--- nfo/perl/libs/Data/Storage.pm 2002/10/27 18:35:07 1.4 +++ nfo/perl/libs/Data/Storage.pm 2002/12/01 22:15:45 1.9 @@ -1,12 +1,29 @@ -# $Id: Storage.pm,v 1.4 2002/10/27 18:35:07 joko Exp $ +# $Id: Storage.pm,v 1.9 2002/12/01 22:15:45 joko Exp $ # # Copyright (c) 2002 Andreas Motl # # See COPYRIGHT section in pod text below for usage and distribution rights. # -################################# +############################################ # # $Log: Storage.pm,v $ +# Revision 1.9 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 +# +# Revision 1.6 2002/11/09 01:04:58 joko +# + updated pod +# +# Revision 1.5 2002/10/29 19:24:18 joko +# - reduced logging +# + added some pod +# # Revision 1.4 2002/10/27 18:35:07 joko # + added pod # @@ -23,24 +40,33 @@ # 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 + +=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: @@ -58,11 +84,101 @@ $self->{storage}->insert($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 this code for additional information. +Please look at their documentation and/or this code for additional information. + + +=head1 REQUIREMENTS + 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 @@ -75,6 +191,10 @@ use warnings; use Data::Storage::Locator; +use Data::Dumper; + +# TODO: actually implement level (integrate with Log::Dispatch) +my $TRACELEVEL = 0; # get logger instance my $logger = Log::Dispatch::Config->instance; @@ -83,13 +203,14 @@ my $invocant = shift; my $class = ref($invocant) || $invocant; #my @args = normalizeArgs(@_); - + my $arg_locator = shift; my $arg_options = shift; - + #my $self = { STORAGEHANDLE => undef, @_ }; my $self = { STORAGEHANDLE => undef, locator => $arg_locator, options => $arg_options }; - $logger->debug( __PACKAGE__ . "[$self->{locator}->{type}]" . "->new(@_)" ); + #$logger->debug( __PACKAGE__ . "[$self->{locator}->{type}]" . "->new(@_)" ); + $logger->debug( __PACKAGE__ . "[$arg_locator->{type}]" . "->new(@_)" ); return bless $self, $class; } @@ -100,7 +221,7 @@ # - 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; @@ -111,20 +232,25 @@ my $method = $AUTOLOAD; $method =~ s/^.*:://; - # advanced logging of AUTOLOAD calls - my $logstring = ""; - $logstring .= __PACKAGE__ . "[$self->{locator}->{type}]" . "->" . $method; - #print "count: ", $#_, "\n"; - #$logstring .= Dumper(@_) if ($#_ != -1); - my $tabcount = int( (80 - length($logstring)) / 10 ); - $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 ;) - $logger->debug( $logstring ); - - # filtering AUTOLOAD calls + # advanced logging of AUTOLOAD calls ... + # ... nice but do it only when TRACING (TODO) is enabled + if ($TRACELEVEL) { + my $logstring = ""; + $logstring .= __PACKAGE__ . "[$self->{locator}->{type}]" . "->" . $method; + #print "count: ", $#_, "\n"; + #$logstring .= Dumper(@_) if ($#_ != -1); + my $tabcount = int( (80 - length($logstring)) / 10 ); + $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 ;) + $logger->debug( $logstring ); + #print join('; ', @_); + } + + # filtering AUTOLOAD calls and first-time-touch of the actual storage impl if ($self->_filter_AUTOLOAD($method)) { + #print "_accessStorage\n"; $self->_accessStorage(); $self->{STORAGEHANDLE}->$method(@_); } @@ -155,7 +281,9 @@ sub _accessStorage { my $self = shift; # TODO: to some tracelevel! - $logger->debug( __PACKAGE__ . "[$self->{locator}->{type}]" . "->_accessStorage()" ); + if ($TRACELEVEL) { + $logger->debug( __PACKAGE__ . "[$self->{locator}->{type}]" . "->_accessStorage()" ); + } if (!$self->{STORAGEHANDLE}) { $self->_createStorageHandle(); } @@ -163,33 +291,28 @@ sub _createStorageHandle { my $self = shift; - my $type = $self->{locator}->{type}; $logger->debug( __PACKAGE__ . "[$type]" . "->_createStorageHandle()" ); my $pkg = "Data::Storage::Handler::" . $type . ""; - # propagate args to handler - # needs some more thoughts! (not only "dbi" to Tangram, when (in future) db is not more the common case) - if ($type eq 'DBI') { - use Data::Storage::Handler::DBI; - #my @args = %{$self->{locator}->{dbi}}; - my @args = %{$self->{locator}}; - # create new storage handle - $self->{STORAGEHANDLE} = $pkg->new( @args ); - } - if ($type eq 'Tangram') { - use Data::Storage::Handler::Tangram; - #$self->{STORAGEHANDLE} = $pkg->new( dsn => $self->{locator}->{dbi}->{dsn} ); - #my @args = %{$self->{locator}->{dbi}}; - my @args = %{$self->{locator}}; - # create new storage handle - $self->{STORAGEHANDLE} = $pkg->new( @args ); - - #$self->{STORAGEHANDLE_UNDERLYING} = $self->{STORAGEHANDLE}->getUnderlyingStorage(); - #$self->{STORAGEHANDLE_UNDERLYING}->_configureCOREHANDLE(); + # try to load perl module at runtime + my $evalstr = "use $pkg;"; + eval($evalstr); + if ($@) { + $logger->error( __PACKAGE__ . "[$type]" . "->_createStorageHandle(): $@" ); + return; } + # build up some