X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2FDigest.pm;h=eb7469a7d71aa0be96b80ff796166cea976adfe6;hb=002b9267a385cf8ff0e7534241cdf3798da8636c;hp=4ad93ff40a1afd351499dd9c3bc6c066cb9cbda9;hpb=70ee44090a3faf48295f65df1a1fe1c53d04be10;p=p5sagit%2Fp5-mst-13.2.git diff --git a/lib/Digest.pm b/lib/Digest.pm index 4ad93ff..eb7469a 100644 --- a/lib/Digest.pm +++ b/lib/Digest.pm @@ -3,25 +3,46 @@ package Digest; use strict; use vars qw($VERSION %MMAP $AUTOLOAD); -$VERSION = "1.01"; +$VERSION = "1.14"; %MMAP = ( - "SHA-1" => "Digest::SHA1", + "SHA-1" => ["Digest::SHA1", ["Digest::SHA", 1], ["Digest::SHA2", 1]], + "SHA-224" => [["Digest::SHA", 224]], + "SHA-256" => [["Digest::SHA", 256], ["Digest::SHA2", 256]], + "SHA-384" => [["Digest::SHA", 384], ["Digest::SHA2", 384]], + "SHA-512" => [["Digest::SHA", 512], ["Digest::SHA2", 512]], "HMAC-MD5" => "Digest::HMAC_MD5", "HMAC-SHA-1" => "Digest::HMAC_SHA1", + "CRC-16" => [["Digest::CRC", type => "crc16"]], + "CRC-32" => [["Digest::CRC", type => "crc32"]], + "CRC-CCITT" => [["Digest::CRC", type => "crcccitt"]], ); sub new { shift; # class ignored my $algorithm = shift; - my $class = $MMAP{$algorithm} || "Digest::$algorithm"; - no strict 'refs'; - unless (exists ${"$class\::"}{"VERSION"}) { - eval "require $class"; - die $@ if $@; + my $impl = $MMAP{$algorithm} || do { + $algorithm =~ s/\W+//; + "Digest::$algorithm"; + }; + $impl = [$impl] unless ref($impl); + my $err; + for (@$impl) { + my $class = $_; + my @args; + ($class, @args) = @$class if ref($class); + no strict 'refs'; + unless (exists ${"$class\::"}{"VERSION"}) { + eval "require $class"; + if ($@) { + $err ||= $@; + next; + } + } + return $class->new(@args, @_); } - $class->new(@_); + die $err; } sub AUTOLOAD @@ -37,15 +58,15 @@ __END__ =head1 NAME -Digest:: - Modules that calculate message digests +Digest - Modules that calculate message digests =head1 SYNOPSIS - $md2 = Digest->MD2; - $md5 = Digest->MD5; - - $sha1 = Digest->SHA1; + $md5 = Digest->new("MD5"); $sha1 = Digest->new("SHA-1"); + $sha256 = Digest->new("SHA-256"); + $sha384 = Digest->new("SHA-384"); + $sha512 = Digest->new("SHA-512"); $hmac = Digest->HMAC_MD5($key); @@ -55,15 +76,22 @@ The C modules calculate digests, also called "fingerprints" or "hashes", of some data, called a message. The digest is (usually) some small/fixed size string. The actual size of the digest depend of the algorithm used. The message is simply a sequence of arbitrary -bytes. +bytes or bits. An important property of the digest algorithms is that the digest is I to change if the message change in some way. Another -property is that digest functions are one-way functions, i.e. it +property is that digest functions are one-way functions, that is it should be I to find a message that correspond to some given digest. Algorithms differ in how "likely" and how "hard", as well as how efficient they are to compute. +Note that the properties of the algorithms change over time, as the +algorithms are analyzed and machines grow faster. If your application +for instance depends on it being "impossible" to generate the same +digest for a different message it is wise to make it easy to plug in +stronger algorithms as the one used grow weaker. Using the interface +documented here should make it easy to change algorithms later. + All C modules provide the same programming interface. A functional interface for simple use, as well as an object oriented interface that can handle messages of arbitrary length and which can @@ -80,7 +108,7 @@ or embedding in places that can't handle arbitrary data. =item I -A twice as long string of (lowercase) hexadecimal digits. +A twice as long string of lowercase hexadecimal digits. =item I @@ -122,9 +150,10 @@ name of the digest algorithm you want to use. The two first forms are simply syntactic sugar which automatically load the right module on first use. The second form allow you to use algorithm names which contains letters which are not legal perl -identifiers, e.g. "SHA-1". +identifiers, e.g. "SHA-1". If no implementation for the given algorithm +can be found, then an exception is raised. -If new() is called as a instance method (i.e. $ctx->new) it will just +If new() is called as an instance method (i.e. $ctx->new) it will just reset the state the object to the state of a newly created object. No new object is created in this case, and the return value is the reference to the object (i.e. $ctx). @@ -138,17 +167,43 @@ a reference to the copy. This is just an alias for $ctx->new. -=item $ctx->add($data,...) +=item $ctx->add( $data, ... ) The $data provided as argument are appended to the message we calculate the digest for. The return value is the $ctx object itself. -=item $ctx->addfile($io_handle) +=item $ctx->addfile( $io_handle ) The $io_handle is read until EOF and the content is appended to the message we calculate the digest for. The return value is the $ctx object itself. +=item $ctx->add_bits( $data, $nbits ) + +=item $ctx->add_bits( $bitstring ) + +The bits provided are appended to the message we calculate the digest +for. The return value is the $ctx object itself. + +The two argument form of add_bits() will add the first $nbits bits +from data. For the last potentially partial byte only the high order +C<< $nbits % 8 >> bits are used. If $nbits is greater than C<< +length($data) * 8 >>, then this method would do the same as C<< +$ctx->add($data) >>, that is $nbits is silently ignored. + +The one argument form of add_bits() takes a $bitstring of "1" and "0" +chars as argument. It's a shorthand for C<< $ctx->add_bits(pack("B*", +$bitstring), length($bitstring)) >>. + +This example shows two calls that should have the same effect: + + $ctx->add_bits("111100001010"); + $ctx->add_bits("\xF0\xA0", 12); + +Most digest algorithms are byte based. For those it is not possible +to add bits that are not a multiple of 8, and the add_bits() method +will croak if you try. + =item $ctx->digest Return the binary digest for the message. @@ -157,7 +212,7 @@ Note that the C operation is effectively a destructive, read-once operation. Once it has been performed, the $ctx object is automatically C and can be used to calculate another digest value. Call $ctx->clone->digest if you want to calculate the digest -without reseting the digest state. +without resetting the digest state. =item $ctx->hexdigest @@ -170,9 +225,46 @@ string. =back +=head1 Digest speed + +This table should give some indication on the relative speed of +different algorithms. It is sorted by throughput based on a benchmark +done with of some implementations of this API: + + Algorithm Size Implementation MB/s + + MD4 128 Digest::MD4 v1.3 165.0 + MD5 128 Digest::MD5 v2.33 98.8 + SHA-256 256 Digest::SHA2 v1.1.0 66.7 + SHA-1 160 Digest::SHA v4.3.1 58.9 + SHA-1 160 Digest::SHA1 v2.10 48.8 + SHA-256 256 Digest::SHA v4.3.1 41.3 + Haval-256 256 Digest::Haval256 v1.0.4 39.8 + SHA-384 384 Digest::SHA2 v1.1.0 19.6 + SHA-512 512 Digest::SHA2 v1.1.0 19.3 + SHA-384 384 Digest::SHA v4.3.1 19.2 + SHA-512 512 Digest::SHA v4.3.1 19.2 + Whirlpool 512 Digest::Whirlpool v1.0.2 13.0 + MD2 128 Digest::MD2 v2.03 9.5 + + Adler-32 32 Digest::Adler32 v0.03 1.3 + CRC-16 16 Digest::CRC v0.05 1.1 + CRC-32 32 Digest::CRC v0.05 1.1 + MD5 128 Digest::Perl::MD5 v1.5 1.0 + CRC-CCITT 16 Digest::CRC v0.05 0.8 + +These numbers was achieved Apr 2004 with ActivePerl-5.8.3 running +under Linux on a P4 2.8 GHz CPU. The last 5 entries differ by being +pure perl implementations of the algorithms, which explains why they +are so slow. + =head1 SEE ALSO -L, L, L, L +L, L, L, +L, L, L, L, +L, L, L, L + +New digest implementations should consider subclassing from L. L @@ -183,4 +275,10 @@ Gisle Aas The C interface is based on the interface originally developed by Neil Winton for his C module. +This library is free software; you can redistribute it and/or +modify it under the same terms as Perl itself. + + Copyright 1998-2001,2003-2004 Gisle Aas. + Copyright 1995-1996 Neil Winton. + =cut