# DB_File.pm -- Perl 5 interface to Berkeley DB
#
-# written by Paul Marquess (pmarquess@bfsec.bt.co.uk)
-# last modified 4th Sept 1996
-# version 1.03
+# written by Paul Marquess (Paul.Marquess@btinternet.com)
+# last modified 1st March 2002
+# version 1.804
+#
+# Copyright (c) 1995-2002 Paul Marquess. All rights reserved.
+# This program is free software; you can redistribute it and/or
+# modify it under the same terms as Perl itself.
+
package DB_File::HASHINFO ;
+require 5.00404;
+
+use warnings;
use strict;
use Carp;
require Tie::Hash;
bless \%x, $pkg ;
}
+
sub TIEHASH
{
my $pkg = shift ;
- bless { 'bsize' => undef,
- 'ffactor' => undef,
- 'nelem' => undef,
- 'cachesize' => undef,
- 'hash' => undef,
- 'lorder' => undef,
- }, $pkg ;
+ bless { VALID => { map {$_, 1}
+ qw( bsize ffactor nelem cachesize hash lorder)
+ },
+ GOT => {}
+ }, $pkg ;
}
+
sub FETCH
{
my $self = shift ;
my $key = shift ;
- return $self->{$key} if exists $self->{$key} ;
+ return $self->{GOT}{$key} if exists $self->{VALID}{$key} ;
my $pkg = ref $self ;
croak "${pkg}::FETCH - Unknown element '$key'" ;
my $key = shift ;
my $value = shift ;
- if ( exists $self->{$key} )
+ if ( exists $self->{VALID}{$key} )
{
- $self->{$key} = $value ;
+ $self->{GOT}{$key} = $value ;
return ;
}
my $self = shift ;
my $key = shift ;
- if ( exists $self->{$key} )
+ if ( exists $self->{VALID}{$key} )
{
- delete $self->{$key} ;
+ delete $self->{GOT}{$key} ;
return ;
}
my $self = shift ;
my $key = shift ;
- exists $self->{$key} ;
+ exists $self->{VALID}{$key} ;
}
sub NotHere
{
- my $pkg = shift ;
+ my $self = shift ;
my $method = shift ;
- croak "${pkg} does not define the method ${method}" ;
+ croak ref($self) . " does not define the method ${method}" ;
}
-sub DESTROY { undef %{$_[0]} }
-sub FIRSTKEY { my $self = shift ; $self->NotHere(ref $self, "FIRSTKEY") }
-sub NEXTKEY { my $self = shift ; $self->NotHere(ref $self, "NEXTKEY") }
-sub CLEAR { my $self = shift ; $self->NotHere(ref $self, "CLEAR") }
+sub FIRSTKEY { my $self = shift ; $self->NotHere("FIRSTKEY") }
+sub NEXTKEY { my $self = shift ; $self->NotHere("NEXTKEY") }
+sub CLEAR { my $self = shift ; $self->NotHere("CLEAR") }
package DB_File::RECNOINFO ;
+use warnings;
use strict ;
@DB_File::RECNOINFO::ISA = qw(DB_File::HASHINFO) ;
{
my $pkg = shift ;
- bless { 'bval' => undef,
- 'cachesize' => undef,
- 'psize' => undef,
- 'flags' => undef,
- 'lorder' => undef,
- 'reclen' => undef,
- 'bfname' => "",
- }, $pkg ;
+ bless { VALID => { map {$_, 1}
+ qw( bval cachesize psize flags lorder reclen bfname )
+ },
+ GOT => {},
+ }, $pkg ;
}
package DB_File::BTREEINFO ;
+use warnings;
use strict ;
@DB_File::BTREEINFO::ISA = qw(DB_File::HASHINFO) ;
{
my $pkg = shift ;
- bless { 'flags' => undef,
- 'cachesize' => undef,
- 'maxkeypage' => undef,
- 'minkeypage' => undef,
- 'psize' => undef,
- 'compare' => undef,
- 'prefix' => undef,
- 'lorder' => undef,
- }, $pkg ;
+ bless { VALID => { map {$_, 1}
+ qw( flags cachesize maxkeypage minkeypage psize
+ compare prefix lorder )
+ },
+ GOT => {},
+ }, $pkg ;
}
package DB_File ;
+use warnings;
use strict;
-use vars qw($VERSION @ISA @EXPORT $AUTOLOAD $DB_BTREE $DB_HASH $DB_RECNO) ;
+our ($VERSION, @ISA, @EXPORT, $AUTOLOAD, $DB_BTREE, $DB_HASH, $DB_RECNO);
+our ($db_version, $use_XSLoader, $splice_end_array);
use Carp;
-$VERSION = "1.03" ;
+$VERSION = "1.804" ;
-#typedef enum { DB_BTREE, DB_HASH, DB_RECNO } DBTYPE;
-#$DB_BTREE = TIEHASH DB_File::BTREEINFO ;
-#$DB_HASH = TIEHASH DB_File::HASHINFO ;
-#$DB_RECNO = TIEHASH DB_File::RECNOINFO ;
+{
+ local $SIG{__WARN__} = sub {$splice_end_array = "@_";};
+ my @a =(1); splice(@a, 3);
+ $splice_end_array =
+ ($splice_end_array =~ /^splice\(\) offset past end of array at /);
+}
+#typedef enum { DB_BTREE, DB_HASH, DB_RECNO } DBTYPE;
$DB_BTREE = new DB_File::BTREEINFO ;
$DB_HASH = new DB_File::HASHINFO ;
$DB_RECNO = new DB_File::RECNOINFO ;
require Tie::Hash;
require Exporter;
use AutoLoader;
-require DynaLoader;
-@ISA = qw(Tie::Hash Exporter DynaLoader);
+BEGIN {
+ $use_XSLoader = 1 ;
+ { local $SIG{__DIE__} ; eval { require XSLoader } ; }
+
+ if ($@) {
+ $use_XSLoader = 0 ;
+ require DynaLoader;
+ @ISA = qw(DynaLoader);
+ }
+}
+
+push @ISA, qw(Tie::Hash Exporter);
@EXPORT = qw(
$DB_BTREE $DB_HASH $DB_RECNO
sub AUTOLOAD {
my($constname);
($constname = $AUTOLOAD) =~ s/.*:://;
- my $val = constant($constname, @_ ? $_[0] : 0);
- if ($! != 0) {
- if ($! =~ /Invalid/) {
- $AutoLoader::AUTOLOAD = $AUTOLOAD;
- goto &AutoLoader::AUTOLOAD;
+ my ($error, $val) = constant($constname);
+ Carp::croak $error if $error;
+ no strict 'refs';
+ *{$AUTOLOAD} = sub { $val };
+ goto &{$AUTOLOAD};
+}
+
+
+eval {
+ # Make all Fcntl O_XXX constants available for importing
+ require Fcntl;
+ my @O = grep /^O_/, @Fcntl::EXPORT;
+ Fcntl->import(@O); # first we import what we want to export
+ push(@EXPORT, @O);
+};
+
+if ($use_XSLoader)
+ { XSLoader::load("DB_File", $VERSION)}
+else
+ { bootstrap DB_File $VERSION }
+
+# Preloaded methods go here. Autoload methods go after __END__, and are
+# processed by the autosplit program.
