From: Perl 5 Porters Date: Fri, 5 Jul 1996 05:47:36 +0000 (+0000) Subject: Update to version 1.02 X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=881083260db7aee4fc680f97d1f1f05d04ae707c;p=p5sagit%2Fp5-mst-13.2.git Update to version 1.02 --- diff --git a/ext/DB_File/DB_File.pm b/ext/DB_File/DB_File.pm index 61ac26a..0fff538 100644 --- a/ext/DB_File/DB_File.pm +++ b/ext/DB_File/DB_File.pm @@ -1,181 +1,143 @@ # DB_File.pm -- Perl 5 interface to Berkeley DB # # written by Paul Marquess (pmarquess@bfsec.bt.co.uk) -# last modified 14th November 1995 -# version 1.01 +# last modified 28th June 1996 +# version 1.02 package DB_File::HASHINFO ; use strict; -use vars qw(%elements); use Carp; +require Tie::Hash; +@DB_File::HASHINFO::ISA = qw(Tie::Hash); -sub TIEHASH +sub new { - bless {} ; + my $pkg = shift ; + my %x ; + tie %x, $pkg ; + bless \%x, $pkg ; } -%elements = ( 'bsize' => 0, - 'ffactor' => 0, - 'nelem' => 0, - 'cachesize' => 0, - 'hash' => 0, - 'lorder' => 0 - ) ; +sub TIEHASH +{ + my $pkg = shift ; + + bless { 'bsize' => undef, + 'ffactor' => undef, + 'nelem' => undef, + 'cachesize' => undef, + 'hash' => undef, + 'lorder' => undef, + }, $pkg ; +} sub FETCH { - return $_[0]{$_[1]} if defined $elements{$_[1]} ; + my $self = shift ; + my $key = shift ; - croak "DB_File::HASHINFO::FETCH - Unknown element '$_[1]'" ; + return $self->{$key} if exists $self->{$key} ; + + my $pkg = ref $self ; + croak "${pkg}::FETCH - Unknown element '$key'" ; } sub STORE { - if ( defined $elements{$_[1]} ) + my $self = shift ; + my $key = shift ; + my $value = shift ; + + if ( exists $self->{$key} ) { - $_[0]{$_[1]} = $_[2] ; + $self->{$key} = $value ; return ; } - croak "DB_File::HASHINFO::STORE - Unknown element '$_[1]'" ; + my $pkg = ref $self ; + croak "${pkg}::STORE - Unknown element '$key'" ; } sub DELETE { - if ( defined $elements{$_[1]} ) + my $self = shift ; + my $key = shift ; + + if ( exists $self->{$key} ) { - delete ${$_[0]}{$_[1]} ; + delete $self->{$key} ; return ; } - croak "DB_File::HASHINFO::DELETE - Unknown element '$_[1]'" ; + my $pkg = ref $self ; + croak "DB_File::HASHINFO::DELETE - Unknown element '$key'" ; } - -sub DESTROY {undef %{$_[0]} } -sub FIRSTKEY { croak "DB_File::HASHINFO::FIRSTKEY is not implemented" } -sub NEXTKEY { croak "DB_File::HASHINFO::NEXTKEY is not implemented" } -sub EXISTS { croak "DB_File::HASHINFO::EXISTS is not implemented" } -sub CLEAR { croak "DB_File::HASHINFO::CLEAR is not implemented" } - -package DB_File::BTREEINFO ; - -use strict; -use vars qw(%elements); -use Carp; - -sub TIEHASH +sub EXISTS { - bless {} ; -} - -%elements = ( 'flags' => 0, - 'cachesize' => 0, - 'maxkeypage' => 0, - 'minkeypage' => 0, - 'psize' => 0, - 'compare' => 0, - 'prefix' => 0, - 'lorder' => 0 - ) ; + my $self = shift ; + my $key = shift ; -sub FETCH -{ - return $_[0]{$_[1]} if defined $elements{$_[1]} ; - - croak "DB_File::BTREEINFO::FETCH - Unknown element '$_[1]'" ; + exists $self->{$key} ; } - -sub STORE +sub NotHere { - if ( defined $elements{$_[1]} ) - { - $_[0]{$_[1]} = $_[2] ; - return ; - } - - croak "DB_File::BTREEINFO::STORE - Unknown element '$_[1]'" ; -} + my $pkg = shift ; + my $method = shift ; -sub DELETE -{ - if ( defined $elements{$_[1]} ) - { - delete ${$_[0]}{$_[1]} ; - return ; - } - - croak "DB_File::BTREEINFO::DELETE - Unknown element '$_[1]'" ; + croak "${pkg} does not define the method ${method}" ; } - -sub DESTROY {undef %{$_[0]} } -sub FIRSTKEY { croak "DB_File::BTREEINFO::FIRSTKEY is not implemented" } -sub NEXTKEY { croak "DB_File::BTREEINFO::NEXTKEY is not implemented" } -sub EXISTS { croak "DB_File::BTREEINFO::EXISTS is not implemented" } -sub CLEAR { croak "DB_File::BTREEINFO::CLEAR is not implemented" } +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") } package DB_File::RECNOINFO ; -use strict; -use vars