Commit | Line | Data |
---|---|---|
3357b1b1 JH |
1 | package Digest; |
2 | ||
3 | use strict; | |
4 | use vars qw($VERSION %MMAP $AUTOLOAD); | |
5 | ||
a9acc356 | 6 | $VERSION = "1.10"; |
3357b1b1 JH |
7 | |
8 | %MMAP = ( | |
b12d758c NC |
9 | "SHA-1" => ["Digest::SHA1", ["Digest::SHA", 1], ["Digest::SHA2", 1]], |
10 | "SHA-256" => [["Digest::SHA", 256], ["Digest::SHA2", 256]], | |
11 | "SHA-384" => [["Digest::SHA", 384], ["Digest::SHA2", 384]], | |
12 | "SHA-512" => [["Digest::SHA", 512], ["Digest::SHA2", 512]], | |
3357b1b1 JH |
13 | "HMAC-MD5" => "Digest::HMAC_MD5", |
14 | "HMAC-SHA-1" => "Digest::HMAC_SHA1", | |
371dcd31 RGS |
15 | "CRC-16" => [["Digest::CRC", type => "crc16"]], |
16 | "CRC-32" => [["Digest::CRC", type => "crc32"]], | |
17 | "CRC-CCITT" => [["Digest::CRC", type => "crcccitt"]], | |
3357b1b1 JH |
18 | ); |
19 | ||
20 | sub new | |
21 | { | |
22 | shift; # class ignored | |
23 | my $algorithm = shift; | |
b12d758c NC |
24 | my $impl = $MMAP{$algorithm} || do { |
25 | $algorithm =~ s/\W+//; | |
26 | "Digest::$algorithm"; | |
27 | }; | |
28 | $impl = [$impl] unless ref($impl); | |
29 | my $err; | |
30 | for (@$impl) { | |
31 | my $class = $_; | |
32 | my @args; | |
33 | ($class, @args) = @$class if ref($class); | |
34 | no strict 'refs'; | |
35 | unless (exists ${"$class\::"}{"VERSION"}) { | |
36 | eval "require $class"; | |
37 | if ($@) { | |
38 | $err ||= $@; | |
39 | next; | |
40 | } | |
41 | } | |
42 | return $class->new(@args, @_); | |
3357b1b1 | 43 | } |
b12d758c | 44 | die $err; |
3357b1b1 JH |
45 | } |
46 | ||
47 | sub AUTOLOAD | |
48 | { | |
49 | my $class = shift; | |
50 | my $algorithm = substr($AUTOLOAD, rindex($AUTOLOAD, '::')+2); | |
51 | $class->new($algorithm, @_); | |
52 | } | |
53 | ||
54 | 1; | |
55 | ||
56 | __END__ | |
57 | ||
58 | =head1 NAME | |
59 | ||
e19eb3c1 | 60 | Digest - Modules that calculate message digests |
3357b1b1 JH |
61 | |
62 | =head1 SYNOPSIS | |
63 | ||
e19eb3c1 | 64 | $md5 = Digest->new("MD5"); |
3357b1b1 | 65 | $sha1 = Digest->new("SHA-1"); |
e19eb3c1 NC |
66 | $sha256 = Digest->new("SHA-256"); |
67 | $sha384 = Digest->new("SHA-384"); | |
68 | $sha512 = Digest->new("SHA-512"); | |
3357b1b1 JH |
69 | |
70 | $hmac = Digest->HMAC_MD5($key); | |
71 | ||
72 | =head1 DESCRIPTION | |
73 | ||
74 | The C<Digest::> modules calculate digests, also called "fingerprints" | |
75 | or "hashes", of some data, called a message. The digest is (usually) | |
76 | some small/fixed size string. The actual size of the digest depend of | |
77 | the algorithm used. The message is simply a sequence of arbitrary | |
b12d758c | 78 | bytes or bits. |
3357b1b1 JH |
79 | |
80 | An important property of the digest algorithms is that the digest is | |
81 | I<likely> to change if the message change in some way. Another | |
82 | property is that digest functions are one-way functions, i.e. it | |
83 | should be I<hard> to find a message that correspond to some given | |
84 | digest. Algorithms differ in how "likely" and how "hard", as well as | |
85 | how efficient they are to compute. | |
86 | ||
87 | All C<Digest::> modules provide the same programming interface. A | |
88 | functional interface for simple use, as well as an object oriented | |
89 | interface that can handle messages of arbitrary length and which can | |
90 | read files directly. | |
91 | ||
92 | The digest can be delivered in three formats: | |
93 | ||
94 | =over 8 | |
95 | ||
96 | =item I<binary> | |
97 | ||
98 | This is the most compact form, but it is not well suited for printing | |
99 | or embedding in places that can't handle arbitrary data. | |
100 | ||
101 | =item I<hex> | |
102 | ||
e19eb3c1 | 103 | A twice as long string of lowercase hexadecimal digits. |
