Code Formatter

In July 2010, Chris Hemedinger author of The SAS Dummy blog wrote an article titled 'Hope for ugly programs'.

That article showed that SAS Enterprise Guide had a shortcut of Ctrl-I ("indent this!") to convert ugly code into something much more readable. The below code is my attempt to emulate the behaviour in Base SAS.

/**************************************************************************
*     Program: codeformatter.sas
*      Author: Tom Bellmer
*     Created: 10Oct2014 
*     Purpose: Make SAS program more readable by placing one statemnt per  
*              line, indent code below PROC and DATA steps and indenting DO
*              constructs
*       Usage: %codeformatter( infile = , outfile = c:\temp\beautify.sas )
**************************************************************************/
%macro codeformatter( inputfile =, outputfile = c:\temp\codeout.sas ) ;
  %if not %sysfunc( fileexist( &inputfile. ) ) %then %do ;
    %put %str(E)RROR: The input file &inputfile. does not exist. ;
    %return ;
  %end ;

  data _null_ ;
    length 
      semicolonlocation startposition indent i commentoff 5 
      sasstatement $8 
      word $32767 ;
    retain commentoff 1 ;

    infile "&inputfile."  lrecl = 32767 truncover end = eof ;
    file   "&outputfile." lrecl = 32767 ;

    do until( eof ) ;
      input line $32767. ;
      startposition = 1 ;

      if find( line, '/*' ) then commentoff = 0 ;

      do i = 1 to max( count( line, ';' ), 1 ) ;
        semicolonlocation = find( line, ';', startposition  ) + 1 ; 

        if semicolonlocation = 1 then word = line ;
        else word = substr( line, startposition, ( semicolonlocation 
          - startposition ) ) ;

        startposition = semicolonlocation ;
        sasstatement = upcase( compress( scan( word, 1 ), ';' ) ) ;

        if sasstatement in ( 'LIBNAME', 'GOPTIONS', 'DATA', 'PROC', 'QUIT'
             , 'RUN', '*', '/*', 'OPTIONS', 'ODS', 'TITLE', 'FOOTNOTE'
             , 'FILENAME', 'RSUBMIT')  then do ;
          if sasstatement in ( 'PROC', 'DATA' ) then put ;
          indent = 0 ;
        end ;
        else indent = max( 2, indent ) ;

        if commentoff and ( find( word, 'end ', 'i' ) 
          or find( word, 'end;', 'i' ) ) 
           then indent = indent - 2 ;
        put +indent word ;

        if commentoff and ( find( lowcase( word ), 'do ' ) 
          or find( lowcase( word ), 'do;' ) ) 
           then indent + 2 ;
      end ;

      if find( line, '*/' ) then commentoff  = 1 ;
 
    end ;
  run ;
%mend ;

/* EOF: codeformatter.sas  */