#!/usr/bin/perl
#
# parse publications strings
#
use warnings;
use strict;
use Data::Dumper;

my $TITLE = 'title';
my $YEAR = 'year';
my $START_PAGE = 'start_page';
my $END_PAGE = 'end_page';
my $JOURNAL = 'journal';
my $TYPE = 'type';
my $AUTHORS = 'authors';
my $VOLUME = 'volume';

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

  # pos($string) = 0;
  # if ($string =~ m/^\d+\.([^:]+): ?((?:[^.]+\([^\)]+\)[^.?!]+|[^.?!]+)[.?!]) ?(\([\w.]+\))? (.+)$/i) {
  # if ($string =~ m/^([^:]+): (.+?[.?!]) (\(\w+\.?\) )?([A-Z](?=\w*[. ]).+)$/i) {
  # while ($string =~ m/\G^\d+\. ([^:]+): (.+?[.?!]) (\(\w+.?\) )?(?=[A-Z]\w+[. ])([A-Z].+)$/g) {
  while ($string =~ m/^\d+\. ([^:]+): (.+?[.?!]) (\(\w+.?\) )?(?=[A-Z]\w+[. ])([A-Z].+)$/g) {
    my $authors = $1;
    $ret{$TITLE} = $2;
    if ($4) {
      $ret{$TYPE} = $3;
      $_ = $4;
    } else {
      $_ = $3;
    }
    if (m/^([^:]+) ([\w()]+): (\d+)-(\d+), (\d+)\./) {
      $ret{$JOURNAL}=$1;
      $ret{$VOLUME}=$2;
      $ret{$START_PAGE}=$3;
      $ret{$END_PAGE}=$4;
      $ret{$YEAR}=$5;
      my @array = split (/ /,$ret{$JOURNAL});
      # last if (10 > scalar(@{[split (/ /,$ret{$JOURNAL})]}));
      last if (scalar(@array) < 10);
    } else {
      last;
    }
  }
  return %ret;
}

my $line = "110. Wunder, E.; Burghardt, U.; Lang, B.; Hamilton, L.: Fanconi's anemia: anomaly of enzyme passage through the nuclear membrane? Anomalous intracellular distribution of topoisomerase activity in placental extracts in a case of Fanconi's anemia. Hum. Genet. 58: 149-155, 1981.";

print "$line\n";
my %pub = parse_pub($line);
#print Dumper(%pub);
print "J:$pub{$JOURNAL}\n\n";
exit;