+
+sub tie_hash_or_array
+{
+ my (@arg) = @_ ;
+ my $tieHASH = ( (caller(1))[3] =~ /TIEHASH/ ) ;
+
+ $arg[4] = tied %{ $arg[4] }
+ if @arg >= 5 && ref $arg[4] && $arg[4] =~ /=HASH/ && tied %{ $arg[4] } ;
+
+ # make recno in Berkeley DB version 2 work like recno in version 1.
+ if ($db_version > 1 and defined $arg[4] and $arg[4] =~ /RECNO/ and
+ $arg[1] and ! -e $arg[1]) {
+ open(FH, ">$arg[1]") or return undef ;
+ close FH ;
+ chmod $arg[3] ? $arg[3] : 0666 , $arg[1] ;
+ }
+
+ DoTie_($tieHASH, @arg) ;
+}
+
+sub TIEHASH
+{
+ tie_hash_or_array(@_) ;
+}
+
+sub TIEARRAY
+{
+ tie_hash_or_array(@_) ;
+}
+
+sub CLEAR
+{
+ my $self = shift;
+ my $key = 0 ;
+ my $value = "" ;
+ my $status = $self->seq($key, $value, R_FIRST());
+ my @keys;
+
+ while ($status == 0) {
+ push @keys, $key;
+ $status = $self->seq($key, $value, R_NEXT());
+ }
+ foreach $key (reverse @keys) {
+ my $s = $self->del($key);
+ }
+}
+
+sub EXTEND { }
+
+sub STORESIZE
+{
+ my $self = shift;
+ my $length = shift ;
+ my $current_length = $self->length() ;
+
+ if ($length < $current_length) {
+ my $key ;
+ for ($key = $current_length - 1 ; $key >= $length ; -- $key)
+ { $self->del($key) }
+ }
+ elsif ($length > $current_length) {
+ $self->put($length-1, "") ;
+ }
+}
+
+
+sub SPLICE
+{
+ my $self = shift;
+ my $offset = shift;
+ if (not defined $offset) {
+ warnings::warnif('uninitialized', 'Use of uninitialized value in splice');
+ $offset = 0;
+ }
+
+ my $length = @_ ? shift : 0;
+ # Carping about definedness comes _after_ the OFFSET sanity check.
+ # This is so we get the same error messages as Perl's splice().
+ #
+
+ my @list = @_;
+
+ my $size = $self->FETCHSIZE();
+
+ # 'If OFFSET is negative then it start that far from the end of
+ # the array.'
+ #
+ if ($offset < 0) {
+ my $new_offset = $size + $offset;
+ if ($new_offset < 0) {
+ die "Modification of non-creatable array value attempted, "
+ . "subscript $offset";
+ }
+ $offset = $new_offset;
+ }
+
+ if (not defined $length) {
+ warnings::warnif('uninitialized', 'Use of uninitialized value in splice');
+ $length = 0;
+ }
+
+ if ($offset > $size) {
+ $offset = $size;
+ warnings::warnif('misc', 'splice() offset past end of array')
+ if $splice_end_array;
+ }
+
+ # 'If LENGTH is omitted, removes everything from OFFSET onward.'
+ if (not defined $length) {
+ $length = $size - $offset;
+ }
+
+ # 'If LENGTH is negative, leave that many elements off the end of
+ # the array.'
+ #
+ if ($length < 0) {
+ $length = $size - $offset + $length;
+
+ if ($length < 0) {
+ # The user must have specified a length bigger than the
+ # length of the array passed in. But perl's splice()
+ # doesn't catch this, it just behaves as for length=0.
+ #
+ $length = 0;
+ }
+ }
+
+ if ($length > $size - $offset) {
+ $length = $size - $offset;
+ }
+
+ # $num_elems holds the current number of elements in the database.
+ my $num_elems = $size;
+
+ # 'Removes the elements designated by OFFSET and LENGTH from an
+ # array,'...
+ #
+ my @removed = ();
+ foreach (0 .. $length - 1) {
+ my $old;
+ my $status = $self->get($offset, $old);
+ if ($status != 0) {
+ my $msg = "error from Berkeley DB on get($offset, \$old)";
+ if ($status == 1) {
+ $msg .= ' (no such element?)';
+ }
+ else {
+ $msg .= ": error status $status";
+ if (defined $! and $! ne '') {
+ $msg .= ", message $!";
+ }
+ }
+ die $msg;
+ }
+ push @removed, $old;
+
+ $status = $self->del($offset);
+ if ($status != 0) {
+ my $msg = "error from Berkeley DB on del($offset)";
+ if ($status == 1) {
+ $msg .= ' (no such element?)';
+ }
+ else {
+ $msg .= ": error status $status";
+ if (defined $! and $! ne '') {
+ $msg .= ", message $!";
+ }
+ }
+ die $msg;
+ }
+
+ -- $num_elems;
+ }
+
+ # ...'and replaces them with the elements of LIST, if any.'
+ my $pos = $offset;
+ while (defined (my $elem = shift @list)) {
+ my $old_pos = $pos;
+ my $status;
+ if ($pos >= $num_elems) {
+ $status = $self->put($pos, $elem);
+ }
+ else {
+ $status = $self->put($pos, $elem, $self->R_IBEFORE);
+ }
+
+ if ($status != 0) {
+ my $msg = "error from Berkeley DB on put($pos, $elem, ...)";
+ if ($status == 1) {
+ $msg .= ' (no such element?)';
+ }
+ else {
+ $msg .= ", error status $status";
+ if (defined $! and $! ne '') {
+ $msg .= ", message $!";
+ }
+ }
+ die $msg;
+ }
+
+ die "pos unexpectedly changed from $old_pos to $pos with R_IBEFORE"
+ if $old_pos != $pos;
+
+ ++ $pos;
+ ++ $num_elems;
+ }
+
+ if (wantarray) {
+ # 'In list context, returns the elements removed from the
+ # array.'
+ #
+ return @removed;
+ }
+ elsif (defined wantarray and not wantarray) {
+ # 'In scalar context, returns the last element removed, or
+ # undef if no elements are removed.'
+ #
+ if (@removed) {
+ my $last = pop @removed;
+ return "$last";
}
else {
- my($pack,$file,$line) = caller;
- croak "Your vendor has not defined DB macro $constname, used at $file line $line.
-";
+ return undef;
}
}
- eval "sub $AUTOLOAD { $val }";
- goto &$AUTOLOAD;
+ elsif (not defined wantarray) {
+ # Void context
+ }
+ else { die }
}
+sub ::DB_File::splice { &SPLICE }
+sub find_dup
+{
+ croak "Usage: \$db->find_dup(key,value)\n"
+ unless @_ == 3 ;
+
+ my $db = shift ;
+ my ($origkey, $value_wanted) = @_ ;
+ my ($key, $value) = ($origkey, 0);
+ my ($status) = 0 ;
-# import borrowed from IO::File
-# exports Fcntl constants if available.
-sub import {
- my $pkg = shift;
- my $callpkg = caller;
- Exporter::export $pkg, $callpkg;
- eval {
- require Fcntl;
- Exporter::export 'Fcntl', $callpkg;
- };
-}
+ for ($status = $db->seq($key, $value, R_CURSOR() ) ;
+ $status == 0 ;
+ $status = $db->seq($key, $value, R_NEXT() ) ) {
-bootstrap DB_File $VERSION;
+ return 0 if $key eq $origkey and $value eq $value_wanted ;
+ }
-# Preloaded methods go here. Autoload methods go after __END__, and are
-# processed by the autosplit program.
