227
|
1 #!/usr/bin/perl -w
|
|
2 #
|
|
3 # A simple utility which will process each "*.txt" file inside a named
|
|
4 # directory.
|
|
5 #
|
|
6 # Any entries with a duplicate title will be alerted.
|
|
7 #
|
|
8 # Steve
|
|
9 #
|
|
10
|
|
11 use strict;
|
|
12 use warnings;
|
|
13
|
|
14
|
|
15 #
|
|
16 # Get the directory and ensure it exists.
|
|
17 #
|
|
18 my $dir = shift;
|
|
19 die "Usage: $0 directory" unless ( defined($dir) );
|
|
20 die "Not a directory : $dir" unless ( -d $dir );
|
|
21
|
|
22
|
|
23 #
|
|
24 # The hash of arrays
|
|
25 #
|
|
26 my $titles;
|
|
27
|
|
28
|
|
29 #
|
|
30 # Find the files.
|
|
31 #
|
|
32 foreach my $file ( sort( glob( $dir . "/*" ) ) )
|
|
33 {
|
|
34
|
|
35 #
|
|
36 # Skip non-files
|
|
37 #
|
|
38 next if ( -d $file );
|
|
39 next if ( $file =~ /~$/ );
|
|
40
|
|
41 #
|
|
42 # Title for this entry.
|
|
43 #
|
|
44 my $title = undef;
|
|
45
|
|
46 #
|
|
47 # Read each file, and look for the title.
|
|
48 #
|
|
49 open( IN, "<", $file )
|
|
50 or die "Failed to read $file - $!";
|
|
51 foreach my $line (<IN>)
|
|
52 {
|
|
53 $title = $2
|
|
54 if ( !defined($title)
|
|
55 && ( $line =~ /^(Subject|Title):(.*)/i ) );
|
|
56
|
|
57 }
|
|
58 close(IN);
|
|
59
|
|
60 #
|
|
61 # Get current entries we might have found with
|
|
62 # this title; and add on the new one.
|
|
63 #
|
|
64 my $a = $titles->{ $title };
|
|
65 push( @$a, $file );
|
|
66 $titles->{ $title } = $a;
|
|
67 }
|
|
68
|
|
69
|
|
70 #
|
|
71 # Now look for dupes
|
|
72 #
|
|
73 my $fail = 0;
|
|
74 foreach my $title ( keys %$titles )
|
|
75 {
|
|
76 my $a = $titles->{ $title };
|
|
77
|
|
78 if ( ( scalar @$a ) > 1 )
|
|
79 {
|
|
80 print "Title: $title\n";
|
|
81 foreach my $file (@$a)
|
|
82 {
|
|
83 print "\t" . $file . "\n";
|
|
84 }
|
|
85
|
|
86 $fail = 1;
|
|
87 }
|
|
88 }
|
|
89
|
|
90
|
|
91 exit($fail);
|