# DB_File.pm -- Perl 5 interface to Berkeley DB
#
# written by Paul Marquess (pmarquess@bfsec.bt.co.uk)
-# last modified 28th June 1996
-# version 1.02
+# last modified 20th Nov 1997
+# version 1.56
+#
+# Copyright (c) 1995, 1996, 1997 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 5.003 ;
+
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 ;
{
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 ;
{
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 => {},
+ }, $pkg ;
}
package DB_File ;
use strict;
-use vars qw($VERSION @ISA @EXPORT $AUTOLOAD $DB_BTREE $DB_HASH $DB_RECNO) ;
+use vars qw($VERSION @ISA @EXPORT $AUTOLOAD $DB_BTREE $DB_HASH $DB_RECNO $db_version) ;
use Carp;
-$VERSION = "1.02" ;
+$VERSION = "1.56" ;
#typedef enum { DB_BTREE, DB_HASH, DB_RECNO } DBTYPE;
-#$DB_BTREE = TIEHASH DB_File::BTREEINFO ;
-#$DB_HASH = TIEHASH DB_File::HASHINFO ;
-#$DB_RECNO = TIEHASH DB_File::RECNOINFO ;
-
$DB_BTREE = new DB_File::BTREEINFO ;
$DB_HASH = new DB_File::HASHINFO ;
$DB_RECNO = new DB_File::RECNOINFO ;
goto &$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);
+};
+
+## 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, '/^O_/';
+# };
+#}
+
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 = "" ;
+ 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 get_dup
{
my $db = shift ;
my $key = shift ;
my $flag = shift ;
- my $value ;
+ my $value = 0 ;
my $origkey = $key ;
my $wantarray = wantarray ;
+ my %values = () ;
my @values = () ;
my $counter = 0 ;
+ my $status = 0 ;
- # get the first value associated with the key, $key
- $db->seq($key, $value, R_CURSOR()) ;
-
- if ( $key eq $origkey) {
+ # iterate through the database until either EOF ($status == 0)
+ # or a different key is encountered ($key ne $origkey).
+ for ($status = $db->seq($key, $value, R_CURSOR()) ;
+ $status == 0 and $key eq $origkey ;
+ $status = $db->seq($key, $value, R_NEXT()) ) {
- while (1) {
- # save the value or count matches
- if ($wantarray)
- { push (@values, $value) ; push(@values, 1) if $flag }
- else
- { ++ $counter }
+ # save the value or count number of matches
+ if ($wantarray) {
+ if ($flag)
+ { ++ $values{$value} }
+ else
+ { push (@values, $value) }
+ }
+ else
+ { ++ $counter }
- # iterate through the database until either EOF
- # or a different key is encountered.
- last if $db->seq($key, $value, R_NEXT()) != 0 or $key ne $origkey ;
- }
}
- $wantarray ? @values : $counter ;
+ return ($wantarray ? ($flag ? %values : @values) : $counter) ;
}
1;
__END__
-=cut
-
=head1 NAME
-DB_File - Perl5 access to Berkeley DB
+DB_File - Perl5 access to Berkeley DB version 1.x
=head1 SYNOPSIS
use DB_File ;
- use Fcntl ;
[$X =] tie %hash, 'DB_File', [$filename, $flags, $mode, $DB_HASH] ;
[$X =] tie %hash, 'DB_File', $filename, $flags, $mode, $DB_BTREE ;
$status = $X->sync([$flags]) ;
$status = $X->fd ;
+ # BTREE only
$count = $X->get_dup($key) ;
@list = $X->get_dup($key) ;
%list = $X->get_dup($key, 1) ;
+ # RECNO only
+ $a = $X->length;
+ $a = $X->pop ;
+ $X->push(list);
+ $a = $X->shift;
+ $X->unshift(list);
+
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 page 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>). 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
+
+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
+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.
+
+If you want to make use of the new features available in Berkeley DB
+2.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 upgraded DB_File to use Berkeley DB version 2, 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.
+
+=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
In addition to the tie() interface, it is also possible to access most
of the functions provided in the Berkeley DB API directly.