+ return $status ;
+}
+sub del_dup
+{
+ croak "Usage: \$db->del_dup(key,value)\n"
+ unless @_ == 3 ;
+
+ my $db = shift ;
+ my ($key, $value) = @_ ;
+ my ($status) = $db->find_dup($key, $value) ;
+ return $status if $status != 0 ;
+
+ $status = $db->del($key, R_CURSOR() ) ;
+ return $status ;
+}
sub get_dup
{
my $counter = 0 ;
my $status = 0 ;
- # get the first value associated with the key, $key
- #$db->seq($key, $value, R_CURSOR()) ;
-
# iterate through the database until either EOF ($status == 0)
# or a different key is encountered ($key ne $origkey).
for ($status = $db->seq($key, $value, R_CURSOR()) ;
1;
__END__
-=cut
-
=head1 NAME
-DB_File - Perl5 access to Berkeley DB
+DB_File - Perl5 access to Berkeley DB version 1.x
=head1 SYNOPSIS
- use DB_File ;
- use strict 'untie' ;
-
+ use DB_File;
+
[$X =] tie %hash, 'DB_File', [$filename, $flags, $mode, $DB_HASH] ;
[$X =] tie %hash, 'DB_File', $filename, $flags, $mode, $DB_BTREE ;
[$X =] tie @array, 'DB_File', $filename, $flags, $mode, $DB_RECNO ;
$count = $X->get_dup($key) ;
@list = $X->get_dup($key) ;
%list = $X->get_dup($key, 1) ;
+ $status = $X->find_dup($key, $value) ;
+ $status = $X->del_dup($key, $value) ;
# RECNO only
$a = $X->length;
$X->push(list);
$a = $X->shift;
$X->unshift(list);
+ @r = $X->splice(offset, length, elements);
+
+ # DBM Filters
+ $old_filter = $db->filter_store_key ( sub { ... } ) ;
+ $old_filter = $db->filter_store_value( sub { ... } ) ;
+ $old_filter = $db->filter_fetch_key ( sub { ... } ) ;
+ $old_filter = $db->filter_fetch_value( sub { ... } ) ;
untie %hash ;
untie @array ;
=head1 DESCRIPTION
B<DB_File> is a module which allows Perl programs to make use of the
-facilities provided by Berkeley DB. If you intend to use this
-module you should really have a copy of the Berkeley DB manual pages at
-hand. The interface defined here mirrors the Berkeley DB interface
-closely.
+facilities provided by Berkeley DB version 1.x (if you have a newer
+version of DB, see L<Using DB_File with Berkeley DB version 2 or greater>).
+It is assumed that you have a copy of the Berkeley DB manual pages at
+hand when reading this documentation. The interface defined here
+mirrors the Berkeley DB interface closely.
Berkeley DB is a C library which provides a consistent interface to a
number of database formats. B<DB_File> provides an interface to all
=back
-=head2 How does DB_File interface to Berkeley DB?
+=head2 Using DB_File with Berkeley DB version 2 or greater
+
+Although B<DB_File> is intended to be used with Berkeley DB version 1,
+it can also be used with version 2, 3 or 4. In this case the interface is
+limited to the functionality provided by Berkeley DB 1.x. Anywhere the
+version 2 or greater interface differs, B<DB_File> arranges for it to work
+like version 1. This feature allows B<DB_File> scripts that were built
+with version 1 to be migrated to version 2 or greater without any changes.
+
+If you want to make use of the new features available in Berkeley DB
+2.x or greater, use the Perl module B<BerkeleyDB> instead.
+
+B<Note:> The database file format has changed multiple times in Berkeley
+DB version 2, 3 and 4. If you cannot recreate your databases, you
+must dump any existing databases with either the C<db_dump> or the
+C<db_dump185> utility that comes with Berkeley DB.
+Once you have rebuilt DB_File to use Berkeley DB version 2 or greater,
+your databases can be recreated using C<db_load>. Refer to the Berkeley DB
+documentation for further details.
+
+Please read L<"COPYRIGHT"> before using version 2.x or greater of Berkeley
+DB with DB_File.
+
+=head2 Interface to Berkeley DB
B<DB_File> allows access to Berkeley DB files using the tie() mechanism
in Perl 5 (for full details, see L<perlfunc/tie()>). This facility
$a->{'cachesize'} = 12345 ;
tie %y, 'DB_File', "filename", $flags, 0777, $a ;
-A few of the values need extra discussion here. When used, the C
+A few of the options need extra discussion here. When used, the C
equivalent of the keys C<hash>, C<compare> and C<prefix> store pointers
to C functions. In B<DB_File> these keys are used to store references
to Perl subs. Below are templates for each of the subs:
See L<Changing the BTREE sort order> for an example of using the
C<compare> template.
+If you are using the DB_RECNO interface and you intend making use of
+C<bval>, you should check out L<The 'bval' Option>.
+
=head2 Default Parameters
It is possible to omit some or all of the final 4 parameters in the
is equivalent to:
- tie %A, "DB_File", "filename", O_CREAT|O_RDWR, 0640, $DB_HASH ;
+ tie %A, "DB_File", "filename", O_CREAT|O_RDWR, 0666, $DB_HASH ;
It is also possible to omit the filename parameter as well, so the
call:
is equivalent to:
- tie %A, "DB_File", undef, O_CREAT|O_RDWR, 0640, $DB_HASH ;
+ tie %A, "DB_File", undef, O_CREAT|O_RDWR, 0666, $DB_HASH ;
See L<In Memory Databases> for a discussion on the use of C<undef>
in place of a filename.
file formats that B<DB_File> supports. It is also very straightforward
to use.
-=head2 A Simple Example.
+=head2 A Simple Example
This example shows how to create a database, add key/value pairs to the
database, delete keys/value pairs and finally how to enumerate the
contents of the database.
+ use warnings ;
+ use strict ;
use DB_File ;
- use strict 'untie' ;
+ our (%h, $k, $v) ;
- tie %h, "DB_File", "fruit", O_RDWR|O_CREAT, 0640, $DB_HASH
+ unlink "fruit" ;
+ tie %h, "DB_File", "fruit", O_RDWR|O_CREAT, 0666, $DB_HASH
or die "Cannot open file 'fruit': $!\n";
# Add a few key/value pairs to the file
here is the output:
Banana Exists
-
+
orange -> orange
tomato -> red
banana -> yellow
BTREE uses. Instead of using the normal lexical ordering, a case
insensitive compare function will be used.
+ use warnings ;
+ use strict ;
use DB_File ;
- use strict 'untie' ;
+
+ my %h ;
sub Compare
{
# specify the Perl sub that will do the comparison
$DB_BTREE->{'compare'} = \&Compare ;
- tie %h, "DB_File", "tree", O_RDWR|O_CREAT, 0640, $DB_BTREE
+ unlink "tree" ;
+ tie %h, "DB_File", "tree", O_RDWR|O_CREAT, 0666, $DB_BTREE
or die "Cannot open file 'tree': $!\n" ;
# Add a key/value pair to the file
you must use the same compare function every time you access the
database.
+=item 3
+
+Duplicate keys are entirely defined by the comparison function.
+In the case-insensitive example above, the keys: 'KEY' and 'key'
+would be considered duplicates, and assigning to the second one
+would overwrite the first. If duplicates are allowed for (with the
+R_DUPS flag discussed below), only a single copy of duplicate keys
+is stored in the database --- so (again with example above) assigning
+three values to the keys: 'KEY', 'Key', and 'key' would leave just
+the first key: 'KEY' in the database with three values. For some
+situations this results in information loss, so care should be taken
+to provide fully qualified comparison functions when necessary.
