--- nfo/perl/libs/Data/README.text 2002/10/27 18:35:50 1.1 +++ nfo/perl/libs/Data/README.text 2002/12/11 06:53:19 1.5 @@ -1,9 +1,17 @@ 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 + +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??? SYNOPSIS - ... the basic way: + BASIC ACCESS + + ADVANCED ACCESS ... via inheritance: @@ -20,43 +28,149 @@ ); $self->{storage}->insert($proxyObj); + 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, + } ); + + } + 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. + 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. + +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 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. + Data::Storage -AUTHORS / COPYRIGHT - The Data::Storage module is Copyright (c) 2002 Andreas Motl. All rights - reserved. + 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). + + 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 - 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. + What else? + + Having this, we were able to do implement a generic data synchronization module more easy, + please look at Data::Transfer. + +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. ACKNOWLEDGEMENTS - Larry Wall and the "perl5-porters" 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 & Co., + Adam Spiers for MySQL::Diff and all contributors. 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. TODO - Handle the following errors/cases: + BUGS - "DBI-Error [Tangram]: DBD::mysql::st execute failed: Unknown column 't1.requestdump' in 'field list'" + "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 - 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 @@ -77,27 +191,80 @@ 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. - Introduce some features: + 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 + - 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, ...) ) - Links: + 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/ @@ -105,5 +272,3 @@ 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