-See L<"Using the Berkeley DB API Directly">.
+See L<THE API INTERFACE>.
=head2 Opening a Berkeley DB Database File
Berkeley DB uses the function dbopen() to open or create a database.
-Below is the C prototype for dbopen().
+Here is the C prototype for dbopen():
DB*
dbopen (const char * file, int flags, int mode,
The values stored in the hashes above are mostly the direct equivalent
of their C counterpart. Like their C counterparts, all are set to a
-default set of values - that means you don't have to set I<all> of the
+default values - that means you don't have to set I<all> of the
values when you only want to change one. Here is an example:
$a = new DB_File::HASHINFO ;
$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:
return $bytes ;
}
-See L<"Using BTREE"> for an example of using the C<compare>
+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
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>
+See L<In Memory Databases> for a discussion on the use of C<undef>
in place of a filename.
-=head2 Handling duplicate keys in BTREE databases
+=head2 In Memory Databases
+
+Berkeley DB allows the creation of in-memory databases by using NULL
+(that is, a C<(char *)0> in C) in place of the filename. B<DB_File>
+uses C<undef> instead of NULL to provide this functionality.
+
+=head1 DB_HASH
+
+The DB_HASH file format is probably the most commonly used of the three
+file formats that B<DB_File> supports. It is also very straightforward
+to use.
+
+=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 strict ;
+ use DB_File ;
+ use vars qw( %h $k $v ) ;
+
+ tie %h, "DB_File", "fruit", O_RDWR|O_CREAT, 0640, $DB_HASH
+ or die "Cannot open file 'fruit': $!\n";
+
+ # Add a few key/value pairs to the file
+ $h{"apple"} = "red" ;
+ $h{"orange"} = "orange" ;
+ $h{"banana"} = "yellow" ;
+ $h{"tomato"} = "red" ;
+
+ # Check for existence of a key
+ print "Banana Exists\n\n" if $h{"banana"} ;
+
+ # Delete a key/value pair.
+ delete $h{"apple"} ;
+
+ # print the contents of the file
+ while (($k, $v) = each %h)
+ { print "$k -> $v\n" }
+
+ untie %h ;
+
+here is the output:
+
+ Banana Exists
+
+ orange -> orange
+ tomato -> red
+ banana -> yellow
+
+Note that the like ordinary associative arrays, the order of the keys
+retrieved is in an apparently random order.
+
+=head1 DB_BTREE
+
+The DB_BTREE format is useful when you want to store data in a given
+order. By default the keys will be stored in lexical order, but as you
+will see from the example shown in the next section, it is very easy to
+define your own sorting function.
+
+=head2 Changing the BTREE sort order
+
+This script shows how to override the default sorting algorithm that
+BTREE uses. Instead of using the normal lexical ordering, a case
+insensitive compare function will be used.
+
+ use strict ;
+ use DB_File ;
+
+ my %h ;
+
+ sub Compare
+ {
+ my ($key1, $key2) = @_ ;
+ "\L$key1" cmp "\L$key2" ;
+ }
+
+ # 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
+ or die "Cannot open file 'tree': $!\n" ;
+
+ # Add a key/value pair to the file
+ $h{'Wall'} = 'Larry' ;
+ $h{'Smith'} = 'John' ;
+ $h{'mouse'} = 'mickey' ;
+ $h{'duck'} = 'donald' ;
+
+ # Delete
+ delete $h{"duck"} ;
+
+ # Cycle through the keys printing them in order.
+ # Note it is not necessary to sort the keys as
+ # the btree will have kept them in order automatically.
+ foreach (keys %h)
+ { print "$_\n" }
+
+ untie %h ;
+
+Here is the output from the code above.
+
+ mouse
+ Smith
+ Wall
-The BTREE file type in Berkeley DB optionally allows a single key to be
-associated with an arbitrary number of values. This option is enabled by
-setting the flags element of C<$DB_BTREE> to R_DUP when creating the
+There are a few point to bear in mind if you want to change the
+ordering in a BTREE database:
+
+=over 5
+
+=item 1.
