use strict;
use warnings;
+our $VERSION = q(0.99_03);
+
use Fcntl qw( :DEFAULT :flock :seek );
+
+use Clone::Any '_clone_data';
use Digest::MD5 ();
+use FileHandle::Fmode ();
use Scalar::Util ();
use DBM::Deep::Engine;
use DBM::Deep::File;
-use vars qw( $VERSION );
-$VERSION = q(0.99_01);
-
##
# Setup constants for users to pass to new()
##
-sub TYPE_HASH () { DBM::Deep::Engine->SIG_HASH }
-sub TYPE_ARRAY () { DBM::Deep::Engine->SIG_ARRAY }
+sub TYPE_HASH () { DBM::Deep::Engine->SIG_HASH }
+sub TYPE_ARRAY () { DBM::Deep::Engine->SIG_ARRAY }
sub _get_args {
my $proto = shift;
my $class = shift;
my ($args) = @_;
- $args->{fileobj} = DBM::Deep::File->new( $args )
- unless exists $args->{fileobj};
+ $args->{storage} = DBM::Deep::File->new( $args )
+ unless exists $args->{storage};
# locking implicitly enables autoflush
if ($args->{locking}) { $args->{autoflush} = 1; }
parent => undef,
parent_key => undef,
- fileobj => undef,
+ storage => undef,
}, $class;
$self->{engine} = DBM::Deep::Engine->new( { %{$args}, obj => $self } );
$self->{$param} = $args->{$param};
}
- $self->{engine}->setup_fh( $self );
+ $self->_engine->setup_fh( $self );
- $self->{fileobj}->set_db( $self );
+ $self->_storage->set_db( $self );
return $self;
}
sub lock {
my $self = shift->_get_self;
- return $self->_fileobj->lock( $self, @_ );
+ return $self->_storage->lock( $self, @_ );
}
sub unlock {
my $self = shift->_get_self;
- return $self->_fileobj->unlock( $self, @_ );
+ return $self->_storage->unlock( $self, @_ );
}
sub _copy_value {
$self->_copy_node( $temp );
$self->unlock();
+ # This will always work because $self, after _get_self() is a HASH
+ if ( $self->{parent} ) {
+ my $c = Scalar::Util::blessed(
+ $self->{parent}->get($self->{parent_key})
+ );
+ if ( $c && !$c->isa( 'DBM::Deep' ) ) {
+ bless $temp, $c;
+ }
+ }
+
return $temp;
}
$struct = $self->_repr( @_ );
}
- return $self->_import( $struct );
+ #XXX This isn't the best solution. Better would be to use Data::Walker,
+ #XXX but that's a lot more thinking than I want to do right now.
+ eval {
+ $self->begin_work;
+ $self->_import( _clone_data( $struct ) );
+ $self->commit;
+ }; if ( $@ ) {
+ $self->rollback;
+ die $@;
+ }
+
+ return 1;
}
+#XXX Need to keep track of who has a fh to this file in order to
+#XXX close them all prior to optimize on Win32/cygwin
sub optimize {
##
# Rebuild entire database into new file, then move
my $self = shift->_get_self;
#XXX Need to create a new test for this
-# if ($self->_fileobj->{links} > 1) {
+# if ($self->_storage->{links} > 1) {
# $self->_throw_error("Cannot optimize: reference count is greater than 1");
# }
+ #XXX Do we have to lock the tempfile?
+
my $db_temp = DBM::Deep->new(
- file => $self->_fileobj->{file} . '.tmp',
+ file => $self->_storage->{file} . '.tmp',
type => $self->_type
);
my $perms = $stats[2] & 07777;
my $uid = $stats[4];
my $gid = $stats[5];
- chown( $uid, $gid, $self->_fileobj->{file} . '.tmp' );
- chmod( $perms, $self->_fileobj->{file} . '.tmp' );
+ chown( $uid, $gid, $self->_storage->{file} . '.tmp' );
+ chmod( $perms, $self->_storage->{file} . '.tmp' );
# q.v. perlport for more information on this variable
if ( $^O eq 'MSWin32' || $^O eq 'cygwin' ) {
# with a soft copy.
##
$self->unlock();
- $self->_fileobj->close;
+ $self->_storage->close;
}
- if (!rename $self->_fileobj->{file} . '.tmp', $self->_fileobj->{file}) {
- unlink $self->_fileobj->{file} . '.tmp';
+ if (!rename $self->_storage->{file} . '.tmp', $self->_storage->{file}) {
+ unlink $self->_storage->{file} . '.tmp';
$self->unlock();
$self->_throw_error("Optimize failed: Cannot copy temp file over original: $!");
}
$self->unlock();
- $self->_fileobj->close;
- $self->_fileobj->open;
- $self->{engine}->setup_fh( $self );
+ $self->_storage->close;
+ $self->_storage->open;
+ $self->_engine->setup_fh( $self );
return 1;
}
my $self = shift->_get_self;
return DBM::Deep->new(
- type => $self->_type,
+ type => $self->_type,
base_offset => $self->_base_offset,
- fileobj => $self->_fileobj,
+ storage => $self->_storage,
+ parent => $self->{parent},
+ parent_key => $self->{parent_key},
);
}
my $func = shift;
if ( $is_legal_filter{$type} ) {
- $self->_fileobj->{"filter_$type"} = $func;
+ $self->_storage->{"filter_$type"} = $func;
return 1;
}
sub begin_work {
my $self = shift->_get_self;
- $self->_fileobj->begin_transaction;
- return 1;
+ return $self->_storage->begin_transaction;
}
sub rollback {
my $self = shift->_get_self;
- $self->_fileobj->end_transaction;
- return 1;
+ return $self->_storage->end_transaction;
}
sub commit {
my $self = shift->_get_self;
- $self->_fileobj->commit_transaction;
- return 1;
+ return $self->_storage->commit_transaction;
}
##
# Accessor methods
##
-sub _fileobj {
+sub _engine {
+ my $self = $_[0]->_get_self;
+ return $self->{engine};
+}
+
+sub _storage {
my $self = $_[0]->_get_self;
- return $self->{fileobj};
+ return $self->{storage};
}
sub _type {
sub _fh {
my $self = $_[0]->_get_self;
- return $self->_fileobj->{fh};
+ return $self->_storage->{fh};
}
##
die "DBM::Deep: $_[1]\n";
}
-sub _is_writable {
- my $fh = shift;
- (O_WRONLY | O_RDWR) & fcntl( $fh, F_GETFL, my $slush = 0);
-}
-
-#sub _is_readable {
-# my $fh = shift;
-# (O_RDONLY | O_RDWR) & fcntl( $fh, F_GETFL, my $slush = 0);
-#}
-
sub _find_parent {
my $self = shift;
while ( $parent->{parent} ) {
$base = (
$parent->_type eq TYPE_HASH
- ? "\{$child->{parent_key}\}"
+ ? "\{q{$child->{parent_key}}\}"
: "\[$child->{parent_key}\]"
) . $base;
$parent = $parent->{parent};
}
if ( $base ) {
- $base = "\$db->get( '$child->{parent_key}' )->" . $base;
+ $base = "\$db->get( q{$child->{parent_key}} )->" . $base;
}
else {
- $base = "\$db->get( '$child->{parent_key}' )";
+ $base = "\$db->get( q{$child->{parent_key}} )";
}
}
return $base;
##
my $self = shift->_get_self;
my ($key, $value, $orig_key) = @_;
+ $orig_key = $key unless defined $orig_key;
-
- if ( $^O ne 'MSWin32' && !_is_writable( $self->_fh ) ) {
+ if ( !FileHandle::Fmode::is_W( $self->_fh ) ) {
$self->_throw_error( 'Cannot write to a readonly filehandle' );
}
- if ( defined $orig_key ) {
+ #XXX The second condition needs to disappear
+ if ( !( $self->_type eq TYPE_ARRAY && $orig_key eq 'length') ) {
my $rhs;
my $r = Scalar::Util::reftype( $value ) || '';
my $lhs = $self->_find_parent;
if ( $lhs ) {
if ( $self->_type eq TYPE_HASH ) {
- $lhs .= "->\{$orig_key\}";
+ $lhs .= "->\{q{$orig_key}\}";
}
else {
$lhs .= "->\[$orig_key\]";
$lhs .= "=$rhs;";
}
else {
- $lhs = "\$db->put('$orig_key',$rhs);";
+ $lhs = "\$db->put(q{$orig_key},$rhs);";
}
- $self->_fileobj->audit($lhs);
+ $self->_storage->audit($lhs);
}
##
##
$self->lock( LOCK_EX );
- my $md5 = $self->{engine}{digest}->($key);
-
- my $tag = $self->{engine}->find_bucket_list( $self->_base_offset, $md5, { create => 1 } );
-
- # User may be storing a hash, in which case we do not want it run
- # through the filtering system
- if ( !ref($value) && $self->_fileobj->{filter_store_value} ) {
- $value = $self->_fileobj->{filter_store_value}->( $value );
+ # User may be storing a complex value, in which case we do not want it run
+ # through the filtering system.
