From: rkinyon Date: Thu, 25 Jan 2007 03:37:02 +0000 (+0000) Subject: r14944@rob-kinyons-computer (orig r8697): rkinyon | 2007-01-24 22:09:50 -0500 X-Git-Tag: 0-99_04~1 X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=b48ae6ec19f6691416f4d3e998b1fa861d6ff745;p=dbsrgits%2FDBM-Deep.git r14944@rob-kinyons-computer (orig r8697): rkinyon | 2007-01-24 22:09:50 -0500 Fixed numerous issues in the 0.99_03 release r14945@rob-kinyons-computer (orig r8698): rkinyon | 2007-01-24 22:30:36 -0500 Continued removal of Clone::Any from everywhere r14946@rob-kinyons-computer (orig r8699): rkinyon | 2007-01-24 22:34:22 -0500 Added more files to the MANIFEST --- diff --git a/Build.PL b/Build.PL index ce77101..d636a23 100644 --- a/Build.PL +++ b/Build.PL @@ -6,8 +6,8 @@ my $build = Module::Build->new( module_name => 'DBM::Deep', license => 'perl', requires => { - 'perl' => '5.6.0', - 'Clone::Any' => '0', + 'perl' => '5.006_000', + 'Clone' => '0.01', 'Digest::MD5' => '1.00', 'Fcntl' => '0.01', 'FileHandle::Fmode' => '0.05', diff --git a/Changes b/Changes index c681f55..6b840a5 100644 --- a/Changes +++ b/Changes @@ -1,6 +1,13 @@ Revision history for DBM::Deep. -0.99_03 Jan ?? 00:00:00 2007 EDT +0.99_04 Jan 24 22:30:00 2007 EDT + - Added the missing lib/DBM/Deep.pod file to the MANIFEST + - Fixed a poorly-designed test that was failing depending on what Clone::Any + - was using. + - All "use 5.6.0;" lines are now "use 5.006_000;" to avoid warnings about + unsupported vstrings in bleadperl. + +0.99_03 Jan 23 22:30:00 2007 EDT - THIS VERSION IS INCOMPATIBLE WITH FILES FROM ALL OTHER PRIOR VERSIONS. - The fileformat changed completely. I will be writing a converter, but it's not there right now. Do NOT expect that this module will diff --git a/MANIFEST b/MANIFEST index f109b57..0343370 100644 --- a/MANIFEST +++ b/MANIFEST @@ -1,6 +1,7 @@ Build.PL Changes lib/DBM/Deep.pm +lib/DBM/Deep.pod lib/DBM/Deep/Array.pm lib/DBM/Deep/Cookbook.pod lib/DBM/Deep/Engine.pm @@ -21,6 +22,7 @@ t/07_locking.t t/08_deephash.t t/09_deeparray.t t/10_largekeys.t +t/11_optimize.t t/12_clone.t t/13_setpack.t t/14_filter.t diff --git a/lib/DBM/Deep.pm b/lib/DBM/Deep.pm index cd839f4..2d00dca 100644 --- a/lib/DBM/Deep.pm +++ b/lib/DBM/Deep.pm @@ -29,16 +29,16 @@ package DBM::Deep; # modify it under the same terms as Perl itself. ## -use 5.6.0; +use 5.006_000; use strict; use warnings; -our $VERSION = q(0.99_03); +our $VERSION = q(0.99_04); use Fcntl qw( :flock ); -use Clone::Any '_clone_data'; +use Clone (); use Digest::MD5 (); use FileHandle::Fmode (); use Scalar::Util (); @@ -246,7 +246,7 @@ sub import { eval { local $SIG{'__DIE__'}; $self->begin_work; - $self->_import( _clone_data( $struct ) ); + $self->_import( Clone::clone( $struct ) ); $self->commit; }; if ( my $e = $@ ) { $self->rollback; diff --git a/lib/DBM/Deep.pod b/lib/DBM/Deep.pod index cd4981b..2312d95 100644 --- a/lib/DBM/Deep.pod +++ b/lib/DBM/Deep.pod @@ -35,12 +35,12 @@ DBM::Deep - A pure perl multi-level hash/array DBM that supports transactions =head1 DESCRIPTION -A unique flat-file database module, written in pure perl. True multi-level +A unique flat-file database module, written in pure perl. True multi-level hash/array support (unlike MLDBM, which is faked), hybrid OO / tie() interface, cross-platform FTPable files, ACID transactions, and is quite fast. Can handle millions of keys and unlimited levels without significant -slow-down. Written from the ground-up in pure perl -- this is NOT a wrapper -around a C-based DBM. Out-of-the-box compatibility with Unix, Mac OS X and +slow-down. Written from the ground-up in pure perl -- this is NOT a wrapper +around a C-based DBM. Out-of-the-box compatibility with Unix, Mac OS X and Windows. =head1 VERSION DIFFERENCES @@ -58,22 +58,22 @@ with 0.983 and before. =head1 SETUP Construction can be done OO-style (which is the recommended way), or using -Perl's tie() function. Both are examined here. +Perl's tie() function. Both are examined here. -=head2 OO CONSTRUCTION +=head2 OO Construction The recommended way to construct a DBM::Deep object is to use the new() method, which gets you a blessed I tied hash (or array) reference. my $db = DBM::Deep->new( "foo.db" ); -This opens a new database handle, mapped to the file "foo.db". If this -file does not exist, it will automatically be created. DB files are +This opens a new database handle, mapped to the file "foo.db". If this +file does not exist, it will automatically be created. DB files are opened in "r+" (read/write) mode, and the type of object returned is a hash, unless otherwise specified (see L below). You can pass a number of options to the constructor to specify things like -locking, autoflush, etc. This is done by passing an inline hash (or hashref): +locking, autoflush, etc. This is done by passing an inline hash (or hashref): my $db = DBM::Deep->new( file => "foo.db", @@ -83,10 +83,10 @@ locking, autoflush, etc. This is done by passing an inline hash (or hashref): Notice that the filename is now specified I the hash with the "file" parameter, as opposed to being the sole argument to the -constructor. This is required if any options are specified. +constructor. This is required if any options are specified. See L below for the complete list. -You can also start with an array instead of a hash. For this, you must +You can also start with an array instead of a hash. For this, you must specify the C parameter: my $db = DBM::Deep->new( @@ -95,14 +95,14 @@ specify the C parameter: ); B Specifing the C parameter only takes effect when beginning -a new DB file. If you create a DBM::Deep object with an existing file, the +a new DB file. If you create a DBM::Deep object with an existing file, the C will be loaded from the file header, and an error will be thrown if the wrong type is passed in. -=head2 TIE CONSTRUCTION +=head2 Tie Construction Alternately, you can create a DBM::Deep handle by using Perl's built-in -tie() function. The object returned from tie() can be used to call methods, +tie() function. The object returned from tie() can be used to call methods, such as lock() and unlock(). (That object can be retrieved from the tied variable at any time using tied() - please see L for more info. @@ -122,18 +122,18 @@ complete list). autoflush => 1 }; -=head2 OPTIONS +=head2 Options There are a number of options that can be passed in when constructing your -DBM::Deep objects. These apply to both the OO- and tie- based approaches. +DBM::Deep objects. These apply to both the OO- and tie- based approaches. =over =item * file -Filename of the DB file to link the handle to. You can pass a full absolute +Filename of the DB file to link the handle to. You can pass a full absolute filesystem path, partial path, or a plain filename if the file is in the -current working directory. This is a required parameter (though q.v. fh). +current working directory. This is a required parameter (though q.v. fh). =item * fh @@ -156,7 +156,7 @@ If you pass in fh and do not set this, it will be set appropriately. =item * type -This parameter specifies what type of object to create, a hash or array. Use +This parameter specifies what type of object to create, a hash or array. Use one of these two constants: =over 4 @@ -167,16 +167,16 @@ one of these two constants: =back -This only takes effect when beginning a new file. This is an optional +This only takes effect when beginning a new file. This is an optional parameter, and defaults to CTYPE_HASH>. =item * locking -Specifies whether locking is to be enabled. DBM::Deep uses Perl's flock() +Specifies whether locking is to be enabled. DBM::Deep uses Perl's flock() function to lock the database in exclusive mode for writes, and shared mode -for reads. Pass any true value to enable. This affects the base DB handle -I that use the same DB file. This is an -optional parameter, and defaults to 1 (enabled). See L below for +for reads. Pass any true value to enable. This affects the base DB handle +I that use the same DB file. This is an +optional parameter, and defaults to 1 (enabled). See L below for more. =item * autoflush @@ -184,7 +184,7 @@ more. Specifies whether autoflush is to be enabled on the underlying filehandle. This obviously slows down write operations, but is required if you may have multiple processes accessing the same DB file (also consider enable I). -Pass any true value to enable. This is an optional parameter, and defaults to 1 +Pass any true value to enable. This is an optional parameter, and defaults to 1 (enabled). =item * filter_* @@ -243,17 +243,17 @@ See L for more information. =head1 TIE INTERFACE With DBM::Deep you can access your databases using Perl's standard hash/array -syntax. Because all DBM::Deep objects are I to hashes or arrays, you can -treat them as such. DBM::Deep will intercept all reads/writes and direct them -to the right place -- the DB file. This has nothing to do with the -L section above. This simply tells you how to use DBM::Deep +syntax. Because all DBM::Deep objects are I to hashes or arrays, you can +treat them as such. DBM::Deep will intercept all reads/writes and direct them +to the right place -- the DB file. This has nothing to do with the +L section above. This simply tells you how to use DBM::Deep using regular hashes and arrays, rather than calling functions like C -and C (although those work too). It is entirely up to you how to want +and C (although those work too). It is entirely up to you how to want to access your databases. -=head2 HASHES +=head2 Hashes -You can treat any DBM::Deep object like a normal Perl hash reference. Add keys, +You can treat any DBM::Deep object like a normal Perl hash reference. Add