+For example, the above comparison routine could be modified to
+additionally compare case-sensitively if two keys are equal in the
+case insensitive comparison:
+
+ sub compare {
+ my($key1, $key2) = @_;
+ lc $key1 cmp lc $key2 ||
+ $key1 cmp $key2;
+ }
+
+And now you will only have duplicates when the keys themselves
+are truly the same. (note: in versions of the db library prior to
+about November 1996, such duplicate keys were retained so it was
+possible to recover the original keys in sets of keys that
+compared as equal).
+
+
=back
-=head2 Handling duplicate keys
+=head2 Handling Duplicate Keys
The BTREE file type optionally allows a single key to be associated
with an arbitrary number of values. This option is enabled by setting
want to manipulate a BTREE database with duplicate keys. Consider this
code:
+ use warnings ;
+ use strict ;
use DB_File ;
- use strict 'untie' ;
-
+
+ my ($filename, %h) ;
+
$filename = "tree" ;
unlink $filename ;
-
+
# Enable duplicate records
$DB_BTREE->{'flags'} = R_DUP ;
-
- tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0640, $DB_BTREE
+
+ tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0666, $DB_BTREE
or die "Cannot open $filename: $!\n";
-
+
# Add some key/value pairs to the file
$h{'Wall'} = 'Larry' ;
$h{'Wall'} = 'Brick' ; # Note the duplicate key
# iterate through the associative array
# and print each key/value pair.
- foreach (keys %h)
+ foreach (sort keys %h)
{ print "$_ -> $h{$_}\n" }
untie %h ;
Here is the script above rewritten using the C<seq> API method.
+ use warnings ;
+ use strict ;
use DB_File ;
- use strict 'untie' ;
-
+
+ my ($filename, $x, %h, $status, $key, $value) ;
+
$filename = "tree" ;
unlink $filename ;
-
+
# Enable duplicate records
$DB_BTREE->{'flags'} = R_DUP ;
-
- $x = tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0640, $DB_BTREE
+
+ $x = tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0666, $DB_BTREE
or die "Cannot open $filename: $!\n";
-
+
# Add some key/value pairs to the file
$h{'Wall'} = 'Larry' ;
$h{'Wall'} = 'Brick' ; # Note the duplicate key
$h{'Wall'} = 'Brick' ; # Note the duplicate key and value
$h{'Smith'} = 'John' ;
$h{'mouse'} = 'mickey' ;
-
+
# iterate through the btree using seq
# and print each key/value pair.
+ $key = $value = 0 ;
for ($status = $x->seq($key, $value, R_FIRST) ;
$status == 0 ;
$status = $x->seq($key, $value, R_NEXT) )
{ print "$key -> $value\n" }
-
+
undef $x ;
untie %h ;
This time we have got all the key/value pairs, including the multiple
values associated with the key C<Wall>.
-=head2 The get_dup method.
+To make life easier when dealing with duplicate keys, B<DB_File> comes with
+a few utility methods.
-B<DB_File> comes with a utility method, called C<get_dup>, to assist in
+=head2 The get_dup() Method
+
+The C<get_dup> method assists in
reading duplicate values from BTREE databases. The method can take the
following forms:
In list context, it returns all the values which match C<$key>. Note
that the values will be returned in an apparently random order.
-In list context, if the second parameter is present and evaluates TRUE,
-the method returns an associative array. The keys of the associative
-array correspond to the the values that matched in the BTREE and the
-values of the array are a count of the number of times that particular
-value occurred in the BTREE.
+In list context, if the second parameter is present and evaluates
+TRUE, the method returns an associative array. The keys of the
+associative array correspond to the values that matched in the BTREE
+and the values of the array are a count of the number of times that
+particular value occurred in the BTREE.
So assuming the database created above, we can use C<get_dup> like
this:
- $cnt = $x->get_dup("Wall") ;
+ use warnings ;
+ use strict ;
+ use DB_File ;
+
+ my ($filename, $x, %h) ;
+
+ $filename = "tree" ;
+
+ # Enable duplicate records
+ $DB_BTREE->{'flags'} = R_DUP ;
+
+ $x = tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0666, $DB_BTREE
+ or die "Cannot open $filename: $!\n";
+
+ my $cnt = $x->get_dup("Wall") ;
print "Wall occurred $cnt times\n" ;
- %hash = $x->get_dup("Wall", 1) ;
+ my %hash = $x->get_dup("Wall", 1) ;
print "Larry is there\n" if $hash{'Larry'} ;
print "There are $hash{'Brick'} Brick Walls\n" ;
- @list = $x->get_dup("Wall") ;
+ my @list = sort $x->get_dup("Wall") ;
print "Wall => [@list]\n" ;
@list = $x->get_dup("Smith") ;
print "Smith => [@list]\n" ;
-
+
@list = $x->get_dup("Dog") ;
print "Dog => [@list]\n" ;
Smith => [John]
Dog => []
+=head2 The find_dup() Method
+
+ $status = $X->find_dup($key, $value) ;
+
+This method checks for the existence of a specific key/value pair. If the
+pair exists, the cursor is left pointing to the pair and the method
+returns 0. Otherwise the method returns a non-zero value.
+
+Assuming the database from the previous example:
+
+ use warnings ;
+ use strict ;
+ use DB_File ;
+
+ my ($filename, $x, %h, $found) ;
+
+ $filename = "tree" ;
+
+ # Enable duplicate records
+ $DB_BTREE->{'flags'} = R_DUP ;
+
+ $x = tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0666, $DB_BTREE
+ or die "Cannot open $filename: $!\n";
+
+ $found = ( $x->find_dup("Wall", "Larry") == 0 ? "" : "not") ;
+ print "Larry Wall is $found there\n" ;
+
+ $found = ( $x->find_dup("Wall", "Harry") == 0 ? "" : "not") ;
+ print "Harry Wall is $found there\n" ;
+
+ undef $x ;
+ untie %h ;
+
+prints this
+
+ Larry Wall is there
+ Harry Wall is not there
+
+
+=head2 The del_dup() Method
+
+ $status = $X->del_dup($key, $value) ;
+
+This method deletes a specific key/value pair. It returns
+0 if they exist and have been deleted successfully.
+Otherwise the method returns a non-zero value.
+
+Again assuming the existence of the C<tree> database
+
+ use warnings ;
+ use strict ;
+ use DB_File ;
+
+ my ($filename, $x, %h, $found) ;
+
+ $filename = "tree" ;
+
+ # Enable duplicate records
+ $DB_BTREE->{'flags'} = R_DUP ;
+
+ $x = tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0666, $DB_BTREE
+ or die "Cannot open $filename: $!\n";
+
+ $x->del_dup("Wall", "Larry") ;
+
+ $found = ( $x->find_dup("Wall", "Larry") == 0 ? "" : "not") ;
+ print "Larry Wall is $found there\n" ;
+
+ undef $x ;
+ untie %h ;
+
+prints this
+
+ Larry Wall is not there
+
=head2 Matching Partial Keys
The BTREE interface has a feature which allows partial keys to be
Here is the relevant quote from the dbopen man page where it defines
the use of the R_CURSOR flag with seq:
-
Note, for the DB_BTREE access method, the returned key is not
necessarily an exact match for the specified key. The returned key
is the smallest key greater than or equal to the specified key,
permitting partial key matches and range searches.
