summaryrefslogtreecommitdiff
path: root/bin/hashl
blob: c444edf8b1ed669c075ab928e4032b5802376a3f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
#!/usr/bin/env perl
## Copyright © 2010 by Daniel Friesel <derf@finalrewind.org>
## License: WTFPL <http://sam.zoy.org/wtfpl>
##   0. You just DO WHAT THE FUCK YOU WANT TO.
use strict;
use warnings;
use 5.010;
use autodie;

use Cwd;
use Digest::SHA qw(sha1_hex);
use File::Find;
use Getopt::Long;
use Storable qw(nstore retrieve);
use Time::Progress;

my $base = getcwd();
my $rel_paths = 1;
my $read_size = (2 ** 20) * 4; # 4 MiB
my $db_file = "$base/.hashl.db";
my $total = 0;
my $cur = 0;
my $timer;

my $VERSION = '0.1';

my $db;

GetOptions(
	'd|database=s' => \$db_file,
);

my $action = $ARGV[0];

if (not defined $action) {
	die("Usage: $0 <action>\n");
}

if (-r $db_file) {
	$db = retrieve($db_file);
}

sub get_total {
	my $file = $File::Find::name;
	if (-f $file and $file ne $db_file) {
		$total++;
	}
}

sub drop_deleted {
	for my $file (keys %{$db}) {
		if (! -e $file) {
			delete $db->{$file};
		}
	}
}

sub hash_file {
	my ($file) = @_;
	my ($fh, $data);

	open($fh, '<', $file);
	binmode($fh);
	read($fh, $data, $read_size);
	close($fh);

	return sha1_hex($data);
}

sub is_in_list {
	my ($file) = @_;
	my $hash = hash_file($file);

	if (grep { $_->{'hash'} eq $hash } values %{$db}) {
		return 1;
	}
	return 0;
}


sub process_file {
	my $file = $File::Find::name;
	my $path = $file;
	my ($size, $mtime) = (stat($file))[7,9];

	local $| = 1;

	if (not -f $file or $file eq $db_file) {
		return;
	}

	$cur++;

	if ($rel_paths) {
		$file = substr($file, length($base) + 1);
	}

	print $timer->report("\r\e[2KUpdating: %p done, %L elapsed, %E remaining", $cur);

	if (exists($db->{$file}) and
			$db->{$file}->{'mtime'} == $mtime and
			$db->{$file}->{'size'} == $size ) {
		return;
	}

	$db->{$file} = {
		hash => hash_file($path),
		mtime => $mtime,
		size => $size,
	};

	if (($cur % 100) == 0) {
		nstore($db, $db_file);
	}
}

if ($action eq 'update') {

	drop_deleted();
	find(\&get_total, $base);

	$timer = Time::Progress->new();
	$timer->attr(
		min => 1,
		max => $total
	);

	find(\&process_file, $base);
	print "\n";
	nstore($db, $db_file);
}
elsif ($action eq 'list') {
	for my $name (sort keys %{$db}) {
		my $file = $db->{$name};
		printf("%s %s\n", $file->{'hash'}, $name);
	}
}
elsif ($action eq 'in-list') {
	if ($ARGV[1]) {
		exit (!is_in_list($ARGV[1]));
	}
	else {
		while (my $line = <STDIN>) {
			chomp $line;
			if (!is_in_list($line)) {
				say $line;
			}
		}
	}
}

__END__

=head1 NAME

B<hashl> - Create database with partial file hashes, check if other files are in it

=head1 SYNOPSIS

B<hashl> [B<-d> I<dbfile>] I<action> [I<args>]

=head1 DESCRIPTION

Actions:

=over

=item B<in-list> [I<file>]

Checks if I<file> is in the database.  Returns 0 if it is, 1 otherwise.

If I<file> is not specified, B<hashl> reads filenames from stdin and returns
those which are not already in the database.

=item B<update>

Update or create hash database.  Iterates over all files below the current
directory.

=back

=head1 OPTIONS

=over

=item B<-d> I<dbfile>

Use I<dbfile> instead of F<.hashl.db>

=back

=head1 CONFIGURATION

None, so far

=head1 DEPENDENCIES

=over

=item * autodie (included with perl E<gt>= 5.10.1)

=item * Digest::SHA

=item * Time::Progress

=back

=head1 BUGS AND LIMITATIONS

Unknown.  This is alpha software.

=head1 EXAMPLES

=head2 LEECHING

First, create a database of your local files:

C<< cd /media/videos; hashl update >>

Now, assume you have a (possibly slow) external share mounted at
F</tmp/mnt/ext>.  You do not want to copy all files to your disk and then use
B<fdupes> or similar to weed out the duplicates.  Since you just used B<hashl>
to create a database with the hashes of the first 4MB of all your files, you
can now use it to check if you (very probably) already have any remote file.
For that, you only need to leech the first 4MB of every file on the share, and
not the whole file.  For example:

C<< for f (/tmp/mnt/ext/**/*(.)); hashl in-list $f || cp -i $f
/media/videos/incoming/ >>

=head2 EXTERNAL HARD DISK

Personally, I have all my videos on an external hard disk, which I usually do
not carry with me.  So, when I get new videos, I put them into F<~/lib/videos>
on my netboo, and then later copy them to the external disk.  Of course, it
can always happen that I get a movie I already have, or forget to move
something from F<~/lib/videos> to the external disk, especially since I also
always have some stuff from the disk in F<~/lib/videos>.

However, I can use B<hashl> to conveniently solve this issue.  Run
periodically:

C<< cd /media/argon; hashl -d ~/lib/video/.argon update >>

Now, I always have a list of files on the external disk with me.  When I get a
new file:

C<< hashl -d ~/lib/video/.argon in-list $file >>

And to find out which files are not on the external disk:

C<< cd ~/lib/video; print -l **/*(.) | hashl -d .argon in-list >>

=head1 AUTHOR

Copyright (C) 2010 by Daniel Friesel E<lt>derf@finalrewind.orgE<gt>

=head1 LICENSE

  0. You just DO WHAT THE FUCK YOU WANT TO.