program capsmark(sequ, capsmarkp, searchp, output);
(* capsmark: read sequence; make features for capitalized regions

  Tom Schneider
  NCI/FCRDC Bldg 469. Room 144
  P.O. Box B
  Frederick, MD  21702-1201
  (301) 846-5581 (-5532 for messages)
  toms@ncifcrf.gov
  http://www-lmmb.ncifcrf.gov/~toms/

  National Cancer Institute
  Laboratory of Mathematical Biology

 *)

label 1; (* end of program *)

const
(* begin module version *)
version = 1.02; (* of capsmark.p 1997 October 17
origin 1997 October 17 *)
updateversion = 1.00; (* defines lowest acceptable current parameter file *)
(* end module version *)

(* begin module describe.capsmark *)
(*
name
   capsmark: read sequence; make features for capitalized regions

synopsis
   capsmark(sequ: in, capsmarkp: in, searchp: out, output: out)

files
   sequ:  raw DNA sequence in lower case except for objects
      of interest marked in upper case.

   searchp:  search parameters for the capitalized regions

   capsmarkp:  parameters to control the program.  The file must contain the
      following parameters, one per line:

      parameterversion: The version number of the program.  This allows the
         user to be warned if an old parameter file is used.

      name: a string of characters to name the sequence.

   output: messages to the user

description
   Sequences are often marked by people with capital letters
   to indicate interesting regions (exons, primers, mutations, etc)
   This program creates lister features for a raw sequence.

examples

documentation

see also
   lister.p

author
   Thomas Dana Schneider

bugs

technical notes

*)
(* end module describe.capsmark *)

var
   sequ, (* file used by this program *)
   capsmarkp, (* file used by this program *)
   searchp: text; (* file used by this program *)

(* begin module halt *)
procedure halt;
(* stop the program.  the procedure performs a goto to the end of the
   program.  you must have a label:
      label 1;
   declared, and also the end of the program must have this label:
      1: end.
   examples are in the module libraries.
   this is the only goto in the delila system. *)
begin
      writeln(output,' program halt.');
      goto 1
end;
(* end module halt version = 'delmod 6.16 84 mar 12 tds/gds'; *)

(* begin module capitalize *)
function capitalize(c: char): char;
(* convert the character c to upper case *)
var
   n: integer; (* c is the n'th letter of the alphabet *)
begin
   n := ord(c);

   if (n >= ord('a')) and
      (n <= ord('z'))
   then c := chr( n - ord('a') + ord('A'));

   capitalize := c
end;
(* end module capitalize prgmod *)

(* begin module decapitalize *)
function decapitalize(c: char): char;
(* convert the character c to lower case *)
var
   n: integer; (* c is the n'th letter of the alphabet *)
begin
   n := ord(c);

   if (n >= ord('A')) and
      (n <= ord('Z'))
   then c := chr( n - ord('A') + ord('a'))
   else c := chr(n);

   decapitalize := c
end;
(* end module decapitalize prgmod *)

(* begin module capsmark.themain *)
procedure themain(var sequ, capsmarkp, searchp: text);
(* the main procedure of the program *)
const
   maxnamelength = 100; (* maximum length name *)
var
   c: char; (* a character in the sequence *)
   name: array[1..maxnamelength] of char; (* name of the sequence *)
   namelength: integer; (* length of the name *)
   n: integer; (* index to the name *)
   parameterversion: real; (* parameter version number *)
   position: integer; (* position in the sequence, starting with 1 *)
   waslower: boolean; (* true if previous character was lower case *)
begin
   writeln(output,'capsmark ',version:4:2);
   reset(capsmarkp);
   readln(capsmarkp, parameterversion);
   if parameterversion < updateversion then begin
      writeln(output, 'You have an old parameter file!');
      halt
   end;

   namelength := 0;
   while not eoln(capsmarkp) do begin
      namelength := namelength + 1;
      read(capsmarkp, name[namelength]);
   end;

   reset(sequ);
   rewrite(searchp);
   writeln(searchp,'* capsmark ',version:4:2);

   position := 0;
   waslower := true;

   while not eof(sequ) do begin
      if eoln(sequ) (* end of line *)
      then begin
         readln(sequ);
(*
         writeln(searchp)
*)
      end
      else begin (* not end of line *)
         read(sequ, c);
         if c in ['a','c','g','t', 'n'] then begin
            position := position + 1;
            if not waslower then begin (* upper case ending *)
               writeln(searchp)
            end;
            waslower := true;
(*
            write(searchp, capitalize(c));
*)
         end
         else if c in ['A','C','G','T','N'] then begin
            position := position + 1;
            if waslower then begin (* begin upper case *)
               write(searchp,'"');
               for n :=1 to namelength
               do write(searchp,name[n]);
               writeln(searchp,'.',position:1,'"')
            end;
            waslower := false;
            write(searchp, decapitalize(c));
            
(*
            write(searchp, decapitalize(c));
*)
         end
         else writeln(output,'unidentified character: ', c);
      end
   end;

   writeln(searchp,'q');

(* 
      searchfeatures: features for the lister program.
         To start the file, simply provide a name inside double quotes
         (eg "EcoRI").
         Subsequent searches (eg gaattc) will be labeled with that name.
         To turn off the features, use an empty quote string, as "".
         The searchfeatures file can be concatenated with other features
         to create the features file for lister.
*)

end;
(* end module capsmark.themain *)

begin
   themain(sequ, capsmarkp, searchp);
1: end.