-
In the example script below, the C<match> sub uses this feature to find
and print the first matching key/value pair given a partial key.
+ use warnings ;
+ use strict ;
use DB_File ;
use Fcntl ;
- use strict 'untie' ;
+
+ my ($filename, $x, %h, $st, $key, $value) ;
sub match
{
my $key = shift ;
- my $value ;
+ my $value = 0;
my $orig_key = $key ;
$x->seq($key, $value, R_CURSOR) ;
print "$orig_key\t-> $key\t-> $value\n" ;
$filename = "tree" ;
unlink $filename ;
- $x = tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0640, $DB_BTREE
+ $x = tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0666, $DB_BTREE
or die "Cannot open $filename: $!\n";
-
+
# Add some key/value pairs to the file
$h{'mouse'} = 'mickey' ;
$h{'Wall'} = 'Larry' ;
$h{'Walls'} = 'Brick' ;
$h{'Smith'} = 'John' ;
-
+
+ $key = $value = 0 ;
print "IN ORDER\n" ;
for ($st = $x->seq($key, $value, R_FIRST) ;
$st == 0 ;
$st = $x->seq($key, $value, R_NEXT) )
-
- { print "$key -> $value\n" }
-
+
+ { print "$key -> $value\n" }
+
print "\nPARTIAL MATCH\n" ;
match "Wa" ;
DB_RECNO provides an interface to flat text files. Both variable and
fixed length records are supported.
-In order to make RECNO more compatible with Perl the array offset for
+In order to make RECNO more compatible with Perl, the array offset for
all RECNO arrays begins at 0 rather than 1 as in Berkeley DB.
As with normal Perl arrays, a RECNO array can be accessed using
-2 the second last, and so on. Attempting to access an element before
the start of the array will raise a fatal run-time error.
+=head2 The 'bval' Option
+
+The operation of the bval option warrants some discussion. Here is the
+definition of bval from the Berkeley DB 1.85 recno manual page:
+
+ The delimiting byte to be used to mark the end of a
+ record for variable-length records, and the pad charac-
+ ter for fixed-length records. If no value is speci-
+ fied, newlines (``\n'') are used to mark the end of
+ variable-length records and fixed-length records are
+ padded with spaces.
+
+The second sentence is wrong. In actual fact bval will only default to
+C<"\n"> when the openinfo parameter in dbopen is NULL. If a non-NULL
+openinfo parameter is used at all, the value that happens to be in bval
+will be used. That means you always have to specify bval when making
+use of any of the options in the openinfo parameter. This documentation
+error will be fixed in the next release of Berkeley DB.
+
+That clarifies the situation with regards Berkeley DB itself. What
+about B<DB_File>? Well, the behavior defined in the quote above is
+quite useful, so B<DB_File> conforms to it.
+
+That means that you can specify other options (e.g. cachesize) and
+still have bval default to C<"\n"> for variable length records, and
+space for fixed length records.
+
+Also note that the bval option only allows you to specify a single byte
+as a delimeter.
+
=head2 A Simple Example
-Here is a simple example that uses RECNO.
+Here is a simple example that uses RECNO (if you are using a version
+of Perl earlier than 5.004_57 this example won't work -- see
+L<Extra RECNO Methods> for a workaround).
+ use warnings ;
+ use strict ;
use DB_File ;
- use strict 'untie' ;
- tie @h, "DB_File", "text", O_RDWR|O_CREAT, 0640, $DB_RECNO
+ my $filename = "text" ;
+ unlink $filename ;
+
+ my @h ;
+ tie @h, "DB_File", $filename, O_RDWR|O_CREAT, 0666, $DB_RECNO
or die "Cannot open file 'text': $!\n" ;
# Add a few key/value pairs to the file
$h[1] = "blue" ;
$h[2] = "yellow" ;
+ push @h, "green", "black" ;
+
+ my $elements = scalar @h ;
+ print "The array contains $elements entries\n" ;
+
+ my $last = pop @h ;
+ print "popped $last\n" ;
+
+ unshift @h, "white" ;
+ my $first = shift @h ;
+ print "shifted $first\n" ;
+
# Check for existence of a key
print "Element 1 Exists with value $h[1]\n" if $h[1] ;
Here is the output from the script:
-
+ The array contains 5 entries
+ popped black
+ shifted white
Element 1 Exists with value blue
- The last element is yellow
- The 2nd last element is blue
+ The last element is green
+ The 2nd last element is yellow
+
+=head2 Extra RECNO Methods
-=head2 Extra Methods
+If you are using a version of Perl earlier than 5.004_57, the tied
+array interface is quite limited. In the example script above
+C<push>, C<pop>, C<shift>, C<unshift>
+or determining the array length will not work with a tied array.
-As you can see from the example above, the tied array interface is
-quite limited. To make the interface more useful, a number of methods
-are supplied with B<DB_File> to simulate the standard array operations
-that are not currently implemented in Perl's tied array interface. All
-these methods are accessed via the object returned from the tie call.
+To make the interface more useful for older versions of Perl, a number
+of methods are supplied with B<DB_File> to simulate the missing array
+operations. All these methods are accessed via the object returned from
+the tie call.
Here are the methods:
Returns the number of elements in the array.
+=item B<$X-E<gt>splice(offset, length, elements);>
+
+Returns a splice of the the array.
+
=back
=head2 Another Example
described above. It also makes use of the API interface directly (see
L<THE API INTERFACE>).
+ use warnings ;
use strict ;
- use vars qw(@h $H $file $i) ;
+ my (@h, $H, $file, $i) ;
use DB_File ;
use Fcntl ;
-
+
$file = "text" ;
unlink $file ;
- $H = tie @h, "DB_File", $file, O_RDWR|O_CREAT, 0640, $DB_RECNO
+ $H = tie @h, "DB_File", $file, O_RDWR|O_CREAT, 0666, $DB_RECNO
or die "Cannot open file $file: $!\n" ;
-
+
# first create a text file to play with
$h[0] = "zero" ;
$h[1] = "one" ;
$h[3] = "three" ;
$h[4] = "four" ;
-
+
# Print the records in order.
#
# The length method is needed here because evaluating a tied
# same again, but use the API functions instead
print "\nREVERSE again\n" ;
- my ($s, $k, $v) ;
+ my ($s, $k, $v) = (0, 0, 0) ;
for ($s = $H->seq($k, $v, R_LAST) ;
$s == 0 ;
$s = $H->seq($k, $v, R_PREV))
B<Important:> If you have saved a copy of the object returned from
C<tie>, the underlying database file will I<not> be closed until both
the tied variable is untied and all copies of the saved object are
-destroyed. See L<The strict untie pragma> for more details.
+destroyed.
use DB_File ;
$db = tie %hash, "DB_File", "filename"
undef $db ;
untie %hash ;
+See L<The untie() Gotcha> for more details.
+
All the functions defined in L<dbopen> are available except for
close() and dbopen() itself. The B<DB_File> method interface to the
supported functions have been implemented to mirror the way Berkeley DB
Returns the file descriptor for the underlying database.
-See L<Locking Databases> for an example of how to make use of the
-C<fd> method to lock your database.
+See L<Locking: The Trouble with fd> for an explanation for why you should
+not use C<fd> to lock your database.
=item B<$status = $X-E<gt>seq($key, $value, $flags) ;>
=back
-=head1 HINTS AND TIPS
+=head1 DBM FILTERS
-=head2 The strict untie pragma
+A DBM Filter is a piece of code that is be used when you I<always>
+want to make the same transformation to all keys and/or values in a
+DBM database.