qw(%elements); -use Carp; +use strict ; + +@DB_File::RECNOINFO::ISA = qw(DB_File::HASHINFO) ; sub TIEHASH { - bless {} ; + my $pkg = shift ; + + bless { 'bval' => undef, + 'cachesize' => undef, + 'psize' => undef, + 'flags' => undef, + 'lorder' => undef, + 'reclen' => undef, + 'bfname' => "", + }, $pkg ; } -%elements = ( 'bval' => 0, - 'cachesize' => 0, - 'psize' => 0, - 'flags' => 0, - 'lorder' => 0, - 'reclen' => 0, - 'bfname' => 0 - ) ; -sub FETCH -{ - return $_[0]{$_[1]} if defined $elements{$_[1]} ; +package DB_File::BTREEINFO ; - croak "DB_File::RECNOINFO::FETCH - Unknown element '$_[1]'" ; -} +use strict ; +@DB_File::BTREEINFO::ISA = qw(DB_File::HASHINFO) ; -sub STORE -{ - if ( defined $elements{$_[1]} ) - { - $_[0]{$_[1]} = $_[2] ; - return ; - } - - croak "DB_File::RECNOINFO::STORE - Unknown element '$_[1]'" ; -} - -sub DELETE +sub TIEHASH { - if ( defined $elements{$_[1]} ) - { - delete ${$_[0]}{$_[1]} ; - return ; - } - - croak "DB_File::RECNOINFO::DELETE - Unknown element '$_[1]'" ; + my $pkg = shift ; + + bless { 'flags' => undef, + 'cachesize' => undef, + 'maxkeypage' => undef, + 'minkeypage' => undef, + 'psize' => undef, + 'compare' => undef, + 'prefix' => undef, + 'lorder' => undef, + }, $pkg ; } -sub DESTROY {undef %{$_[0]} } -sub FIRSTKEY { croak "DB_File::RECNOINFO::FIRSTKEY is not implemented" } -sub NEXTKEY { croak "DB_File::RECNOINFO::NEXTKEY is not implemented" } -sub EXISTS { croak "DB_File::BTREEINFO::EXISTS is not implemented" } -sub CLEAR { croak "DB_File::BTREEINFO::CLEAR is not implemented" } - - - package DB_File ; use strict; @@ -183,12 +145,16 @@ use vars qw($VERSION @ISA @EXPORT $AUTOLOAD $DB_BTREE $DB_HASH $DB_RECNO) ; use Carp; -$VERSION = "1.01" ; +$VERSION = "1.02" ; #typedef enum { DB_BTREE, DB_HASH, DB_RECNO } DBTYPE; -$DB_BTREE = TIEHASH DB_File::BTREEINFO ; -$DB_HASH = TIEHASH DB_File::HASHINFO ; -$DB_RECNO = TIEHASH DB_File::RECNOINFO ; +#$DB_BTREE = TIEHASH DB_File::BTREEINFO ; +#$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 ; require Tie::Hash; require Exporter; @@ -197,6 +163,7 @@ require DynaLoader; @ISA = qw(Tie::Hash Exporter DynaLoader); @EXPORT = qw( $DB_BTREE $DB_HASH $DB_RECNO + BTREEMAGIC BTREEVERSION DB_LOCK @@ -225,6 +192,7 @@ require DynaLoader; R_SETCURSOR R_SNAPSHOT __R_UNUSED + ); sub AUTOLOAD { @@ -251,6 +219,43 @@ bootstrap DB_File $VERSION; # Preloaded methods go here. Autoload methods go after __END__, and are # processed by the autosplit program. + +sub get_dup +{ + croak "Usage: \$db->get_dup(key [,flag])\n" + unless @_ == 2 or @_ == 3 ; + + my $db = shift ; + my $key = shift ; + my $flag = shift ; + my $value ; + my $origkey = $key ; + my $wantarray = wantarray ; + my @values = () ; + my $counter = 0 ; + + # get the first value associated with the key, $key + $db->seq($key, $value, R_CURSOR()) ; + + if ( $key eq $origkey) { + + while (1) { + # save the value or count matches + if ($wantarray) + { push (@values, $value) ; push(@values, 1) if $flag } + 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 : $counter ; +} + + 1; __END__ @@ -263,18 +268,27 @@ DB_File - Perl5 access to Berkeley DB =head1 SYNOPSIS use DB_File ; + use Fcntl ; + + [$X =] tie %hash, 'DB_File', [$filename, $flags, $mode, $DB_HASH] ; + [$X =] tie %hash, 'DB_File', $filename, $flags, $mode, $DB_BTREE ; + [$X =] tie @array, 'DB_File', $filename, $flags, $mode, $DB_RECNO ; - [$X =] tie %hash, DB_File, $filename [, $flags, $mode, $DB_HASH] ; + [$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 ; $status = $X->del($key [, $flags]) ; $status = $X->put($key, $value [, $flags]) ; $status = $X->get($key, $value [, $flags]) ; - $status = $X->seq($key, $value [, $flags]) ; + $status = $X->seq($key, $value , $flags) ; $status = $X->sync([$flags]) ; $status = $X->fd ; + $count = $X->get_dup($key) ; + @list = $X->get_dup($key) ; + %list = $X->get_dup($key, 1) ; + untie %hash ; untie @array ; @@ -282,7 +296,7 @@ DB_File - Perl5 access to Berkeley DB B 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 manualpage at +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. @@ -294,9 +308,9 @@ The file types are: =over 5 -=item DB_HASH +=item B -This database type allows arbitrary key/data pairs to be stored in data +This database type allows arbitrary key/value pairs to be stored in data files. This is equivalent to the functionality provided by other hashing packages like DBM, NDBM, ODBM, GDBM, and SDBM. Remember though, the files created using DB_HASH are not compatible with any of the @@ -307,16 +321,21 @@ applications, is built into Berkeley DB. If you do need to use your own hashing algorithm it is possible to write your own in Perl and have B use it instead. -=item DB_BTREE +When opening an existing database, you may omit the final three arguments +to C; they default to O_RDWR, 0644, and $DB_HASH. If you're +creating a new file, you need to specify at least the C<$flags> +argument, which must include O_CREAT. -The btree format allows arbitrary key/data pairs to be stored in a +=item B + +The btree format allows arbitrary key/value pairs to be stored in a sorted, balanced binary tree. As with the DB_HASH format, it is possible to provide a user defined Perl routine to perform the comparison of keys. By default, though, the keys are stored in lexical order. -=item DB_RECNO +=item B DB_RECNO allows both fixed-length and variable-length flat text files to be manipulated using the same key/value pair interface as in DB_HASH @@ -333,10 +352,11 @@ allows B to access Berkeley DB files using either an associative array (for DB_HASH & DB_BTREE file types) or an ordinary array (for the DB_RECNO file type). -In addition to the tie() interface, it is also possible to use most of -the functions provided in the Berkeley DB API. +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">. -=head2 Differences with Berkeley DB +=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(). @@ -352,35 +372,284 @@ I points to a data structure which allows tailoring of the specific interface method. This interface is handled slightly differently in B. Here is -an equivalent call using B. +an equivalent call using B: - tie %array, DB_File, $filename, $flags, $mode, $DB_HASH ; + tie %array, 'DB_File', $filename, $flags, $mode, $DB_HASH ; The C, C and C parameters are the direct equivalent of their dbopen() counterparts. The final parameter $DB_HASH performs the function of both the C and C parameters in dbopen(). -In the example above $DB_HASH is actually a reference to a hash -object. B has three of these pre-defined references. Apart -from $DB_HASH, there is also $DB_BTREE and $DB_RECNO. +In the example above $DB_HASH is actually a pre-defined reference to a +hash object. B has three of these pre-defined references. +Apart from $DB_HASH, there is also $DB_BTREE and $DB_RECNO. The keys allowed in each of these pre-defined references is limited to the names used in the equivalent C structure. So, for example, the $DB_HASH reference will only allow keys called C, C, -C, C, C and C. +C, C, C and C. + +To change one of these elements, just assign to it like this: + + $DB_HASH->{'cachesize'} = 10000 ; + +The three predefined variables $DB_HASH, $DB_BTREE and $DB_RECNO are +usually adequate for most applications. If you do need to create extra +instances of these objects, constructors are available for each file +type. + +Here are examples of the constructors and the valid options available +for DB_HASH, DB_BTREE and DB_RECNO respectively. + + $a = new DB_File::HASHINFO ; + $a->{'bsize'} ; + $a->{'cachesize'} ; + $a->{'ffactor'}; + $a->{'hash'} ; + $a->{'lorder'} ; + $a->{'nelem'} ; + + $b = new DB_File::BTREEINFO ; + $b->{'flags'} ; + $b->{'cachesize'} ; + $b->{'maxkeypage'} ; + $b->{'minkeypage'} ; + $b->{'psize'} ; + $b->{'compare'} ; + $b->{'prefix'} ; + $b->{'lorder'} ; + + $c = new DB_File::RECNOINFO ; + $c->{'bval'} ; + $c->{'cachesize'} ; + $c->{'psize'} ; + $c->{'flags'} ; + $c->{'lorder'} ; + $c->{'reclen'} ; + $c->{'bfname'} ; + +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 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, $a ; + +A few of the values need extra discussion here. When used, the C +equivalent of the keys C, C and C store pointers +to C functions. In B these keys are used to store references +to Perl subs. Below are templates for each of the subs: + + sub hash + { + my ($data) = @_ ; + ... + # return the hash value for $data + return $hash ; + } -To change one of these elements, just assign to it like this + sub compare + { + my ($key, $key2) = @_ ; + ... + # return 0 if $key1 eq $key2 + # -1 if $key1 lt $key2 + # 1 if $key1 gt $key2 + return (-1 , 0 or 1) ; + } - $DB_HASH->{cachesize} = 10000 ; + sub prefix + { + my ($key, $key2) = @_ ; + ... + # return number of bytes of $key2 which are + # necessary to determine that it is greater than $key1 + return $bytes ; + } +See L<"Using BTREE"> for an example of using the C + +=head2 Default Parameters + +It is possible to omit some or all of the final 4 parameters in the +call to C and let them take default values. As DB_HASH is the most +common file format used, the call: + + tie %A, "DB_File", "filename" ; + +is equivalent to: + + tie %A, "DB_File", "filename", O_CREAT|O_RDWR, 0640, $DB_HASH ; + +It is also possible to omit the filename parameter as well, so the +call: + + tie %A, "DB_File" ; + +is equivalent to: + + tie %A, "DB_File", undef, O_CREAT|O_RDWR, 0640, $DB_HASH ; + +See L<"In Memory Databases"> for a discussion on the use of C +in place of a filename. + +=head2 Handling duplicate keys in BTREE databases + +The BTREE file type in Berkeley DB optionally allows a single key to be +associated with an arbitrary number of values. This option is enabled by +setting the flags element of C<$DB_BTREE> to R_DUP when creating the +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 DB_File ; + use Fcntl ; + + $filename = "tree" ; + unlink $filename ; + + # Enable duplicate records + $DB_BTREE->{'flags'} = R_DUP ; + + 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{'Wall'} = 'Larry' ; + $h{'Wall'} = 'Brick' ; # Note the duplicate key + $h{'Smith'} = 'John' ; + $h{'mouse'} = 'mickey' ; + + # iterate through the associative array + # and print each key/value pair. + foreach (keys %h) + { print "$_ -> $h{$_}\n" } + +Here is the output: + + Smith -> John + Wall -> Larry + Wall -> Larry + mouse -> mickey + +As you can see 2 records have been successfully created with key C +- the only thing is, when they are retrieved from the database they +both I to have the same value, namely C. 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 +keys, but it cannot be used to read them back from the database. + +The way to get around this problem is to use the Berkeley DB API method +called C. This method allows sequential access to key/value +pairs. See L<"Using the Berkeley DB API Directly"> for details of both +the C method and the API in general. + +Here is the script above rewritten using the C API method. + + use DB_File ; + use Fcntl ; + + $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 + 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{'Smith'} = 'John' ; + $h{'mouse'} = 'mickey' ; + + # Point to the first record in the btree + $x->seq($key, $value, R_FIRST) ; + + # now iterate through the rest of the btree + # and print each key/value pair. + print "$key -> $value\n" ; + while ( $x->seq($key, $value, R_NEXT) == 0) + { print "$key -> $value\n" } + + undef $x ; + untie %h ; + +that prints: + + Smith -> John + Wall -> Brick + Wall -> Larry + mouse -> mickey + +This time we have got all the key/value pairs, including both the +values associated with the key C. + +C comes with a utility method, called C, to assist in +reading duplicate values from BTREE databases. The method can take the +following forms: + + $count = $x->get_dup($key) ; + @list = $x->get_dup($key) ; + %list = $x->get_dup($key, 1) ; + +In a scalar context the method returns the number of values associated +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. + +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>. + +So assuming the database created above, we can use C like +this: + + $cnt = $x->get_dups("Wall") ; + print "Wall occurred $cnt times\n" ; + + %hash = $x->get_dups("Wall", 1) ; + print "Larry is there\n" if $hash{'Larry'} ; + + @list = $x->get_dups("Wall") ; + print "Wall => [@list]\n" ; + + @list = $x->get_dups("Smith") ; + print "Smith => [@list]\n" ; + + @list = $x->get_dups("Dog") ; + print "Dog => [@list]\n" ; + + +and it will print: + + Wall occurred 2 times + Larry is there + Wall => [Brick Larry] + Smith => [John] + Dog => [] =head2 RECNO +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. -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 +negative indexes. The index -1 refers to the last element of the array, +-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 @@ -389,65 +658,155 @@ Berkeley DB allows the creation of in-memory databases by using NULL uses C instead of NULL to provide this functionality. -=head2 Using the Berkeley DB Interface Directly +=head2 Using the Berkeley DB API Directly As well as accessing Berkeley DB using a tied hash or array, it is also -possible to make direct use of most of the functions defined in the +possible to make direct use of most of the API functions defined in the Berkeley DB documentation. +To do this you need to store a copy of the object returned from the tie. -To do this you need to remember the return value from the tie. - - $db = tie %hash, DB_File, "filename" + $db = tie %hash, "DB_File", "filename" ; Once you have done that, you can access the Berkeley DB API functions -directly. +as B methods directly like this: $db->put($key, $value, R_NOOVERWRITE) ; -All the functions defined in L are available except for -close() and dbopen() itself. The B interface to these -functions have been implemented to mirror the the way Berkeley DB -works. In particular note that all the functions return only a status -value. Whenever a Berkeley DB function returns data via one of its -parameters, the B equivalent does exactly the same. +B If you have saved a copy of the object returned from +C, the underlying database file will I be closed until both +the tied variable is untied and all copies of the saved object are +destroyed. + + use DB_File ; + $db = tie %hash, "DB_File", "filename" + or die "Cannot tie filename: $!" ; + ... + undef $db ; + untie %hash ; + +All the functions defined in L are available except for +close() and dbopen() itself. The B method interface to the +supported functions have been implemented to mirror the way Berkeley DB +works whenever possible. In particular note that: + +=over 5 + +=item * + +The methods return a status value. All return 0 on success. +All return -1 to signify an error and set C<$!