CONTRIBUTING000664001750001750 614612404270735 14157 0ustar00taitai000000000000XML-Atom-OWL-0.104NAME CONTRIBUTING DESCRIPTION If you're reading this document, that means you might be thinking about helping me out with this project. Thanks! Here's some ways you could help out: * Bug reports Found a bug? Great! (Well, not so great I suppose.) The place to report them is . Don't e-mail me about it, as your e-mail is more than likely to get lost amongst the spam. An example script clearly demonstrating the bug (preferably written using Test::More) would be greatly appreciated. * Patches If you've found a bug and written a fix for it, even better! Generally speaking you should check out the latest copy of the code from the source repository rather than using the CPAN distribution. The file META.yml should contain a link to the source repository. If not, then try or submit a bug report. (As far as I'm concerned the lack of a link is a bug.) Many of my distributions are also mirrored at . To submit the patch, do a pull request on GitHub or Bitbucket, or attach a diff file to a bug report. Unless otherwise stated, I'll assume that your contributions are licensed under the same terms as the rest of the project. (If using git, feel free to work in a branch. For Mercurial, I'd prefer bookmarks within the default branch.) * Documentation If there's anything unclear in the documentation, please submit this as a bug report or patch as above. Non-toy example scripts that I can bundle would also be appreciated. * Translation Translations of documentation would be welcome. For translations of error messages and other strings embedded in the code, check with me first. Sometimes the English strings may not in a stable state, so it would be a waste of time translating them. Coding Style I tend to write using something approximating the Allman style, using tabs for indentation and Unix-style line breaks. * * I nominally encode all source files as UTF-8, though in practice most of them use a 7-bit-safe ASCII-compatible subset of UTF-8. AUTHOR Toby Inkster . COPYRIGHT AND LICENCE Copyright (c) 2012-2014 by Toby Inkster. CONTRIBUTING is available under three different licences permitting its redistribution: the CC-BY-SA_UK-2.0 licence, plus the same licences as Perl itself, which is distributed under the GNU General Public Licence version 1, and the Artistic Licence. This file is licensed under the Creative Commons Attribution-ShareAlike 2.0 UK: England & Wales License. To view a copy of this license, visit . This file is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. COPYRIGHT000664001750001750 230612404270735 13612 0ustar00taitai000000000000XML-Atom-OWL-0.104Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/ Upstream-Name: XML-Atom-OWL Upstream-Contact: TOBYINK and Toby Inkster Source: https://metacpan.org/release/XML-Atom-OWL Files: CONTRIBUTING INSTALL LICENSE TODO examples/identica.pl examples/simple_example.pl Copyright: Unknown License: Unknown Files: Changes META.json META.yml dist.ini doap.ttl Copyright: Copyright 2014 Toby Inkster. License: GPL-1.0+ or Artistic-1.0 Files: COPYRIGHT CREDITS SIGNATURE Copyright: None License: public-domain Files: README lib/XML/Atom/OWL.pm Copyright: Copyright 2010-2011 Toby Inkster. License: GPL-1.0+ or Artistic-1.0 Files: t/01basic.t Copyright: Copyright 2011 Toby Inkster. License: GPL-1.0+ or Artistic-1.0 Files: Makefile.PL Copyright: Copyright 2013 Toby Inkster. License: GPL-1.0+ or Artistic-1.0 License: Artistic-1.0 This software is Copyright (c) 2014 by the copyright holder(s). This is free software, licensed under: The Artistic License 1.0 License: GPL-1.0 This software is Copyright (c) 2014 by the copyright holder(s). This is free software, licensed under: The GNU General Public License, Version 1, February 1989 CREDITS000664001750001750 11412404270730 13305 0ustar00taitai000000000000XML-Atom-OWL-0.104Maintainer: - TOBYINK - Toby Inkster Changes000664001750001750 277712404270730 13621 0ustar00taitai000000000000XML-Atom-OWL-0.104XML-Atom-OWL ============ Created: 2010-01-15 Home page: Bug tracker: Maintainer: Toby Inkster 0.104 2014-09-11 [ Packaging ] - Switch to Dist::Inkt. 0.103 2011-10-27 [ Packaging ] - Module::Package::RDF [ Other ] - Added: ActivityStrea.ms support. - Updated: use 5.010 0.102 2011-03-05 [ Documentation ] - Various formatting fixes and other minor improvements to documentation. [ Other ] - use Scalar::Util qw(blessed). 0.101 2010-07-19 [ Bug Fixes ] - Fix packaging error; Makefile.PL and META.yml didn't note dependency on common::sense. 0.100 2010-07-19 [ REGRESSIONS ] - Switched to using common::sense instead of strict, but didn't note change in Makefile.PL/META.yml [ Other ] - Automatically call 'consume' as required. 0.04 2010-04-29 - Keep base URI and lang information for element. 0.03 2010-04-28 - Added: Ability to automatically fetch links and include the content as if it had been inline. - Compliance improvements for element. 0.02 2010-01-23 - Added: Support arbitrary other extensions using XML literals. - Added: Support for Atom License Extension - Added: Support for Atom Threading Extension - Added: Support for Feed Paging and Archiving 0.01 2010-01-18 First release INSTALL000664001750001750 167512404270726 13360 0ustar00taitai000000000000XML-Atom-OWL-0.104 Installing XML-Atom-OWL should be straightforward. INSTALLATION WITH CPANMINUS If you have cpanm, you only need one line: % cpanm XML::Atom::OWL If you are installing into a system-wide directory, you may need to pass the "-S" flag to cpanm, which uses sudo to install the module: % cpanm -S XML::Atom::OWL INSTALLATION WITH THE CPAN SHELL Alternatively, if your CPAN shell is set up, you should just be able to do: % cpan XML::Atom::OWL MANUAL INSTALLATION As a last resort, you can manually install it. Download the tarball and unpack it. Consult the file META.json for a list of pre-requisites. Install these first. To build XML-Atom-OWL: % perl Makefile.PL % make && make test Then install it: % make install If you are installing into a system-wide directory, you may need to run: % sudo make install LICENSE000664001750001750 4365512404270726 13360 0ustar00taitai000000000000XML-Atom-OWL-0.104This software is copyright (c) 2014 by Toby Inkster. This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. Terms of the Perl programming language system itself a) the GNU General Public License as published by the Free Software Foundation; either version 1, or (at your option) any later version, or b) the "Artistic License" --- The GNU General Public License, Version 1, February 1989 --- This software is Copyright (c) 2014 by Toby Inkster. This is free software, licensed under: The GNU General Public License, Version 1, February 1989 GNU GENERAL PUBLIC LICENSE Version 1, February 1989 Copyright (C) 1989 Free Software Foundation, Inc. 