-If you run Perl version 5.004 or later (actually any version from the
-5.003_01 development release on will suffice) and you make use of the
-Berkeley DB API, it is is I<very> strongly recommended that you always
-include the C<use strict 'untie'> pragma in any of your scripts that
-make use of B<DB_File>.
+There are four methods associated with DBM Filters. All work identically,
+and each is used to install (or uninstall) a single DBM Filter. Each
+expects a single parameter, namely a reference to a sub. The only
+difference between them is the place that the filter is installed.
-Even if you don't currently make use of the API interface, it is still
-a good idea to include the pragma. It won't affect the performance of
-your script, but it will prevent problems in the future.
+To summarise:
-If possible you should try to run with the full strict pragma, but that
-is another story. For further details see L<strict> and
-L<perldsc/WHY YOU SHOULD ALWAYS C<use strict>>.
+=over 5
-To illustrate the importance of including the untie pragma, here is an
-example script that fails in an unexpected place because it doesn't use
-it:
+=item B<filter_store_key>
- use DB_File ;
- use Fcntl ;
-
- $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
- or die "Cannot tie first time: $!" ;
-
- $x{123} = 456 ;
-
- untie %x ;
-
- $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
- or die "Cannot tie second time: $!" ;
+If a filter has been installed with this method, it will be invoked
+every time you write a key to a DBM database.
- untie %x ;
+=item B<filter_store_value>
-When run the script will produce this error message:
+If a filter has been installed with this method, it will be invoked
+every time you write a value to a DBM database.
- Cannot tie second time: Invalid argument at bad.file line 12.
-Although the error message above refers to the second tie statement in
-the script, the source of the problem is really with the untie
-statement that precedes it.
+=item B<filter_fetch_key>
-To understand why there is a problem at all with the untie statement,
-consider what the tie does for a moment.
+If a filter has been installed with this method, it will be invoked
+every time you read a key from a DBM database.
-Whenever the tie is executed, it creates a logical link between a Perl
-variable, the associative array C<%x> in this case, and a Berkeley DB
-database, C<tst.fil>. The logical link ensures that all operation on
-the associative array are automatically mirrored to the database file.
+=item B<filter_fetch_value>
-In normal circumstances the untie is enough to break the logical link
-and also close the database. In this particular case there is another
-logical link, namely the API object returned from the tie and stored in
-C<$X>. Whenever the untie is executed in this case, only the link
-between the associative array and the database will be broken. The API
-object in C<$X> is still valid, so the database will not be closed.
+If a filter has been installed with this method, it will be invoked
+every time you read a value from a DBM database.
-The end result of this is that when the second tie is executed, the
-database will be in an inconsistent state (i.e. it is still opened by
-the first tie) - thus the second tie will fail.
+=back
-If the C<use strict 'untie'> pragma is included in the script, like
-this:
+You can use any combination of the methods, from none, to all four.
+
+All filter methods return the existing filter, if present, or C<undef>
+in not.
+
+To delete a filter pass C<undef> to it.
+
+=head2 The Filter
+
+When each filter is called by Perl, a local copy of C<$_> will contain
+the key or value to be filtered. Filtering is achieved by modifying
+the contents of C<$_>. The return code from the filter is ignored.
+
+=head2 An Example -- the NULL termination problem.
+Consider the following scenario. You have a DBM database
+that you need to share with a third-party C application. The C application
+assumes that I<all> keys and values are NULL terminated. Unfortunately
+when Perl writes to DBM databases it doesn't use NULL termination, so
+your Perl application will have to manage NULL termination itself. When
+you write to the database you will have to use something like this:
+
+ $hash{"$key\0"} = "$value\0" ;
+
+Similarly the NULL needs to be taken into account when you are considering
+the length of existing keys/values.
+
+It would be much better if you could ignore the NULL terminations issue
+in the main application code and have a mechanism that automatically
+added the terminating NULL to all keys and values whenever you write to
+the database and have them removed when you read from the database. As I'm
+sure you have already guessed, this is a problem that DBM Filters can
+fix very easily.
+
+ use warnings ;
+ use strict ;
use DB_File ;
- use Fcntl ;
- use strict 'untie' ;
-
- $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
- or die "Cannot tie first time: $!" ;
-
- $x{123} = 456 ;
-
- untie %x ;
-
- $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
- or die "Cannot tie second time: $!" ;
-then the error message becomes:
+ my %hash ;
+ my $filename = "/tmp/filt" ;
+ unlink $filename ;
- Can't untie: 1 inner references still exist at bad.file line 11.
+ my $db = tie %hash, 'DB_File', $filename, O_CREAT|O_RDWR, 0666, $DB_HASH
+ or die "Cannot open $filename: $!\n" ;
-which pinpoints the real problem. Finally the script can now be
-modified to fix the original problem by destroying the API object
-before the untie:
+ # Install DBM Filters
+ $db->filter_fetch_key ( sub { s/\0$// } ) ;
+ $db->filter_store_key ( sub { $_ .= "\0" } ) ;
+ $db->filter_fetch_value( sub { s/\0$// } ) ;
+ $db->filter_store_value( sub { $_ .= "\0" } ) ;
- ...
- $x{123} = 456 ;
+ $hash{"abc"} = "def" ;
+ my $a = $hash{"ABC"} ;
+ # ...
+ undef $db ;
+ untie %hash ;
- undef $X ;
- untie %x ;
-
- $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
- ...
+Hopefully the contents of each of the filters should be
+self-explanatory. Both "fetch" filters remove the terminating NULL,
+and both "store" filters add a terminating NULL.
-=head2 Locking Databases
-Concurrent access of a read-write database by several parties requires
-them all to use some kind of locking. Here's an example of Tom's that
-uses the I<fd> method to get the file descriptor, and then a careful
-open() to give something Perl will flock() for you. Run this repeatedly
-in the background to watch the locks granted in proper order.
+=head2 Another Example -- Key is a C int.
- use strict 'untie';
- use DB_File;
+Here is another real-life example. By default, whenever Perl writes to
+a DBM database it always writes the key and value as strings. So when
+you use this:
- use strict;
+ $hash{12345} = "soemthing" ;
- sub LOCK_SH { 1 }
- sub LOCK_EX { 2 }
- sub LOCK_NB { 4 }
- sub LOCK_UN { 8 }
+the key 12345 will get stored in the DBM database as the 5 byte string
+"12345". If you actually want the key to be stored in the DBM database
+as a C int, you will have to use C<pack> when writing, and C<unpack>
+when reading.
- my($oldval, $fd, $db, %db, $value, $key);
+Here is a DBM Filter that does it:
- $key = shift || 'default';
- $value = shift || 'magic';
+ use warnings ;
+ use strict ;
+ use DB_File ;
+ my %hash ;
+ my $filename = "/tmp/filt" ;
+ unlink $filename ;
- $value .= " $$";
- $db = tie(%db, 'DB_File', '/tmp/foo.db', O_CREAT|O_RDWR, 0644)
- || die "dbcreat /tmp/foo.db $!";
- $fd = $db->fd;
- print "$$: db fd is $fd\n";
- open(DB_FH, "+<&=$fd") || die "dup $!";
+ my $db = tie %hash, 'DB_File', $filename, O_CREAT|O_RDWR, 0666, $DB_HASH
+ or die "Cannot open $filename: $!\n" ;
+ $db->filter_fetch_key ( sub { $_ = unpack("i", $_) } ) ;
+ $db->filter_store_key ( sub { $_ = pack ("i", $_) } ) ;
+ $hash{123} = "def" ;
+ # ...