keys, or even nested hashes (or arrays) using standard Perl syntax: my $db = DBM::Deep->new( "foo.db" ); @@ -271,8 +271,8 @@ You can even step through hash keys using the normal Perl C function: } Remember that Perl's C function extracts I key from the hash and -pushes them onto an array, all before the loop even begins. If you have an -extremely large hash, this may exhaust Perl's memory. Instead, consider using +pushes them onto an array, all before the loop even begins. If you have an +extremely large hash, this may exhaust Perl's memory. Instead, consider using Perl's C function, which pulls keys/values one at a time, using very little memory: @@ -281,7 +281,7 @@ little memory: } Please note that when using C, you should always pass a direct -hash reference, not a lookup. Meaning, you should B do this: +hash reference, not a lookup. Meaning, you should B do this: # NEVER DO THIS while (my ($key, $value) = each %{$db->{foo}}) { # BAD @@ -291,13 +291,13 @@ FETCH() on the $db handle, resulting in a "new" hash for foo every time, so it effectively keeps returning the first key over and over again. Instead, assign a temporary variable to C<$db->{foo}>, then pass that to each(). -=head2 ARRAYS +=head2 Arrays As with hashes, you can treat any DBM::Deep object like a normal Perl array -reference. This includes inserting, removing and manipulating elements, +reference. This includes inserting, removing and manipulating elements, and the C, C, C, C and C functions. The object must have first been created using type CTYPE_ARRAY>, -or simply be a nested array reference inside a hash. Example: +or simply be a nested array reference inside a hash. Example: my $db = DBM::Deep->new( file => "foo-array.db", @@ -317,7 +317,7 @@ or simply be a nested array reference inside a hash. Example: =head1 OO INTERFACE In addition to the I interface, you can also use a standard OO interface -to manipulate all aspects of DBM::Deep databases. Each type of object (hash or +to manipulate all aspects of DBM::Deep databases. Each type of object (hash or array) has its own methods, but both types share the following common methods: C, C, C, C and C. C and C are aliases to C and C, respectively. @@ -330,17 +330,17 @@ These are the constructor and copy-functions. =item * put() / store() -Stores a new hash key/value pair, or sets an array element value. Takes two -arguments, the hash key or array index, and the new value. The value can be -a scalar, hash ref or array ref. Returns true on success, false on failure. +Stores a new hash key/value pair, or sets an array element value. Takes two +arguments, the hash key or array index, and the new value. The value can be +a scalar, hash ref or array ref. Returns true on success, false on failure. $db->put("foo", "bar"); # for hashes $db->put(1, "bar"); # for arrays =item * get() / fetch() -Fetches the value of a hash key or array element. Takes one argument: the hash -key or array index. Returns a scalar, hash ref or array ref, depending on the +Fetches the value of a hash key or array element. Takes one argument: the hash +key or array index. Returns a scalar, hash ref or array ref, depending on the data type stored. my $value = $db->get("foo"); # for hashes @@ -348,31 +348,27 @@ data type stored. =item * exists() -Checks if a hash key or array index exists. Takes one argument: the hash key -or array index. Returns true if it exists, false if not. +Checks if a hash key or array index exists. Takes one argument: the hash key +or array index. Returns true if it exists, false if not. if ($db->exists("foo")) { print "yay!\n"; } # for hashes if ($db->exists(1)) { print "yay!\n"; } # for arrays =item * delete() -Deletes one hash key/value pair or array element. Takes one argument: the hash -key or array index. Returns true on success, false if not found. For arrays, +Deletes one hash key/value pair or array element. Takes one argument: the hash +key or array index. Returns true on success, false if not found. For arrays, the remaining elements located after the deleted element are NOT moved over. The deleted element is essentially just undefined, which is exactly how Perl's -internal arrays work. Please note that the space occupied by the deleted -key/value or element is B reused again -- see L -below for details and workarounds. +internal arrays work. $db->delete("foo"); # for hashes $db->delete(1); # for arrays =item * clear() -Deletes B hash keys or array elements. Takes no arguments. No return -value. Please note that the space occupied by the deleted keys/values or -elements is B reused again -- see L below for -details and workarounds. +Deletes B hash keys or array elements. Takes no arguments. No return +value. $db->clear(); # hashes or arrays @@ -389,9 +385,13 @@ transactions. Data going in and out. +=item * begin_work() / commit() / rollback() + +These are the transactional functions. L for more information. + =back -=head2 HASHES +=head2 Hashes For hashes, DBM::Deep supports all the common methods described above, and the following additional methods: C and C. @@ -400,8 +400,8 @@ following additional methods: C and C. =item * first_key() -Returns the "first" key in the hash. As with built-in Perl hashes, keys are -fetched in an undefined order (which appears random). Takes no arguments, +Returns the "first" key in the hash. As with built-in Perl hashes, keys are +fetched in an undefined order (which appears random). Takes no arguments, returns the key as a scalar value. my $key = $db->first_key(); @@ -434,7 +434,7 @@ Here are some examples of using hashes: if ($db->exists("foo")) { $db->delete("foo"); } -=head2 ARRAYS +=head2 Arrays For arrays, DBM::Deep supports all the common methods described above, and the following additional methods: C, C, C, C, @@ -444,28 +444,28 @@ C and C. =item * length() -Returns the number of elements in the array. Takes no arguments. +Returns the number of elements in the array. Takes no arguments. my $len = $db->length(); =item * push() -Adds one or more elements onto the end of the array. Accepts scalars, hash -refs or array refs. No return value. +Adds one or more elements onto the end of the array. Accepts scalars, hash +refs or array refs. No return value. $db->push("foo", "bar", {}); =item * pop() -Fetches the last element in the array, and deletes it. Takes no arguments. -Returns undef if array is empty. Returns the element value. +Fetches the last element in the array, and deletes it. Takes no arguments. +Returns undef if array is empty. Returns the element value. my $elem = $db->pop(); =item * shift() Fetches the first element in the array, deletes it, then shifts all the -remaining elements over to take up the space. Returns the element value. This +remaining elements over to take up the space. Returns the element value. This method is not recommended with large arrays -- see L below for details. @@ -474,16 +474,16 @@ details. =item * unshift() Inserts one or more elements onto the beginning of the array, shifting all -existing elements over to make room. Accepts scalars, hash refs or array refs. -No return value. This method is not recommended with large arrays -- see +existing elements over to make room. Accepts scalars, hash refs or array refs. +No return value. This method is not recommended with large arrays -- see below for details. $db->unshift("foo", "bar", {}); =item * splice() -Performs exactly like Perl's built-in function of the same name. See L for usage -- it is too complicated to document here. This method is +Performs exactly like Perl's built-in function of the same name. See L for usage -- it is too complicated to document here. This method is not recommended with large arrays -- see L below for details. =back @@ -524,16 +524,16 @@ C parameter when constructing your DBM::Deep object (see L ); This causes DBM::Deep to C the underlying filehandle with exclusive -mode for writes, and shared mode for reads. This is required if you have +mode for writes, and shared mode for reads. This is required if you have multiple processes accessing the same database file, to avoid file corruption. -Please note that C does NOT work for files over NFS. See L does NOT work for files over NFS. See L below for more. -=head2 EXPLICIT LOCKING +=head2 Explicit Locking You can explicitly lock a database, so it remains locked for multiple -actions. This is done by calling the C method, and passing an -optional lock mode argument (defaults to exclusive mode). This is particularly +actions. This is done by calling the C method, and passing an +optional lock mode argument (defaults to exclusive mode). This is particularly useful for things like counters, where the current value needs to be fetched, then incremented, then stored again. @@ -550,8 +550,8 @@ then incremented, then stored again. $db->unlock(); You can pass C an optional argument, which specifies which mode to use -(exclusive or shared). Use one of these two constants: -CLOCK_EX> or CLOCK_SH>. These are passed +(exclusive or shared). Use one of these two constants: +CLOCK_EX> or CLOCK_SH>. These are passed directly to C, and are the same as the constants defined in Perl's L module. @@ -563,14 +563,14 @@ L module. You can import existing complex structures by calling the C method, and export an entire database into an in-memory structure using the C -method. Both are examined here. +method. Both are examined here. -=head2 IMPORTING +=head2 Importing -Say you have an existing hash with nested hashes/arrays inside it. Instead of +Say you have an existing hash with nested hashes/arrays inside it. Instead of walking the structure and adding keys/elements to the database as you go, -simply