# DB_File.pm -- Perl 5 interface to Berkeley DB
#
# written by Paul Marquess (Paul.Marquess@btinternet.com)
-# last modified 21st February 1999
-# version 1.64
+# last modified 4th September 1999
+# version 1.71
#
-# Copyright (c) 1995-9 Paul Marquess. All rights reserved.
+# Copyright (c) 1995-1999 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.
use Carp;
-$VERSION = "1.64" ;
+$VERSION = "1.71" ;
#typedef enum { DB_BTREE, DB_HASH, DB_RECNO } DBTYPE;
$DB_BTREE = new DB_File::BTREEINFO ;
require Tie::Hash;
require Exporter;
use AutoLoader;
-require DynaLoader;
-@ISA = qw(Tie::Hash Exporter DynaLoader);
+use XSLoader ();
+@ISA = qw(Tie::Hash Exporter);
@EXPORT = qw(
$DB_BTREE $DB_HASH $DB_RECNO
($constname = $AUTOLOAD) =~ s/.*:://;
my $val = constant($constname, @_ ? $_[0] : 0);
if ($! != 0) {
- if ($! =~ /Invalid/) {
+ if ($! =~ /Invalid/ || $!{EINVAL}) {
$AutoLoader::AUTOLOAD = $AUTOLOAD;
goto &AutoLoader::AUTOLOAD;
}
# };
#}
-bootstrap DB_File $VERSION;
+XSLoader::load 'DB_File', $VERSION;
# Preloaded methods go here. Autoload methods go after __END__, and are
# processed by the autosplit program.
$a = $X->shift;
$X->unshift(list);
+ # 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 ;
B<DB_File> is a module which allows Perl programs to make use of the
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>). 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.
+version of DB, see L<Using DB_File with Berkeley DB version 2 or 3>).
+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 Using DB_File with Berkeley DB version 2
+=head2 Using DB_File with Berkeley DB version 2 or 3
Although B<DB_File> is intended to be used with Berkeley DB version 1,
-it can also be used with version 2. In this case the interface is
+it can also be used with version 2.or 3 In this case the interface is
limited to the functionality provided by Berkeley DB 1.x. Anywhere the
-version 2 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 without any changes.
+version 2 or 3 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 3 without any changes.
If you want to make use of the new features available in Berkeley DB
-2.x, use the Perl module B<BerkeleyDB> instead.
+2.x or 3.x, use the Perl module B<BerkeleyDB> instead.
At the time of writing this document the B<BerkeleyDB> module is still
alpha quality (the version number is < 1.0), and so unsuitable for use
in any serious development work. Once its version number is >= 1.0, it
is considered stable enough for real work.
-B<Note:> The database file format has changed in Berkeley DB version 2.
-If you cannot recreate your databases, you must dump any existing
-databases with the C<db_dump185> utility that comes with Berkeley DB.
-Once you have rebuilt DB_File to use Berkeley DB version 2, your
+B<Note:> The database file format has changed in both Berkeley DB
+version 2 and 3. If you cannot recreate your databases, you must dump
+any existing databases with the C<db_dump185> utility that comes with
+Berkeley DB.
+Once you have rebuilt DB_File to use Berkeley DB version 2 or 3, 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 of Berkeley DB with
-DB_File.
+Please read L<"COPYRIGHT"> before using version 2.x or 3.x of Berkeley
+DB with DB_File.
=head2 Interface to Berkeley DB
use DB_File ;
use vars qw( %h $k $v ) ;
+ unlink "fruit" ;
tie %h, "DB_File", "fruit", O_RDWR|O_CREAT, 0640, $DB_HASH
or die "Cannot open file 'fruit': $!\n";
# specify the Perl sub that will do the comparison
$DB_BTREE->{'compare'} = \&Compare ;
+ unlink "tree" ;
tie %h, "DB_File", "tree", O_RDWR|O_CREAT, 0640, $DB_BTREE
or die "Cannot open file 'tree': $!\n" ;