+
+The new compare function must be specified when you create the database.
+
+=item 2.
+
+You cannot change the ordering once the database has been created. Thus
+you must use the same compare function every time you access the
database.
+=back
+
+=head2 Handling Duplicate Keys
+
+The BTREE file type optionally allows a single key to be associated
+with an arbitrary number of values. This option is enabled by setting
+the flags element of C<$DB_BTREE> to R_DUP when creating the database.
+
There are some difficulties in using the tied hash interface if you
want to manipulate a BTREE database with duplicate keys. Consider this
code:
+ use strict ;
use DB_File ;
- use Fcntl ;
-
+
+ use vars qw($filename %h ) ;
+
$filename = "tree" ;
unlink $filename ;
# 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' ;
$h{'mouse'} = 'mickey' ;
foreach (keys %h)
{ print "$_ -> $h{$_}\n" }
+ untie %h ;
+
Here is the output:
Smith -> John
Wall -> Larry
Wall -> Larry
+ Wall -> Larry
mouse -> mickey
-As you can see 2 records have been successfully created with key C<Wall>
+As you can see 3 records have been successfully created with key C<Wall>
- the only thing is, when they are retrieved from the database they
-both I<seem> to have the same value, namely C<Larry>. The problem is
-caused by the way that the associative array interface works.
-Basically, when the associative array interface is used to fetch the
-value associated with a given key, it will only ever retrieve the first
-value.
+I<seem> to have the same value, namely C<Larry>. The problem is caused
+by the way that the associative array interface works. Basically, when
+the associative array interface is used to fetch the value associated
+with a given key, it will only ever retrieve the first value.
Although it may not be immediately obvious from the code above, the
associative array interface can be used to write values with duplicate
The way to get around this problem is to use the Berkeley DB API method
called C<seq>. This method allows sequential access to key/value
-pairs. See L<"Using the Berkeley DB API Directly"> for details of both
-the C<seq> method and the API in general.
+pairs. See L<THE API INTERFACE> for details of both the C<seq> method
+and the API in general.
Here is the script above rewritten using the C<seq> API method.
+ use strict ;
use DB_File ;
- use Fcntl ;
+ use vars qw($filename $x %h $status $key $value) ;
+
$filename = "tree" ;
unlink $filename ;
# 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' ;
- # Point to the first record in the btree
- $x->seq($key, $value, R_FIRST) ;
-
- # now iterate through the rest of the btree
+ # iterate through the btree using seq
# and print each key/value pair.
- print "$key -> $value\n" ;
- while ( $x->seq($key, $value, R_NEXT) == 0)
+ $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 $x ;
Smith -> John
Wall -> Brick
+ Wall -> Brick
Wall -> Larry
mouse -> mickey
-This time we have got all the key/value pairs, including both the
+This time we have got all the key/value pairs, including the multiple
values associated with the key C<Wall>.
-C<DB_File> comes with a utility method, called C<get_dup>, to assist in
+=head2 The get_dup() Method
+
+B<DB_File> comes with a utility method, called C<get_dup>, to assist in
reading duplicate values from BTREE databases. The method can take the
following forms:
with the key, C<$key>.
In list context, it returns all the values which match C<$key>. Note
-that the values returned will be in an apparently random order.
+that the values will be returned in an apparently random order.
-If the second parameter is present and evaluates TRUE, the method
-returns an associative array whose keys correspond to the the values
-from the BTREE and whose values are all C<1>.
+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_dups> like
+So assuming the database created above, we can use C<get_dup> like
this:
- $cnt = $x->get_dups("Wall") ;
+ my $cnt = $x->get_dup("Wall") ;
print "Wall occurred $cnt times\n" ;
- %hash = $x->get_dups("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_dups("Wall") ;
+ my @list = $x->get_dup("Wall") ;
print "Wall => [@list]\n" ;
- @list = $x->get_dups("Smith") ;
+ @list = $x->get_dup("Smith") ;
print "Smith => [@list]\n" ;
- @list = $x->get_dups("Dog") ;
+ @list = $x->get_dup("Dog") ;
print "Dog => [@list]\n" ;
and it will print:
- Wall occurred 2 times
+ Wall occurred 3 times
Larry is there
- Wall => [Brick Larry]
+ There are 2 Brick Walls
+ Wall => [Brick Brick Larry]
Smith => [John]
Dog => []
-=head2 RECNO
+=head2 Matching Partial Keys
+
+The BTREE interface has a feature which allows partial keys to be
+matched. This functionality is I<only> available when the C<seq> method
+is used along with the R_CURSOR flag.