pass a reference to the C method. This recursively adds -everything to an existing DBM::Deep object for you. Here is an example: +simply pass a reference to the C method. This recursively adds +everything to an existing DBM::Deep object for you. Here is an example: my $struct = { key1 => "value1", @@ -588,7 +588,7 @@ everything to an existing DBM::Deep object for you. Here is an example: print $db->{key1} . "\n"; # prints "value1" This recursively imports the entire C<$struct> object into C<$db>, including -all nested hashes and arrays. If the DBM::Deep object contains exsiting data, +all nested hashes and arrays. If the DBM::Deep object contains exsiting data, keys are merged with the existing ones, replacing if they already exist. The C method can be called on any database level (not just the base level), and works with both hash and array DB types. @@ -603,12 +603,12 @@ failre). As a result, you cannot call C from within a transaction. This restriction will be lifted when subtransactions are added in a future release. -=head2 EXPORTING +=head2 Exporting Calling the C method on an existing DBM::Deep object will return -a reference to a new in-memory copy of the database. The export is done +a reference to a new in-memory copy of the database. The export is done recursively, so all nested hashes/arrays are all exported to standard Perl -objects. Here is an example: +objects. Here is an example: my $db = DBM::Deep->new( "foo.db" ); @@ -623,8 +623,8 @@ objects. Here is an example: print $struct->{key1} . "\n"; # prints "value1" This makes a complete copy of the database in memory, and returns a reference -to it. The C method can be called on any database level (not just -the base level), and works with both hash and array DB types. Be careful of +to it. The C method can be called on any database level (not just +the base level), and works with both hash and array DB types. Be careful of large databases -- you can store a lot more data in a DBM::Deep object than an in-memory Perl structure. @@ -635,29 +635,29 @@ in a later release. =head1 FILTERS DBM::Deep has a number of hooks where you can specify your own Perl function -to perform filtering on incoming or outgoing data. This is a perfect +to perform filtering on incoming or outgoing data. This is a perfect way to extend the engine, and implement things like real-time compression or -encryption. Filtering applies to the base DB level, and all child hashes / -arrays. Filter hooks can be specified when your DBM::Deep object is first -constructed, or by calling the C method at any time. There are +encryption. Filtering applies to the base DB level, and all child hashes / +arrays. Filter hooks can be specified when your DBM::Deep object is first +constructed, or by calling the C method at any time. There are four available filter hooks, described below: =over =item * filter_store_key -This filter is called whenever a hash key is stored. It +This filter is called whenever a hash key is stored. It is passed the incoming key, and expected to return a transformed key. =item * filter_store_value -This filter is called whenever a hash key or array element is stored. It +This filter is called whenever a hash key or array element is stored. It is passed the incoming value, and expected to return a transformed value. =item * filter_fetch_key This filter is called whenever a hash key is fetched (i.e. via -C or C). It is passed the transformed key, +C or C). It is passed the transformed key, and expected to return the plain key. =item * filter_fetch_value @@ -681,19 +681,19 @@ Here are the two ways to setup a filter hook: $db->set_filter( "filter_fetch_value", \&my_filter_fetch ); Your filter function will be called only when dealing with SCALAR keys or -values. When nested hashes and arrays are being stored/fetched, filtering -is bypassed. Filters are called as static functions, passed a single SCALAR -argument, and expected to return a single SCALAR value. If you want to +values. When nested hashes and arrays are being stored/fetched, filtering +is bypassed. Filters are called as static functions, passed a single SCALAR +argument, and expected to return a single SCALAR value. If you want to remove a filter, set the function reference to C: $db->set_filter( "filter_store_value", undef ); -=head2 REAL-TIME ENCRYPTION EXAMPLE +=head2 Real-time Encryption Example Here is a working example that uses the I module to do real-time encryption / decryption of keys & values with DBM::Deep Filters. Please visit L for more -on I. You'll also need the I module. +on I. You'll also need the I module. use DBM::Deep; use Crypt::Blowfish; @@ -731,7 +731,7 @@ on I. You'll also need the I module. return $cipher->decrypt( $_[0] ); } -=head2 REAL-TIME COMPRESSION EXAMPLE +=head2 Real-time Compression Example Here is a working example