3357b1b1 JH |
104 | |
105 | =item I<base64> | |
106 | ||
107 | A string of portable printable characters. This is the base64 encoded | |
108 | representation of the digest with any trailing padding removed. The | |
109 | string will be about 30% longer than the binary version. | |
110 | L<MIME::Base64> tells you more about this encoding. | |
111 | ||
112 | =back | |
113 | ||
114 | ||
115 | The functional interface is simply importable functions with the same | |
116 | name as the algorithm. The functions take the message as argument and | |
117 | return the digest. Example: | |
118 | ||
119 | use Digest::MD5 qw(md5); | |
120 | $digest = md5($message); | |
121 | ||
122 | There are also versions of the functions with "_hex" or "_base64" | |
123 | appended to the name, which returns the digest in the indicated form. | |
124 | ||
125 | =head1 OO INTERFACE | |
126 | ||
127 | The following methods are available for all C<Digest::> modules: | |
128 | ||
129 | =over 4 | |
130 | ||
131 | =item $ctx = Digest->XXX($arg,...) | |
132 | ||
133 | =item $ctx = Digest->new(XXX => $arg,...) | |
134 | ||
135 | =item $ctx = Digest::XXX->new($arg,...) | |
136 | ||
137 | The constructor returns some object that encapsulate the state of the | |
138 | message-digest algorithm. You can add data to the object and finally | |
139 | ask for the digest. The "XXX" should of course be replaced by the proper | |
140 | name of the digest algorithm you want to use. | |
141 | ||
142 | The two first forms are simply syntactic sugar which automatically | |
143 | load the right module on first use. The second form allow you to use | |
144 | algorithm names which contains letters which are not legal perl | |
897ff129 RGS |
145 | identifiers, e.g. "SHA-1". If no implementation for the given algorithm |
146 | can be found, then an exception is raised. | |
3357b1b1 | 147 | |
67859229 | 148 | If new() is called as an instance method (i.e. $ctx->new) it will just |
3357b1b1 JH |
149 | reset the state the object to the state of a newly created object. No |
150 | new object is created in this case, and the return value is the | |
151 | reference to the object (i.e. $ctx). | |
152 | ||
70ee4409 JH |
153 | =item $other_ctx = $ctx->clone |
154 | ||
155 | The clone method creates a copy of the digest state object and returns | |
156 | a reference to the copy. | |
157 | ||
3357b1b1 JH |
158 | =item $ctx->reset |
159 | ||
160 | This is just an alias for $ctx->new. | |
161 | ||
e19eb3c1 | 162 | =item $ctx->add( $data, ... ) |
3357b1b1 JH |
163 | |
164 | The $data provided as argument are appended to the message we | |
165 | calculate the digest for. The return value is the $ctx object itself. | |
166 | ||
e19eb3c1 | 167 | =item $ctx->addfile( $io_handle ) |
3357b1b1 JH |
168 | |
169 | The $io_handle is read until EOF and the content is appended to the | |
170 | message we calculate the digest for. The return value is the $ctx | |
171 | object itself. | |
172 | ||
e19eb3c1 | 173 | =item $ctx->add_bits( $data, $nbits ) |
b12d758c | 174 | |
e19eb3c1 | 175 | =item $ctx->add_bits( $bitstring ) |
b12d758c NC |
176 | |
177 | The bits provided are appended to the message we calculate the digest | |
178 | for. The return value is the $ctx object itself. | |
179 | ||
180 | The two argument form of add_bits() will add the first $nbits bits | |
181 | from data. For the last potentially partial byte only the high order | |
182 | C<< $nbits % 8 >> bits are used. If $nbits is greater than C<< | |
183 | length($data) * 8 >>, then this method would do the same as C<< | |
184 | $ctx->add($data) >>, i.e. $nbits is silently ignored. | |
185 | ||
186 | The one argument form of add_bits() takes a $bitstring of "1" and "0" | |