+
+ $x->seq($key, $value, R_CURSOR) ;
+
+Here is the relevant quote from the dbopen man page where it defines
+the use of the R_CURSOR flag with seq:
+
+ Note, for the DB_BTREE access method, the returned key is not
+ necessarily an exact match for the specified key. The returned key
+ is the smallest key greater than or equal to the specified key,
+ permitting partial key matches and range searches.
+
+In the example script below, the C<match> sub uses this feature to find
+and print the first matching key/value pair given a partial key.
+
+ use strict ;
+ use DB_File ;
+ use Fcntl ;
+
+ use vars qw($filename $x %h $st $key $value) ;
+
+ sub match
+ {
+ my $key = shift ;
+ 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
+ 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 "\nPARTIAL MATCH\n" ;
+
+ match "Wa" ;
+ match "A" ;
+ match "a" ;
+
+ undef $x ;
+ untie %h ;
+
+Here is the output:
+
+ IN ORDER
+ Smith -> John
+ Wall -> Larry
+ Walls -> Brick
+ mouse -> mickey
+
+ PARTIAL MATCH
+ Wa -> Wall -> Larry
+ A -> Smith -> John
+ a -> mouse -> mickey
+
+=head1 DB_RECNO
+
+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
all RECNO arrays begins at 0 rather than 1 as in Berkeley DB.
-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 In Memory Databases
+=head2 The 'bval' Option
-Berkeley DB allows the creation of in-memory databases by using NULL
-(that is, a C<(char *)0> in C) in place of the filename. B<DB_File>
-uses C<undef> instead of NULL to provide this functionality.
+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 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.
+
+=head2 A Simple Example
+
+Here is a simple example that uses RECNO.
+
+ use strict ;
+ use DB_File ;
+
+ my @h ;
+ tie @h, "DB_File", "text", O_RDWR|O_CREAT, 0640, $DB_RECNO
+ or die "Cannot open file 'text': $!\n" ;
+
+ # Add a few key/value pairs to the file
+ $h[0] = "orange" ;
+ $h[1] = "blue" ;
+ $h[2] = "yellow" ;
+
+ # Check for existence of a key
+ print "Element 1 Exists with value $h[1]\n" if $h[1] ;
+
+ # use a negative index
+ print "The last element is $h[-1]\n" ;
+ print "The 2nd last element is $h[-2]\n" ;
+
+ untie @h ;
+
+Here is the output from the script:
+
+
+ Element 1 Exists with value blue
+ The last element is yellow
+ The 2nd last element is blue
+
+=head2 Extra Methods
+
+As you can see from the example above, the tied array interface is
+quite limited. To make the interface more useful, a number of methods
+are supplied with B<DB_File> to simulate the standard array operations
+that are not currently implemented in Perl's tied array interface. All
+these methods are accessed via the object returned from the tie call.
+
+Here are the methods:
+
+=over 5
+
+=item B<$X-E<gt>push(list) ;>
+
+Pushes the elements of C<list> to the end of the array.
+
+=item B<$value = $X-E<gt>pop ;>
+
+Removes and returns the last element of the array.
+
+=item B<$X-E<gt>shift>
+
+Removes and returns the first element of the array.
+
+=item B<$X-E<gt>unshift(list) ;>
+
+Pushes the elements of C<list> to the start of the array.
+
+=item B<$X-E<gt>length>
+
+Returns the number of elements in the array.
+
+=back
+
+=head2 Another Example
+
+Here is a more complete example that makes use of some of the methods
+described above. It also makes use of the API interface directly (see
+L<THE API INTERFACE>).
