#!/usr/bin/perl -w

# Print http results for all dlib urls on the first trial

use strict;

my $fn = "dlib_and_doi_urls_uniq.txt";
my $first_result = "http_responses/2004-09-09result.txt";

my $total_urls = 0;
my $total_avail = 0;
my $total_unavail = 0;

open(F, $fn) || die("Can't open $fn: $!");
while (my $url = <F>) {
	chomp($url);

	# See if url was found last time
	my $result = found_url($url);
	if ($result == -1) {
		#print "Problem: can't find [$url]\n";
		# urls we couldn't find are just the article urls
		# that we can say were definately available
		$total_avail++;
		print "$url\t1\n";
	}
	elsif ($result == 1) {
		$total_avail++;
		print "$url\t1\n";
	}
	else {
		$total_unavail++;
		print "$url\t0\n";
	}
	$total_urls++;
}
close F;


print "\nTotal urls:  $total_urls\n";
print "Total available: $total_avail (" . ($total_avail/$total_urls) . " %)\n";
print "Total not available: $total_unavail (". ($total_unavail/$total_urls) . " %)\n";



# returns 1 if url was available, 0 if not, -1
# if not found

sub found_url {

        my $url_find = shift;

        my $file;

        open(FILE, $first_result) || die("Can't open $first_result: $!\n");
        while (my $line = <FILE>) {
                chomp($line);
		my ($url, $len, $code) = split(/ /, $line);
		if ($url eq $url_find) {
			$code = 200 if ($code == 304 || $code == 301 || $code == 302);
			$code = "200-0" if ($code == 200 && $len == 0);
			if ($code eq '200') {
				close FILE;
				return 1;
			}
			else {
				close FILE;
				return 0;
			}
		}
        }
        close FILE;

        # never found url
        return -1;
}