Re: Another "this should have triggered more rules" post

[mouss]

Skip wrote:

What would be a command line equivalent that I can test this expression against my current inbox in order to see if I would have had any FPs? Something like

for file in *; do egrep ^To:.*(?:,[^,]{1,80}){20} $file;done

but this will only check one line (the To: header is obviously many, many lines long) and generates a syntax error as is.

perl script.pl *

==== script.pl
#! perl

use strict;


my @files = @ARGV;


foreach my $_file (@files) {
    my %header = read_headers($_file) ;

    if ($header{"to"} =~ /(?:,[^,]{1,80}){100}/) {
        print "$_file: MATCH100\n";
    } elsif ($header{"to"} =~ /(?:,[^,]{1,80}){50}/) {
        print "$_file: MATCH50\n";
    } elsif ($header{"to"} =~ /(?:,[^,]{1,80}){20}/) {
        print "$_file: MATCH20\n";
    }


}


# This reads all the headers, should we need them
sub read_headers()
{
    my $_file = $_[0];

    my $cur_hdr = ":"; # invalid
    my %header = ();

    open (IN, $_file) or die "Cannot open $_file: [EMAIL PROTECTED]";
    while (<IN>) {
        # compress whitespace (also remove trailing space)
        $_ =~ s/\s+$//;
        $_ =~ s/\s+/ /g;

        # blank line: end of header
        if (! /\S/) {
            last;
        }

        # new header
        if (/^(\S+):/) {
            $cur_hdr = lc($1);
            $header{$cur_hdr} .= $';
            next;
        }

        # header continuation
        if (/^\s+/) {
            $header{$cur_hdr} .= $';
            next;
        }

        # missing blank line.
        last;
    }
    close(IN);

    return %header;
}