+
+ use strict ;
+ use vars qw(@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
+ or die "Cannot open file $file: $!\n" ;
+
+ # first create a text file to play with
+ $h[0] = "zero" ;
+ $h[1] = "one" ;
+ $h[2] = "two" ;
+ $h[3] = "three" ;
+ $h[4] = "four" ;
+
+
+ # Print the records in order.
+ #
+ # The length method is needed here because evaluating a tied
+ # array in a scalar context does not return the number of
+ # elements in the array.
+
+ print "\nORIGINAL\n" ;
+ foreach $i (0 .. $H->length - 1) {
+ print "$i: $h[$i]\n" ;
+ }
+ # use the push & pop methods
+ $a = $H->pop ;
+ $H->push("last") ;
+ print "\nThe last record was [$a]\n" ;
+
+ # and the shift & unshift methods
+ $a = $H->shift ;
+ $H->unshift("first") ;
+ print "The first record was [$a]\n" ;
+
+ # Use the API to add a new record after record 2.
+ $i = 2 ;
+ $H->put($i, "Newbie", R_IAFTER) ;
+
+ # and a new record before record 1.
+ $i = 1 ;
+ $H->put($i, "New One", R_IBEFORE) ;
+
+ # delete record 3
+ $H->del(3) ;
+
+ # now print the records in reverse order
+ print "\nREVERSE\n" ;
+ for ($i = $H->length - 1 ; $i >= 0 ; -- $i)
+ { print "$i: $h[$i]\n" }
+
+ # same again, but use the API functions instead
+ print "\nREVERSE again\n" ;
+ my ($s, $k, $v) = (0, 0, 0) ;
+ for ($s = $H->seq($k, $v, R_LAST) ;
+ $s == 0 ;
+ $s = $H->seq($k, $v, R_PREV))
+ { print "$k: $v\n" }
+
+ undef $H ;
+ untie @h ;
+
+and this is what it outputs:
+
+ ORIGINAL
+ 0: zero
+ 1: one
+ 2: two
+ 3: three
+ 4: four
+
+ The last record was [four]
+ The first record was [zero]
+
+ REVERSE
+ 5: last
+ 4: three
+ 3: Newbie
+ 2: one
+ 1: New One
+ 0: first
+
+ REVERSE again
+ 5: last
+ 4: three
+ 3: Newbie
+ 2: one
+ 1: New One
+ 0: first
+
+Notes:
-=head2 Using the Berkeley DB API Directly
+=over 5
+
+=item 1.
+
+Rather than iterating through the array, C<@h> like this:
+
+ foreach $i (@h)
+
+it is necessary to use either this:
+
+ foreach $i (0 .. $H->length - 1)
+
+or this:
+
+ for ($a = $H->get($k, $v, R_FIRST) ;
+ $a == 0 ;
+ $a = $H->get($k, $v, R_NEXT) )
+
+=item 2.
+
+Notice that both times the C<put> method was used the record index was
+specified using a variable, C<$i>, rather than the literal value
+itself. This is because C<put> will return the record number of the
+inserted line via that parameter.
+
+=back
+
+=head1 THE API INTERFACE
As well as accessing Berkeley DB using a tied hash or array, it is also
possible to make direct use of most of the API functions defined in the
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.
+destroyed.
use DB_File ;
$db = tie %hash, "DB_File", "filename"
undef $db ;
untie %hash ;
+See L<The untie() Gotcha> for more details.
+
All the functions defined in L<dbopen> are available except for
close() and dbopen() itself. The B<DB_File> method interface to the
supported functions have been implemented to mirror the way Berkeley DB
=over 5
-=item C<$status = $X-E<gt>get($key, $value [, $flags]) ;>
+=item B<$status = $X-E<gt>get($key, $value [, $flags]) ;>
Given a key (C<$key>) this method reads the value associated with it
from the database. The value read from the database is returned in the
No flags are currently defined for this method.
-=item C<$status = $X-E<gt>put($key, $value [, $flags]) ;>
+=item B<$status = $X-E<gt>put($key, $value [, $flags]) ;>
Stores the key/value pair in the database.