that uses the I module to do real-time compression / decompression of keys & values with DBM::Deep Filters. @@ -764,13 +764,13 @@ more on I. return Compress::Zlib::memGunzip( $_[0] ) ; } -B Filtering of keys only applies to hashes. Array "keys" are +B Filtering of keys only applies to hashes. Array "keys" are actually numerical index numbers, and are not filtered. =head1 ERROR HANDLING Most DBM::Deep methods return a true value for success, and call die() on -failure. You can wrap calls in an eval block to catch the die. +failure. You can wrap calls in an eval block to catch the die. my $db = DBM::Deep->new( "foo.db" ); # create hash eval { $db->push("foo"); }; # ILLEGAL -- push is array-only call @@ -790,7 +790,7 @@ by specifying the 'pack_size' parameter when constructing the file. ); This tells DBM::Deep to pack all file offsets with 8-byte (64-bit) quad words -instead of 32-bit longs. After setting these values your DB files have a +instead of 32-bit longs. After setting these values your DB files have a theoretical maximum size of 16 XB (exabytes). You can also use C 'small'> in order to use 16-bit file @@ -803,7 +803,7 @@ parameters are per-file, meaning you can access 32-bit and 64-bit files, as you choose. B We have not personally tested files larger than 2 GB -- all my -systems have only a 32-bit Perl. However, I have received user reports that +systems have only a 32-bit Perl. However, I have received user reports that this does indeed work! =head1 LOW-LEVEL ACCESS @@ -814,23 +814,23 @@ you can call the C<_fh()> method, which returns the handle: my $fh = $db->_fh(); This method can be called on the root level of the datbase, or any child -hashes or arrays. All levels share a I structure, which contains things +hashes or arrays. All levels share a I structure, which contains things like the filehandle, a reference counter, and all the options specified -when you created the object. You can get access to this file object by +when you created the object. You can get access to this file object by calling the C<_storage()> method. my $file_obj = $db->_storage(); This is useful for changing options after the object has already been created, -such as enabling/disabling locking. You can also store your own temporary user +such as enabling/disabling locking. You can also store your own temporary user data in this structure (be wary of name collision), which is then accessible from any child hash or array. =head1 CUSTOM DIGEST ALGORITHM DBM::Deep by default uses the I (MD5) algorithm for hashing -keys. However you can override this, and use another algorithm (such as SHA-256) -or even write your own. But please note that DBM::Deep currently expects zero +keys. However you can override this, and use another algorithm (such as SHA-256) +or even write your own. But please note that DBM::Deep currently expects zero collisions, so your algorithm has to be I, so to speak. Collision detection may be introduced in a later version. @@ -838,7 +838,7 @@ You can specify a custom digest algorithm by passing it into the parameter list for new(), passing a reference to a subroutine as the 'digest' parameter, and the length of the algorithm's hashes (in bytes) as the 'hash_size' parameter. Here is a working example that uses a 256-bit hash from the -I module. Please see +I module. Please see L for more information. use DBM::Deep; @@ -877,7 +877,7 @@ evaluation of some edge cases. I hope to be able to re-enable circular references in a future version after 1.00. This means that circular references are B available. -DBM::Deep has B support for circular references. Meaning you +DBM::Deep has B support for circular references. Meaning you can have a nested hash key or array element that points to a parent object. This relationship is stored in the DB file, and is preserved between sessions. Here is an example: @@ -921,8 +921,14 @@ the transaction. =back -Transactions in DBM::Deep are done using the MVCC method, the same method used -by the InnoDB MySQL engine. +Transactions in DBM::Deep are done using a variant of the MVCC method, the +same method used by the InnoDB MySQL engine. + +=head2 Software-Transactional Memory + +The addition of transactions to this module provides the basis for STM within +Perl 5. Contention is resolved using a default last-write-wins. Currently, +this default cannot be changed, but it will be addressed in a future version. =head1 PERFORMANCE @@ -971,14 +977,14 @@ DBM::Deep to use 16bit addresses, meaning that the seek times will be less. The following are items that are planned to be added in future releases. These are separate from the L below. -=head2 SUB-TRANSACTIONS +=head2 Sub-Transactions Right now, you cannot run a transaction within a transaction. Removing this restriction is technically straightforward, but the combinatorial