+ if ( !ref($value) && $self->_storage->{filter_store_value} ) {
+ $value = $self->_storage->{filter_store_value}->( $value );
}
- ##
- # Add key/value to bucket list
- ##
- my $result = $self->{engine}->add_bucket( $tag, $md5, $key, $value, undef, $orig_key );
+ $self->_engine->write_value( $self->_base_offset, $key, $value, $orig_key );
$self->unlock();
- return $result;
+ return 1;
}
sub FETCH {
##
my $self = shift->_get_self;
my ($key, $orig_key) = @_;
-
- my $md5 = $self->{engine}{digest}->($key);
+ $orig_key = $key unless defined $orig_key;
##
# Request shared lock for reading
##
$self->lock( LOCK_SH );
- my $tag = $self->{engine}->find_bucket_list( $self->_base_offset, $md5 );
- if (!$tag) {
- $self->unlock();
- return;
- }
-
- ##
- # Get value from bucket list
- ##
- my $result = $self->{engine}->get_bucket_value( $tag, $md5, $orig_key );
+ my $result = $self->_engine->read_value( $self->_base_offset, $key, $orig_key );
$self->unlock();
# Filters only apply to scalar values, so the ref check is making
# sure the fetched bucket is a scalar, not a child hash or array.
- return ($result && !ref($result) && $self->_fileobj->{filter_fetch_value})
- ? $self->_fileobj->{filter_fetch_value}->($result)
+ return ($result && !ref($result) && $self->_storage->{filter_fetch_value})
+ ? $self->_storage->{filter_fetch_value}->($result)
: $result;
}
##
my $self = shift->_get_self;
my ($key, $orig_key) = @_;
+ $orig_key = $key unless defined $orig_key;
- if ( $^O ne 'MSWin32' && !_is_writable( $self->_fh ) ) {
+ if ( !FileHandle::Fmode::is_W( $self->_fh ) ) {
$self->_throw_error( 'Cannot write to a readonly filehandle' );
}
if ( defined $orig_key ) {
my $lhs = $self->_find_parent;
if ( $lhs ) {
- $self->_fileobj->audit( "delete $lhs;" );
+ $self->_storage->audit( "delete $lhs;" );
}
else {
- $self->_fileobj->audit( "\$db->delete('$orig_key');" );
+ $self->_storage->audit( "\$db->delete('$orig_key');" );
}
}
##
$self->lock( LOCK_EX );
- my $md5 = $self->{engine}{digest}->($key);
-
- my $tag = $self->{engine}->find_bucket_list( $self->_base_offset, $md5 );
- if (!$tag) {
- $self->unlock();
- return;
- }
-
##
# Delete bucket
##
- my $value = $self->{engine}->get_bucket_value( $tag, $md5 );
+ my $value = $self->_engine->delete_key( $self->_base_offset, $key, $orig_key );
- if (defined $value && !ref($value) && $self->_fileobj->{filter_fetch_value}) {
- $value = $self->_fileobj->{filter_fetch_value}->($value);
+ if (defined $value && !ref($value) && $self->_storage->{filter_fetch_value}) {
+ $value = $self->_storage->{filter_fetch_value}->($value);
}
- my $result = $self->{engine}->delete_bucket( $tag, $md5, $orig_key );
-
- ##
- # If this object is an array and the key deleted was on the end of the stack,
- # decrement the length variable.
- ##
-
$self->unlock();
return $value;
my $self = shift->_get_self;
my ($key) = @_;
- my $md5 = $self->{engine}{digest}->($key);
-
##
# Request shared lock for reading
##
$self->lock( LOCK_SH );
- my $tag = $self->{engine}->find_bucket_list( $self->_base_offset, $md5 );
- if (!$tag) {
- $self->unlock();
-
- ##
- # For some reason, the built-in exists() function returns '' for false
- ##
- return '';
- }
-
- ##
- # Check if bucket exists and return 1 or ''
- ##
- my $result = $self->{engine}->bucket_exists( $tag, $md5 ) || '';
+ my $result = $self->_engine->key_exists( $self->_base_offset, $key );
$self->unlock();
##
my $self = shift->_get_self;
- if ( $^O ne 'MSWin32' && !_is_writable( $self->_fh ) ) {
+ if ( !FileHandle::Fmode::is_W( $self->_fh ) ) {
$self->_throw_error( 'Cannot write to a readonly filehandle' );
}
$lhs = '@{' . $lhs . '}';
}
- $self->_fileobj->audit( "$lhs = ();" );
+ $self->_storage->audit( "$lhs = ();" );
}
##
##
$self->lock( LOCK_EX );
+ if ( $self->_type eq TYPE_HASH ) {
+ my $key = $self->first_key;
+ while ( $key ) {
+ # Retrieve the key before deleting because we depend on next_key
+ my $next_key = $self->next_key( $key );
+ $self->_engine->delete_key( $self->_base_offset, $key, $key );
+ $key = $next_key;
+ }
+ }
+ else {
+ my $size = $self->FETCHSIZE;
+ for my $key ( 0 .. $size - 1 ) {
+ $self->_engine->delete_key( $self->_base_offset, $key, $key );
+ }
+ $self->STORESIZE( 0 );
+ }
#XXX This needs updating to use _release_space
- $self->{engine}->write_tag(
- $self->_base_offset, $self->_type,
- chr(0)x$self->{engine}{index_size},
- );
+# $self->_engine->write_tag(
+# $self->_base_offset, $self->_type,
+# chr(0)x$self->_engine->{index_size},
+# );
$self->unlock();
use DBM::Deep;
my $db = DBM::Deep->new( "foo.db" );
- $db->{key} = 'value'; # tie() style
+ $db->{key} = 'value';
print $db->{key};
- $db->put('key' => 'value'); # OO style
+ $db->put('key' => 'value');
print $db->get('key');
# true multi-level support
42, 99,
];
-=head1 DESCRIPTION
-
-A unique flat-file database module, written in pure perl. True
-multi-level hash/array support (unlike MLDBM, which is faked), hybrid
-OO / tie() interface, cross-platform FTPable files, and quite fast. Can
-handle millions of keys and unlimited hash levels without significant
-slow-down. Written from the ground-up in pure perl -- this is NOT a
-wrapper around a C-based DBM. Out-of-the-box compatibility with Unix,
-Mac OS X and Windows.