+ undef $db ;
+ untie %hash ;
- unless (flock (DB_FH, LOCK_SH | LOCK_NB)) {
- print "$$: CONTENTION; can't read during write update!
- Waiting for read lock ($!) ....";
- unless (flock (DB_FH, LOCK_SH)) { die "flock: $!" }
- }
- print "$$: Read lock granted\n";
+This time only two filters have been used -- we only need to manipulate
+the contents of the key, so it wasn't necessary to install any value
+filters.
- $oldval = $db{$key};
- print "$$: Old value was $oldval\n";
- flock(DB_FH, LOCK_UN);
+=head1 HINTS AND TIPS
+
+
+=head2 Locking: The Trouble with fd
- unless (flock (DB_FH, LOCK_EX | LOCK_NB)) {
- print "$$: CONTENTION; must have exclusive lock!
- Waiting for write lock ($!) ....";
- unless (flock (DB_FH, LOCK_EX)) { die "flock: $!" }
- }
+Until version 1.72 of this module, the recommended technique for locking
+B<DB_File> databases was to flock the filehandle returned from the "fd"
+function. Unfortunately this technique has been shown to be fundamentally
+flawed (Kudos to David Harris for tracking this down). Use it at your own
+peril!
- print "$$: Write lock granted\n";
- $db{$key} = $value;
- $db->sync;
- sleep 10;
+The locking technique went like this.
+ $db = tie(%db, 'DB_File', '/tmp/foo.db', O_CREAT|O_RDWR, 0666)
+ || die "dbcreat /tmp/foo.db $!";
+ $fd = $db->fd;
+ open(DB_FH, "+<&=$fd") || die "dup $!";
+ flock (DB_FH, LOCK_EX) || die "flock: $!";
+ ...
+ $db{"Tom"} = "Jerry" ;
+ ...
flock(DB_FH, LOCK_UN);
undef $db;
untie %db;
close(DB_FH);
- print "$$: Updated db to $key=$value\n";
-=head2 Sharing databases with C applications
+In simple terms, this is what happens:
+
+=over 5
+
+=item 1.
+
+Use "tie" to open the database.
+
+=item 2.
+
+Lock the database with fd & flock.
+
+=item 3.
+
+Read & Write to the database.
+
+=item 4.
+
+Unlock and close the database.
+
+=back
+
+Here is the crux of the problem. A side-effect of opening the B<DB_File>
+database in step 2 is that an initial block from the database will get
+read from disk and cached in memory.
+
+To see why this is a problem, consider what can happen when two processes,
+say "A" and "B", both want to update the same B<DB_File> database
+using the locking steps outlined above. Assume process "A" has already
+opened the database and has a write lock, but it hasn't actually updated
+the database yet (it has finished step 2, but not started step 3 yet). Now
+process "B" tries to open the same database - step 1 will succeed,
+but it will block on step 2 until process "A" releases the lock. The
+important thing to notice here is that at this point in time both
+processes will have cached identical initial blocks from the database.
+
+Now process "A" updates the database and happens to change some of the
+data held in the initial buffer. Process "A" terminates, flushing
+all cached data to disk and releasing the database lock. At this point
+the database on disk will correctly reflect the changes made by process
+"A".
+
+With the lock released, process "B" can now continue. It also updates the
+database and unfortunately it too modifies the data that was in its
+initial buffer. Once that data gets flushed to disk it will overwrite
+some/all of the changes process "A" made to the database.
+
+The result of this scenario is at best a database that doesn't contain
+what you expect. At worst the database will corrupt.
+
+The above won't happen every time competing process update the same
+B<DB_File> database, but it does illustrate why the technique should
+not be used.
+
+=head2 Safe ways to lock a database
+
+Starting with version 2.x, Berkeley DB has internal support for locking.
+The companion module to this one, B<BerkeleyDB>, provides an interface
+to this locking functionality. If you are serious about locking
+Berkeley DB databases, I strongly recommend using B<BerkeleyDB>.
+
+If using B<BerkeleyDB> isn't an option, there are a number of modules
+available on CPAN that can be used to implement locking. Each one
+implements locking differently and has different goals in mind. It is
+therefore worth knowing the difference, so that you can pick the right
+one for your application. Here are the three locking wrappers:
+
+=over 5
+
+=item B<Tie::DB_Lock>
+
+A B<DB_File> wrapper which creates copies of the database file for
+read access, so that you have a kind of a multiversioning concurrent read
+system. However, updates are still serial. Use for databases where reads
+may be lengthy and consistency problems may occur.
+
+=item B<Tie::DB_LockFile>
+
+A B<DB_File> wrapper that has the ability to lock and unlock the database
+while it is being used. Avoids the tie-before-flock problem by simply
+re-tie-ing the database when you get or drop a lock. Because of the
+flexibility in dropping and re-acquiring the lock in the middle of a
+session, this can be massaged into a system that will work with long
+updates and/or reads if the application follows the hints in the POD
+documentation.
+
+=item B<DB_File::Lock>
+
+An extremely lightweight B<DB_File> wrapper that simply flocks a lockfile
+before tie-ing the database and drops the lock after the untie. Allows
+one to use the same lockfile for multiple databases to avoid deadlock
+problems, if desired. Use for databases where updates are reads are
+quick and simple flock locking semantics are enough.
+
+=back
+
+=head2 Sharing Databases With C Applications
There is no technical reason why a Berkeley DB database cannot be
shared by both a Perl and a C application.
The vast majority of problems that are reported in this area boil down
to the fact that C strings are NULL terminated, whilst Perl strings are
-not.
+not. See L<DBM FILTERS> for a generic way to work around this problem.
Here is a real example. Netscape 2.0 keeps a record of the locations you
visit along with the time you last visited them in a DB_HASH database.
I<ggh> script (available from your nearest CPAN archive in
F<authors/id/TOMC/scripts/nshist.gz>).
+ use warnings ;
+ use strict ;
use DB_File ;
use Fcntl ;
- use strict 'untie' ;
+ my ($dotdir, $HISTORY, %hist_db, $href, $binary_time, $date) ;
$dotdir = $ENV{HOME} || $ENV{LOGNAME};
$HISTORY = "$dotdir/.netscape/history.db";
untie %hist_db ;
+=head2 The untie() Gotcha
+
+If you make use of the Berkeley DB API, it is I<very> strongly
+recommended that you read L<perltie/The untie Gotcha>.
+
+Even if you don't currently make use of the API interface, it is still
+worth reading it.
+
+Here is an example which illustrates the problem from a B<DB_File>
+perspective:
+
+ use DB_File ;
+ use Fcntl ;
+
+ my %x ;
+ my $X ;
+
+ $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_TRUNC
+ or die "Cannot tie first time: $!" ;
+
+ $x{123} = 456 ;
+
+ untie %x ;
+
+ tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
+ or die "Cannot tie second time: $!" ;
+
+ untie %x ;
+
+When run, the script will produce this error message:
+
+ Cannot tie second time: Invalid argument at bad.file line 14.
+
+Although the error message above refers to the second tie() statement
+in the script, the source of the problem is really with the untie()
+statement that precedes it.
+
+Having read L<perltie> you will probably have already guessed that the
+error is caused by the extra copy of the tied object stored in C<$X>.