187 | chars as argument. It's a shorthand for C<< $ctx->add_bits(pack("B*", | |
188 | $bitstring), length($bitstring)) >>. | |
189 | ||
190 | This example shows two calls that should have the same effect: | |
191 | ||
192 | $ctx->add_bits("111100001010"); | |
193 | $ctx->add_bits("\xF0\xA0", 12); | |
194 | ||
195 | Most digest algorithms are byte based. For those it is not possible | |
196 | to add bits that are not a multiple of 8, and the add_bits() method | |
197 | will croak if you try. | |
198 | ||
3357b1b1 JH |
199 | =item $ctx->digest |
200 | ||
201 | Return the binary digest for the message. | |
202 | ||
203 | Note that the C<digest> operation is effectively a destructive, | |
204 | read-once operation. Once it has been performed, the $ctx object is | |
205 | automatically C<reset> and can be used to calculate another digest | |
70ee4409 JH |
206 | value. Call $ctx->clone->digest if you want to calculate the digest |
207 | without reseting the digest state. | |
3357b1b1 JH |
208 | |
209 | =item $ctx->hexdigest | |
210 | ||
211 | Same as $ctx->digest, but will return the digest in hexadecimal form. | |
212 | ||
213 | =item $ctx->b64digest | |
214 | ||
215 | Same as $ctx->digest, but will return the digest as a base64 encoded | |
216 | string. | |
217 | ||
218 | =back | |
219 | ||
e19eb3c1 NC |
220 | =head1 Digest speed |
221 | ||
222 | This table should give some indication on the relative speed of | |
223 | different algorithms. It is sorted by throughput based on a benchmark | |
224 | done with of some implementations of this API: | |
225 | ||
371dcd31 RGS |
226 | Algorithm Size Implementation MB/s |
227 | ||
228 | MD4 128 Digest::MD4 v1.3 165.0 | |
229 | MD5 128 Digest::MD5 v2.33 98.8 | |
230 | SHA-256 256 Digest::SHA2 v1.1.0 66.7 | |
231 | SHA-1 160 Digest::SHA v4.3.1 58.9 | |
232 | SHA-1 160 Digest::SHA1 v2.10 48.8 | |
233 | SHA-256 256 Digest::SHA v4.3.1 41.3 | |
234 | Haval-256 256 Digest::Haval256 v1.0.4 39.8 | |
235 | SHA-384 384 Digest::SHA2 v1.1.0 19.6 | |
236 | SHA-512 512 Digest::SHA2 v1.1.0 19.3 | |
237 | SHA-384 384 Digest::SHA v4.3.1 19.2 | |
238 | SHA-512 512 Digest::SHA v4.3.1 19.2 | |
239 | Whirlpool 512 Digest::Whirlpool v1.0.2 13.0 | |
240 | MD2 128 Digest::MD2 v2.03 9.5 | |
241 | ||
242 | Adler-32 32 Digest::Adler32 v0.03 1.3 | |
243 | CRC-16 16 Digest::CRC v0.05 1.1 | |
244 | CRC-32 32 Digest::CRC v0.05 1.1 | |
245 | MD5 128 Digest::Perl::MD5 v1.5 1.0 | |
246 | CRC-CCITT 16 Digest::CRC v0.05 0.8 | |
247 | ||
248 | These numbers was achieved Apr 2004 with ActivePerl-5.8.3 running | |
249 | under Linux on a P4 2.8 GHz CPU. The last 5 entries differ by being | |
e19eb3c1 NC |
250 | pure perl implementations of the algorithms, which explains why they |
251 | are so slow. | |
252 | ||
3357b1b1 JH |
253 | =head1 SEE ALSO |
254 | ||
371dcd31 RGS |
255 | L<Digest::Adler32>, L<Digest::CRC>, L<Digest::Haval256>, |
256 | L<Digest::HMAC>, L<Digest::MD2>, L<Digest::MD4>, L<Digest::MD5>, | |
257 | L<Digest::SHA>, L<Digest::SHA1>, L<Digest::SHA2>, L<Digest::Whirlpool> | |
e19eb3c1 NC |
258 | |
259 | New digest implementations should consider subclassing from L<Digest::base>. | |
3357b1b1 JH |
260 | |
261 | L<MIME::Base64> | |
262 | ||
263 | =head1 AUTHOR | |
264 | ||
265 | Gisle Aas <gisle@aas.no> | |
266 | ||
267 | The C<Digest::> interface is based on the interface originally | |
268 | developed by Neil Winton for his C<MD5> module. | |
269 | ||
e19eb3c1 NC |
270 | This library is free software; you can redistribute it and/or |
271 | modify it under the same terms as Perl itself. | |
272 | ||
897ff129 | 273 | Copyright 1998-2001,2003-2004 Gisle Aas. |
e19eb3c1 NC |
274 | Copyright 1995-1996 Neil Winton. |
275 | ||
3357b1b1 | 276 | =cut |