+ tie my %db, 'DBM::Deep', 'foo.db';
+ $db{key} = 'value';
+ print $db{key};
-=head1 VERSION DIFFERENCES
+ tied(%db)->put('key' => 'value');
+ print tied(%db)->get('key');
-B<NOTE>: 0.99_01 and above have significant file format differences from 0.98 and
-before. While attempts have been made to be backwards compatible, no guarantees.
+=head1 DESCRIPTION
-=head1 INSTALLATION
+A unique flat-file database module, written in pure perl. True multi-level
+hash/array support (unlike MLDBM, which is faked), hybrid OO / tie()
+interface, cross-platform FTPable files, ACID transactions, and is quite fast.
+Can handle millions of keys and unlimited levels without significant
+slow-down. Written from the ground-up in pure perl -- this is NOT a wrapper
+around a C-based DBM. Out-of-the-box compatibility with Unix, Mac OS X and
+Windows.
-Hopefully you are using Perl's excellent CPAN module, which will download
-and install the module for you. If not, get the tarball, and run these
-commands:
+=head1 VERSION DIFFERENCES
- tar zxf DBM-Deep-*
- cd DBM-Deep-*
- perl Makefile.PL
- make
- make test
- make install
+B<NOTE>: 0.99_01 and above have significant file format differences from 0.983 and
+before. There will be a backwards-compatibility layer in 1.00, but that is
+slated for a later 0.99_x release. This version is B<NOT> backwards compatible
+with 0.983 and before.
=head1 SETUP
=head2 OO CONSTRUCTION
The recommended way to construct a DBM::Deep object is to use the new()
-method, which gets you a blessed, tied hash or array reference.
+method, which gets you a blessed I<and> tied hash (or array) reference.
- my $db = DBM::Deep->new( "foo.db" );
+ my $db = DBM::Deep->new( "foo.db" );
This opens a new database handle, mapped to the file "foo.db". If this
file does not exist, it will automatically be created. DB files are
hash, unless otherwise specified (see L<OPTIONS> below).
You can pass a number of options to the constructor to specify things like
-locking, autoflush, etc. This is done by passing an inline hash:
+locking, autoflush, etc. This is done by passing an inline hash (or hashref):
- my $db = DBM::Deep->new(
- file => "foo.db",
- locking => 1,
- autoflush => 1
- );
+ my $db = DBM::Deep->new(
+ file => "foo.db",
+ locking => 1,
+ autoflush => 1
+ );
Notice that the filename is now specified I<inside> the hash with
the "file" parameter, as opposed to being the sole argument to the
constructor. This is required if any options are specified.
See L<OPTIONS> below for the complete list.
-
-
You can also start with an array instead of a hash. For this, you must
specify the C<type> parameter:
- my $db = DBM::Deep->new(
- file => "foo.db",
- type => DBM::Deep->TYPE_ARRAY
- );
+ my $db = DBM::Deep->new(
+ file => "foo.db",
+ type => DBM::Deep->TYPE_ARRAY
+ );
B<Note:> Specifing the C<type> parameter only takes effect when beginning
a new DB file. If you create a DBM::Deep object with an existing file, the
Alternately, you can create a DBM::Deep handle by using Perl's built-in
tie() function. The object returned from tie() can be used to call methods,
-such as lock() and unlock(), but cannot be used to assign to the DBM::Deep
-file (as expected with most tie'd objects).
+such as lock() and unlock(). (That object can be retrieved from the tied
+variable at any time using tied() - please see L<perltie/> for more info.
- my %hash;
- my $db = tie %hash, "DBM::Deep", "foo.db";
+ my %hash;
+ my $db = tie %hash, "DBM::Deep", "foo.db";
- my @array;
- my $db = tie @array, "DBM::Deep", "bar.db";
+ my @array;
+ my $db = tie @array, "DBM::Deep", "bar.db";
As with the OO constructor, you can replace the DB filename parameter with
a hash containing one or more options (see L<OPTIONS> just below for the
complete list).
- tie %hash, "DBM::Deep", {
- file => "foo.db",
- locking => 1,
- autoflush => 1
- };
+ tie %hash, "DBM::Deep", {
+ file => "foo.db",
+ locking => 1,
+ autoflush => 1
+ };
=head2 OPTIONS
open it write-only or append-only, an exception will be thrown immediately as DBM::Deep
needs to read from the fh.
+=item * audit_file / audit_fh
+
+These are just like file/fh, except for auditing. Please see L</AUDITING> for
+more information.
+
=item * file_offset
This is the offset within the file that the DBM::Deep db starts. Most of the time, you will
=item * locking
-Specifies whether locking is to be enabled. DBM::Deep uses Perl's Fnctl flock()
-function to lock the database in exclusive mode for writes, and shared mode for
-reads. Pass any true value to enable. This affects the base DB handle I<and
-any child hashes or arrays> that use the same DB file. This is an optional
-parameter, and defaults to 0 (disabled). See L<LOCKING> below for more.
+Specifies whether locking is to be enabled. DBM::Deep uses Perl's flock()
+function to lock the database in exclusive mode for writes, and shared mode
+for reads. Pass any true value to enable. This affects the base DB handle
+I<and any child hashes or arrays> that use the same DB file. This is an
+optional parameter, and defaults to 0 (disabled). See L<LOCKING> below for
+more.
