--- nfo/perl/libs/Data/Storage.pm 2002/11/17 06:07:18 1.7 +++ nfo/perl/libs/Data/Storage.pm 2002/12/19 16:27:59 1.14 @@ -1,12 +1,42 @@ -# $Id: Storage.pm,v 1.7 2002/11/17 06:07:18 joko Exp $ +# $Id: Storage.pm,v 1.14 2002/12/19 16:27:59 joko Exp $ # # Copyright (c) 2002 Andreas Motl # # See COPYRIGHT section in pod text below for usage and distribution rights. # -################################# +############################################ # # $Log: Storage.pm,v $ +# Revision 1.14 2002/12/19 16:27:59 joko +# - moved 'sub dropDb' to Data::Storage::Handler::DBI +# +# Revision 1.13 2002/12/17 21:54:12 joko +# + feature when using Tangram: +# + what? each object created should delivered with a globally(!?) unique identifier (GUID) besides the native tangram object id (OID) +# + patched Tangram::Storage (jonen) +# + enhanced Data::Storage::Schema::Tangram (joko) +# + enhanced Data::Storage::Handler::Tangram 'sub getObjectByGuid' (jonen) +# + how? +# + each concrete (non-abstract) class gets injected with an additional field/property called 'guid' - this is done (dynamically) on schema level +# + this property ('guid') gets filled on object creation/insertion from 'sub Tangram::Storage::_insert' using Data::UUID from CPAN +# + (as for now) this property can get accessed by calling 'getObjectByGuid' on the already known storage-handle used throughout the application +# +# Revision 1.12 2002/12/12 02:50:15 joko +# + this now (unfortunately) needs DBI for some helper functions +# + TODO: these have to be refactored to another scope! (soon!) +# +# Revision 1.11 2002/12/11 06:53:19 joko +# + updated pod +# +# Revision 1.10 2002/12/07 03:37:23 joko +# + updated pod +# +# Revision 1.9 2002/12/01 22:15:45 joko +# - sub createDb: moved to handler +# +# Revision 1.8 2002/11/29 04:48:23 joko +# + updated pod +# # Revision 1.7 2002/11/17 06:07:18 joko # + creating the handler is easier than proposed first - for now :-) # + sub testAvailability @@ -34,25 +64,33 @@ # Revision 1.1 2002/10/10 03:43:12 cvsjoko # + new # -################################# +############################################ -# aim_V1: should encapsulate Tangram, DBI, DBD::CSV and LWP:: to access them in an unordinary way ;) -# aim_V2: introduce a generic layered structure, refactor *SUBLAYER*-stuff, make (e.g.) this possible: -# - Perl Data::Storage[DBD::CSV] -> Perl LWP:: -> Internet HTTP/FTP/* -> Host Daemon -> csv-file BEGIN { -$Data::Storage::VERSION = 0.01; + $Data::Storage::VERSION = 0.02; } =head1 NAME -Data::Storage - Interface for accessing various Storage implementations for Perl in an independent way + Data::Storage - Interface for accessing various Storage implementations for Perl in an independent way + + +=head1 AIMS + + - should encapsulate Tangram, DBI, DBD::CSV and LWP:: to access them in an unordinary (more convenient) way ;) + - introduce a generic layered structure, refactor *SUBLAYER*-stuff, make (e.g.) this possible: + Perl Data::Storage[DBD::CSV] -> Perl LWP:: -> Internet HTTP/FTP/* -> Host Daemon -> csv-file + - provide generic synchronization mechanisms across arbitrary/multiple storages based on ident/checksum + maybe it's possible to have schema-, structural- and semantical modifications synchronized??? + =head1 SYNOPSIS - ... the basic way: +=head2 BASIC ACCESS +=head2 ADVANCED ACCESS ... via inheritance: @@ -70,20 +108,101 @@ $self->{storage}->insert($proxyObj); +=head2 SYNCHRONIZATION + + my $nodemapping = { + 'LangText' => 'langtexts.csv', + 'Currency' => 'currencies.csv', + 'Country' => 'countries.csv', + }; + + my $propmapping = { + 'LangText' => [ + [ 'source:lcountrykey' => 'target:country' ], + [ 'source:lkey' => 'target:key' ], + [ 'source:lvalue' => 'target:text' ], + ], + 'Currency' => [ + [ 'source:ckey' => 'target:key' ], + [ 'source:cname' => 'target:text' ], + ], + 'Country' => [ + [ 'source:ckey' => 'target:key' ], + [ 'source:cname' => 'target:text' ], + ], + }; + + sub syncResource { + + my $self = shift; + my $node_source = shift; + my $mode = shift; + my $opts = shift; + + $mode ||= ''; + $opts->{erase} ||= 0; + + $logger->info( __PACKAGE__ . "->syncResource( node_source $node_source mode $mode erase $opts->{erase} )"); + + # resolve metadata for syncing requested resource + my $node_target = $nodemapping->{$node_source}; + my $mapping = $propmapping->{$node_source}; + + if (!