#!perl

=head2 NAME

Find commas in 650s

=head2

Looks for commas in file of extracted fields.
Best for 650 fields.
The result can then be scanned for personal names that should be 600s.
Input file should be result (export file) from fieldextraction.pl or similar file.
Output file is list of lines matching the desired regular expression.

=cut 

print "Input file: ";
$inputfile = <>;
chomp $inputfile;
$inputfile =~ s/^\"(.*)\"$/$1/;
print "Export file: ";
$exportfile = <>;
chomp $exportfile;
$exportfile =~ s/^\"(.*)\"$/$1/;

open (IN, "<$inputfile") || die ("can't open in");
open (OUT, ">$exportfile") || die ("can't open out");
my $linecount = 0;
while (my $line = <IN>) {
chomp $line;
#remove extra spaces between tabs
$line =~ s/\t\s{7}\@/\t\@/g;
#remove count, tag, and first subfield code
$line =~ s/^\d+?\t\d{3}\s[ \d][ \d]\s\@\w\t//;

#use 'if' for positive, 'unless' for negative, or 'if' + !~
if ($line =~ /,/) {
print OUT "$line\n";
$linecount++;
}
}
close IN;
close OUT;
print "$linecount lines identified\n";
print "Press Enter to quit";
<>;