=item * autoflush
You can treat any DBM::Deep object like a normal Perl hash reference. Add keys,
or even nested hashes (or arrays) using standard Perl syntax:
- my $db = DBM::Deep->new( "foo.db" );
+ my $db = DBM::Deep->new( "foo.db" );
- $db->{mykey} = "myvalue";
- $db->{myhash} = {};
- $db->{myhash}->{subkey} = "subvalue";
+ $db->{mykey} = "myvalue";
+ $db->{myhash} = {};
+ $db->{myhash}->{subkey} = "subvalue";
- print $db->{myhash}->{subkey} . "\n";
+ print $db->{myhash}->{subkey} . "\n";
You can even step through hash keys using the normal Perl C<keys()> function:
- foreach my $key (keys %$db) {
- print "$key: " . $db->{$key} . "\n";
- }
+ foreach my $key (keys %$db) {
+ print "$key: " . $db->{$key} . "\n";
+ }
Remember that Perl's C<keys()> function extracts I<every> key from the hash and
pushes them onto an array, all before the loop even begins. If you have an
-extra large hash, this may exhaust Perl's memory. Instead, consider using
+extremely large hash, this may exhaust Perl's memory. Instead, consider using
Perl's C<each()> function, which pulls keys/values one at a time, using very
little memory:
- while (my ($key, $value) = each %$db) {
- print "$key: $value\n";
- }
+ while (my ($key, $value) = each %$db) {
+ print "$key: $value\n";
+ }
Please note that when using C<each()>, you should always pass a direct
hash reference, not a lookup. Meaning, you should B<never> do this:
- # NEVER DO THIS
- while (my ($key, $value) = each %{$db->{foo}}) { # BAD
+ # NEVER DO THIS
+ while (my ($key, $value) = each %{$db->{foo}}) { # BAD
This causes an infinite loop, because for each iteration, Perl is calling
FETCH() on the $db handle, resulting in a "new" hash for foo every time, so
The object must have first been created using type C<DBM::Deep-E<gt>TYPE_ARRAY>,
or simply be a nested array reference inside a hash. Example:
- my $db = DBM::Deep->new(
- file => "foo-array.db",
- type => DBM::Deep->TYPE_ARRAY
- );
+ my $db = DBM::Deep->new(
+ file => "foo-array.db",
+ type => DBM::Deep->TYPE_ARRAY
+ );
- $db->[0] = "foo";
- push @$db, "bar", "baz";
- unshift @$db, "bah";
+ $db->[0] = "foo";
+ push @$db, "bar", "baz";
+ unshift @$db, "bah";
- my $last_elem = pop @$db; # baz
- my $first_elem = shift @$db; # bah
- my $second_elem = $db->[1]; # bar
+ my $last_elem = pop @$db; # baz
+ my $first_elem = shift @$db; # bah
+ my $second_elem = $db->[1]; # bar
- my $num_elements = scalar @$db;
+ my $num_elements = scalar @$db;
=head1 OO INTERFACE
In addition to the I<tie()> interface, you can also use a standard OO interface
to manipulate all aspects of DBM::Deep databases. Each type of object (hash or
array) has its own methods, but both types share the following common methods:
-C<put()>, C<get()>, C<exists()>, C<delete()> and C<clear()>.
+C<put()>, C<get()>, C<exists()>, C<delete()> and C<clear()>. C<fetch()> and
+C<store(> are aliases to C<put()> and C<get()>, respectively.
=over
arguments, the hash key or array index, and the new value. The value can be
a scalar, hash ref or array ref. Returns true on success, false on failure.
- $db->put("foo", "bar"); # for hashes
- $db->put(1, "bar"); # for arrays
+ $db->put("foo", "bar"); # for hashes
+ $db->put(1, "bar"); # for arrays
=item * get() / fetch()
key or array index. Returns a scalar, hash ref or array ref, depending on the
data type stored.
- my $value = $db->get("foo"); # for hashes
- my $value = $db->get(1); # for arrays
+ my $value = $db->get("foo"); # for hashes
+ my $value = $db->get(1); # for arrays
=item * exists()
Checks if a hash key or array index exists. Takes one argument: the hash key
or array index. Returns true if it exists, false if not.
- if ($db->exists("foo")) { print "yay!\n"; } # for hashes
- if ($db->exists(1)) { print "yay!\n"; } # for arrays
+ if ($db->exists("foo")) { print "yay!\n"; } # for hashes
+ if ($db->exists(1)) { print "yay!\n"; } # for arrays
=item * delete()
key/value or element is B<not> reused again -- see L<UNUSED SPACE RECOVERY>
below for details and workarounds.
- $db->delete("foo"); # for hashes
- $db->delete(1); # for arrays
+ $db->delete("foo"); # for hashes
+ $db->delete(1); # for arrays
=item * clear()
elements is B<not> reused again -- see L<UNUSED SPACE RECOVERY> below for
details and workarounds.
- $db->clear(); # hashes or arrays
+ $db->clear(); # hashes or arrays
=item * lock() / unlock()
=item * optimize()
-Recover lost disk space.
+Recover lost disk space. This is important to do, especially if you use
+transactions.
=item * import() / export()
fetched in an undefined order (which appears random). Takes no arguments,
returns the key as a scalar value.
- my $key = $db->first_key();
+ my $key = $db->first_key();
=item * next_key()
Returns the "next" key in the hash, given the previous one as the sole argument.
Returns undef if there are no more keys to be fetched.
- $key = $db->next_key($key);
+ $key = $db->next_key($key);
=back
Here are some examples of using hashes:
- my $db = DBM::Deep->new( "foo.db" );
+ my $db = DBM::Deep->new( "foo.db" );
- $db->put("foo", "bar");
- print "foo: " . $db->get("foo") . "\n";
+ $db->put("foo", "bar");
+ print "foo: " . $db->get("foo") . "\n";
- $db->put("baz", {}); # new child hash ref
- $db->get("baz")->put("buz", "biz");
- print "buz: " . $db->get("baz")->get("buz") . "\n";
+ $db->put("baz", {}); # new child hash ref
+ $db->get("baz")->put("buz", "biz");
+ print "buz: " . $db->get("baz")->get("buz") . "\n";
- my $key = $db->first_key();
- while ($key) {
- print "$key: " . $db->get($key) . "\n";
- $key = $db->next_key($key);
- }
+ my $key = $db->first_key();
+ while ($key) {
+ print "$key: " . $db->get($key) . "\n";
+ $key = $db->next_key($key);
+ }
- if ($db->exists("foo")) { $db->delete("foo"); }
+ if ($db->exists("foo")) { $db->delete("foo"); }
=head2 ARRAYS
Returns the number of elements in the array. Takes no arguments.
- my $len = $db->length();
+ my $len = $db->length();
=item * push()
Adds one or more elements onto the end of the array. Accepts scalars, hash
refs or array refs. No return value.
- $db->push("foo", "bar", {});
+ $db->push("foo", "bar", {});
=item * pop()
Fetches the last element in the array, and deletes it. Takes no arguments.
Returns undef if array is empty. Returns the element value.
- my $elem = $db->pop();
+ my $elem = $db->pop();
=item * shift()
method is not recommended with large arrays -- see L<LARGE ARRAYS> below for
details.
- my $elem = $db->shift();
+ my $elem = $db->shift();
=item * unshift()
No return value. This method is not recommended with large arrays -- see
<LARGE ARRAYS> below for details.
- $db->unshift("foo", "bar", {});
+ $db->unshift("foo", "bar", {});
=item * splice()
Here are some examples of using arrays:
- my $db = DBM::Deep->new(
- file => "foo.db",
- type => DBM::Deep->TYPE_ARRAY
- );
+ my $db = DBM::Deep->new(
+ file => "foo.db",
+ type => DBM::Deep->TYPE_ARRAY
+ );
- $db->push("bar", "baz");
- $db->unshift("foo");
- $db->put(3, "buz");
+ $db->push("bar", "baz");
+ $db->unshift("foo");
+ $db->put(3, "buz");
- my $len = $db->length();
- print "length: $len\n"; # 4
+ my $len = $db->length();
+ print "length: $len\n"; # 4
- for (my $k=0; $k<$len; $k++) {
- print "$k: " . $db->get($k) . "\n";
- }
+ for (my $k=0; $k<$len; $k++) {
+ print "$k: " . $db->get($k) . "\n";
+ }
- $db->splice(1, 2, "biz", "baf");
+ $db->splice(1, 2, "biz", "baf");
- while (my $elem = shift @$db) {
- print "shifted: $elem\n";
- }
+ while (my $elem = shift @$db) {
+ print "shifted: $elem\n";
+ }
=head1 LOCKING
Enable automatic file locking by passing a true value to the C<locking>
parameter when constructing your DBM::Deep object (see L<SETUP> above).