$node_target || !$mapping) { + # loggger.... "no target, sorry!" + print "error while resolving resource metadata", "\n"; + return; + } + + if ($opts->{erase}) { + $self->_erase_all($node_source); + } + + # create new sync object + my $sync = Data::Transfer::Sync->new( + storages => { + L => $self->{bizWorks}->{backend}, + R => $self->{bizWorks}->{resources}, + }, + id_authorities => [qw( L ) ], + checksum_authorities => [qw( L ) ], + write_protected => [qw( R ) ], + verbose => 1, + ); + + # sync + # todo: filter!? + $sync->syncNodes( { + direction => $mode, # | +PUSH | +PULL | -FULL | +IMPORT | -EXPORT + method => 'checksum', # | -timestamp | -manual + source => "L:$node_source", + source_ident => 'storage_method:id', + source_exclude => [qw( id cs )], + target => "R:$node_target", + target_ident => 'property:oid', + mapping => $mapping, + } ); + + } + + =head2 NOTE -This module heavily relies on DBI and Tangram, but adds a lot of additional bugs and quirks. -Please look at their documentation and/or this code for additional information. + This module heavily relies on DBI and Tangram, but adds a lot of additional bugs and quirks. + Please look at their documentation and/or this code for additional information. =head1 REQUIREMENTS -For full functionality: - DBI from CPAN - Tangram from CPAN - Class::Tangram from CPAN - MySQL::Diff from http://adamspiers.org/computing/mysqldiff/ - ... and all their dependencies + For full functionality: + DBI from CPAN + DBD::mysql from CPAN + Tangram 2.04 from CPAN (hmmm, 2.04 won't do in some cases) + Tangram 2.05 from http://... (2.05 seems okay but there are also additional patches from our side) + Class::Tangram from CPAN + DBD::CSV from CPAN + MySQL::Diff from http://adamspiers.org/computing/mysqldiff/ + ... and all their dependencies =cut @@ -98,6 +217,9 @@ use Data::Storage::Locator; use Data::Dumper; +# TODO: wipe out! +use DBI; + # TODO: actually implement level (integrate with Log::Dispatch) my $TRACELEVEL = 0; @@ -126,7 +248,7 @@ # - Deep recursion on subroutine "Data::Storage::AUTOLOAD" # - Deep recursion on subroutine "Data::Storage::Handler::Abstract::AUTOLOAD" # - Deep recursion on anonymous subroutine at [...] - # we also might filter log messages caused by logging itself in "advanced logging of AUTOLOAD calls" + # we also might filter log messages caused by logging to itself in "advanced logging of AUTOLOAD calls" my $self = shift; our $AUTOLOAD; @@ -148,12 +270,12 @@ $logstring .= "\t" x $tabcount . "(AUTOLOAD)"; # TODO: only ok if logstring doesn't contain # e.g. "Data::Storage[Tangram]->insert(SystemEvent=HASH(0x5c0034c)) (AUTOLOAD)" - # but that would be way too specific as long as we don't have an abstract handler for this ;) + # but that would be _way_ too specific as long as we don't have an abstract handler for this ;) $logger->debug( $logstring ); #print join('; ', @_); } - # filtering AUTOLOAD calls + # filtering AUTOLOAD calls and first-time-touch of the actual storage impl if ($self->_filter_AUTOLOAD($method)) { #print "_accessStorage\n"; $self->_accessStorage(); @@ -213,8 +335,9 @@ #my @args = %{$self->{locator}}; my @args = (); - # create new storage handle object, propagate arguments to handler - # pass locator by reference to be able to store status information in it + # - create new storage handle object + # - propagate arguments to handler + # - pass locator by reference to be able to store status- or