Valid flags are R_CURSOR, R_IAFTER, R_IBEFORE, R_NOOVERWRITE and
R_SETCURSOR.
-=item C<$status = $X-E<gt>del($key [, $flags]) ;>
+=item B<$status = $X-E<gt>del($key [, $flags]) ;>
Removes all key/value pairs with key C<$key> from the database.
R_CURSOR is the only valid flag at present.
-=item C<$status = $X-E<gt>fd ;>
+=item B<$status = $X-E<gt>fd ;>
Returns the file descriptor for the underlying database.
-See L<"Locking Databases"> for an example of how to make use of the
+See L<Locking Databases> for an example of how to make use of the
C<fd> method to lock your database.
-=item C<$status = $X-E<gt>seq($key, $value, $flags) ;>
+=item B<$status = $X-E<gt>seq($key, $value, $flags) ;>
This interface allows sequential retrieval from the database. See
L<dbopen> for full details.
The flags parameter is mandatory. The valid flag values are R_CURSOR,
R_FIRST, R_LAST, R_NEXT and R_PREV.
-=item C<$status = $X-E<gt>sync([$flags]) ;>
+=item B<$status = $X-E<gt>sync([$flags]) ;>
Flushes any cached buffers to disk.
=back
-=head1 EXAMPLES
-
-It is always a lot easier to understand something when you see a real
-example. So here are a few.
-
-=head2 Using HASH
-
- use DB_File ;
- use Fcntl ;
-
- tie %h, "DB_File", "hashed", O_RDWR|O_CREAT, 0640, $DB_HASH
- or die "Cannot open file 'hashed': $!\n";
-
- # Add a key/value pair to the file
- $h{"apple"} = "orange" ;
-
- # Check for existence of a key
- print "Exists\n" if $h{"banana"} ;
-
- # Delete
- delete $h{"apple"} ;
-
- untie %h ;
-
-=head2 Using BTREE
-
-Here is a sample of code which uses BTREE. Just to make life more
-interesting the default comparison function will not be used. Instead
-a Perl sub, C<Compare()>, will be used to do a case insensitive
-comparison.
-
- use DB_File ;
- use Fcntl ;
-
- sub Compare
- {
- my ($key1, $key2) = @_ ;
-
- "\L$key1" cmp "\L$key2" ;
- }
-
- $DB_BTREE->{'compare'} = 'Compare' ;
-
- tie %h, "DB_File", "tree", O_RDWR|O_CREAT, 0640, $DB_BTREE
- or die "Cannot open file 'tree': $!\n" ;
-
- # Add a key/value pair to the file
- $h{'Wall'} = 'Larry' ;
- $h{'Smith'} = 'John' ;
- $h{'mouse'} = 'mickey' ;
- $h{'duck'} = 'donald' ;
-
- # Delete
- delete $h{"duck"} ;
-
- # Cycle through the keys printing them in order.
- # Note it is not necessary to sort the keys as
- # the btree will have kept them in order automatically.
- foreach (keys %h)
- { print "$_\n" }
-
- untie %h ;
-
-Here is the output from the code above.
-
- mouse
- Smith
- Wall
-
+=head1 HINTS AND TIPS
-=head2 Using RECNO
-
-Here is a simple example that uses RECNO.
-
- use DB_File ;
- use Fcntl ;
-
- $DB_RECNO->{'psize'} = 3000 ;
-
- tie @h, "DB_File", "text", O_RDWR|O_CREAT, 0640, $DB_RECNO
- or die "Cannot open file 'text': $!\n" ;
-
- # Add a key/value pair to the file
- $h[0] = "orange" ;
-
- # Check for existence of a key
- print "Exists\n" if $h[1] ;
-
- untie @h ;
=head2 Locking Databases
open() to give something Perl will flock() for you. Run this repeatedly
in the background to watch the locks granted in proper order.
- use Fcntl;
use DB_File;
use strict;
print "$$: Write lock granted\n";
$db{$key} = $value;
- $db->sync;
+ $db->sync; # to flush
sleep 10;
flock(DB_FH, LOCK_UN);
close(DB_FH);
print "$$: Updated db to $key=$value\n";
-=head1 HISTORY
+=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.