- my $db = DBM::Deep->new(
- file => "foo.db",
- locking => 1
- );
+ my $db = DBM::Deep->new(
+ file => "foo.db",
+ locking => 1
+ );
This causes DBM::Deep to C<flock()> the underlying filehandle with exclusive
mode for writes, and shared mode for reads. This is required if you have
useful for things like counters, where the current value needs to be fetched,
then incremented, then stored again.
- $db->lock();
- my $counter = $db->get("counter");
- $counter++;
- $db->put("counter", $counter);
- $db->unlock();
+ $db->lock();
+ my $counter = $db->get("counter");
+ $counter++;
+ $db->put("counter", $counter);
+ $db->unlock();
- # or...
+ # or...
- $db->lock();
- $db->{counter}++;
- $db->unlock();
+ $db->lock();
+ $db->{counter}++;
+ $db->unlock();
You can pass C<lock()> an optional argument, which specifies which mode to use
-(exclusive or shared). Use one of these two constants: C<DBM::Deep-E<gt>LOCK_EX>
-or C<DBM::Deep-E<gt>LOCK_SH>. These are passed directly to C<flock()>, and are the
-same as the constants defined in Perl's C<Fcntl> module.
+(exclusive or shared). Use one of these two constants:
+C<DBM::Deep-E<gt>LOCK_EX> or C<DBM::Deep-E<gt>LOCK_SH>. These are passed
+directly to C<flock()>, and are the same as the constants defined in Perl's
+L<Fcntl/> module.
- $db->lock( DBM::Deep->LOCK_SH );
- # something here
- $db->unlock();
+ $db->lock( $db->LOCK_SH );
+ # something here
+ $db->unlock();
=head1 IMPORTING/EXPORTING
simply pass a reference to the C<import()> method. This recursively adds
everything to an existing DBM::Deep object for you. Here is an example:
- my $struct = {
- key1 => "value1",
- key2 => "value2",
- array1 => [ "elem0", "elem1", "elem2" ],
- hash1 => {
- subkey1 => "subvalue1",
- subkey2 => "subvalue2"
- }
- };
+ my $struct = {
+ key1 => "value1",
+ key2 => "value2",
+ array1 => [ "elem0", "elem1", "elem2" ],
+ hash1 => {
+ subkey1 => "subvalue1",
+ subkey2 => "subvalue2"
+ }
+ };
- my $db = DBM::Deep->new( "foo.db" );
- $db->import( $struct );
+ my $db = DBM::Deep->new( "foo.db" );
+ $db->import( $struct );
- print $db->{key1} . "\n"; # prints "value1"
+ print $db->{key1} . "\n"; # prints "value1"
This recursively imports the entire C<$struct> object into C<$db>, including
all nested hashes and arrays. If the DBM::Deep object contains exsiting data,
level), and works with both hash and array DB types.
B<Note:> Make sure your existing structure has no circular references in it.
-These will cause an infinite loop when importing.
+These will cause an infinite loop when importing. There are plans to fix this
+in a later release.
=head2 EXPORTING
recursively, so all nested hashes/arrays are all exported to standard Perl
objects. Here is an example:
- my $db = DBM::Deep->new( "foo.db" );
+ my $db = DBM::Deep->new( "foo.db" );
- $db->{key1} = "value1";
- $db->{key2} = "value2";
- $db->{hash1} = {};
- $db->{hash1}->{subkey1} = "subvalue1";
- $db->{hash1}->{subkey2} = "subvalue2";
+ $db->{key1} = "value1";
+ $db->{key2} = "value2";
+ $db->{hash1} = {};
+ $db->{hash1}->{subkey1} = "subvalue1";
+ $db->{hash1}->{subkey2} = "subvalue2";
- my $struct = $db->export();
+ my $struct = $db->export();
- print $struct->{key1} . "\n"; # prints "value1"
+ print $struct->{key1} . "\n"; # prints "value1"
This makes a complete copy of the database in memory, and returns a reference
to it. The C<export()> method can be called on any database level (not just
in-memory Perl structure.
B<Note:> Make sure your database has no circular references in it.
-These will cause an infinite loop when exporting.
+These will cause an infinite loop when exporting. There are plans to fix this
+in a later release.
=head1 FILTERS
Here are the two ways to setup a filter hook:
- my $db = DBM::Deep->new(
- file => "foo.db",
- filter_store_value => \&my_filter_store,
- filter_fetch_value => \&my_filter_fetch
- );
+ my $db = DBM::Deep->new(
+ file => "foo.db",
+ filter_store_value => \&my_filter_store,
+ filter_fetch_value => \&my_filter_fetch
+ );
- # or...
+ # or...
- $db->set_filter( "filter_store_value", \&my_filter_store );
- $db->set_filter( "filter_fetch_value", \&my_filter_fetch );
+ $db->set_filter( "filter_store_value", \&my_filter_store );
+ $db->set_filter( "filter_fetch_value", \&my_filter_fetch );
Your filter function will be called only when dealing with SCALAR keys or
values. When nested hashes and arrays are being stored/fetched, filtering
argument, and expected to return a single SCALAR value. If you want to
remove a filter, set the function reference to C<undef>:
- $db->set_filter( "filter_store_value", undef );
+ $db->set_filter( "filter_store_value", undef );
=head2 REAL-TIME ENCRYPTION EXAMPLE
Please visit L<http://search.cpan.org/search?module=Crypt::Blowfish> for more
on I<Crypt::Blowfish>. You'll also need the I<Crypt::CBC> module.
- use DBM::Deep;
- use Crypt::Blowfish;
- use Crypt::CBC;
-
- my $cipher = Crypt::CBC->new({
- 'key' => 'my secret key',
- 'cipher' => 'Blowfish',
- 'iv' => '$KJh#(}q',
- 'regenerate_key' => 0,
- 'padding' => 'space',
- 'prepend_iv' => 0
- });
-
- my $db = DBM::Deep->new(
- file => "foo-encrypt.db",
- filter_store_key => \&my_encrypt,
- filter_store_value => \&my_encrypt,
- filter_fetch_key => \&my_decrypt,
- filter_fetch_value => \&my_decrypt,
- );
-
- $db->{key1} = "value1";
- $db->{key2} = "value2";
- print "key1: " . $db->{key1} . "\n";
- print "key2: " . $db->{key2} . "\n";
-
- undef $db;
- exit;
-
- sub my_encrypt {
- return $cipher->encrypt( $_[0] );
- }
- sub my_decrypt {
- return $cipher->decrypt( $_[0] );
- }
+ use DBM::Deep;
+ use Crypt::Blowfish;
+ use Crypt::CBC;
+
+ my $cipher = Crypt::CBC->new({
+ 'key' => 'my secret key',
+ 'cipher' => 'Blowfish',
+ 'iv' => '$KJh#(}q',
+ 'regenerate_key' => 0,
+ 'padding' => 'space',
+ 'prepend_iv' => 0
+ });
+
+ my $db = DBM::Deep->new(
+ file => "foo-encrypt.db",
+ filter_store_key => \&my_encrypt,
+ filter_store_value => \&my_encrypt,
+ filter_fetch_key => \&my_decrypt,
+ filter_fetch_value => \&my_decrypt,
+ );
+
+ $db->{key1} = "value1";
+ $db->{key2} = "value2";
+ print "key1: " . $db->{key1} . "\n";
+ print "key2: " . $db->{key2} . "\n";
+
+ undef $db;
+ exit;
+
+ sub my_encrypt {
+ return $cipher->encrypt( $_[0] );
+ }
+ sub my_decrypt {
+ return $cipher->decrypt( $_[0] );
+ }
=head2 REAL-TIME COMPRESSION EXAMPLE
Please visit L<http://search.cpan.org/search?module=Compress::Zlib> for
more on I<Compress::Zlib>.