# iterate through the associative array
# and print each key/value pair.
- foreach (keys %h)
+ foreach (sort keys %h)
{ print "$_ -> $h{$_}\n" }
untie %h ;
So assuming the database created above, we can use C<get_dup> like
this:
+ use strict ;
+ use DB_File ;
+
+ use vars qw($filename $x %h ) ;
+
+ $filename = "tree" ;
+
+ # Enable duplicate records
+ $DB_BTREE->{'flags'} = R_DUP ;
+
+ $x = tie %h, "DB_File", $filename, O_RDWR|O_CREAT, 0640, $DB_BTREE
+ or die "Cannot open $filename: $!\n";
+
my $cnt = $x->get_dup("Wall") ;
print "Wall occurred $cnt times\n" ;
print "Larry is there\n" if $hash{'Larry'} ;
print "There are $hash{'Brick'} Brick Walls\n" ;
- my @list = $x->get_dup("Wall") ;
+ my @list = sort $x->get_dup("Wall") ;
print "Wall => [@list]\n" ;
@list = $x->get_dup("Smith") ;
prints this
- Larry Wall is there
+ Larry Wall is there
Harry Wall is not there
$st == 0 ;
$st = $x->seq($key, $value, R_NEXT) )
- { print "$key -> $value\n" }
+ { print "$key -> $value\n" }
print "\nPARTIAL MATCH\n" ;
use strict ;
use DB_File ;
+ my $filename = "text" ;
+ unlink $filename ;
+
my @h ;
- tie @h, "DB_File", "text", O_RDWR|O_CREAT, 0640, $DB_RECNO
+ tie @h, "DB_File", $filename, O_RDWR|O_CREAT, 0640, $DB_RECNO
or die "Cannot open file 'text': $!\n" ;
# Add a few key/value pairs to the file
The array contains 5 entries
popped black
- unshifted white
+ shifted white
Element 1 Exists with value blue
The last element is green
The 2nd last element is yellow
=back
+=head1 DBM FILTERS
+
+A DBM Filter is a piece of code that is be used when you I<always>
+want to make the same transformation to all keys and/or values in a
+DBM database.
+
+There are four methods associated with DBM Filters. All work identically,
+and each is used to install (or uninstall) a single DBM Filter. Each
+expects a single parameter, namely a reference to a sub. The only
+difference between them is the place that the filter is installed.
+
+To summarise:
+
+=over 5
+
+=item B<filter_store_key>
+
+If a filter has been installed with this method, it will be invoked
+every time you write a key to a DBM database.
+
+=item B<filter_store_value>
+
+If a filter has been installed with this method, it will be invoked
+every time you write a value to a DBM database.
+
+
+=item B<filter_fetch_key>
+
+If a filter has been installed with this method, it will be invoked
+every time you read a key from a DBM database.
+
+=item B<filter_fetch_value>
+
+If a filter has been installed with this method, it will be invoked
+every time you read a value from a DBM database.
+
+=back
+
+You can use any combination of the methods, from none, to all four.
+
+All filter methods return the existing filter, if present, or C<undef>
+in not.
+
+To delete a filter pass C<undef> to it.
+
+=head2 The Filter
+
+When each filter is called by Perl, a local copy of C<$_> 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 strict ;
+ use DB_File ;
+
+ my %hash ;
+ my $filename = "/tmp/filt" ;
+ unlink $filename ;
+
+ my $db = tie %hash, 'DB_File', $filename, O_CREAT|O_RDWR, 0666, $DB_HASH
+ or die "Cannot open $filename: $!\n" ;
+
+ # 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" } ) ;
+
+ $hash{"abc"} = "def" ;
+ my $a = $hash{"ABC"} ;
+ # ...
+ undef $db ;
+ untie %hash ;
+
+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 Another Example -- Key is a C int.
+
+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:
+
+ $hash{12345} = "soemthing" ;
+
+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.
+
+Here is a DBM Filter that does it:
+
+ use strict ;
+ use DB_File ;
+ my %hash ;
+ my $filename = "/tmp/filt" ;
+ unlink $filename ;
+
+
+ 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 ;
+
+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.
+
=head1 HINTS AND TIPS
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.
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 REFERENCES
+
+Articles that are either about B<DB_File> or make use of it.
+
+=over 5
+
+=item 1.
+
+I<Full-Text Searching in Perl>, Tim Kientzle (tkientzle@ddj.com),
+Dr. Dobb's Journal, Issue 295, January 1999, pp 34-41
+
+=back
+
=head1 HISTORY
Moved to the Changes file.
L<perlmod/CPAN> for details), in the directory
F<modules/by-module/DB_File>.
-This version of B<DB_File> will work with either version 1.x or 2.x of
-Berkeley DB, but is limited to the functionality provided by version 1.
+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.
-The official web site for Berkeley DB is
-F<http://www.sleepycat.com/db>. The ftp equivalent is
-F<ftp.sleepycat.com:/pub>. Both versions 1 and 2 of Berkeley DB are
-available there.
+The official web site for Berkeley DB is F<http://www.sleepycat.com>.
+All versions of Berkeley DB are available there.
Alternatively, Berkeley DB version 1 is available at your nearest CPAN
archive in F<src/misc/db.1.85.tar.gz>.
=head1 COPYRIGHT
-Copyright (c) 1995-9 Paul Marquess. All rights reserved. This program
+Copyright (c) 1995-1999 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.
=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