+
+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.
+This is usually stored in the file F<~/.netscape/history.db>. The key
+field in the database is the location string and the value field is the
+time the location was last visited stored as a 4 byte binary value.
+
+If you haven't already guessed, the location string is stored with a
+terminating NULL. This means you need to be careful when accessing the
+database.
+
+Here is a snippet of code that is loosely based on Tom Christiansen's
+I<ggh> script (available from your nearest CPAN archive in
+F<authors/id/TOMC/scripts/nshist.gz>).
+
+ use strict ;
+ use DB_File ;
+ use Fcntl ;
+
+ use vars qw( $dotdir $HISTORY %hist_db $href $binary_time $date ) ;
+ $dotdir = $ENV{HOME} || $ENV{LOGNAME};
+
+ $HISTORY = "$dotdir/.netscape/history.db";
+
+ tie %hist_db, 'DB_File', $HISTORY
+ or die "Cannot open $HISTORY: $!\n" ;;
+
+ # Dump the complete database
+ while ( ($href, $binary_time) = each %hist_db ) {
+
+ # remove the terminating NULL
+ $href =~ s/\x00$// ;
+
+ # convert the binary time into a user friendly string
+ $date = localtime unpack("V", $binary_time);
+ print "$date $href\n" ;
+ }
+
+ # check for the existence of a specific key
+ # remember to add the NULL
+ if ( $binary_time = $hist_db{"http://mox.perl.com/\x00"} ) {
+ $date = localtime unpack("V", $binary_time) ;
+ print "Last visited mox.perl.com on $date\n" ;
+ }
+ else {
+ print "Never visited mox.perl.com\n"
+ }
+
+ 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 ;
-=over
+ $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_TRUNC
+ or die "Cannot tie first time: $!" ;
-=item 0.1
+ $x{123} = 456 ;
-First Release.
+ untie %x ;
-=item 0.2
+ tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
+ or die "Cannot tie second time: $!" ;
-When B<DB_File> is opening a database file it no longer terminates the
-process if I<dbopen> returned an error. This allows file protection
-errors to be caught at run time. Thanks to Judith Grass
-E<lt>grass@cybercash.comE<gt> for spotting the bug.
+ untie %x ;
-=item 0.3
+When run, the script will produce this error message:
-Added prototype support for multiple btree compare callbacks.
+ Cannot tie second time: Invalid argument at bad.file line 14.
-=item 1.0
+Although the error message above refers to the second tie() statement
+in the script, the source of the problem is really with the untie()
+statement that precedes it.
-B<DB_File> has been in use for over a year. To reflect that, the
-version number has been incremented to 1.0.
+Having read L<perltie> you will probably have already guessed that the
+error is caused by the extra copy of the tied object stored in C<$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 alreday open via the catch-all
+"Invalid argument" doesn't help.
-Added complete support for multiple concurrent callbacks.
+If you run the script with the C<-w> flag the error message becomes:
-Using the I<push> method on an empty list didn't work properly. This
-has been fixed.
+ untie attempted while 1 inner references still exist at bad.file line 12.
+ Cannot tie second time: Invalid argument at bad.file line 14.
-=item 1.01
+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:
-Fixed a core dump problem with SunOS.
+ ...
+ $x{123} = 456 ;
+
+ undef $X ;
+ untie %x ;
+
+ $X = tie %x, 'DB_File', 'tst.fil' , O_RDWR|O_CREAT
+ ...
+
+
+=head1 COMMON QUESTIONS
+
+=head2 Why is there Perl source in my database?
+
+If you look at the contents of a database file created by DB_File,
+there can sometimes be part of a Perl script included in it.
+
+This happens because Berkeley DB uses dynamic memory to allocate
+buffers which will subsequently be written to the database file. Being
+dynamic, the memory could have been used for anything before DB
+malloced it. As Berkeley DB doesn't clear the memory once it has been
+allocated, the unused portions will contain random junk. In the case
+where a Perl script gets written to the database, the random junk will
+correspond to an area of dynamic memory that happened to be used during
+the compilation of the script.
