program bkdb(book, database, output);
(* bkdb: convert a book to database format for the sites program

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

  National Cancer Institute
  Laboratory of Mathematical Biology

  1991
 *)

label 1; (* end of program *)

const
(* begin module version *)
version = 1.01; (* of bkdb.p 1991 January 14
origin 1991 Jan 14 *)
(* end module version *)

(* begin module describe.bkdb *)
(*
name
   bkdb: convert a book to database format for the sites program

synopsis
   bkdb(book: in, database: out, output: out)

files
   book: a book containing many sequences of the same size.
   database: the format used by the sites program.
   output: messages to the user

description
   The program converts a book to the database format used by the sites
   program.

examples

documentation

see also
   sites.p

author
   Thomas Dana Schneider

bugs
  It sure would be nice to have on uniform type of format, but the GenBank
  format is not yet defined (and it is 5 years after GenBank was told
  by a national advisor to do this!), so we wait.

technical notes

*)
(* end module describe.bkdb *)

(* begin module book.const *)
(* constants needed for book manipulations *)

      dnamax = 3000;  (* length of dna arrays *)
      namelength = 20; (* maximum key name length *)
      linelength = 80; (* maximum line readable in book *)

(* end module book.const version = 'delmod 6.60 91 Jan 11 tds/gds' *)

type
(* begin module book.type *)
(* types needed for book manipulations *)

      chset = set of 'a'..'z';

      (* types defined in book definition *)

      alpha = packed array[1..namelength] of char; (* this is not alfa *)

      (* name is a left justified string with blanks following the
         characters *)
      name = record
         letters: alpha;
         length: 0..namelength (* zero means an unspecified structure *)
      end;

      lineptr = ^line;
      line = record (* a line of characters *)
         letters: packed array [1..linelength] of char;
         length: 0..linelength;
         next: lineptr
      end;

      direction = (plus, minus, dircomplement, dirhomologous);
      configuration = (linear, circular);
      state = (on, off);


      header = record (* header of key *)
         keynam: name; (* key name of structure *)
         fulnam: lineptr; (* full name of structure *)
         note:   lineptr (* note key *)
      end;


      (* base types *)
      base = (a,c,g,t);
      dnaptr = ^dnastring;
      dnarange = 0..dnamax;
      seq = packed array[1..dnamax] of base;
      dnastring = record
         part: seq;
         length: dnarange;
         next: dnaptr
      end;


      orgkey = record (* organism key *)
         hea: header;
         mapunit: lineptr (* genetic map units *)
      end;

      chrkey = record (* chromosome key *)
         hea: header;
         mapbeg: real; (* number of genetic map beginning *)
         mapend: real (* number of genetic map ending *)
      end;

      pieceptr = ^piece;
      piekey = record (* piece key *)
         hea: header;
         mapbeg: real; (* genetic map beginning *)
         coocon: configuration; (* configruation (circular/linear) *)
         coodir: direction; (* direction (+/-) relative to genetic map *)
         coobeg: integer; (* beginning nucleotide *)
         cooend: integer; (* ending nucleotide *)
         piecon: configuration; (* configruation (circular/linear) *)
         piedir: direction; (* direction (+/-) relative to coordinates *)
         piebeg: integer; (* beginning nucleotide *)
         pieend: integer; (* ending nucleotide *)
      end;


      piece = record
         key: piekey;
         dna: dnaptr
      end;

      reference = record
         pienam : name;  (* name of piece referred to *)
         mapbeg : real;  (* genetic map beginning *)
         refdir : direction;  (* direction relative to coordinates *)
         refbeg : integer;  (* beginning nucleotide *)
         refend : integer;  (* ending nucleotide *)
      end;

      genkey = record  (* gene key *)
         hea : header;
         ref : reference;
      end;

      trakey = record  (* transcript key *)
         hea : header;
         ref : reference;
      end;

      markerptr = ^marker;
      markey = record (* marker key *)
         hea : header;
         ref : reference;
         sta : state;
         phenotype : lineptr;
         next : markerptr;
      end;

      marker = record
         key : markey;
         dna : dnaptr;
      end;

(* end module book.type version = 'delmod 6.60 91 Jan 11 tds/gds' *)

var
   book, database: text; (* files used by this program *)

(* begin module book.var *)
(* ************************************************************************ *)
(* global variables needed for book manipulations *)

      (* free storage: *)
      freeline: lineptr; (* unused lines *)
      freedna: dnaptr; (* unused dnas *)

      readnumber: boolean; (* whether to read a number from the notes, or
                              to read in the notes *)
      number: integer; (* the number of the item just read *)
      numbered: boolean; (* true when the item just read is numbered *)
      skipunnum: boolean; (* a control variable to allow skipping of
                             un-numbered items in the book *)