additional arguments to pass on + #my @args = %{$self->{locator}}; + my @args = (); + + # - create new storage handle object + # - propagate arguments to handler + # - pass locator by reference to be able to store status- or meta-information in it + $self->{STORAGEHANDLE} = $pkg->new( locator => $self->{locator}, @args ); + } sub addLogDispatchHandler { @@ -221,13 +344,10 @@ } 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 { @@ -245,39 +365,24 @@ if ( my $dbh = DBI->connect($dsn, '', '', { PrintError => 0, } ) ) { + + # TODO: REVIEW $dbh->disconnect(); + return 1; } else { - $logger->error( __PACKAGE__ . "[$self->{locator}->{type}]" . "->testDsn(): " . "DBI-error: " . $DBI::errstr ); + $logger->warning( __PACKAGE__ . "[$self->{locator}->{type}]" . "->testDsn(): " . "DBI-error: " . $DBI::errstr ); } } -sub createDb { +sub testAvailability { 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; - + my $status = $self->testDsn(); + $self->{locator}->{status}->{available} = $status; + return $status; } + sub dropDb { my $self = shift; my $dsn = $self->{locator}->{dbi}->{dsn}; @@ -297,7 +402,9 @@ $ok = 1; } } + $dbh->disconnect(); + } return $ok; @@ -314,7 +421,7 @@ =head1 DESCRIPTION -Data::Storage is module for a accessing various "data structures" stored inside +Data::Storage is a module for accessing various "data structures" stored inside various "data containers". It sits on top of DBI and/or Tangram. @@ -329,9 +436,9 @@ =head1 ACKNOWLEDGEMENTS -Larry Wall and the C for Perl, -Tim Bunce for DBI, Jean-Louis Leroy for Tangram and Set::Object, -Sam Vilain for Class::Tangram. +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 and related, +Adam Spiers for MySQL::Diff and all contributors. =head1 SUPPORT / WARRANTY @@ -342,17 +449,18 @@ =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 @@ -373,29 +481,73 @@ R retrieve -> no, not subject of this aspect since it is about deployment only U update -> yes, just by user-interaction; maybe automatically if it can be determined that data wouldn't be lost D delete -> yes, just by user-interaction - It's all about not to be able to loose data simply while this is in alpha stage. + + It's all about not to be able to loose data simply while this is in pre-alpha stage. + And loosing data by being able to modify and redeploy schemas easily is definitely quite easy. + + As we can see, creations of Classes and new Class variables is handled + 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), - which seems to be most commonly used today, perhaps handle objects with OIFML. - 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 programmer. + - 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), + which seems to be most commonly used today, perhaps handle objects with OIFML. + 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 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 -=head3 Links: +=head3 LINKS / REFERENCES + Specs: UML 1.3 Spec: http://cgi.omg.org/cgi-bin/doc?ad/99-06-08.pdf XMI 1.1 Spec: http://cgi.omg.org/cgi-bin/doc?ad/99-10-02.pdf XMI 2.0 Spec: http://cgi.omg.org/docs/ad/01-06-12.pdf ODMG: http://odmg.org/ OIFML: http://odmg.org/library/readingroom/oifml.pdf - Co-operative UML Editor: http://www.darmstadt.gmd.de/concert/activities/internal/umledit.html - further readings: + CASE Tools: + Rational Rose (commercial): http://www.rational.com/products/rose/ + Together (commercial): http://www.oi.com/products/controlcenter/index.jsp + InCASE - Tangram-based Universal Object Editor + Sybase PowerDesigner: http://www.sybase.com/powerdesigner + + UML Editors: + Fujaba (free, university): http://www.fujaba.de/ + ArgoUML (free): http://argouml.tigris.org/ + Poseidon (commercial): http://www.gentleware.com/products/poseidonDE.php3 + Co-operative UML Editor (research): http://www.darmstadt.gmd.de/concert/activities/internal/umledit.html + Metamill (commercial): http://www.metamill.com/ + Violet (university, research, education): http://www.horstmann.com/violet/ + PyUt (free): http://pyut.sourceforge.net/ + (Dia (free): http://www.lysator.liu.se/~alla/dia/) + UMLet (free, university): http://www.swt.tuwien.ac.at/umlet/index.html + Voodoo (free): http://voodoo.sourceforge.net/ + Umbrello UML Modeller: http://uml.sourceforge.net/ + + UML Tools: + http://www.objectsbydesign.com/tools/umltools_byPrice.html + + Further readings: http://www.google.com/search?q=web+based+uml+editor&hl=en&lr=&ie=UTF-8&oe=UTF-8&start=10&sa=N http://www.fernuni-hagen.de/DVT/Aktuelles/01FHHeidelberg.pdf http://www.enhyper.com/src/documentation/ @@ -403,5 +555,3 @@ http://citeseer.nj.nec.com/vilain00diagrammatic.html http://archive.devx.com/uml/articles/Smith01/Smith01-3.asp - maybe useful for / to be integrated with: - ArapXML: http://xml.coverpages.org/ni2001-09-24-b.html