+
+Unless you don't like the possibility of there being part of your Perl
+scripts embedded in a database file, this is nothing to worry about.
+
+=head2 How do I store complex data structures with DB_File?
+
+Although B<DB_File> cannot do this directly, there is a module which
+can layer transparently over B<DB_File> to accomplish this feat.
+
+Check out the MLDBM module, available on CPAN in the directory
+F<modules/by-module/MLDBM>.
+
+=head2 What does "Invalid Argument" mean?
+
+You will get this error message when one of the parameters in the
+C<tie> call is wrong. Unfortunately there are quite a few parameters to
+get wrong, so it can be difficult to figure out which one it is.
+
+Here are a couple of possibilities:
+
+=over 5
+
+=item 1.
-The return value from TIEHASH wasn't set to NULL when dbopen returned
-an error.
+Attempting to reopen a database without closing it.
-=item 1.02
+=item 2.
-Merged OS2 specific code into DB_File.xs
+Using the O_WRONLY flag.
-Removed some redundant code in DB_File.xs.
+=back
+
+=head2 What does "Bareword 'DB_File' not allowed" mean?
-Documentation update.
+You will encounter this particular error message when you have the
+C<strict 'subs'> pragma (or the full strict pragma) in your script.
+Consider this script:
-Allow negative subscripts with RECNO interface.
+ use strict ;
+ use DB_File ;
+ use vars qw(%x) ;
+ tie %x, DB_File, "filename" ;
-Changed the default flags from O_RDWR to O_CREAT|O_RDWR.
+Running it produces the error in question:
-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.
+ Bareword "DB_File" not allowed while "strict subs" in use
-Added get_dups method.
+To get around the error, place the word C<DB_File> in either single or
+double quotes, like this:
-=head1 WARNINGS
+ tie %x, "DB_File", "filename" ;
-If you happen to find any other functions defined in the source for
-this module that have not been mentioned in this document -- beware. I
-may drop them at a moments notice.
+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
-If you cannot find any, then either you didn't look very hard or the
-moment has passed and I have dropped them.
+Moved to the Changes file.
=head1 BUGS
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.
+records using the RECNO file format. This problem has been fixed since
+version 1.85 of Berkeley DB.
I am sure there are bugs in the code. If you do find any, or can
suggest any enhancements, I would welcome your comments.
=head1 AVAILABILITY
-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.
+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>.
-If you are running IRIX, then get Berkeley DB from
+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.
+
+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.
+
+Alternatively, Berkeley DB version 1 is available at your nearest CPAN
+archive in F<src/misc/db.1.85.tar.gz>.
+
+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.
+=head1 COPYRIGHT
+
+Copyright (c) 1997 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.
+
+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.
+
+The license for Berkeley DB version 2, and how it relates to DB_File
+does need some extra clarification. Here are are few words taken from
+the Berkeley DB FAQ regarding the version 2 license:
+
+ The major difference is that the license for DB 2.0, when
+ downloaded from the net, requires that the software that
+ uses DB 2.0 be freely redistributable.
+
+That means that if you want to use DB_File, and you have changed either
+the source for Berkeley DB or Perl, then the changes must be freely
+available.
+
+In the case of Perl, the term source refers to the complete source
+code for Perl (e.g. sv.c, toke.c, perl.h) and any external modules that
+you are using (e.g. DB_File, Tk).
+
+Note that any Perl scripts that you write are your property - this
+includes scripts that make use of DB_File. Neither the Perl license or
+the Berkeley DB license place any restriction on what you have to do
+with them.
+
+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.
+
+
=head1 SEE ALSO
L<perl(1)>, L<dbopen(3)>, L<hash(3)>, L<recno(3)>, L<btree(3)>
-Berkeley DB is available from F<ftp.cs.berkeley.edu> in the directory
-F</ucb/4bsd>.
-
=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>.
+Questions about the DB system itself may be addressed to
+E<lt>db@sleepycat.com<gt>.
=cut