#!/usr/bin/perl
#
# parse the pubmed links to searchable format
#
use warnings;
use strict;
use File::Basename;

sub parse_pub ($) {
  my $string = shift @_;
  local $_;

  if ($string =~ m/^.+?:.+?\. (.+)+$/) {
    $_ = $1;
    if (m/(.+?) (\d+): (\d+)-\d+, (\d+)./) {
      return "${1}[JO] AND ${4}[DP] AND ${2}[VI] AND ${3}[PG]";
    } else {
      return undef;
    }
  }
  return;
}

my $omimf = shift @ARGV || "-";

open (INF,"$omimf") or die "Unable to open '$omimf': $!";

my $within = 0;		# within field area
my $key = "";		# current type
my $i = 1;		# line number
my $space = 0;		# was last line space
my $extra = "";		# entries are in multiple lines

while (<INF>) {
  chomp;
  s/\r$//;
  !m/\*FIELD\* RF/ && !$within && next;
  if (m/\*FIELD\*/ && $within) {
    $within = 0;
    exit;
  } elsif (m/\*FIELD\* RF/) {
    $within = 1;
  } else {
    if (!$_) {
      $space = 1;
    } else {
      $space = 0;
    }
    if ($space) {
      chop ($extra);
      if ($extra =~ m/^.+?:.+?\. (.+)+$/) {
        $extra = $1;
        # print "$string,$1\n";
        if ($extra =~ m/(.+?) (\d+): (\d+)-\d+, (\d+)./) {
          print "${1}[JO] AND ${4}[DP] AND ${2}[VI] AND ${3}[PG]\n";
        } else {
          # return undef;
        }
      }
#       if ($key = parse_pub($extra)) {
#         # print "$key\n";
#       } else {
#         print "$extra\n";
#       }
    } else {
      $extra .= "$_ ";
    }
  } # main else
}

exit;