(* ************************************************************************ *)
(* end module book.var version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* 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 6.60 91 Jan 11 tds/gds' *)

(* begin module package.nextbase *)
(* ************************************************************************ *)
(* begin module package.getpiece *)
(* ************************************************************************ *)
(* begin module package.brpiece *)
(* ************************************************************************ *)
(* begin module book.basis *)
(* procedures needed for book manipulations *)

(* get procedures should be used for all linked lists of records *)

procedure getline(var l: lineptr);
(* obtain a line from the free line list or by making a new one *)
begin
      if freeline<>nil
         then begin
            l:=freeline;
            freeline:=freeline^.next
         end
         else new(l);
      l^.length:=0;
      l^.next:=nil
end;

procedure getdna(var l: dnaptr);
begin
      if freedna<>nil
         then begin
            l:=freedna;
            freedna:=freedna^.next
         end
         else new(l);
      l^.length:=0;
      l^.next:=nil
end;

(* clear procedures should be called each time the records are no longer needed
         failure to do this may result in a stack overflow. *)

procedure clearline(var l: lineptr);
(* return a line to the free line list *)
var   lptr: lineptr;
begin
      if l<>nil then begin
         lptr:=l;
         l:=l^.next;
         lptr^.next:=freeline;
         freeline:=lptr
      end
end;

procedure cleardna(var l: dnaptr);
var   lptr: dnaptr;
begin
      if l<>nil then begin
         lptr:=l;
         l:=l^.next;
         lptr^.next:=freedna;
         freedna:=lptr
      end
end;

procedure clearheader(var h: header);
(* clear the header h (remove lines to free storage) *)
begin
      with h do begin
         clearline(fulnam);
         while note<>nil do clearline(note)
      end
end;

procedure clearpiece(var p: pieceptr);
(* clear the dna of the piece *)
begin
      while p^.dna<>nil do cleardna(p^.dna);
      clearheader(p^.key.hea)
end;

function chartobase(ch:char):base;
(* convert a character into a base *)
begin
      case ch of
         'a': chartobase:=a;
         'c': chartobase:=c;
         'g': chartobase:=g;
         't': chartobase:=t
      end
end;

function basetochar(ba:base):char;
(* convert a base into a character *)
begin
      case ba of
         a: basetochar:='a';
         c: basetochar:='c';
         g: basetochar:='g';
         t: basetochar:='t';
      end
end;

function complement(ba:base):base;
(* take the complement of ba *)
begin
      case ba of
         a: complement:=t;
         c: complement:=g;
         g: complement:=c;
         t: complement:=a;
      end
end;

function pietoint(p: integer; pie: pieceptr): integer;
(* p is a coordinate on the piece.
   we want to transform p into a number
   from 1 to n: an internal coordinate system for
   easy manipulation of piece coordinates *)
var   i: integer; (* an intermediate value *)
begin
      with pie^.key do begin
         case piedir of
            plus:  if p>=piebeg
                   then i:=p-piebeg+1
                   else i:=(p-coobeg)+(cooend-piebeg)+2;
            minus: if p<=piebeg
                   then i:=piebeg-p+1
                   else i:=(cooend-p)+(piebeg-coobeg)+2
         end;
         pietoint:=i
      end
end;

function inttopie(i: integer; pie: pieceptr):integer;
(* i is in the range 1 to some maximum.  it is an internal coordinate
   system for the program.  we want to do a
   coordinate transformation to obtain
   a value in the range of the piece called pie:
   i=1 corresponds to piebeg and
   i=its maximum corresponds to pieend *)
var   p: integer; (* an intermediate value *)
begin
      with pie^.key do begin
         case piedir of
            plus: begin
               p:=piebeg+(i-1);
               if p>cooend
                  then if coocon=circular
                     then p:=p-(cooend-coobeg+1)
            end;
            minus: begin
               p:=piebeg-(i-1);
               if p<coobeg
                  then if coocon=circular
                     then p:=p+(cooend-coobeg+1)
            end
         end;
         inttopie:=p
      end
end;

function piecelength(pie: pieceptr): integer;
(* return the length of the dna in pie *)
begin
      piecelength:=pietoint(pie^.key.pieend,pie)
end;