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The license agreements of most software companies try to keep users at the mercy of those companies. By contrast, our General Public License is intended to guarantee your freedom to share and change free software--to make sure the software is free for all its users. The General Public License applies to the Free Software Foundation's software and to any other program whose authors commit to using it. You can use it for your programs, too. When we speak of free software, we are referring to freedom, not price. Specifically, the General Public License is designed to make sure that you have the freedom to give away or sell copies of free software, that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs; and that you know you can do these things. To protect your rights, we need to make restrictions that forbid anyone to deny you these rights or to ask you to surrender the rights. These restrictions translate to certain responsibilities for you if you distribute copies of the software, or if you modify it. For example, if you distribute copies of a such a program, whether gratis or for a fee, you must give the recipients all the rights that you have. You must make sure that they, too, receive or can get the source code. And you must tell them their rights. We protect your rights with two steps: (1) copyright the software, and (2) offer you this license which gives you legal permission to copy, distribute and/or modify the software. Also, for each author's protection and ours, we want to make certain that everyone understands that there is no warranty for this free software. If the software is modified by someone else and passed on, we want its recipients to know that what they have is not the original, so that any problems introduced by others will not reflect on the original authors' reputations. The precise terms and conditions for copying, distribution and modification follow. GNU GENERAL PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 0. This License Agreement applies to any program or other work which contains a notice placed by the copyright holder saying it may be distributed under the terms of this General Public License. The "Program", below, refers to any such program or work, and a "work based on the Program" means either the Program or any work containing the Program or a portion of it, either verbatim or with modifications. Each licensee is addressed as "you". 1. You may copy and distribute verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice and disclaimer of warranty; keep intact all the notices that refer to this General Public License and to the absence of any warranty; and give any other recipients of the Program a copy of this General Public License along with the Program. You may charge a fee for the physical act of transferring a copy. 2. You may modify your copy or copies of the Program or any portion of it, and copy and distribute such modifications under the terms of Paragraph 1 above, provided that you also do the following: a) cause the modified files to carry prominent notices stating that you changed the files and the date of any change; and b) cause the whole of any work that you distribute or publish, that in whole or in part contains the Program or any part thereof, either with or without modifications, to be licensed at no charge to all third parties under the terms of this General Public License (except that you may choose to grant warranty protection to some or all third parties, at your option). c) If the modified program normally reads commands interactively when run, you must cause it, when started running for such interactive use in the simplest and most usual way, to print or display an announcement including an appropriate copyright notice and a notice that there is no warranty (or else, saying that you provide a warranty) and that users may redistribute the program under these conditions, and telling the user how to view a copy of this General Public License. d) You may charge a fee for the physical act of transferring a copy, and you may at your option offer warranty protection in exchange for a fee. Mere aggregation of another independent work with the Program (or its derivative) on a volume of a storage or distribution medium does not bring the other work under the scope of these terms. 3. You may copy and distribute the Program (or a portion or derivative of it, under Paragraph 2) in object code or executable form under the terms of Paragraphs 1 and 2 above provided that you also do one of the following: a) accompany it with the complete corresponding machine-readable source code, which must be distributed under the terms of Paragraphs 1 and 2 above; or, b) accompany it with a written offer, valid for at least three years, to give any third party free (except for a nominal charge for the cost of distribution) a complete machine-readable copy of the corresponding source code, to be distributed under the terms of Paragraphs 1 and 2 above; or, c) accompany it with the information you received as to where the corresponding source code may be obtained. (This alternative is allowed only for noncommercial distribution and only if you received the program in object code or executable form alone.) Source code for a work means the preferred form of the work for making modifications to it. For an executable file, complete source code means all the source code for all modules it contains; but, as a special exception, it need not include source code for modules which are standard libraries that accompany the operating system on which the executable file runs, or for standard header files or definitions files that accompany that operating system. 4. You may not copy, modify, sublicense, distribute or transfer the Program except as expressly provided under this General Public License. Any attempt otherwise to copy, modify, sublicense, distribute or transfer the Program is void, and will automatically terminate your rights to use the Program under this License. However, parties who have received copies, or rights to use copies, from you under this General Public License will not have their licenses terminated so long as such parties remain in full compliance. 5. By copying, distributing or modifying the Program (or any work based on the Program) you indicate your acceptance of this license to do so, and all its terms and conditions. 6. Each time you redistribute the Program (or any work based on the Program), the recipient automatically receives a license from the original licensor to copy, distribute or modify the Program subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. 7. The Free Software Foundation may publish revised and/or new versions of the General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies a version number of the license which applies to it and "any later version", you have the option of following the terms and conditions either of that version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the license, you may choose any version ever published by the Free Software Foundation. 8. If you wish to incorporate parts of the Program into other free programs whose distribution conditions are different, write to the author to ask for permission. For software which is copyrighted by the Free Software Foundation, write to the Free Software Foundation; we sometimes make exceptions for this. Our decision will be guided by the two goals of preserving the free status of all derivatives of our free software and of promoting the sharing and reuse of software generally. NO WARRANTY 9. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 10. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. END OF TERMS AND CONDITIONS Appendix: How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to humanity, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively convey the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) 19yy This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 1, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program; if not, write to the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston MA 02110-1301 USA Also add information on how to contact you by electronic and paper mail. If the program is interactive, make it output a short notice like this when it starts in an interactive mode: Gnomovision version 69, Copyright (C) 19xx name of author Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, the commands you use may be called something other than `show w' and `show c'; they could even be mouse-clicks or menu items--whatever suits your program. You should also get your employer (if you work as a programmer) or your school, if any, to sign a "copyright disclaimer" for the program, if necessary. Here a sample; alter the names: Yoyodyne, Inc., hereby disclaims all copyright interest in the program `Gnomovision' (a program to direct compilers to make passes at assemblers) written by James Hacker. , 1 April 1989 Ty Coon, President of Vice That's all there is to it! --- The Artistic License 1.0 --- This software is Copyright (c) 2014 by Toby Inkster. This is free software, licensed under: The Artistic License 1.0 The Artistic License Preamble The intent of this document is to state the conditions under which a Package may be copied, such that the Copyright Holder maintains some semblance of artistic control over the development of the package, while giving the users of the package the right to use and distribute the Package in a more-or-less customary fashion, plus the right to make reasonable modifications. Definitions: - "Package" refers to the collection of files distributed by the Copyright Holder, and derivatives of that collection of files created through textual modification. - "Standard Version" refers to such a Package if it has not been modified, or has been modified in accordance with the wishes of the Copyright Holder. - "Copyright Holder" is whoever is named in the copyright or copyrights for the package. - "You" is you, if you're thinking about copying or distributing this Package. - "Reasonable copying fee" is whatever you can justify on the basis of media cost, duplication charges, time of people involved, and so on. (You will not be required to justify it to the Copyright Holder, but only to the computing community at large as a market that must bear the fee.) - "Freely Available" means that no fee is charged for the item itself, though there may be fees involved in handling the item. It also means that recipients of the item may redistribute it under the same conditions they received it. 1. You may make and give away verbatim copies of the source form of the Standard Version of this Package without restriction, provided that you duplicate all of the original copyright notices and associated disclaimers. 2. You may apply bug fixes, portability fixes and other modifications derived from the Public Domain or from the Copyright Holder. A Package modified in such a way shall still be considered the Standard Version. 3. You may otherwise modify your copy of this Package in any way, provided that you insert a prominent notice in each changed file stating how and when you changed that file, and provided that you do at least ONE of the following: a) place your modifications in the Public Domain or otherwise make them Freely Available, such as by posting said modifications to Usenet or an equivalent medium, or placing the modifications on a major archive site such as ftp.uu.net, or by allowing the Copyright Holder to include your modifications in the Standard Version of the Package. b) use the modified Package only within your corporation or organization. c) rename any non-standard executables so the names do not conflict with standard executables, which must also be provided, and provide a separate manual page for each non-standard executable that clearly documents how it differs from the Standard Version. d) make other distribution arrangements with the Copyright Holder. 4. You may distribute the programs of this Package in object code or executable form, provided that you do at least ONE of the following: a) distribute a Standard Version of the executables and library files, together with instructions (in the manual page or equivalent) on where to get the Standard Version. b) accompany the distribution with the machine-readable source of the Package with your modifications. c) accompany any non-standard executables with their corresponding Standard Version executables, giving the non-standard executables non-standard names, and clearly documenting the differences in manual pages (or equivalent), together with instructions on where to get the Standard Version. d) make other distribution arrangements with the Copyright Holder. 5. You may charge a reasonable copying fee for any distribution of this Package. You may charge any fee you choose for support of this Package. You may not charge a fee for this Package itself. However, you may distribute this Package in aggregate with other (possibly commercial) programs as part of a larger (possibly commercial) software distribution provided that you do not advertise this Package as a product of your own. 6. The scripts and library files supplied as input to or produced as output from the programs of this Package do not automatically fall under the copyright of this Package, but belong to whomever generated them, and may be sold commercially, and may be aggregated with this Package. 7. C or perl subroutines supplied by you and linked into this Package shall not be considered part of this Package. 8. The name of the Copyright Holder may not be used to endorse or promote products derived from this software without specific prior written permission. 9. THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE. The End MANIFEST000664001750001750 32712404270735 13431 0ustar00taitai000000000000XML-Atom-OWL-0.104CONTRIBUTING COPYRIGHT CREDITS Changes INSTALL LICENSE MANIFEST META.json META.yml Makefile.PL README SIGNATURE TODO dist.ini doap.ttl examples/identica.pl examples/simple_example.pl lib/XML/Atom/OWL.pm t/01basic.t META.json000664001750001750 411312404270735 13736 0ustar00taitai000000000000XML-Atom-OWL-0.104{ "abstract" : "parse an Atom file into RDF", "author" : [ "Toby Inkster ", "TOBYINK " ], "dynamic_config" : 0, "generated_by" : "Moose::Meta::Class::__ANON__::SERIAL::12 version , CPAN::Meta::Converter version 2.140640", "keywords" : [ "ActivityStrea.ms", "Atom", "AtomOWL", "Feed", "OWL", "RDF", "Syndication" ], "license" : [ "perl_5" ], "meta-spec" : { "url" : "http://search.cpan.org/perldoc?CPAN::Meta::Spec", "version" : "2" }, "name" : "XML-Atom-OWL", "no_index" : { "directory" : [ "eg", "examples", "inc", "t", "xt" ] }, "optional_features" : {}, "prereqs" : { "configure" : { "requires" : { "ExtUtils::MakeMaker" : "6.17" } }, "runtime" : { "requires" : { "Carp" : "1.00", "DateTime" : "0", "Encode" : "0", "HTTP::Link::Parser" : "0.100", "LWP::UserAgent" : "0", "MIME::Base64" : "0", "RDF::Trine" : "0.135", "Scalar::Util" : "0", "URI" : "1.30", "URI::URL" : "0", "XML::LibXML" : "1.70", "common::sense" : "0" } }, "test" : { "requires" : { "Test::More" : "0.61" } } }, "provides" : { "XML::Atom::OWL" : { "file" : "lib/XML/Atom/OWL.pm", "version" : "0.104" } }, "release_status" : "stable", "resources" : { "X_identifier" : "http://purl.org/NET/cpan-uri/dist/XML-Atom-OWL/project", "bugtracker" : { "web" : "http://rt.cpan.org/Dist/Display.html?Queue=XML-Atom-OWL" }, "homepage" : "https://metacpan.org/release/XML-Atom-OWL", "license" : [ "http://dev.perl.org/licenses/" ], "repository" : { "type" : "svn", "web" : "http://goddamn.co.uk/svn-web/perlmods/browse/XML-Atom-OWL/" } }, "version" : "0.104" } META.yml000664001750001750 243112404270735 13567 0ustar00taitai000000000000XML-Atom-OWL-0.104--- abstract: 'parse an Atom file into RDF' author: - 'Toby Inkster ' - 'TOBYINK ' build_requires: Test::More: '0.61' configure_requires: ExtUtils::MakeMaker: '6.17' dynamic_config: 0 generated_by: 'Moose::Meta::Class::__ANON__::SERIAL::12 version , CPAN::Meta::Converter version 2.140640' keywords: - ActivityStrea.ms - Atom - AtomOWL - Feed - OWL - RDF - Syndication license: perl meta-spec: url: http://module-build.sourceforge.net/META-spec-v1.4.html version: '1.4' name: XML-Atom-OWL no_index: directory: - eg - examples - inc - t - xt optional_features: {} provides: XML::Atom::OWL: file: lib/XML/Atom/OWL.pm version: '0.104' requires: Carp: '1.00' DateTime: '0' Encode: '0' HTTP::Link::Parser: '0.100' LWP::UserAgent: '0' MIME::Base64: '0' RDF::Trine: '0.135' Scalar::Util: '0' URI: '1.30' URI::URL: '0' XML::LibXML: '1.70' common::sense: '0' resources: X_identifier: http://purl.org/NET/cpan-uri/dist/XML-Atom-OWL/project bugtracker: http://rt.cpan.org/Dist/Display.html?Queue=XML-Atom-OWL homepage: https://metacpan.org/release/XML-Atom-OWL license: http://dev.perl.org/licenses/ repository: http://goddamn.co.uk/svn-web/perlmods/browse/XML-Atom-OWL/ version: '0.104' Makefile.PL000664001750001750 1321612404270735 14313 0ustar00taitai000000000000XML-Atom-OWL-0.104use strict; use ExtUtils::MakeMaker 6.17; my $EUMM = eval( $ExtUtils::MakeMaker::VERSION ); my $meta = { "abstract" => "parse an Atom file into RDF", "author" => [ "Toby Inkster ", "TOBYINK ", ], "dynamic_config" => 0, "generated_by" => "Moose::Meta::Class::__ANON__::SERIAL::12 version , CPAN::Meta::Converter version 2.140640", "keywords" => [ "ActivityStrea.ms", "Atom", "AtomOWL", "Feed", "OWL", "RDF", "Syndication", ], "license" => ["perl_5"], "meta-spec" => { url => "http://search.cpan.org/perldoc?CPAN::Meta::Spec", version => 2, }, "name" => "XML-Atom-OWL", "no_index" => { directory => ["eg", "examples", "inc", "t", "xt"] }, "prereqs" => { configure => { requires => { "ExtUtils::MakeMaker" => 6.17 } }, runtime => { requires => { "Carp" => "1.00", "common::sense" => 0, "DateTime" => 0, "Encode" => 0, "HTTP::Link::Parser" => "0.100", "LWP::UserAgent" => 0, "MIME::Base64" => 0, "RDF::Trine" => 0.135, "Scalar::Util" => 0, "URI" => "1.30", "URI::URL" => 0, "XML::LibXML" => "1.70", }, }, test => { requires => { "Test::More" => 0.61 } }, }, "provides" => { "XML::Atom::OWL" => { file => "lib/XML/Atom/OWL.pm", version => 0.104 }, }, "release_status" => "stable", "resources" => { bugtracker => { web => "http://rt.cpan.org/Dist/Display.html?Queue=XML-Atom-OWL", }, homepage => "https://metacpan.org/release/XML-Atom-OWL", license => ["http://dev.perl.org/licenses/"], repository => { type => "svn", web => "http://goddamn.co.uk/svn-web/perlmods/browse/XML-Atom-OWL/", }, X_identifier => "http://purl.org/NET/cpan-uri/dist/XML-Atom-OWL/project", }, "version" => 0.104, }; my %dynamic_config; my %WriteMakefileArgs = ( ABSTRACT => $meta->{abstract}, AUTHOR => ($EUMM >= 6.5702 ? $meta->{author} : $meta->{author}[0]), DISTNAME => $meta->{name}, VERSION => $meta->{version}, EXE_FILES => [ map $_->{file}, values %{ $meta->{x_provides_scripts} || {} } ], NAME => do { my $n = $meta->{name}; $n =~ s/-/::/g; $n }, test => { TESTS => "t/*.t" }, %dynamic_config, ); $WriteMakefileArgs{LICENSE} = $meta->{license}[0] if $EUMM >= 6.3001; sub deps { my %r; for my $stage (@_) { for my $dep (keys %{$meta->{prereqs}{$stage}{requires}}) { next if $dep eq 'perl'; my $ver = $meta->{prereqs}{$stage}{requires}{$dep}; $r{$dep} = $ver if !exists($r{$dep}) || $ver >= $r{$dep}; } } \%r; } my ($build_requires, $configure_requires, $runtime_requires, $test_requires); if ($EUMM >= 6.6303) { $WriteMakefileArgs{BUILD_REQUIRES} ||= deps('build'); $WriteMakefileArgs{CONFIGURE_REQUIRES} ||= deps('configure'); $WriteMakefileArgs{TEST_REQUIRES} ||= deps('test'); $WriteMakefileArgs{PREREQ_PM} ||= deps('runtime'); } elsif ($EUMM >= 6.5503) { $WriteMakefileArgs{BUILD_REQUIRES} ||= deps('build', 'test'); $WriteMakefileArgs{CONFIGURE_REQUIRES} ||= deps('configure'); $WriteMakefileArgs{PREREQ_PM} ||= deps('runtime'); } elsif ($EUMM >= 6.52) { $WriteMakefileArgs{CONFIGURE_REQUIRES} ||= deps('configure'); $WriteMakefileArgs{PREREQ_PM} ||= deps('runtime', 'build', 'test'); } else { $WriteMakefileArgs{PREREQ_PM} ||= deps('configure', 'build', 'test', 'runtime'); } { my ($minperl) = reverse sort( grep defined && /^[0-9]+(\.[0-9]+)?$/, map $meta->{prereqs}{$_}{requires}{perl}, qw( configure build runtime ) ); if (defined($minperl)) { die "Installing $meta->{name} requires Perl >= $minperl" unless $] >= $minperl; $WriteMakefileArgs{MIN_PERL_VERSION} ||= $minperl if $EUMM >= 6.48; } } sub FixMakefile { return unless -d 'inc'; my $file = shift; local *MAKEFILE; open MAKEFILE, "< $file" or die "FixMakefile: Couldn't open $file: $!; bailing out"; my $makefile = do { local $/; }; close MAKEFILE or die $!; $makefile =~ s/\b(test_harness\(\$\(TEST_VERBOSE\), )/$1'inc', /; $makefile =~ s/( -I\$\(INST_ARCHLIB\))/ -Iinc$1/g; $makefile =~ s/( "-I\$\(INST_LIB\)")/ "-Iinc"$1/g; $makefile =~ s/^(FULLPERL = .*)/$1 "-Iinc"/m; $makefile =~ s/^(PERL = .*)/$1 "-Iinc"/m; open MAKEFILE, "> $file" or die "FixMakefile: Couldn't open $file: $!; bailing out"; print MAKEFILE $makefile or die $!; close MAKEFILE or die $!; } my $mm = WriteMakefile(%WriteMakefileArgs); FixMakefile($mm->{FIRST_MAKEFILE} || 'Makefile'); exit(0); README000664001750001750 1373012404270726 13222 0ustar00taitai000000000000XML-Atom-OWL-0.104NAME XML::Atom::OWL - parse an Atom file into RDF SYNOPSIS use XML::Atom::OWL; $parser = XML::Atom::OWL->new($xml, $baseuri); $graph = $parser->graph; DESCRIPTION This has a pretty similar interface to RDF::RDFa::Parser. Constructor `new($xml, $baseuri, \%options, $storage)` This method creates a new XML::Atom::OWL object and returns it. The $xml variable may contain an XML (Atom) string, or an XML::LibXML::Document object. If a string, the document is parsed using XML::LibXML, which will throw an exception if it is not well-formed. XML::Atom::OWL does not catch the exception. The base URI is used to resolve relative URIs found in the document. Currently only one option is defined, 'no_fetch_content_src', a boolean indicating whether URLs should be automatically fetched and added to the model as if inline content had been provided. They are fetched by default, but it's pretty rare for feeds to include this attribute. $storage