> to the exact +error code. The return code 1 generally (but not always) means that the +key specified did not exist in the database. + +Other return codes are defined. See below and in the Berkeley DB +documentation for details. The Berkeley DB documentation should be used +as the definitive source. + +=item * -All the constants defined in L are also available. +Whenever a Berkeley DB function returns data via one of its parameters, +the equivalent B method does exactly the same. -Below is a list of the functions available. +=item * + +If you are careful, it is possible to mix API calls with the tied +hash/array interface in the same piece of code. Although only a few of +the methods used to implement the tied interface currently make use of +the cursor, you should always assume that the cursor has been changed +any time the tied hash/array interface is used. As an example, this +code will probably not do what you expect: + + $X = tie %x, 'DB_File', $filename, O_RDWR|O_CREAT, 0777, $DB_BTREE + or die "Cannot tie $filename: $!" ; + + # Get the first key/value pair and set the cursor + $X->seq($key, $value, R_FIRST) ; + + # this line will modify the cursor + $count = scalar keys %x ; + + # Get the second key/value pair. + # oops, it didn't, it got the last key/value pair! + $X->seq($key, $value, R_NEXT) ; + +The code above can be rearranged to get around the problem, like this: + + $X = tie %x, 'DB_File', $filename, O_RDWR|O_CREAT, 0777, $DB_BTREE + or die "Cannot tie $filename: $!" ; + + # this line will modify the cursor + $count = scalar keys %x ; + + # Get the first key/value pair and set the cursor + $X->seq($key, $value, R_FIRST) ; + + # Get the second key/value pair. + # worked this time. + $X->seq($key, $value, R_NEXT) ; + +=back + +All the constants defined in L for use in the flags parameters +in the methods defined below are also available. Refer to the Berkeley +DB documentation for the precise meaning of the flags values. + +Below is a list of the methods available. =over 5 -=item get +=item C<$status = $X-Eget($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 +C<$value> parameter. -Same as in C except that the flags parameter is optional. -Remember the value associated with the key you request is returned in -the $value parameter. +If the key does not exist the method returns 1. -=item put +No flags are currently defined for this method. -As usual the flags parameter is optional. +=item C<$status = $X-Eput($key, $value [, $flags]) ;> -If you use either the R_IAFTER or R_IBEFORE flags, the key parameter +Stores the key/value pair in the database. + +If you use either the R_IAFTER or R_IBEFORE flags, the C<$key> parameter will have the record number of the inserted key/value pair set. -=item del +Valid flags are R_CURSOR, R_IAFTER, R_IBEFORE, R_NOOVERWRITE and +R_SETCURSOR. + +=item C<$status = $X-Edel($key [, $flags]) ;> -The flags parameter is optional. +Removes all key/value pairs with key C<$key> from the database. -=item fd +A return code of 1 means that the requested key was not in the +database. -As in I. +R_CURSOR is the only valid flag at present. -=item seq +=item C<$status = $X-Efd ;> -The flags parameter is optional. +Returns the file descriptor for the underlying database. -Both the key and value parameters will be set. +See L<"Locking Databases"> for an example of how to make use of the +C method to lock your database. -=item sync +=item C<$status = $X-Eseq($key, $value, $flags) ;> -The flags parameter is optional. +This interface allows sequential retrieval from the database. See +L for full details. + +Both the C<$key> and C<$value> parameters will be set to the key/value +pair read from the database. + +The flags parameter is mandatory. The valid flag values are R_CURSOR, +R_FIRST, R_LAST, R_NEXT and R_PREV. + +=item C<$status = $X-Esync([$flags]) ;> + +Flushes any cached buffers to disk. + +R_RECNOSYNC is the only valid flag at present. =back @@ -460,56 +819,58 @@ example. So here are a few. use DB_File ; use Fcntl ; - - tie %h, "DB_File", "hashed", O_RDWR|O_CREAT, 0640, $DB_HASH ; - + + 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 $h{"apple"} ; - + untie %h ; =head2 Using BTREE -Here is sample of code which used BTREE. Just to make life more -interesting the default comparision function will not be used. Instead +Here is a sample of code which uses BTREE. Just to make life more +interesting the default comparison function will not be used. Instead a Perl sub, C, will be used to do a case insensitive comparison. use DB_File ; use Fcntl ; - + sub Compare { my ($key1, $key2) = @_ ; - + "\L$key1" cmp "\L$key2" ; } - - $DB_BTREE->{compare} = 'Compare' ; - - tie %h, 'DB_File', "tree", O_RDWR|O_CREAT, 0640, $DB_BTREE ; - + + $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. @@ -521,21 +882,23 @@ Here is the output from the code above. =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 ; - + + $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 ; + untie @h ; =head2 Locking Databases @@ -588,9 +951,11 @@ in the background to watch the locks granted in proper order. print "$$: Write lock granted\n"; $db{$key} = $value; + $db->sync; sleep 10; flock(DB_FH, LOCK_UN); + undef $db; untie %db; close(DB_FH); print "$$: Updated db to $key=$value\n"; @@ -631,11 +996,28 @@ Fixed a core dump problem with SunOS. The return value from TIEHASH wasn't set to NULL when dbopen returned an error. +=item 1.02 + +Merged OS2 specific code into DB_File.xs + +Removed some redundant code in DB_File.xs. + +Documentation update. + +Allow negative subscripts with RECNO interface. + +Changed the default flags from O_RDWR to O_CREAT|O_RDWR. + +The example code which showed how to lock a database needed a call to +C added. Without it the resultant database file was empty. + +Added get_dups method. + =head1 WARNINGS -If you happen 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. +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. If you cannot find any, then either you didn't look very hard or the moment has passed and I have dropped them. @@ -656,6 +1038,10 @@ L for a list) in F, or via the host F in F. It is I under the GPL. +If you are running IRIX, then get Berkeley DB from +F. It has the patches necessary to +compile properly on IRIX 5.3. + =head1 SEE ALSO L, L, L, L, L @@ -666,8 +1052,8 @@ F. =head1 AUTHOR The DB_File interface was written by Paul Marquess -. +Epmarquess@bfsec.bt.co.ukE. Questions about the DB system itself may be addressed to Keith Bostic -. +Ebostic@cs.berkeley.eduE. =cut diff --git a/ext/DB_File/DB_File.xs b/ext/DB_File/DB_File.xs index dd9e03d..f344794 100644 --- a/ext/DB_File/DB_File.xs +++ b/ext/DB_File/DB_File.xs @@ -3,8 +3,8 @@ DB_File.xs -- Perl 5 interface to Berkeley DB written by Paul Marquess (pmarquess@bfsec.bt.co.uk) - last modified 14th November 1995 - version 1.01 + last modified 26th June 1996 + version 1.02 All comments/suggestions/problems are welcome @@ -17,6 +17,11 @@ 1.01 - Fixed a SunOS core dump problem. The return value from TIEHASH wasn't set to NULL when dbopen returned an error. + 1.02 - Use ALIAS to define TIEARRAY. + Removed some redundant commented code. + Merged OS2 code into the main distribution. + Allow negative subscripts with RECNO interface. + Changed the default flags to O_CREAT|O_RDWR */ #include "EXTERN.h" @@ -45,7 +50,7 @@ union INFO { } ; -/* #define TRACE */ +/* #define TRACE */ #define db_DESTROY(db) ((db->dbp)->close)(db->dbp) #define db_DELETE(db, key, flags) ((db->dbp)->del)(db->dbp, &key, flags) @@ -61,14 +66,18 @@ union INFO { #define db_sync(db, flags) ((db->dbp)->sync)(db->dbp, flags) -#define OutputValue(arg, name) \ - { if (RETVAL == 0) sv_setpvn(arg, name.data, name.size) ; } +#define OutputValue(arg, name) \ + { if (RETVAL == 0) { \ + sv_setpvn(arg, name.data, name.size) ; \ + } \ + } #define OutputKey(arg, name) \ { if (RETVAL == 0) \ { \ - if (db->type != DB_RECNO) \ + if (db->type != DB_RECNO) { \ sv_setpvn(arg, name.data, name.size); \ + } \ else \ sv_setiv(arg, (I32)*(I32*)name.data - 1); \ } \ @@ -235,7 +244,7 @@ RECNOINFO recno ; printf (" lorder = %d\n", recno.lorder) ; printf (" reclen = %d\n", recno.reclen) ; printf (" bval = %d\n", recno.bval) ; - printf (" bfname = %s\n", recno.bfname) ; + printf (" bfname = %d [%s]\n", recno.bfname, recno.bfname) ; } PrintBtree(btree) @@ -278,6 +287,27 @@ DB * db ; return (RETVAL) ; } +static recno_t +GetRecnoKey(db, value) +DB_File db ; +I32 value ; +{ + if (value < 0) { + /* Get the length of the array */ + I32 length = GetArrayLength(db->dbp) ; + + /* check for attempt to write before start of array */ + if (length + value + 1 <= 0) + croak("Modification of non-creatable array value attempted, subscript %d", value) ; + + value = length + value + 1 ; + } + else + ++ value ; + + return value ; +} + static DB_File ParseOpenInfo(name, flags, mode, sv, string) char * name ; @@ -291,8 +321,8 @@ char * string ; union INFO info ; DB_File RETVAL = (DB_File)safemalloc(sizeof(DB_File_type)) ; void * openinfo = NULL ; - /* DBTYPE type = DB_HASH ; */ + /* Default to HASH */ RETVAL->hash = RETVAL->compare = RETVAL->prefix = NULL ; RETVAL->type = DB_HASH ; @@ -415,7 +445,10 @@ char * string ; } svp = hv_fetch(action, "bfname", 6, FALSE); - info.recno.bfname = (char *) svp ? SvPV(*svp,na) : 0; + if (svp) { + char * ptr = SvPV(*svp,na) ; + info.recno.bfname = (char*) na ? ptr : 0 ; + } PrintRecno(info) ; } @@ -424,17 +457,14 @@ char * string ; } - RETVAL->dbp = dbopen(name, flags, mode, RETVAL->type, openinfo) ; - -#if 0 - /* kludge mode on: RETVAL->type for DB_RECNO is set to DB_BTREE - so remember a DB_RECNO by saving the address - of one of it's internal routines - */ - if (RETVAL->dbp && type == DB_RECNO) - DB_recno_close = RETVAL->dbp->close ; -#endif + /* OS2 Specific Code */ +#ifdef OS2 +#ifdef __EMX__ + flags |= O_BINARY; +#endif /* __EMX__ */ +#endif /* OS2 */ + RETVAL->dbp = dbopen(name, flags, mode, RETVAL->type, openinfo) ; return (RETVAL) ; } @@ -695,10 +725,11 @@ constant(name,arg) DB_File -db_TIEHASH(dbtype, name=undef, flags=O_RDWR, mode=0640, type=DB_HASH) +db_TIEHASH(dbtype, name=undef, flags=O_CREAT|O_RDWR, mode=0640, type=DB_HASH) char * dbtype int flags int mode + ALIAS: TIEARRAY = 1 CODE: { char * name = (char *) NULL ; @@ -717,9 +748,6 @@ db_TIEHASH(dbtype, name=undef, flags=O_RDWR, mode=0640, type=DB_HASH) OUTPUT: RETVAL -BOOT: - newXS("DB_File::TIEARRAY", XS_DB_File_db_TIEHASH, file); - int db_DESTROY(db) DB_File db diff --git a/ext/DB_File/Makefile.PL b/ext/DB_File/Makefile.PL index 4cda635..39b8bc7 100644 --- a/ext/DB_File/Makefile.PL +++ b/ext/DB_File/Makefile.PL @@ -1,11 +1,16 @@ -use ExtUtils::MakeMaker; +use ExtUtils::MakeMaker 5.16 ; +use Config ; + +# OS2 is a special case, so check for it now. +my $OS2 = "-DOS2" if $Config{'osname'} eq 'os2' ; WriteMakefile( - NAME => 'DB_File', - LIBS => ["-L/usr/local/lib -ldb"], - MAN3PODS => ' ', # Pods will be built by installman. - #INC => '-I/usr/local/include', + NAME => 'DB_File', + LIBS => ["-L/usr/local/lib -ldb"], + MAN3PODS => ' ', # Pods will be built by installman. + #INC => '-I/usr/local/include', VERSION_FROM => 'DB_File.pm', - XSPROTOARG => '-noprototypes', # XXX remove later? -); + XSPROTOARG => '-noprototypes', + DEFINE => "$OS2", + ); diff --git a/ext/DB_File/typemap b/ext/DB_File/typemap index 4acc65e..5ca9c54 100644 --- a/ext/DB_File/typemap +++ b/ext/DB_File/typemap @@ -1,8 +1,8 @@ # typemap for Perl 5 interface to Berkeley DB # # written by Paul Marquess (pmarquess@bfsec.bt.co.uk) -# last modified 23rd June 1994 -# version 0.1 +# last modified 28th June 1996 +# version 0.2 # #################################### DB SECTION # @@ -15,15 +15,12 @@ DBTKEY T_dbtkeydatum INPUT T_dbtkeydatum - if (db->type != DB_RECNO) - { + if (db->type != DB_RECNO) { $var.data = SvPV($arg, na); $var.size = (int)na; } - else - { - Value = SvIV($arg) ; - ++ Value ; + else { + Value = GetRecnoKey(db, SvIV($arg)) ; $var.data = & Value; $var.size = (int)sizeof(recno_t); }