(* end module book.basis version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.getto *)
function getto(var thefile: text; ch: chset): char;
(* search the file for a character in the first line which is a
   member of the set ch. *)
var achar: char;
begin
      achar:=' ';
      while (not(achar in ch)) and (not eof(thefile))
         do readln(thefile,achar);
      if (achar in ch) then getto:=achar
                       else getto:=' '
end;
(* end module book.getto version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.skipstar *)
procedure skipstar(var thefile:text);
(* skip start of line (or star = '*'). *)
begin (* skipstar *)
      if thefile^ <> '*' then begin
         writeln(output,' procedure skipstar: bad book');
         writeln(output,' "*" expected as first character on the line, but "',
                        thefile^,'" was found');
         halt
      end;
      get(thefile); (* skip the star *)

      if thefile^ <> ' ' then begin
         writeln(output,' procedure skipstar: bad book');
         writeln(output,' "* " expected on a line but "*',
                        thefile^,'" was found');
         halt
      end;
      get(thefile) (* skip the blank *)
end; (* skipstar *)
(* end module book.skipstar version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brreanum *)
procedure brreanum(var thefile: text; var reanum: real);
(* read a real number from the file *)
begin
      skipstar(thefile);
      readln(thefile,reanum);
end;
(* end module book.brreanum version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brnumber *)
procedure brnumber(var thefile: text; var num: integer);
(* read a number from the file *)
begin
      skipstar(thefile);
      readln(thefile,num)
end;
(* end module book.brnumber version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brname *)
procedure brname(var thefile: text; var nam: name);
(* read a name from the file *)
var   i: integer; (* an index to the name *)
      c: char; (* a character read *)
begin (* brname *)
      skipstar(thefile);
      with nam do begin
         length:=0;
         repeat
            length:=succ(length);
            read(thefile,c);
            letters[length] := c
         until (eoln(thefile)) or
               (length>=namelength) or
               (letters[length]=' ');
         if letters[length]=' ' then length:=length-1;
         if length<namelength
            then for i:=length+1 to namelength do letters[i]:=' '
      end;
      readln(thefile)
end; (* brname *)
(* end module book.brname version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brline *)
procedure brline(var thefile: text; var l: lineptr);
(* read a line from the file *)
var
      i,j: integer;
      acharacter: char;
begin
      skipstar(thefile);
      i:=0;
      while (not eoln(thefile)) do begin
         i:=succ(i);
         read(thefile,acharacter);
         l^.letters[i]:=acharacter
      end;
      if i<l^.length then for j:=i+1 to l^.length do l^.letters[j]:=' ';
      l^.length:=i;
      l^.next:=nil;
      readln(thefile)
end;
(* end module book.brline version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brdirect *)
procedure brdirect(var thefile: text; var direct: direction);
(* read a direction *)
var   ch: char;
begin
      skipstar(thefile);
      readln(thefile,ch);
      if ch='+' then direct:=plus
                else direct:=minus
end;
(* end module book.brdirect version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brconfig *)
procedure brconfig(var thefile: text; var config: configuration);
(* read a configuration *)
var   ch: char;
begin
      skipstar(thefile);
      readln(thefile,ch);
      if ch='l' then config:=linear
                else config:=circular
end;
(* end module book.brconfig version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brnotenumber *)
procedure brnotenumber(var thefile: text; var note: lineptr);
(* book note reading to obtain the number of the object.
the procedure returns the value of the number as a global.
(this is not such a good practice, but we are stuck with it for now.) *)
begin (* brnotenumber *)
      note:=nil;
      numbered := false;
      number := 0; (* force number to zero if there
         is no number at all *)
      (* the next character is n or * depending on whether there are notes *)
      if thefile^ = 'n' then begin
         readln(thefile);
         if thefile^ <> 'n' then begin
            skipstar(thefile);
            if not eoln(thefile) then begin
               if thefile^ = '#' then begin
                  numbered := true;
                  get(thefile); (* move past the number symbol *)
                  read(thefile,number);
               end
            end;
            repeat
               readln(thefile)
            until thefile^ = 'n';
            readln(thefile)
         end
         else readln(thefile)
      end
end; (* brnotenumber *)
(* end module book.brnotenumber version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brnote *)
procedure brnote(var thefile: text; var note: lineptr);
(* read note key *)
var
      newnote: lineptr; (* the new note *)
      previousnote: lineptr; (* the last line of the notes *)
begin (* brnote *)
      note:=nil;
      if thefile^ = 'n' then begin (* enter note *)
         readln(thefile);
         if thefile^ <> 'n' then begin (* abort null note (n/n) *)
            getline(note);
            newnote:=note;
            while thefile^ <> 'n' do begin (* wait until end of note *)
               brline(thefile,newnote);
               previousnote:=newnote;
               (* get next note *)
               getline(newnote^.next);
               newnote:=newnote^.next;
            end;
            (* last note was not used, so: *)
            clearline(newnote);
            previousnote^.next:=nil;
            readln(thefile)
         end
         else readln(thefile)
      end
end; (* brnote *)
(* end module book.brnote version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brheader *)
procedure brheader(var thefile: text; var hea: header);
(* read the header of a key. *)
begin
      with hea do begin
         (* read key name *)
         brname(thefile,keynam);

