-
Notifications
You must be signed in to change notification settings - Fork 33
/
lzt2_file_compression.pl
executable file
·204 lines (161 loc) · 5.02 KB
/
lzt2_file_compression.pl
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
#!/usr/bin/perl
# Author: Daniel "Trizen" Șuteu
# License: GPLv3
# Created on: 21 May 2014
# Latest edit on: 28 May 2014
# Website: https://github.com/trizen
# A new type of LZ compression, featuring a very short decompression time.
use 5.010;
use strict;
use autodie;
use warnings;
use Getopt::Std qw(getopts);
use File::Basename qw(basename);
use constant {
PKGNAME => 'lzt2',
VERSION => '0.01',
FORMAT => 'lzt2',
};
use constant {
MIN => 9,
BUFFER => 2**16,
SIGNATURE => uc(FORMAT) . chr(1),
};
sub usage {
my ($code) = @_;
print <<"EOH";
usage: $0 [options] [input file] [output file]
options:
-e : extract
-i <filename> : input filename
-o <filename> : output filename
-r : rewrite output
-v : version number
-h : this message
examples:
$0 document.txt
$0 document.txt archive.${\FORMAT}
$0 archive.${\FORMAT} document.txt
$0 -e -i archive.${\FORMAT} -o document.txt
EOH
exit($code // 0);
}
sub version {
printf("%s %s\n", PKGNAME, VERSION);
exit;
}
sub main {
my %opt;
getopts('ei:o:vhr', \%opt);
$opt{h} && usage(0);
$opt{v} && version();
my ($input, $output) = @ARGV;
$input //= $opt{i} // usage(2);
$output //= $opt{o};
my $ext = qr{\.${\FORMAT}\z}io;
if ($opt{e} || $input =~ $ext) {
if (not defined $output) {
($output = basename($input)) =~ s{$ext}{}
|| die "$0: no output file specified!\n";
}
if (not $opt{r} and -e $output) {
print "'$output' already exists! -- Replace? [y/N] ";
<STDIN> =~ /^y/i || exit 17;
}
decompress($input, $output)
|| die "$0: error: decompression failed!\n";
}
elsif ($input !~ $ext || (defined($output) && $output =~ $ext)) {
$output //= basename($input) . '.' . FORMAT;
compress($input, $output)
|| die "$0: error: compression failed!\n";
}
else {
warn "$0: don't know what to do...\n";
usage(1);
}
}
sub valid_archive {
my ($fh) = @_;
if (read($fh, (my $sig), length(SIGNATURE), 0) == length(SIGNATURE)) {
$sig eq SIGNATURE || return;
}
return 1;
}
sub compress {
my ($input, $output) = @_;
# Open the input file
open my $fh, '<:raw', $input;
# Open the output file and write the archive signature
open my $out_fh, '>:raw', $output;
print {$out_fh} SIGNATURE;
while ((my $len = read($fh, (my $block), BUFFER)) > 0) {
my %dict;
foreach my $i (reverse(MIN .. 255)) {
for (my $lim = $len - $i * 2, my $j = 0 ; $j <= $lim ; $j++) {
if ((my $pos = index($block, substr($block, $j, $i), $j + $i)) != -1) {
if (not exists $dict{$pos} or $i > $dict{$pos}[1]) {
$dict{$pos} = [$j, $i];
}
}
else {
$j += int($i / MIN) - 1;
}
}
}
my @pairs;
my $last_pos = 0;
my $uncompressed = '';
for (my $i = 0 ; $i < $len ; $i++, $last_pos++) {
if (exists $dict{$i}) {
my ($key, $vlen) = @{$dict{$i}};
push @pairs, [$last_pos, $key, $vlen];
$i += $vlen - 1;
$last_pos = 0;
}
else {
$uncompressed .= substr($block, $i, 1);
}
}
my $uncomp_len = length($uncompressed);
printf("%3d -> %3d (%.2f%%)\n", $len, $uncomp_len, ($len - $uncomp_len) / $len * 100);
print {$out_fh} pack('S', $uncomp_len - 1), pack('S', scalar @pairs), (map { pack('SSC', @{$_}) } @pairs), $uncompressed;
}
close $fh;
close $out_fh;
}
sub decompress {
my ($input, $output) = @_;
# Open and validate the input file
open my $fh, '<:raw', $input;
valid_archive($fh) || die "$0: file `$input' is not a \U${\FORMAT}\E archive!\n";
# Open the output file
open my $out_fh, '>:raw', $output;
while (read($fh, (my $len_byte), 2) > 0) {
read($fh, (my $groups_byte), 2);
my @dict;
for my $i (1 .. unpack('S', $groups_byte)) {
read($fh, (my $positions), 5);
push @dict, [unpack('SSC', $positions)];
}
my $len = unpack('S', $len_byte) + 1;
read($fh, (my $block), $len);
my $last_pos = 0;
my $decompressed = '';
for (my $i = 0 ; $i <= $len ; $i++) {
if (@dict and ($i - $last_pos == $dict[0][0])) {
$decompressed .= substr($decompressed, $dict[0][1], $dict[0][2]);
$last_pos = --$i;
shift @dict;
}
else {
$decompressed .= substr($block, $i, 1);
}
}
print {$out_fh} $decompressed;
}
close $fh;
close $out_fh;
}
main();
exit(0);