explosion of possible usecases hurts my head. If this is something you want to see immediately, please submit many testcases. -=head2 CACHING +=head2 Caching If a user is willing to assert upon opening the file that this process will be the only consumer of that datafile, then there are a number of caching @@ -987,7 +993,7 @@ DBM::Deep is more vulnerable to losing data due to unflushed changes. It also means a much larger in-memory footprint. As such, it's not clear exactly how this should be done. Suggestions are welcome. -=head2 RAM-ONLY +=head2 Ram-only The techniques used in DBM::Deep simply require a seekable contiguous datastore. This could just as easily be a large string as a file. By using @@ -995,6 +1001,21 @@ substr, the STM capabilities of DBM::Deep could be used within a single-process. I have no idea how I'd specify this, though. Suggestions are welcome. +=head2 Importing using Data::Walker + +Right now, importing is done using C to make a complete copy +in memory, then tying that copy. It would be much better to use +L to walk the data structure instead, particularly in the case +of large datastructures. + +=head2 Different contention resolution mechanisms + +Currently, the only contention resolution mechanism is last-write-wins. This +is the mechanism used by most RDBMSes and should be good enough for most uses. +For advanced uses of STM, other contention mechanisms will be needed. If you +have an idea of how you'd like to see contention resolution in DBM::Deep, +please let me know. + =head1 CAVEATS, ISSUES & BUGS This section describes all the known issues with DBM::Deep. These are issues @@ -1003,10 +1024,10 @@ exactly right. It you have found something that is not listed below, please send an e-mail to L. Likewise, if you think you know of a way around one of these issues, please let me know. -=head2 REFERENCES +=head2 References -(The reasons given assume a high level of Perl understanding, specifically of -references. You can safely skip this section.) +(The following assumes a high level of Perl understanding, specifically of +references. Most users can safely skip this section.) Currently, the only references supported are HASH and ARRAY. The other reference types (SCALAR, CODE, GLOB, and REF) cannot be supported for various reasons. @@ -1034,8 +1055,9 @@ The discussion here refers to the following type of example: is( $val, 50, "What actually gets stored in the DB file?" ); The problem is one of synchronization. When the variable being referred to -changes value, the reference isn't notified. This means that the new value won't -be stored in the datafile for other processes to read. There is no TIEREF. +changes value, the reference isn't notified, which is kind of the point of +references. This means that the new value won't be stored in the datafile for +other processes to read. There is no TIEREF. It is theoretically possible to store references to values already within a DBM::Deep object because everything already is synchronized, but the change to @@ -1047,35 +1069,37 @@ all to support a feature that has never been requested. =item * CODE L provides a mechanism for serializing coderefs, -including saving off all closure state. However, just as for SCALAR and REF, +including saving off all closure state. This would allow for DBM::Deep to +store the code for a subroutine. Then, whenever the subroutine is read, the +code could be C'ed into being. However, just as for SCALAR and REF, that closure state may change without notifying the DBM::Deep object storing -the reference. +the reference. Again, this would generally be considered a feature. =back -=head2 FILE CORRUPTION +=head2 File corruption -The current level of error handling in DBM::Deep is minimal. Files I checked -for a 32-bit signature when opened, but other corruption in files can cause -segmentation faults. DBM::Deep may try to C past the end of a file, or get -stuck in an infinite loop depending on the level of corruption. File write -operations are not checked for failure (for speed), so if you happen to run -out of disk space, DBM::Deep will probably fail in a bad way. These things will -be addressed in a later version of DBM::Deep. +The current level of error handling in DBM::Deep is minimal. Files I checked +for a 32-bit signature when opened, but any other form of corruption in the +datafile can cause segmentation faults. DBM::Deep may try to C past +the end of a file, or get stuck in an infinite loop depending on the level and +type of corruption. File write operations are not checked for failure (for +speed), so if you happen to run out of disk space, DBM::Deep will probably fail in +a bad way. These things will be addressed in a later version of DBM::Deep. -=head2 DB OVER NFS +=head2 DB over NFS -Beware of using DBM::Deep files over NFS. DBM::Deep uses