meta-information in it $self->{STORAGEHANDLE} = $pkg->new( locator => $self->{locator}, @args ); } @@ -248,13 +371,10 @@ } sub removeLogDispatchHandler { - - my $self = shift; - my $name = shift; - #my $logger = shift; - - $logger->remove($name); - + my $self = shift; + my $name = shift; + #my $logger = shift; + $logger->remove($name); } sub getDbName { @@ -265,20 +385,6 @@ return $database_name; } -sub testDsn { - my $self = shift; - my $dsn = $self->{locator}->{dbi}->{dsn}; - my $result; - if ( my $dbh = DBI->connect($dsn, '', '', { - PrintError => 0, - } ) ) { - $dbh->disconnect(); - return 1; - } else { - $logger->warning( __PACKAGE__ . "[$self->{locator}->{type}]" . "->testDsn(): " . "DBI-error: " . $DBI::errstr ); - } -} - sub testAvailability { my $self = shift; my $status = $self->testDsn(); @@ -286,60 +392,27 @@ return $status; } -sub createDb { +sub isConnected { my $self = shift; - my $dsn = $self->{locator}->{dbi}->{dsn}; - - $logger->debug( __PACKAGE__ . "->createDb( dsn $dsn )" ); - - $dsn =~ s/database=(.+?);//; - my $database_name = $1; - - my $ok; - - if ( my $dbh = DBI->connect($dsn, '', '', { - PrintError => 0, - } ) ) { - if ($database_name) { - if ($dbh->do("CREATE DATABASE $database_name;")) { - $ok = 1; - } - } - $dbh->disconnect(); - } - - return $ok; - + # TODO: REVIEW! + return 1 if $self->{STORAGEHANDLE}; } -sub dropDb { +sub testDsn { my $self = shift; my $dsn = $self->{locator}->{dbi}->{dsn}; - - $logger->debug( __PACKAGE__ . "->dropDb( dsn $dsn )" ); - - $dsn =~ s/database=(.+?);//; - my $database_name = $1; - - my $ok; - + my $result; if ( my $dbh = DBI->connect($dsn, '', '', { PrintError => 0, } ) ) { - if ($database_name) { - if ($dbh->do("DROP DATABASE $database_name;")) { - $ok = 1; - } - } + + # TODO: REVIEW $dbh->disconnect(); + + return 1; + } else { + $logger->warning( __PACKAGE__ . "[$self->{locator}->{type}]" . "->testDsn(): " . "DBI-error: " . $DBI::errstr ); } - - return $ok; -} - -sub isConnected { - my $self = shift; - return 1 if $self->{STORAGEHANDLE}; } 1; @@ -348,44 +421,64 @@ =head1 DESCRIPTION -Data::Storage is module for a accessing various "data structures" stored inside -various "data containers". It sits on top of DBI and/or Tangram. +=head2 Data::Storage + Data::Storage is a module for accessing various "data structures / kinds of structured data" stored inside + various "data containers". + We tried to use the AdapterPattern (http://c2.com/cgi/wiki?AdapterPattern) to implement a wrapper-layer + around core CPAN modules (Tangram, DBI). + +=head2 Why? + + You will get a better code-structure (not bad for later maintenance) in growing Perl code projects, + especially when using multiple database connections at the same time. + You will be able to switch between different _kinds_ of implementations used for storing data. + Your code will use the very same API to access these storage layers. + ... implementation has to be changed for now + Maybe you will be able to switch "on-the-fly" without changing any bits in code in the future.... + ... but that's not the focus -=head1 AUTHORS / COPYRIGHT +=head2 What else? + + Having this, we were able to do implement a generic data synchronization module more easy, + please look at Data::Transfer. -The Data::Storage module is Copyright (c) 2002 Andreas Motl. -All rights reserved. -You may distribute it under the terms of either the GNU General Public -License or the Artistic License, as specified in the Perl README file. +=head1 AUTHORS / COPYRIGHT + + The Data::Storage module is Copyright (c) 2002 Andreas Motl. + All rights reserved. + You may distribute it under the terms of either the GNU General Public + License or the Artistic License, as specified in the Perl README file. =head1 ACKNOWLEDGEMENTS -Larry Wall for Perl, Tim Bunce for DBI, Jean-Louis Leroy for Tangram and Set::Object, -Sam Vilain for Class::Tangram, Adam Spiers for MySQL::Diff