+If you haven't, then the problem boils down to the fact that the
+B<DB_File> destructor, DESTROY, will not be called until I<all>
+references to the tied object are destroyed. Both the tied variable,
+C<%x>, and C<$X> above hold a reference to the object. The call to
+untie() will destroy the first, but C<$X> still holds a valid
+reference, so the destructor will not get called and the database file
+F<tst.fil> will remain open. The fact that Berkeley DB then reports the
+attempt to open a database that is already open via the catch-all
+"Invalid argument" doesn't help.
+
+If you run the script with the C<-w> flag the error message becomes:
+
+ untie attempted while 1 inner references still exist at bad.file line 12.
+ Cannot tie second time: Invalid argument at bad.file line 14.
+
+which pinpoints the real problem. Finally the script can now be
+modified to fix the original problem by destroying the API object
+before the untie:
+
+ ...
+ $x{123} = 456 ;
+
+ undef $X ;
+ untie %x ;
+
+ $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
+ ...
+
=head1 COMMON QUESTIONS
=item 1.
-Attempting to reopen a database without closing it. See
-L<The strict untie pragma> for an example.
+Attempting to reopen a database without closing it.
=item 2.
C<strict 'subs'> pragma (or the full strict pragma) in your script.
Consider this script:
+ use warnings ;
use strict ;
use DB_File ;
- use vars qw(%x) ;
+ my %x ;
tie %x, DB_File, "filename" ;
Running it produces the error in question:
Although it might seem like a real pain, it is really worth the effort
of having a C<use strict> in all your scripts.
-=head1 HISTORY
-
-=over
-
-=item 0.1
-
-First Release.
-
-=item 0.2
-
-When B<DB_File> is opening a database file it no longer terminates the
-process if I<dbopen> returned an error. This allows file protection
-errors to be caught at run time. Thanks to Judith Grass
-E<lt>grass@cybercash.comE<gt> for spotting the bug.
+=head1 REFERENCES
-=item 0.3
+Articles that are either about B<DB_File> or make use of it.
-Added prototype support for multiple btree compare callbacks.
-
-=item 1.0
-
-B<DB_File> has been in use for over a year. To reflect that, the
-version number has been incremented to 1.0.
-
-Added complete support for multiple concurrent callbacks.
-
-Using the I<push> method on an empty list didn't work properly. This
-has been fixed.
-
-=item 1.01
+=over 5
-Fixed a core dump problem with SunOS.
+=item 1.
-The return value from TIEHASH wasn't set to NULL when dbopen returned
-an error.
+I<Full-Text Searching in Perl>, Tim Kientzle (tkientzle@ddj.com),
+Dr. Dobb's Journal, Issue 295, January 1999, pp 34-41
-=item 1.02
+=back
-Merged OS/2 specific code into DB_File.xs
+=head1 HISTORY
-Removed some redundant code in DB_File.xs.
+Moved to the Changes file.
-Documentation update.
+=head1 BUGS
-Allow negative subscripts with RECNO interface.
+Some older versions of Berkeley DB had problems with fixed length
+records using the RECNO file format. This problem has been fixed since
+version 1.85 of Berkeley DB.
-Changed the default flags from O_RDWR to O_CREAT|O_RDWR.
+I am sure there are bugs in the code. If you do find any, or can
+suggest any enhancements, I would welcome your comments.
-The example code which showed how to lock a database needed a call to
-C<sync> added. Without it the resultant database file was empty.
+=head1 AVAILABILITY
-Added get_dup method.
+B<DB_File> comes with the standard Perl source distribution. Look in
+the directory F<ext/DB_File>. Given the amount of time between releases
+of Perl the version that ships with Perl is quite likely to be out of
+date, so the most recent version can always be found on CPAN (see
+L<perlmod/CPAN> for details), in the directory
+F<modules/by-module/DB_File>.
-=item 1.03
+This version of B<DB_File> will work with either version 1.x, 2.x or
+3.x of Berkeley DB, but is limited to the functionality provided by
+version 1.
-Documentation update.
+The official web site for Berkeley DB is F<http://www.sleepycat.com>.
+All versions of Berkeley DB are available there.
-B<DB_File> now imports the constants (O_RDWR, O_CREAT etc.) from Fcntl
-automatically.
+Alternatively, Berkeley DB version 1 is available at your nearest CPAN
+archive in F<src/misc/db.1.85.tar.gz>.
-The standard hash function C<exists> is now supported.
+If you are running IRIX, then get Berkeley DB version 1 from
+F<http://reality.sgi.com/ariel>. It has the patches necessary to
+compile properly on IRIX 5.3.
-Modified the behavior of get_dup. When it returns an associative
-array, the value is the count of the number of matching BTREE values.
+=head1 COPYRIGHT
-=head1 BUGS
+Copyright (c) 1995-2002 Paul Marquess. All rights reserved. This program
+is free software; you can redistribute it and/or modify it under the
+same terms as Perl itself.
-Some older versions of Berkeley DB had problems with fixed length
-records using the RECNO file format. The newest version at the time of
-writing was 1.85 - this seems to have fixed the problems with RECNO.
+Although B<DB_File> is covered by the Perl license, the library it
+makes use of, namely Berkeley DB, is not. Berkeley DB has its own
+copyright and its own license. Please take the time to read it.
-I am sure there are bugs in the code. If you do find any, or can
-suggest any enhancements, I would welcome your comments.
+Here are are few words taken from the Berkeley DB FAQ (at
+F<http://www.sleepycat.com>) regarding the license:
-=head1 AVAILABILITY
+ Do I have to license DB to use it in Perl scripts?
-B<DB_File> comes with the standard Perl source distribution. Look in
-the directory F<ext/DB_File>.
+ No. The Berkeley DB license requires that software that uses
+ Berkeley DB be freely redistributable. In the case of Perl, that
+ software is Perl, and not your scripts. Any Perl scripts that you
+ write are your property, including scripts that make use of
+ Berkeley DB. Neither the Perl license nor the Berkeley DB license
+ place any restriction on what you may do with them.
-Berkeley DB is available at your nearest CPAN archive (see
-L<perlmod/"CPAN"> for a list) in F<src/misc/db.1.85.tar.gz>, or via the
-host F<ftp.cs.berkeley.edu> in F</ucb/4bsd/db.tar.gz>. It is I<not> under
-the GPL.
+If you are in any doubt about the license situation, contact either the
+Berkeley DB authors or the author of DB_File. See L<"AUTHOR"> for details.
-If you are running IRIX, then get Berkeley DB from
-F<http://reality.sgi.com/ariel>. It has the patches necessary to
-compile properly on IRIX 5.3.
=head1 SEE ALSO
-L<perl(1)>, L<dbopen(3)>, L<hash(3)>, L<recno(3)>, L<btree(3)>
+L<perl(1)>, L<dbopen(3)>, L<hash(3)>, L<recno(3)>, L<btree(3)>,
+L<dbmfilter>
=head1 AUTHOR
The DB_File interface was written by Paul Marquess
-E<lt>pmarquess@bfsec.bt.co.ukE<gt>.
-Questions about the DB system itself may be addressed to Keith Bostic
-E<lt>bostic@cs.berkeley.eduE<gt>.
+E<lt>Paul.Marquess@btinternet.comE<gt>.
+Questions about the DB system itself may be addressed to
+E<lt>db@sleepycat.com<gt>.
=cut
projects / p5sagit/p5-mst-13.2.git / blobdiff