGE OF THE STRING (FOR ENGLISH STRING RUSSIAN SYMBOLS ARE         */
/* REPLACED BY ENGLISH COPIES AND FOR RUSSIAN STRING SYMBOLS ARE          */
/* REPLACED BY RUSSIAN COPIES)                                            */
/**************************************************************************/ 
proc fcmp outlib=sasuser.userfuncs.mystring;
FUNCTION fix_layout_misprints(string $) $ 1000;
length letter $2 result $1000;

eng_count=0;
rus_count=0;

len=klength(string);

do i=1 to len;
  letter=ksubstr(string,i,1);
  if letter in ("А","а","Б","б","В","в","Г","г","Д","д","Е","е","Ё","ё","Ж","ж"
      "З","з","И","и","Й","й","К","к","Л","л","М","м","Н","н","О","о","П","п","Р","р",
      "С","с","Т","т","У","у","Ф","ф","Х","х","Ц","ц","Ч","ч","Ш","ш","Щ","щ","Ъ","ъ"
      "Ы","ы","Ь","ь","Э","э","Ю","ю","Я","я") 
  then rus_count+1;
  if rank('A') <= rank(letter) <=rank('z') 
  then eng_count+1;
end;

if rus_count>=eng_count
then result=ktranslate(string,"АаВЕеКкМОоРрСсТХх","AaBEeKkMOoPpCcTXx");
else result=ktranslate(string,"AaBEeKkMOoPpCcTXx","АаВЕеКкМОоРрСсТХх");

return(result);
endsub;
run;

/***********/
/* EXAMPLE */
/***********/
options cmplib=sasuser.userfuncs;
data _null_;
good_str="Иванов";
err_str="Ивaнов";
fixed_str=fix_layout_misprints(err_str);

put "Good string=" good_str;
put "Error string=" err_str;
put "Fixed string=" fixed_str;

rus_count_in_err=count_rus_letters(err_str);
put "Count or Cyrillic symbols in error string=" rus_count_in_err;

eng_count_in_err=count_eng_letters(err_str);
put "Count or English symbols in error string=" eng_count_in_err;

is_error_str_russian=is_string_russian(err_str);
put "Is error string language Russian=" is_error_str_russian;

if (good_str ne err_str) 
then put "Before clearing - strings are not equal to each other";

if (good_str = fixed_str) 
then put "After clearing - strings are equal to each other";
run;

Comparing strings with symbols from different alphabets

2 Answers2