is an RDF::Trine::Storage object. If undef, then a new temporary store is created. Public Methods `uri` Returns the base URI of the document being parsed. This will usually be the same as the base URI provided to the constructor. Optionally it may be passed a parameter - an absolute or relative URI - in which case it returns the same URI which it was passed as a parameter, but as an absolute URI, resolved relative to the document's base URI. This seems like two unrelated functions, but if you consider the consequence of passing a relative URI consisting of a zero-length string, it in fact makes sense. `dom` Returns the parsed XML::LibXML::Document. `graph` This method will return an RDF::Trine::Model object with all statements of the full graph. This method automatically calls `consume`. `root_identifier` Returns the blank node or URI for the root element of the Atom document as an RDF::Trine::Node Calls `consume` automatically. `set_callbacks(\%callbacks)` Set callback functions for the parser to call on certain events. These are only necessary if you want to do something especially unusual. $p->set_callbacks({ 'pretriple_resource' => sub { ... } , 'pretriple_literal' => sub { ... } , 'ontriple' => undef , }); For details of the callback functions, see the section CALLBACKS. `set_callbacks` must be used *before* `consume`. `set_callbacks` itself returns a reference to the parser object itself. `consume` The document is parsed. Triples extracted from the document are passed to the callbacks as each one is found; triples are made available in the model returned by the `graph` method. This function returns the parser object itself, making it easy to abbreviate several of XML::Atom::OWL's functions: my $iterator = XML::Atom::OWL->new(undef, $uri) ->consume->graph->as_stream; You probably only need to call this explicitly if you're using callbacks. CALLBACKS Several callback functions are provided. These may be set using the `set_callbacks` function, which taskes a hashref of keys pointing to coderefs. The keys are named for the event to fire the callback on. pretriple_resource This is called when a triple has been found, but before preparing the triple for adding to the model. It is only called for triples with a non-literal object value. The parameters passed to the callback function are: * A reference to the `XML::Atom::OWL` object * A reference to the `XML::LibXML::Element` being parsed * Subject URI or bnode (string) * Predicate URI (string) * Object URI or bnode (string) * Graph URI or bnode (string or undef) The callback should return 1 to tell the parser to skip this triple (not add it to the graph); return 0 otherwise. pretriple_literal This is the equivalent of pretriple_resource, but is only called for triples with a literal object value. The parameters passed to the callback function are: * A reference to the `XML::Atom::OWL` object * A reference to the `XML::LibXML::Element` being parsed * Subject URI or bnode (string) * Predicate URI (string) * Object literal (string) * Datatype URI (string or undef) * Language (string or undef) * Graph URI or bnode (string or undef) Beware: sometimes both a datatype *and* a language will be passed. This goes beyond the normal RDF data model.) The callback should return 1 to tell the parser to skip this triple (not add it to the graph); return 0 otherwise. ontriple This is called once a triple is ready to be added to the graph. (After the pretriple callbacks.) The parameters passed to the callback function are: * A reference to the `XML::Atom::OWL` object * A reference to the `XML::LibXML::Element` being parsed * An RDF::Trine::Statement object. The callback should return 1 to tell the parser to skip this triple (not add it to the graph); return 0 otherwise. The callback may modify the RDF::Trine::Statement object. BUGS Please report any bugs to . SEE ALSO RDF::Trine, XML::Atom::FromOWL. . AUTHOR Toby Inkster . COPYRIGHT AND LICENCE Copyright 2010-2011 Toby Inkster This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself. DISCLAIMER OF WARRANTIES THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE. SIGNATURE000664001750001750 332412404270736 13605 0ustar00taitai000000000000XML-Atom-OWL-0.104This file contains message digests of all files listed in MANIFEST, signed via the Module::Signature module, version 0.73. To verify the content in this distribution, first make sure you have Module::Signature installed, then type: % cpansign -v It will check each file's integrity, as well as the signature's validity. If "==> Signature verified OK! <==" is not displayed, the distribution may already have been compromised, and you should not run its Makefile.PL or Build.PL. -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 SHA1 33317486c4fa2cf7fec85bf92ed38ac0f64233a0 CONTRIBUTING SHA1 dc7074e0b10e84dad7b999a415528208841b30dd COPYRIGHT SHA1 540e627824058dc4b3f75009923f7af8f8e388c8 CREDITS SHA1 f291ebf2fab9418c0e7cab3975edd8e965190218 Changes SHA1 adfa712345ef85b70b3c253b53bc11e4698820b1 INSTALL SHA1 34f5e12514b91055de4b164a1f2327ef5c30ba53 LICENSE SHA1 092e1886fd9baa742234e5387c2ab6802eb97d59 MANIFEST SHA1 5a8d4f8fec6e644facf234fd1063d1c82d103dd0 META.json SHA1 0918fe94a0addce66bdfbab8319aa5d352fcf519 META.yml SHA1 07ee155d21ce9827d190ad727beb9504ea4860c1 Makefile.PL SHA1 d8fb914b6582fc142f2a82ee82594128d915239c README SHA1 ca0c7aae46fa685d14a1317c019badaa8c88d5fe TODO SHA1 674034d4c12e7a0de08aa1fa2101e458771bf020 dist.ini SHA1 b63813eb9f6c05bde3bc16e8a18ac0824fb4570f doap.ttl SHA1 63780e60ef721a18013dd575d7668f336315d54a examples/identica.pl SHA1 9e5d9a0ef1a1173896c83ca0abbb1bf45e4074fb examples/simple_example.pl SHA1 0e60b04d952b84319b701b46ef2af68e0aced4b9 lib/XML/Atom/OWL.pm SHA1 37ab48ecfd43df3754f6e186984e93bc74b7f807 t/01basic.t -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iEUEARECAAYFAlQRcd4ACgkQzr+BKGoqfTmZgwCXaFjjkgc0eBW2xqLxsWLbeB2N HgCbBNd853GAHKPHFeWJf9soVKV76tQ= =1B9s -----END PGP SIGNATURE----- TODO000664001750001750 7112404270726 12744 0ustar00taitai000000000000XML-Atom-OWL-0.104- Support - Perhaps support PoCo in Atom? dist.ini000664001750001750 7512404270726 13724 0ustar00taitai000000000000XML-Atom-OWL-0.104;;class='Dist::Inkt::Profile::TOBYINK' ;;name='XML-Atom-OWL' doap.ttl000664001750001750 2131012404270735 14003 0ustar00taitai000000000000XML-Atom-OWL-0.104@prefix dc: . @prefix doap: . @prefix doap-changeset: . @prefix doap-deps: . @prefix foaf: . @prefix owl: . @prefix rdfs: . @prefix xsd: . a doap:Project; dc:contributor ; doap-deps:runtime-requirement [ doap-deps:on "Carp 1.00"^^doap-deps:CpanId ], [ doap-deps:on "common::sense 0"^^doap-deps:CpanId ], [ doap-deps:on "URI::URL 0"^^doap-deps:CpanId ], [ doap-deps:on "XML::LibXML 1.70"^^doap-deps:CpanId ], [ doap-deps:on "DateTime 0"^^doap-deps:CpanId ], [ doap-deps:on "Encode 0"^^doap-deps:CpanId ], [ doap-deps:on "HTTP::Link::Parser 0.100"^^doap-deps:CpanId; ], [ doap-deps:on "LWP::UserAgent 0"^^doap-deps:CpanId ], [ doap-deps:on "MIME::Base64 0"^^doap-deps:CpanId ], [ doap-deps:on "RDF::Trine 0.135"^^doap-deps:CpanId ], [ doap-deps:on "Scalar::Util 0"^^doap-deps:CpanId ], [ doap-deps:on "URI 1.30"^^doap-deps:CpanId ]; doap-deps:test-requirement [ doap-deps:on "Test::More 0.61"^^doap-deps:CpanId ]; doap:bug-database ; doap:category [ rdfs:label "Atom"@en ], [ rdfs:label "AtomOWL"@en ], [ rdfs:label "RDF"@en ], [ rdfs:label "Feed"@en ], [ rdfs:label "Syndication"@en ], [ rdfs:label "OWL"@en ], [ rdfs:label "ActivityStrea.ms" ]; doap:created "2010-01-15"^^xsd:date; doap:developer ; doap:documenter ; doap:download-page ; doap:homepage ; doap:license ; doap:maintainer ; doap:name "XML-Atom-OWL"; doap:programming-language "Perl"; doap:release , , , , , , , , ; doap:repository [ a doap:SVNRepository; doap:browse ; ]; doap:shortdesc "parse an Atom file into RDF"@en; doap:tester . a doap:Version; rdfs:label "First release"@en; dc:issued "2010-01-18"^^xsd:date; doap:file-release ; doap:revision "0.01"^^xsd:string. a doap:Version; dc:issued "2010-01-23"^^xsd:date; doap-changeset:changeset [ a doap-changeset:ChangeSet; doap-changeset:item [ a doap-changeset:Addition; rdfs:label "Support for Atom Threading Extension"@en; rdfs:seeAlso ; ], [ a doap-changeset:Addition; rdfs:label "Support for Feed Paging and Archiving"@en; rdfs:seeAlso ; ], [ a doap-changeset:Addition; rdfs:label "Support for Atom License Extension"@en; rdfs:seeAlso ; ], [ a doap-changeset:Addition; rdfs:label "Support arbitrary other extensions using XML literals."@en; ]; doap-changeset:versus ; ]; doap:file-release ; doap:revision "0.02"^^xsd:string. a doap:Version; dc:issued "2010-04-28"^^xsd:date; doap-changeset:changeset [ a doap-changeset:ChangeSet; doap-changeset:item [ a doap-changeset:Addition; rdfs:label "Ability to automatically fetch links and include the content as if it had been inline."@en; ], [ rdfs:label "Compliance improvements for element."@en; ]; doap-changeset:versus ; ]; doap:file-release ; doap:revision "0.03"^^xsd:string. a doap:Version; dc:issued "2010-04-29"^^xsd:date; doap-changeset:changeset [ a doap-changeset:ChangeSet; doap-changeset:item [ rdfs:label "Keep base URI and lang information for element."@en; rdfs:comment "Useful for XML-Atom-Microformats."@en; ]; doap-changeset:versus ; ]; doap:file-release ; doap:revision "0.04"^^xsd:string. a doap:Version; dc:issued "2010-07-19"^^xsd:date; doap-changeset:changeset [ a doap-changeset:ChangeSet; doap-changeset:item [ rdfs:label "Automatically call 'consume' as required."@en; ], [ a doap-changeset:Regression; rdfs:label "Switched to using common::sense instead of strict, but didn't note change in Makefile.PL/META.yml"@en; ]; doap-changeset:versus ; ]; doap:file-release ; doap:revision "0.100"^^xsd:string. a doap:Version; dc:issued "2010-07-19"^^xsd:date; doap-changeset:changeset [ a doap-changeset:ChangeSet; doap-changeset:item [ a doap-changeset:Bugfix; rdfs:label "Fix packaging error; Makefile.PL and META.yml didn't note dependency on common::sense."@en; ]; doap-changeset:versus ; ]; doap:file-release ; doap:revision "0.101"^^xsd:string. a doap:Version; dc:issued "2011-03-05"^^xsd:date; doap-changeset:changeset [ a doap-changeset:ChangeSet; doap-changeset:item [ a doap-changeset:Documentation; rdfs:label "Various formatting fixes and other minor improvements to documentation."@en; ], [ rdfs:label "use Scalar::Util qw(blessed)."@en ]; doap-changeset:versus ; ]; doap:file-release ; doap:revision "0.102"^^xsd:string. a doap:Version; dc:issued "2011-10-27"^^xsd:date; doap-changeset:changeset [ a doap-changeset:ChangeSet; doap-changeset:item [ a doap-changeset:Addition; rdfs:label "ActivityStrea.ms support."@en; ], [ a doap-changeset:Packaging; rdfs:label "Module::Package::RDF"@en; ], [ a doap-changeset:Update; rdfs:label "use 5.010"@en; ]; doap-changeset:versus ; ]; doap:file-release ; doap:revision "0.103"^^xsd:string. a doap:Version; dc:identifier "XML-Atom-OWL-0.104"^^xsd:string; dc:issued "2014-09-11"^^xsd:date; doap-changeset:changeset [ doap-changeset:item [ a doap-changeset:Packaging; rdfs:label "Switch to Dist::Inkt."; ]; ]; doap-changeset:released-by ; doap:file-release ; doap:revision "0.104"^^xsd:string. a foaf:Person; foaf:homepage ; foaf:mbox ; foaf:name "Toby Inkster"; foaf:page ; owl:sameAs . identica.pl000664001750001750 30612404270726 16230 0ustar00taitai000000000000XML-Atom-OWL-0.104/examples#!/usr/bin/perl use XML::Atom::OWL; use RDF::TrineShortcuts; my $p = XML::Atom::OWL->new(undef, 'http://identi.ca/api/statuses/user_timeline/36737.atom'); print rdf_string($p->graph => 'Turtle'); simple_example.pl000664001750001750 402612404270726 17477 0ustar00taitai000000000000XML-Atom-OWL-0.104/examplesuse lib "lib"; use XML::Atom::OWL; use JSON; my $atom = < dive into mark A <em>lot</em> of effort went into making this effortless 2005-07-31T12:29:29Z tag:example.org,2003:3 Copyright (c) 2003, Mark Pilgrim Example Toolkit Atom draft-07 snapshot tag:example.org,2003:3.2397 2005-07-31T12:29:29Z 2003-12-13T08:29:29-04:00 Mark Pilgrim http://example.org/ f8dy@example.com Sam Ruby Joe Gregorio

[Update: The Atom draft is finished.]

http://example.net/id/2 ATOM my $awol = XML::Atom::OWL->new($atom, 'http://example.net/')->consume; print to_json($awol->graph->as_hashref, {pretty=>1,canonical=>1}); 01basic.t000664001750001750 10012404270726 14137 0ustar00taitai000000000000XML-Atom-OWL-0.104/tuse Test::More tests => 1; BEGIN { use_ok('XML::Atom::OWL') }; OWL.pm000664001750001750 11210112404270726 15457 0ustar00taitai000000000000XML-Atom-OWL-0.104/lib/XML/Atompackage XML::Atom::OWL; use 5.010; use common::sense; use Carp 1.00; use DateTime 0; use Encode 0 qw(encode_utf8); use HTTP::Link::Parser 0.100; use LWP::UserAgent 0; use MIME::Base64 0 qw(decode_base64); use RDF::Trine 0.135; use Scalar::Util 0 qw(blessed); use URI 1.30; use XML::LibXML 1.70 qw(:all); use constant AAIR_NS => 'http://xmlns.notu.be/aair#'; use constant ATOM_NS => 'http://www.w3.org/2005/Atom'; use constant AWOL_NS => 'http://bblfish.net/work/atom-owl/2006-06-06/#'; use constant AS_NS => 'http://activitystrea.ms/spec/1.0/'; use constant AX_NS => 'http://buzzword.org.uk/rdf/atomix#'; use constant FH_NS => 'http://purl.org/syndication/history/1.0'; use constant FOAF_NS => 'http://xmlns.com/foaf/0.1/'; use constant IANA_NS => 'http://www.iana.org/assignments/relation/'; use constant RDF_NS => 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'; use constant RDF_TYPE => 'http://www.w3.org/1999/02/22-rdf-syntax-ns#type'; use constant THR_NS => 'http://purl.org/syndication/thread/1.0'; use constant XSD_NS => 'http://www.w3.org/2001/XMLSchema#'; our $VERSION = '0.104'; sub new { my $class = shift; my $content = shift; my $baseuri = shift; my $options = shift || undef; my $store = shift || undef; my $domtree; unless (defined $content) { my $ua = LWP::UserAgent->new; $ua->agent(sprintf('%s/%s ', __PACKAGE__, $VERSION)); $ua->default_header("Accept" => "application/atom+xml, application/xml;q=0.1, text/xml;q=0.1"); my $response = $ua->get($baseuri); croak "HTTP response not successful\n" unless $response->is_success; croak "Non-Atom HTTP response\n" unless $response->content_type =~ m`^(text/xml)|(application/(atom\+xml|xml))$`; $content = $response->decoded_content; } if (blessed($content) and $content->isa('XML::LibXML::Document')) { ($domtree, $content) = ($content, $content->toString); } else { my $xml_parser = XML::LibXML->new; $domtree = $xml_parser->parse_string($content); } $store = RDF::Trine::Store::DBI->temporary_store unless defined $store; my $self = bless { 'content' => $content, 'baseuri' => $baseuri, 'options' => $options, 'DOM' => $domtree, 'sub' => {}, 'RESULTS' => RDF::Trine::Model->new($store), }, $class; return $self; } sub uri { my $this = shift; my $param = shift || ''; my $opts = shift || {}; if ((ref $opts) =~ /^XML::LibXML/) { my $x = {'element' => $opts}; $opts = $x; } if ($param =~ /^([a-z][a-z0-9\+\.