- use DBM::Deep;
- use Compress::Zlib;
-
- my $db = DBM::Deep->new(
- file => "foo-compress.db",
- filter_store_key => \&my_compress,
- filter_store_value => \&my_compress,
- filter_fetch_key => \&my_decompress,
- filter_fetch_value => \&my_decompress,
- );
-
- $db->{key1} = "value1";
- $db->{key2} = "value2";
- print "key1: " . $db->{key1} . "\n";
- print "key2: " . $db->{key2} . "\n";
-
- undef $db;
- exit;
-
- sub my_compress {
- return Compress::Zlib::memGzip( $_[0] ) ;
- }
- sub my_decompress {
- return Compress::Zlib::memGunzip( $_[0] ) ;
- }
+ use DBM::Deep;
+ use Compress::Zlib;
+
+ my $db = DBM::Deep->new(
+ file => "foo-compress.db",
+ filter_store_key => \&my_compress,
+ filter_store_value => \&my_compress,
+ filter_fetch_key => \&my_decompress,
+ filter_fetch_value => \&my_decompress,
+ );
+
+ $db->{key1} = "value1";
+ $db->{key2} = "value2";
+ print "key1: " . $db->{key1} . "\n";
+ print "key2: " . $db->{key2} . "\n";
+
+ undef $db;
+ exit;
+
+ sub my_compress {
+ return Compress::Zlib::memGzip( $_[0] ) ;
+ }
+ sub my_decompress {
+ return Compress::Zlib::memGunzip( $_[0] ) ;
+ }
B<Note:> Filtering of keys only applies to hashes. Array "keys" are
actually numerical index numbers, and are not filtered.
Most DBM::Deep methods return a true value for success, and call die() on
failure. You can wrap calls in an eval block to catch the die.
- my $db = DBM::Deep->new( "foo.db" ); # create hash
- eval { $db->push("foo"); }; # ILLEGAL -- push is array-only call
+ my $db = DBM::Deep->new( "foo.db" ); # create hash
+ eval { $db->push("foo"); }; # ILLEGAL -- push is array-only call
- print $@; # prints error message
+ print $@; # prints error message
=head1 LARGEFILE SUPPORT
DBM::Deep by default uses 32-bit file offset tags, but these can be changed
by specifying the 'pack_size' parameter when constructing the file.
- DBM::Deep->new(
- filename => $filename,
- pack_size => 'large',
- );
+ DBM::Deep->new(
+ filename => $filename,
+ pack_size => 'large',
+ );
This tells DBM::Deep to pack all file offsets with 8-byte (64-bit) quad words
instead of 32-bit longs. After setting these values your DB files have a
If you require low-level access to the underlying filehandle that DBM::Deep uses,
you can call the C<_fh()> method, which returns the handle:
- my $fh = $db->_fh();
+ my $fh = $db->_fh();
This method can be called on the root level of the datbase, or any child
hashes or arrays. All levels share a I<root> structure, which contains things
like the filehandle, a reference counter, and all the options specified
when you created the object. You can get access to this file object by
-calling the C<_fileobj()> method.
+calling the C<_storage()> method.
- my $file_obj = $db->_fileobj();
+ my $file_obj = $db->_storage();
This is useful for changing options after the object has already been created,
such as enabling/disabling locking. You can also store your own temporary user
I<Digest::SHA256> module. Please see
L<http://search.cpan.org/search?module=Digest::SHA256> for more information.
- use DBM::Deep;
- use Digest::SHA256;
+ use DBM::Deep;
+ use Digest::SHA256;
- my $context = Digest::SHA256::new(256);
+ my $context = Digest::SHA256::new(256);
- my $db = DBM::Deep->new(
- filename => "foo-sha.db",
- digest => \&my_digest,
- hash_size => 32,
- );
+ my $db = DBM::Deep->new(
+ filename => "foo-sha.db",
+ digest => \&my_digest,
+ hash_size => 32,
+ );
- $db->{key1} = "value1";
- $db->{key2} = "value2";
- print "key1: " . $db->{key1} . "\n";
- print "key2: " . $db->{key2} . "\n";
+ $db->{key1} = "value1";
+ $db->{key2} = "value2";
+ print "key1: " . $db->{key1} . "\n";
+ print "key2: " . $db->{key2} . "\n";
- undef $db;
- exit;
+ undef $db;
+ exit;
- sub my_digest {
- return substr( $context->hash($_[0]), 0, 32 );
- }
+ sub my_digest {
+ return substr( $context->hash($_[0]), 0, 32 );
+ }
B<Note:> Your returned digest strings must be B<EXACTLY> the number
of bytes you specify in the hash_size parameter (in this case 32).
This relationship is stored in the DB file, and is preserved between sessions.
Here is an example:
- my $db = DBM::Deep->new( "foo.db" );
+ my $db = DBM::Deep->new( "foo.db" );
- $db->{foo} = "bar";
- $db->{circle} = $db; # ref to self
+ $db->{foo} = "bar";
+ $db->{circle} = $db; # ref to self
- print $db->{foo} . "\n"; # prints "bar"
- print $db->{circle}->{foo} . "\n"; # prints "bar" again
+ print $db->{foo} . "\n"; # prints "bar"
+ print $db->{circle}->{foo} . "\n"; # prints "bar" again
B<Note>: Passing the object to a function that recursively walks the
object tree (such as I<Data::Dumper> or even the built-in C<optimize()> or
C<export()> methods) will result in an infinite loop. This will be fixed in
a future release.
+=head1 AUDITING
+
+New in 0.99_01 is the ability to audit your databases actions. By passing in
+audit_file (or audit_fh) to the constructor, all actions will be logged to
+that file. The format is one that is suitable for eval'ing against the
+database to replay the actions. Please see t/33_audit_trail.t for an example
+of how to do this.
+
+=head1 TRANSACTIONS
+
+New in 0.99_01 is ACID transactions. Every DBM::Deep object is completely
+transaction-ready - it is not an option you have to turn on. Three new methods
+have been added to support them. They are:
+
+=over 4
+
+=item * begin_work()
+
+This starts a transaction.
+
+=item * commit()
+
+This applies the changes done within the transaction to the mainline and ends
+the transaction.
+
+=item * rollback()
+
+This discards the changes done within the transaction to the mainline and ends
+the transaction.
+
+=back
+
+Transactions in DBM::Deep are done using the MVCC method, the same method used
+by the InnoDB MySQL table type.
+
=head1 CAVEATS / ISSUES / BUGS
This section describes all the known issues with DBM::Deep. It you have found
but in the meantime you can call the built-in C<optimize()> method from time to
time (perhaps in a crontab or something) to recover all your unused space.
- $db->optimize(); # returns true on success
+ $db->optimize(); # returns true on success
This rebuilds the ENTIRE database into a new file, then moves it on top of
the original. The new file will have no unused space, thus it will take up as
=item * CODE
-L<http://search.cpan.org/search?module=Data::Dump::Streamer> provides a
-mechanism for serializing coderefs, including saving off all closure state.