flock(), which works +Beware of using DBM::Deep files over NFS. DBM::Deep uses flock(), which works well on local filesystems, but will NOT protect you from file corruption over -NFS. I've heard about setting up your NFS server with a locking daemon, then +NFS. I've heard about setting up your NFS server with a locking daemon, then using C to lock your files, but your mileage may vary there as well. -From what I understand, there is no real way to do it. However, if you need +From what I understand, there is no real way to do it. However, if you need access to the underlying filehandle in DBM::Deep for using some other kind of locking scheme like C, see the L section above. -=head2 COPYING OBJECTS +=head2 Copying Objects -Beware of copying tied objects in Perl. Very strange things can happen. +Beware of copying tied objects in Perl. Very strange things can happen. Instead, use DBM::Deep's C method which safely copies the object and returns a new, blessed and tied hash or array to the same level in the DB. @@ -1084,21 +1108,21 @@ returns a new, blessed and tied hash or array to the same level in the DB. B: Since clone() here is cloning the object, not the database location, any modifications to either $db or $copy will be visible to both. -=head2 LARGE ARRAYS +=head2 Large Arrays Beware of using C, C or C with large arrays. These functions cause every element in the array to move, which can be murder on DBM::Deep, as every element has to be fetched from disk, then stored again in -a different location. This will be addressed in a future version. +a different location. This will be addressed in a future version. -=head2 WRITEONLY FILES +=head2 Writeonly Files If you pass in a filehandle to new(), you may have opened it in either a readonly or writeonly mode. STORE will verify that the filehandle is writable. However, there doesn't seem to be a good way to determine if a filehandle is readable. And, if the filehandle isn't readable, it's not clear what will happen. So, don't do that. -=head2 ASSIGNMENTS WITHIN TRANSACTIONS +=head2 Assignments Within Transactions The following will I work as one might expect: @@ -1170,7 +1194,7 @@ Digest::SHA256(3), Crypt::Blowfish(3), Compress::Zlib(3) =head1 LICENSE -Copyright (c) 2007 Rob Kinyon. All Rights Reserved. +Copyright (c) 2007 Rob Kinyon. All Rights Reserved. This is free software, you may use it and distribute it under the same terms as Perl itself. diff --git a/lib/DBM/Deep/Array.pm b/lib/DBM/Deep/Array.pm index d9ea66e..3d5804f 100644 --- a/lib/DBM/Deep/Array.pm +++ b/lib/DBM/Deep/Array.pm @@ -1,11 +1,11 @@ package DBM::Deep::Array; -use 5.6.0; +use 5.006_000; use strict; use warnings; -our $VERSION = '0.99_03'; +our $VERSION = '0.99_04'; # This is to allow DBM::Deep::Array to handle negative indices on # its own. Otherwise, Perl would intercept the call to negative diff --git a/lib/DBM/Deep/Engine.pm b/lib/DBM/Deep/Engine.pm index c5fca98..a491892 100644 --- a/lib/DBM/Deep/Engine.pm +++ b/lib/DBM/Deep/Engine.pm @@ -1,10 +1,10 @@ package DBM::Deep::Engine; -use 5.6.0; +use 5.006_000; use strict; -our $VERSION = q(0.99_03); +our $VERSION = q(0.99_04); use Scalar::Util (); diff --git a/lib/DBM/Deep/File.pm b/lib/DBM/Deep/File.pm index 4fda95c..84a98d4 100644 --- a/lib/DBM/Deep/File.pm +++ b/lib/DBM/Deep/File.pm @@ -1,11 +1,11 @@ package DBM::Deep::File; -use 5.6.0; +use 5.006_000; use strict; use warnings; -our $VERSION = q(0.99_03); +our $VERSION = q(0.99_04); use Fcntl qw( :DEFAULT :flock :seek ); diff --git a/lib/DBM/Deep/Hash.pm b/lib/DBM/Deep/Hash.pm index 4b3d1d4..fb27097 100644 --- a/lib/DBM/Deep/Hash.pm +++ b/lib/DBM/Deep/Hash.pm @@ -1,11 +1,11 @@ package DBM::Deep::Hash; -use 5.6.0; +use 5.006_000; use strict; use warnings; -our $VERSION = q(0.99_03); +our $VERSION = q(0.99_04); use base 'DBM::Deep'; diff --git a/t/17_import.t b/t/17_import.t index a23b2ed..204be66 100644 --- a/t/17_import.t +++ b/t/17_import.t @@ -97,16 +97,17 @@ use_ok( 'DBM::Deep' ); $db->{foo} = 'bar'; + my $x; my $struct = { key1 => [ - 2, sub {}, 3, + 2, \$x, 3, ], }; eval { $db->import( $struct ); }; - like( $@, qr/Storage of references of type 'CODE' is not supported/, 'Error message correct' ); + like( $@, qr/Storage of references of type 'SCALAR' is not supported/, 'Error message correct' ); cmp_deeply( $db, diff --git a/t/37_delete_edge_cases.t b/t/37_delete_edge_cases.t index 82d95ea..d873906 100644 --- a/t/37_delete_edge_cases.t +++ b/t/37_delete_edge_cases.t @@ -4,7 +4,7 @@ use strict; use Test::More tests => 4; use Test::Deep; -use Clone::Any qw( clone ); +use Clone qw( clone ); use t::common qw( new_fh ); use_ok( 'DBM::Deep' ); diff --git a/t/common.pm b/t/common.pm index d8a9a7e..3b4958c 100644 --- a/t/common.pm +++ b/t/common.pm @@ -1,6 +1,6 @@ package t::common; -use 5.6.0; +use 5.006_000; use strict; use warnings;