\-]*)\:/i) { # seems to be an absolute URI, so can safely return "as is". return $param; } elsif ($opts->{'require-absolute'}) { return undef; } my $base = $this->{baseuri}; if ($opts->{'element'}) { $base = $this->get_node_base($opts->{'element'}); } my $url = URI->new($param); my $rv = $url->abs($base)->as_string; while ($rv =~ m!^(http://.*)(\.\./|\.)+(\.\.|\.)?$!i) { $rv = $1; } return $rv; } sub dom { my $this = shift; return $this->{DOM}; } sub graph { my $this = shift; $this->consume; return $this->{RESULTS}; } sub graphs { my $this = shift; $this->consume; return { $this->{'baseuri'} => $this->{RESULTS} }; } sub root_identifier { my $self = shift; $self->consume; if ($self->{'root_identifier'} =~ /^_:(.*)/) { return RDF::Trine::Node::Blank->new($1); } else { return RDF::Trine::Node::Resource->new($self->{'root_identifier'}); } } sub set_callbacks # Set callback functions for handling RDF triples. { my $this = shift; if ('HASH' eq ref $_[0]) { $this->{'sub'} = $_[0]; } elsif (defined $_[0]) { die("What kind of callback hashref was that??\n"); } else { $this->{'sub'} = undef; } return $this; } sub consume { my $self = shift; return $self if $self->{'comsumed'}; my $root = $self->dom->documentElement; if ($root->namespaceURI eq ATOM_NS and $root->localname eq 'feed') { $self->{'root_identifier'} = $self->consume_feed($root); } elsif ($root->namespaceURI eq ATOM_NS and $root->localname eq 'entry') { $self->{'root_identifier'} = $self->consume_entry($root); } $self->{'comsumed'}++; return $self; } sub consume_feed { my $self = shift; my $feed = shift; my $skip_entries = shift || 0; # Feed my $feed_identifier = $self->bnode($feed); $self->rdf_triple($feed, $feed_identifier, RDF_TYPE, AWOL_NS.'Feed'); # Common stuff $self->consume_feed_or_entry($feed, $feed_identifier); # fh:archive and fh:complete if ($feed->getChildrenByTagNameNS(FH_NS, 'archive')) { $self->rdf_triple($feed, $feed_identifier, RDF_TYPE, AX_NS.'ArchiveFeed'); } my $complete = 0; if ($feed->getChildrenByTagNameNS(FH_NS, 'complete')) { $complete = 1; $self->rdf_triple($feed, $feed_identifier, RDF_TYPE, AX_NS.'CompleteFeed'); } my $last_listid; # entry unless ($skip_entries) { my @elems = $feed->getChildrenByTagNameNS(ATOM_NS, 'entry'); foreach my $e (@elems) { my $entry_identifier = $self->consume_entry($e); $self->rdf_triple($e, $feed_identifier, AWOL_NS.'entry', $entry_identifier); # If this feed is known to be complete, include an rdf:List # to assist in open-world reasoning. if ($complete) { my $listid = $self->bnode; if (defined $last_listid) { $self->rdf_triple($e, $last_listid, RDF_NS.'rest', $listid); } else { $self->rdf_triple($e, $feed_identifier, AX_NS.'entry-list', $listid); } $self->rdf_triple($e, $listid, RDF_TYPE, RDF_NS.'List'); $self->rdf_triple($e, $listid, RDF_NS.'first', $entry_identifier); $last_listid = $listid; } } } if ($complete) { if (defined $last_listid) { $self->rdf_triple($feed, $last_listid, RDF_NS.'rest', RDF_NS.'nil'); } else { $self->rdf_triple($feed, $feed_identifier, AX_NS.'entry-list', RDF_NS.'nil'); } } # icon and logo foreach my $role (qw(icon logo)) { my @elems = $feed->getChildrenByTagNameNS(ATOM_NS, $role); foreach my $e (@elems) { my $img = $self->uri($e->textContent, $e); $self->rdf_triple($e, $feed_identifier, AWOL_NS.$role, $img); $self->rdf_triple($e, $img, RDF_TYPE, FOAF_NS.'Image'); } } # generator { my @elems = $feed->getChildrenByTagNameNS(ATOM_NS, 'generator'); foreach my $e (@elems) { my $gen_identifier = $self->consume_generator($e); $self->rdf_triple($e, $feed_identifier, AWOL_NS.'generator', $gen_identifier); } } # subtitle { my @elems = $feed->getChildrenByTagNameNS(ATOM_NS, 'subtitle'); foreach my $e (@elems) { my $content_identifier = $self->consume_textconstruct($e); $self->rdf_triple($e, $feed_identifier, AWOL_NS.'subtitle', $content_identifier); } } return $feed_identifier; } sub consume_entry { my $self = shift; my $entry = shift; # Entry my $entry_identifier = $self->bnode($entry); $self->rdf_triple($entry, $entry_identifier, RDF_TYPE, AWOL_NS.'Entry'); # Common stuff $self->consume_feed_or_entry($entry, $entry_identifier); # published { my @elems = $entry->getChildrenByTagNameNS(ATOM_NS, 'published'); foreach my $e (@elems) { $self->rdf_triple_literal($e, $entry_identifier, AWOL_NS.'published', $e->textContent, XSD_NS.'dateTime'); } } # summary { my @elems = $entry->getChildrenByTagNameNS(ATOM_NS, 'content'); foreach my $e (@elems) { my $content_identifier = $self->consume_content($e); $self->rdf_triple($e, $entry_identifier, AWOL_NS.'content', $content_identifier); } } # source { my @elems = $entry->getChildrenByTagNameNS(ATOM_NS, 'source'); foreach my $e (@elems) { my $feed_identifier = $self->consume_feed($e, 1); $self->rdf_triple($e, $entry_identifier, AWOL_NS.'source', $feed_identifier); } } # summary { my @elems = $entry->getChildrenByTagNameNS(ATOM_NS, 'summary'); foreach my $e (@elems) { my $content_identifier = $self->consume_textconstruct($e); $self->rdf_triple($e, $entry_identifier, AWOL_NS.'summary', $content_identifier); } } # thr:in-reply-to { my @elems = $entry->getChildrenByTagNameNS(THR_NS, 'in-reply-to'); foreach my $e (@elems) { my $irt_id = $self->consume_inreplyto($e); $self->rdf_triple($e, $entry_identifier, AX_NS.'in-reply-to', $irt_id); } } # thr:total { my @elems = $entry->getChildrenByTagNameNS(THR_NS, 'total'); foreach my $e (@elems) { my $total = $e->textContent; $self->rdf_triple_literal($e, $entry_identifier, AX_NS.'total', $total, XSD_NS.'integer'); } } return $entry_identifier; } sub consume_feed_or_entry { my $self = shift; my $fore = shift; my $id = shift; my @elems = $fore->getChildrenByTagNameNS(ATOM_NS, 'id'); foreach my $e (@elems) { my $_id = $self->uri($e->textContent, $e); $self->rdf_triple_literal($e, $id, AWOL_NS.'id', $_id, XSD_NS.'anyURI'); } my $is_as = 0; # activitystreams:object, activitystreams:target foreach my $role (qw(object target)) { my @elems = $fore->getChildrenByTagNameNS(AS_NS, $role); foreach my $e (@elems) { $is_as++; my $obj_id = $self->consume_entry($e, $id); $self->rdf_triple($e, $id, AAIR_NS.'activity'.ucfirst($role), $obj_id); } } # activitystreams:verb { my @elems = $fore->getChildrenByTagNameNS(AS_NS, 'verb'); foreach my $e (@elems) { $is_as++; my $url = $e->textContent; $url =~ s/(^\s*)|(\s*$)//g; $self->rdf_triple($e, $id, AAIR_NS.'activityVerb', URI->new($url)->abs('http://activitystrea.ms/schema/1.0/')->as_string); } if ($is_as && !@elems) { $self->rdf_triple($fore, $id, AAIR_NS.'activityVerb', "http://activitystrea.ms/schema/1.0/post"); } } # activitystreams:object-type { my @elems = $fore->getChildrenByTagNameNS(AS_NS, 'object-type'); foreach my $e (@elems) { my $url = $e->textContent; $url =~ s/(^\s*)|(\s*$)//g; $self->rdf_triple($e, $id, RDF_NS.'type', URI->new($url)->abs('http://activitystrea.ms/schema/1.0/')->as_string); } } # authors and contributors foreach my $role (qw(author contributor)) { my @elems = $fore->getChildrenByTagNameNS(ATOM_NS, $role); foreach my $e (@elems) { my $person_identifier = $self->consume_person($e); $self->rdf_triple($e, $id, AWOL_NS.