/**********************************************************************
 * create a dictionary from a variable of strings
 * Peng Zeng 
 * 07-25-2019
 **********************************************************************/

data texts;
   input str $1-80;
datalines; 
One of the advantages.of the SAS/IML matrix language, 
Notice that the delimiters! do not ... include
;
proc print data = texts; run;


data dictionary_raw;
   length word $20;
   set texts;
   delims = ' ,.!';
   numWords = countw(str, delims); /* count number of words */
   do i = 1 to numWords;
      word = scan(str, i, delims); /* extract i-th word */
      output;
   end;
run;

proc print data = dictionary_raw; run;

proc sql;
   create table dictionary as 
   select distinct upcase(word) as word
   from dictionary_raw
   order by word;
quit;

proc print data = dictionary; run;

/**********************************************************************
 * THE END
 **********************************************************************/