and all contributors. + Larry Wall for Perl, Tim Bunce for DBI, Jean-Louis Leroy for Tangram and Set::Object, + Sam Vilain for Class::Tangram, Jochen Wiedmann and Jeff Zucker for DBD::CSV & Co., + Adam Spiers for MySQL::Diff and all contributors. =head1 SUPPORT / WARRANTY -Data::Storage is free software. IT COMES WITHOUT WARRANTY OF ANY KIND. + Data::Storage is free software. IT COMES WITHOUT WARRANTY OF ANY KIND. =head1 TODO -=head2 Handle the following errors/cases: +=head2 BUGS + +"DBI-Error [Tangram]: DBD::mysql::st execute failed: Unknown column 't1.requestdump' in 'field list'" -=head3 "DBI-Error [Tangram]: DBD::mysql::st execute failed: Unknown column 't1.requestdump' in 'field list'" + ... occours when operating on object-attributes not introduced yet: + this should be detected and appended/replaced through: + "Schema-Error detected, maybe (just) an inconsistency. + Please check if your declaration in schema-module "a" matches structure in database "b" or try to run" + db_setup.pl --dbkey=import --action=deploy - ... occours when operating on object-attributes not introduced yet: - this should be detected and appended/replaced through: - "Schema-Error detected, maybe (just) an inconsistency. - Please check if your declaration in schema-module "a" matches structure in database "b" or try to run" - db_setup.pl --dbkey=import --action=deploy -=head3 Compare schema (structure diff) with database ... +Compare schema (structure diff) with database ... ... when issuing "db_setup.pl --dbkey=import --action=deploy" on a database with an already deployed schema, use an additional "--update" then @@ -414,7 +507,7 @@ automatically and this is believed to be the most common case under normal circumstances. -=head2 Introduce some features: +=head2 FEATURES - Get this stuff together with UML (Unified Modeling Language) and/or standards from ODMG. - Make it possible to load/save schemas in XMI (XML Metadata Interchange), @@ -422,14 +515,37 @@ Integrate/bundle this with a web-/html-based UML modeling tool or some other interesting stuff like the "Co-operative UML Editor" from Uni Darmstadt. (web-/java-based) - Enable Round Trip Engineering. Keep code and diagrams in sync. Don't annoy/bother the programmers. - - Add some more handlers: - - look at DBD::CSV, Text::CSV, XML::CSV, XML::Excel - - Add some more locations/locators: - - PerlDAV: http://www.webdav.org/perldav/ - - Move to t3, use InCASE + - Add support for some more handlers/locators to be able to + access the following standards/protocols/interfaces/programs/apis transparently: + + DBD::CSV (via Data::Storage::Handler::DBI) + (-) Text::CSV, XML::CSV, XML::Excel + - MAPI + - LDAP + - DAV (look at PerlDAV: http://www.webdav.org/perldav/) + - Mbox (use formail for seperating/splitting entries/nodes) + - Cyrus (cyrdeliver - what about cyrretrieve (export)???) + - use File::DiffTree, use File::Compare + - Hibernate + - "Win32::UserAccountDb" + - "*nix::UserAccountDb" + - .wab - files (Windows Address Book) + - .pst - files (Outlook Post Storage?) + - XML (e.g. via XML::Simple?) + - Move to t3, look at InCASE + - some kind of security layer for methods/objects + - acls (stored via tangram/ldap?) for functions, methods and objects (entity- & data!?) + - where are the hooks needed then? + - is Data::Storage & Co. okay, or do we have to touch the innards of DBI and/or Tangram? + - an attempt to start could be: + - 'sub getACLByObjectId($id, $context)' + - 'sub getACLByMethodname($id, $context)' + - 'sub getACLByName($id, $context)' + ( would require a kinda registry to look up these very names pointing to arbitrary locations (code, data, ...) ) + - add more hooks and various levels + - better integrate introduced 'getObjectByGuid'-mechanism from Data::Storage::Handler::Tangram -=head3 Links: +=head3 LINKS / REFERENCES Specs: UML 1.3 Spec: http://cgi.omg.org/cgi-bin/doc?ad/99-06-08.pdf