         (* read full name *)
         getline(fulnam);
         brline(thefile,fulnam);

         (* read note key *)
         if readnumber then brnotenumber(thefile,note)
                       else brnote(thefile,note)
      end
end;
(* end module book.brheader version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brpiekey *)
procedure brpiekey(var thefile: text; var pie: piekey);
(* read piece key *)
begin
      with pie do begin
         brheader(thefile,hea);
         brreanum(thefile,mapbeg);
         brconfig(thefile,coocon);
         brdirect(thefile,coodir);
         brnumber(thefile,coobeg);
         brnumber(thefile,cooend);
         brconfig(thefile,piecon);
         brdirect(thefile,piedir);
         brnumber(thefile,piebeg);
         brnumber(thefile,pieend);
      end
end;
(* end module book.brpiekey version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brdna *)
procedure brdna(var thefile: text; var dna: dnaptr);
(* read in dna from thefile *)
(* note: if the dna were circularized, by linking the last dnastring
to the first, then the cleardna routine could not clear properly,
and would loop forever... there is no reason to do that, since a simple
mod function will allow one to access the circle. *)
var
      ch: char;
      workdna: dnaptr;
begin
      getdna(dna);
      workdna:=dna;
      ch:=getto(thefile,['d']);
      read(thefile,ch); (* skipstar *)
      while (ch = '*') do
      begin
         read(thefile,ch); (* skip blank *)
         repeat
            read(thefile,ch);
            if ch in ['a','c','g','t'] then begin
               if workdna^.length=dnamax then begin
                  getdna(workdna^.next);
                  workdna:=workdna^.next
               end;
               workdna^.length:=succ(workdna^.length);
               workdna^.part[workdna^.length]:=chartobase(ch)
            end
         until eoln(thefile);
         readln(thefile); (* go to next line *)
         read(thefile,ch); (* ch is either '*' or 'd' *)
      end;
      readln(thefile)
end;
(* end module book.brdna version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brpiece *)
procedure brpiece(var thefile: text; var pie: pieceptr);
(* read in a piece *)
begin
      brpiekey(thefile,pie^.key);
      if numbered or (not skipunnum)
         then brdna(thefile,pie^.dna)
end;
(* end module book.brpiece version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.brinit *)
procedure brinit(var book: text);
(* check that the book is ok to read, and
   set up the global variables for br routines *)
begin (* brinit *)
      (* halt if the book is bad (first word is 'halt') or the first
         character is not * *)
      reset(book);
      if not eof(book) then begin
         (* check for the date line *)
         if book^ <> '*' then begin
            if book^ <> 'h'
            then writeln(output, ' this is not the first line of a book:')
            else writeln(output, ' bad book:');
            write(output, ' ');

            while not (eoln(book) or eof(book)) do begin
               write(output, book^);
               get(book)
            end;
            writeln(output);
            halt
         end
      end
      else begin
         writeln(output, ' book is empty');
         halt
      end;

      (* initialize free storage *)
      freeline:=nil;
      freedna:=nil;

      readnumber:=true; (* usually we read in numbers for items *)
      number:=0; (* arbitrary value *)
      numbered:=false; (* the piece has no number (none yet read in) *)
      skipunnum:=false;
end; (* brinit *)
(* end module book.brinit version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* ************************************************************************ *)
(* end module package.brpiece version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.getpiece *)
procedure getpiece(var thefile: text; var pie: pieceptr);
(* move to and read in the next piece in the book *)
var   ch: char;
begin
      ch:=getto(thefile,['p']); (* get to the next p(iece) in the book *)
      if ch<>' ' then begin
         brpiece(thefile,pie);
         ch:=getto(thefile,['p']); (* read past closing p *)
      end
end;
(* end module book.getpiece version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* ************************************************************************ *)
(* end module package.getpiece version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module book.stepbase *)
function stepbase(startdna: dnaptr; var dna: dnaptr; var d: dnarange): base;
(* advance d by one base in dna and then return the base at the new d.
   (this means that one should initialize d to zero)
   if we go past the last base, we restart at startdna.
   note: d is not the number of the base... it is used as a
   record for stepbase.  do not mess with it, and do not use it to find
   out what base you are on.  use a separate counter.  *)
begin
      if (d=dnamax) or (d=dna^.length) then begin
         d:=1;
         dna:=dna^.next;
         if dna=nil then dna:=startdna
      end
      else d:=succ(d);
      stepbase:=dna^.part[d]
end;
(* end module book.stepbase version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module nextbase *)
procedure initnextbase(var book: text; var pie: pieceptr;
                       var lastbase, endofbook: boolean);
(* initialize variables for function nextbase.
   book is the book to be read,
   pie is the piece,
   lastbase is the flag that is true when we are at the
   last base of a piece,
   and endofbook is true if we are at the end of the book (see nextbase). *)
begin
      brinit(book);