-However, just as for SCALAR and REF, that closure state may change without
-notifying the DBM::Deep object storing the reference.
+L<Data::Dump::Streamer/> provides a mechanism for serializing coderefs,
+including saving off all closure state. However, just as for SCALAR and REF,
+that closure state may change without notifying the DBM::Deep object storing
+the reference.
=back
=head2 DB OVER NFS
-Beware of using DB files over NFS. DBM::Deep uses flock(), which works well on local
-filesystems, but will NOT protect you from file corruption over NFS. I've heard
-about setting up your NFS server with a locking daemon, then using lockf() to
-lock your files, but your mileage may vary there as well. From what I
-understand, there is no real way to do it. However, if you need access to the
-underlying filehandle in DBM::Deep for using some other kind of locking scheme like
-lockf(), see the L<LOW-LEVEL ACCESS> section above.
+Beware of using DBM::Deep files over NFS. DBM::Deep uses flock(), which works
+well on local filesystems, but will NOT protect you from file corruption over
+NFS. I've heard about setting up your NFS server with a locking daemon, then
+using lockf() to lock your files, but your mileage may vary there as well.
+From what I understand, there is no real way to do it. However, if you need
+access to the underlying filehandle in DBM::Deep for using some other kind of
+locking scheme like lockf(), see the L<LOW-LEVEL ACCESS> section above.
=head2 COPYING OBJECTS
Instead, use DBM::Deep's C<clone()> method which safely copies the object and
returns a new, blessed, tied hash or array to the same level in the DB.
- my $copy = $db->clone();
+ my $copy = $db->clone();
B<Note>: Since clone() here is cloning the object, not the database location, any
-modifications to either $db or $copy will be visible in both.
+modifications to either $db or $copy will be visible to both.
=head2 LARGE ARRAYS
doesn't seem to be a good way to determine if a filehandle is readable. And, if the
filehandle isn't readable, it's not clear what will happen. So, don't do that.
-=head1 PERFORMANCE
-
-This section discusses DBM::Deep's speed and memory usage.
-
-=head2 SPEED
-
-Obviously, DBM::Deep isn't going to be as fast as some C-based DBMs, such as
-the almighty I<BerkeleyDB>. But it makes up for it in features like true
-multi-level hash/array support, and cross-platform FTPable files. Even so,
-DBM::Deep is still pretty fast, and the speed stays fairly consistent, even
-with huge databases. Here is some test data:
-
- Adding 1,000,000 keys to new DB file...
-
- At 100 keys, avg. speed is 2,703 keys/sec
- At 200 keys, avg. speed is 2,642 keys/sec
- At 300 keys, avg. speed is 2,598 keys/sec
- At 400 keys, avg. speed is 2,578 keys/sec
- At 500 keys, avg. speed is 2,722 keys/sec
- At 600 keys, avg. speed is 2,628 keys/sec
- At 700 keys, avg. speed is 2,700 keys/sec
- At 800 keys, avg. speed is 2,607 keys/sec
- At 900 keys, avg. speed is 2,190 keys/sec
- At 1,000 keys, avg. speed is 2,570 keys/sec
- At 2,000 keys, avg. speed is 2,417 keys/sec
- At 3,000 keys, avg. speed is 1,982 keys/sec
- At 4,000 keys, avg. speed is 1,568 keys/sec
- At 5,000 keys, avg. speed is 1,533 keys/sec
- At 6,000 keys, avg. speed is 1,787 keys/sec
- At 7,000 keys, avg. speed is 1,977 keys/sec
- At 8,000 keys, avg. speed is 2,028 keys/sec
- At 9,000 keys, avg. speed is 2,077 keys/sec
- At 10,000 keys, avg. speed is 2,031 keys/sec
- At 20,000 keys, avg. speed is 1,970 keys/sec
- At 30,000 keys, avg. speed is 2,050 keys/sec
- At 40,000 keys, avg. speed is 2,073 keys/sec
- At 50,000 keys, avg. speed is 1,973 keys/sec
- At 60,000 keys, avg. speed is 1,914 keys/sec
- At 70,000 keys, avg. speed is 2,091 keys/sec
- At 80,000 keys, avg. speed is 2,103 keys/sec
- At 90,000 keys, avg. speed is 1,886 keys/sec
- At 100,000 keys, avg. speed is 1,970 keys/sec
- At 200,000 keys, avg. speed is 2,053 keys/sec
- At 300,000 keys, avg. speed is 1,697 keys/sec
- At 400,000 keys, avg. speed is 1,838 keys/sec
- At 500,000 keys, avg. speed is 1,941 keys/sec
- At 600,000 keys, avg. speed is 1,930 keys/sec
- At 700,000 keys, avg. speed is 1,735 keys/sec
- At 800,000 keys, avg. speed is 1,795 keys/sec
- At 900,000 keys, avg. speed is 1,221 keys/sec
- At 1,000,000 keys, avg. speed is 1,077 keys/sec
-
-This test was performed on a PowerMac G4 1gHz running Mac OS X 10.3.2 & Perl
-5.8.1, with an 80GB Ultra ATA/100 HD spinning at 7200RPM. The hash keys and
-values were between 6 - 12 chars in length. The DB file ended up at 210MB.
-Run time was 12 min 3 sec.
-
-=head2 MEMORY USAGE
-
-One of the great things about DBM::Deep is that it uses very little memory.
-Even with huge databases (1,000,000+ keys) you will not see much increased
-memory on your process. DBM::Deep relies solely on the filesystem for storing
-and fetching data. Here is output from I</usr/bin/top> before even opening a
-database handle:
-
- PID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM TIME COMMAND
- 22831 root 11 0 2716 2716 1296 R 0.0 0.2 0:07 perl
-
-Basically the process is taking 2,716K of memory. And here is the same
-process after storing and fetching 1,000,000 keys:
-
- PID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM TIME COMMAND
- 22831 root 14 0 2772 2772 1328 R 0.0 0.2 13:32 perl
-
-Notice the memory usage increased by only 56K. Test was performed on a 700mHz
-x86 box running Linux RedHat 7.2 & Perl 5.6.1.
-
-=head1 DB FILE FORMAT
-
-In case you were interested in the underlying DB file format, it is documented
-here in this section. You don't need to know this to use the module, it's just
-included for reference.
-
-=head2 SIGNATURE
-
-DBM::Deep files always start with a 32-bit signature to identify the file type.
-This is at offset 0. The signature is "DPDB" in network byte order. This is
-checked for when the file is opened and an error will be thrown if it's not found.
-
-=head2 TAG
-
-The DBM::Deep file is in a I<tagged format>, meaning each section of the file
-has a standard header containing the type of data, the length of data, and then
-the data itself. The type is a single character (1 byte), the length is a
-32-bit unsigned long in network byte order, and the data is, well, the data.
-Here is how it unfolds:
-
-=head2 MASTER INDEX
-
-Immediately after the 32-bit file signature is the I<Master Index> record.
-This is a standard tag header followed by 1024 bytes (in 32-bit mode) or 2048
-bytes (in 64-bit mode) of data. The type is I<H> for hash or I<A> for array,
-depending on how the DBM::Deep object was constructed.
-
-The index works by looking at a I<MD5 Hash> of the hash key (or array index
-number). The first 8-bit char of the MD5 signature is the offset into the
-index, multipled by 4 in 32-bit mode, or 8 in 64-bit mode. The value of the
-index element is a file offset of the next tag for the key/element in question,
-which is usually a I<Bucket List> tag (see below).
-
-The next tag I<could> be another index, depending on how many keys/elements
-exist. See L<RE-INDEXING> below for details.
-
-=head2 BUCKET LIST
-
-A I<Bucket List> is a collection of 16 MD5 hashes for keys/elements, plus
-file offsets to where the actual data is stored. It starts with a standard
-tag header, with type I<B>, and a data size of 320 bytes in 32-bit mode, or
-384 bytes in 64-bit mode. Each MD5 hash is stored in full (16 bytes), plus
-the 32-bit or 64-bit file offset for the I<Bucket> containing the actual data.
-When the list fills up, a I<Re-Index> operation is performed (See
-L<RE-INDEXING> below).
-
-=head2 BUCKET
-
-A I<Bucket> is a tag containing a key/value pair (in hash mode), or a
-index/value pair (in array mode). It starts with a standard tag header with
-type I<D> for scalar data (string, binary, etc.), or it could be a nested
-hash (type I<H>) or array (type I<A>). The value comes just after the tag
-header. The size reported in the tag header is only for the value, but then,
-just after the value is another size (32-bit unsigned long) and then the plain
-key itself. Since the value is likely to be fetched more often than the plain
-key, I figured it would be I<slightly> faster to store the value first.
-
-If the type is I<H> (hash) or I<A> (array), the value is another I<Master Index>
-record for the nested structure, where the process begins all over again.
-
-=head2 RE-INDEXING
-
-After a I<Bucket List> grows to 16 records, its allocated space in the file is
-exhausted. Then, when another key/element comes in, the list is converted to a
-new index record. However, this index will look at the next char in the MD5
-hash, and arrange new Bucket List pointers accordingly. This process is called
-I<Re-Indexing>. Basically, a new index tag is created at the file EOF, and all
-17 (16 + new one) keys/elements are removed from the old Bucket List and
-inserted into the new index. Several new Bucket Lists are created in the
-process, as a new MD5 char from the key is being examined (it is unlikely that
-the keys will all share the same next char of their MD5s).
-
-Because of the way the I<MD5> algorithm works, it is impossible to tell exactly
-when the Bucket Lists will turn into indexes, but the first round tends to
-happen right around 4,000 keys. You will see a I<slight> decrease in
-performance here, but it picks back up pretty quick (see L<SPEED> above). Then
-it takes B<a lot> more keys to exhaust the next level of Bucket Lists. It's
-right around 900,000 keys. This process can continue nearly indefinitely --
-right up until the point the I<MD5> signatures start colliding with each other,
-and this is B<EXTREMELY> rare -- like winning the lottery 5 times in a row AND
-getting struck by lightning while you are walking to cash in your tickets.
-Theoretically, since I<MD5> hashes are 128-bit values, you I<could> have up to
-340,282,366,921,000,000,000,000,000,000,000,000,000 keys/elements (I believe
-this is 340 unodecillion, but don't quote me).
-
-=head2 STORING
-
-When a new key/element is stored, the key (or index number) is first run through
-I<Digest::MD5> to get a 128-bit signature (example, in hex:
-b05783b0773d894396d475ced9d2f4f6). Then, the I<Master Index> record is checked
-for the first char of the signature (in this case I<b0>). If it does not exist,
-a new I<Bucket List> is created for our key (and the next 15 future keys that
-happen to also have I<b> as their first MD5 char). The entire MD5 is written
-to the I<Bucket List> along with the offset of the new I<Bucket> record (EOF at
-this point, unless we are replacing an existing I<Bucket>), where the actual
-data will be stored.
-
-=head2 FETCHING
-
-Fetching an existing key/element involves getting a I<Digest::MD5> of the key
-(or index number), then walking along the indexes. If there are enough
-keys/elements in this DB level, there might be nested indexes, each linked to
-a particular char of the MD5. Finally, a I<Bucket List> is pointed to, which
-contains up to 16 full MD5 hashes. Each is checked for equality to the key in
-question. If we found a match, the I<Bucket> tag is loaded, where the value and
-plain key are stored.
-
-Fetching the plain key occurs when calling the I<first_key()> and I<next_key()>
-methods. In this process the indexes are walked systematically, and each key
-fetched in increasing MD5 order (which is why it appears random). Once the
-I<Bucket> is found, the value is skipped and the plain key returned instead.
-B<Note:> Do not count on keys being fetched as if the MD5 hashes were
-alphabetically sorted. This only happens on an index-level -- as soon as the
-I<Bucket Lists> are hit, the keys will come out in the order they went in --
-so it's pretty much undefined how the keys will come out -- just like Perl's
-built-in hashes.
-
=head1 CODE COVERAGE
-We use B<Devel::Cover> to test the code coverage of our tests, below is the
-B<Devel::Cover> report on this module's test suite.
+B<Devel::Cover> is used to test the code coverage of the tests. Below is the
+B<Devel::Cover> report on this distribution's test suite.
- ----------------------------------- ------ ------ ------ ------ ------ ------
- File stmt bran cond sub time total
- ----------------------------------- ------ ------ ------ ------ ------ ------
- blib/lib/DBM/Deep.pm 94.9 80.6 73.0 100.0 37.9 90.4
- blib/lib/DBM/Deep/Array.pm 100.0 91.1 100.0 100.0 18.2 98.1
- blib/lib/DBM/Deep/Engine.pm 98.9 87.3 80.0 100.0 34.2 95.2
- blib/lib/DBM/Deep/Hash.pm 100.0 87.5 100.0 100.0 9.7 97.3
- Total 97.9 85.9 79.7 100.0 100.0 94.3
- ----------------------------------- ------ ------ ------ ------ ------ ------
+ ---------------------------- ------ ------ ------ ------ ------ ------ ------
+ File stmt bran cond sub pod time total
+ ---------------------------- ------ ------ ------ ------ ------ ------ ------
+ blib/lib/DBM/Deep.pm 96.2 89.0 75.0 95.8 89.5 36.0 92.9
+ blib/lib/DBM/Deep/Array.pm 96.1 88.3 100.0 96.4 100.0 15.9 94.7
+ blib/lib/DBM/Deep/Engine.pm 96.6 86.6 89.5 100.0 0.0 20.0 91.0
+ blib/lib/DBM/Deep/File.pm 99.4 88.3 55.6 100.0 0.0 19.6 89.5
+ blib/lib/DBM/Deep/Hash.pm 98.5 83.3 100.0 100.0 100.0 8.5 96.3
+ Total 96.9 87.4 81.2 98.0 38.5 100.0 92.1
+ ---------------------------- ------ ------ ------ ------ ------ ------ ------
=head1 MORE INFORMATION
Check out the DBM::Deep Google Group at L<http://groups.google.com/group/DBM-Deep>
-or send email to L<DBM-Deep@googlegroups.com>.
+or send email to L<DBM-Deep@googlegroups.com>. You can also visit #dbm-deep on
+irc.perl.org
-=head1 AUTHORS
+The source code repository is at L<http://svn.perl.org/modules/DBM-Deep>
-Joseph Huckaby, L<jhuckaby@cpan.org>
+=head1 MAINTAINERS
Rob Kinyon, L<rkinyon@cpan.org>
+Originally written by Joseph Huckaby, L<jhuckaby@cpan.org>
+
Special thanks to Adam Sah and Rich Gaushell! You know why :-)
=head1 SEE ALSO