      new(pie);
      with pie^ do begin
         with key.hea do begin
            fulnam:=nil;
            note:=nil
         end;
         dna:=nil
      end;

      lastbase:=true; (* this will trigger reading of the next piece *)
      if eof(book) then endofbook:=true
                   else endofbook:=false
end;

function nextbase(var book: text;  (* the book being read *)
(* the next variables can be ignored *)
                  var pie: pieceptr; (* the piece *)
                  var dnalink: dnaptr; (* the current link we are on *)
                  var dnalinkspot: dnarange; (* the spot in the dnalink *)
(* these are useful to the general user: *)
                  var dnaspot, (* integer in 1 to length, which base this is *)
                      length: integer; (* length of this piece *)
                  var lastbase, (* true if the base was the last one on
                                   the piece. *)
                      endofbook: boolean) (* true when we have reached
                                             the end of the book *)
                  : base;
(* the user simply declares variables for
   book, pie, dnalink, dnalinkspot (of the appropriate type)
note: you can convert the valuespot to published coordinates by
      pubcoords:= inttopie(dnaspot,pie);

warning: if the end of the book has been reached, then endofbook
is true, but the value returned by the function has no meaning.
*)
begin
      if not lastbase then begin
         nextbase:=stepbase(pie^.dna,dnalink,dnalinkspot);
         dnaspot:=succ(dnaspot);
         if dnaspot = length then lastbase:=true
      end
      else begin (* we are at the last base of the previous piece *)
         clearpiece(pie);
         getpiece(book,pie);
         if not eof(book) then begin
            dnalink:=pie^.dna;
            dnalinkspot:=0;
            dnaspot:=0;
            length:=piecelength(pie);
            lastbase:=false;
            endofbook:=false;
            nextbase:=nextbase(book,pie,dnalink,dnalinkspot,
                               dnaspot,length,lastbase,endofbook)
         end
         else begin
            endofbook:=true; (* we have reached the end of the book *)
            lastbase:=false; (* we are no longer at the last base *)
            nextbase:=a (* a fake value *)
         end
      end
end;
(* end module nextbase version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* ************************************************************************ *)
(* end module package.nextbase version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module copyaline *)
procedure copyaline(var fin, fout: text);
(* copy a line from file fin to file fout *)
begin (* copyaline *)
      while not eoln(fin) do begin
         fout^ := fin^;
         put(fout);
         get(fin)
      end;
      readln(fin);
      writeln(fout);
end; (* copyaline *)
(* end module copyaline version = 'delmod 6.60 91 Jan 11 tds/gds' *)

(* begin module bkdb.themain *)
procedure themain(var book, database: text);
(* the main procedure of the program *)
var
      (* these variables are all defined in nextbase *)
      pie: pieceptr;
      dnalink: dnaptr;
      dnalinkspot: dnarange;
      dnaspot, length: integer;
      lastbase, endofbook: boolean;

      (* this variable is needed to catch the value of nextbase,
         so that we can check that we have not reached the end of the book. *)
      c: char;
begin
   writeln(output,'bkdb ',version:4:2);

   reset(book);
   rewrite(database);
   copyaline(book,database);

   initnextbase(book,pie,lastbase,endofbook);

(*
   writeln(database,' demonstration of package.nextbase');
   writeln(database,' the bases of the book are given,',
                  ' followed by two numbers:');
   writeln(database,' the first is the internal coordinate of the base.');
   writeln(database,' the second is the published coordinate of the base.');
*)

   while not endofbook do begin
      c:=basetochar(
         nextbase(book,pie,dnalink,dnalinkspot,
                  dnaspot,length,lastbase,endofbook));
      if not endofbook
         then write(database,c);
      (* number is the current number of the piece (global variable) *)
      if lastbase
         then writeln(database,' p',number:1,' primer expt year month day')
   end
end;
(* end module bkdb.themain *)

begin
   themain(book, database);
1: end.