$role, $person_identifier); if ($role eq 'author' and $is_as) { $self->rdf_triple($e, $person_identifier, RDF_NS.'type', AAIR_NS.'Actor'); $self->rdf_triple($e, $id, AAIR_NS.'activityActor', $person_identifier); } } } # updated { my @elems = $fore->getChildrenByTagNameNS(ATOM_NS, 'updated'); foreach my $e (@elems) { $self->rdf_triple_literal($e, $id, AWOL_NS.'updated', $e->textContent, XSD_NS.'dateTime'); } } # link { my @elems = $fore->getChildrenByTagNameNS(ATOM_NS, 'link'); foreach my $e (@elems) { my $link_identifier = $self->consume_link($e, $id); $self->rdf_triple($e, $id, AWOL_NS.'link', $link_identifier); } } # title and rights foreach my $role (qw(title rights)) { my @elems = $fore->getChildrenByTagNameNS(ATOM_NS, $role); foreach my $e (@elems) { my $content_identifier = $self->consume_textconstruct($e); $self->rdf_triple($e, $id, AWOL_NS.$role, $content_identifier); } } # category { my @elems = $fore->getChildrenByTagNameNS(ATOM_NS, 'category'); foreach my $e (@elems) { my $cat_identifier = $self->consume_category($e, $id); $self->rdf_triple($e, $id, AWOL_NS.'category', $cat_identifier); } } # Unknown Extensions! { my @elems = $fore->getChildrenByTagName('*'); foreach my $e (@elems) { next if $e->namespaceURI eq ATOM_NS; next if $e->namespaceURI eq AS_NS; next if $e->namespaceURI eq FH_NS; next if $e->namespaceURI eq THR_NS; my $xml = $self->xmlify_inclusive($e); $self->rdf_triple_literal($e, $id, AX_NS.'extension-element', $xml, RDF_NS.'XMLLiteral'); } } return $id; } sub consume_textconstruct { my $self = shift; my $elem = shift; my $id = $self->bnode($elem); $self->rdf_triple($elem, $id, RDF_TYPE, AWOL_NS.'TextContent'); my $lang = $self->get_node_lang($elem); if (lc $elem->getAttribute('type') eq 'xhtml') { my $cnt = $self->xmlify($elem, $lang); $self->rdf_triple_literal($elem, $id, AWOL_NS.'xhtml', $cnt, RDF_NS.'XMLLiteral'); } elsif (lc $elem->getAttribute('type') eq 'html') { my $cnt = $elem->textContent; $self->rdf_triple_literal($elem, $id, AWOL_NS.'html', $cnt, undef, $lang); } else { my $cnt = $elem->textContent; $self->rdf_triple_literal($elem, $id, AWOL_NS.'text', $cnt, undef, $lang); } return $id; } sub consume_content { my $self = shift; my $elem = shift; my $id = $self->bnode($elem); $self->rdf_triple($elem, $id, RDF_TYPE, AWOL_NS.'Content'); my $lang = $self->get_node_lang($elem); my $base = $self->get_node_base($elem); if ($elem->hasAttribute('src')) { my $link = $self->uri($elem->getAttribute('src'), $elem); $self->rdf_triple($elem, $id, AWOL_NS.'src', $link); if ($self->{'options'}->{'no_fetch_content_src'}) { $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', $elem->getAttribute('type')) if $elem->hasAttribute('type'); } else { my $ua = LWP::UserAgent->new; $ua->agent(sprintf('%s/%s ', __PACKAGE__, $VERSION)); if ($elem->hasAttribute('type')) { $ua->default_header("Accept" => $elem->getAttribute('type').", */*;q=0.1"); } else { $ua->default_header("Accept" => "application/xhtml+xml, text/html, text/plain, */*;q=0.1"); } my $response = $ua->get($self->uri($elem->getAttribute('src'), $elem)); if ($response->is_success) { $self->rdf_triple_literal($elem, $id, AWOL_NS.'body', $response->decoded_content); if ($response->content_type) { $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', $response->content_type); } elsif ($elem->hasAttribute('type')) { $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', $elem->getAttribute('type')); } if ($response->content_language =~ /^\s*([a-z]{2,3})\b/i) { $self->rdf_triple_literal($elem, $id, AWOL_NS.'lang', lc $1, XSD_NS.'language'); } if ($response->base) { $self->rdf_triple($elem, $id, AWOL_NS.'base', $response->base); } } else { $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', $elem->getAttribute('type')) if $elem->hasAttribute('type'); } } } elsif (lc $elem->getAttribute('type') eq 'text' or !$elem->hasAttribute('type')) { my $cnt = $elem->textContent; $self->rdf_triple_literal($elem, $id, AWOL_NS.'body', $cnt, undef, $lang); $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', 'text/plain'); $self->rdf_triple_literal($elem, $id, AWOL_NS.'lang', $lang, XSD_NS.'language') if $lang; $self->rdf_triple($elem, $id, AWOL_NS.'base', $base) if $base; } elsif (lc $elem->getAttribute('type') eq 'xhtml') { my $cnt = $self->xmlify($elem, $lang); $self->rdf_triple_literal($elem, $id, AWOL_NS.'body', $cnt, RDF_NS.'XMLLiteral'); $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', 'application/xhtml+xml'); $self->rdf_triple_literal($elem, $id, AWOL_NS.'lang', $lang, XSD_NS.'language') if $lang; $self->rdf_triple($elem, $id, AWOL_NS.'base', $base) if $base; } elsif (lc $elem->getAttribute('type') eq 'html') { my $cnt = $elem->textContent; $self->rdf_triple_literal($elem, $id, AWOL_NS.'body', $cnt, undef, $lang); $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', 'text/html'); $self->rdf_triple_literal($elem, $id, AWOL_NS.'lang', $lang, XSD_NS.'language') if $lang; $self->rdf_triple($elem, $id, AWOL_NS.'base', $base) if $base; } elsif ($elem->getAttribute('type') =~ m'([\+\/]xml)$'i) { my $cnt = $self->xmlify($elem, $lang); $self->rdf_triple_literal($elem, $id, AWOL_NS.'body', $cnt, RDF_NS.'XMLLiteral'); $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', $elem->getAttribute('type')); $self->rdf_triple_literal($elem, $id, AWOL_NS.'lang', $lang, XSD_NS.'language') if $lang; $self->rdf_triple($elem, $id, AWOL_NS.'base', $base) if $base; } elsif ($elem->getAttribute('type') =~ m'^text\/'i) { my $cnt = $elem->textContent; $self->rdf_triple_literal($elem, $id, AWOL_NS.'body', $cnt, undef, $lang); $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', $elem->getAttribute('type')); $self->rdf_triple_literal($elem, $id, AWOL_NS.'lang', $lang, XSD_NS.'language') if $lang; $self->rdf_triple($elem, $id, AWOL_NS.'base', $base) if $base; } elsif ($elem->hasAttribute('type')) { my $cnt = $elem->textContent; $self->rdf_triple_literal($elem, $id, AWOL_NS.'body', decode_base64($cnt)); $self->rdf_triple_literal($elem, $id, AWOL_NS.'type', $elem->getAttribute('type')); $self->rdf_triple_literal($elem, $id, AWOL_NS.'lang', $lang, XSD_NS.'language') if $lang; $self->rdf_triple($elem, $id, AWOL_NS.'base', $base) if $base; } return $id; } sub consume_person { my $self = shift; my $person = shift; # Person my $person_identifier = $self->bnode($person); $self->rdf_triple($person, $person_identifier, RDF_TYPE, AWOL_NS.'Person'); # name { my @elems = $person->getChildrenByTagNameNS(ATOM_NS, 'name'); foreach my $e (@elems) { $self->rdf_triple_literal($e, $person_identifier, AWOL_NS.'name', $e->textContent); } } # uri { my @elems = $person->getChildrenByTagNameNS(ATOM_NS, 'uri'); foreach my $e (@elems) { my $link = $self->uri($e->textContent, $e); $self->rdf_triple($e, $person_identifier, AWOL_NS.'uri', $link); } } # email { my @elems = $person->getChildrenByTagNameNS(ATOM_NS, 'email'); foreach my $e (@elems) { $self->rdf_triple($e, $person_identifier, AWOL_NS.'email', 'mailto:'.$e->textContent); } } return $person_identifier; } sub consume_generator { my $self = shift; my $elem = shift; # Person my $identifier = $self->bnode($elem); $self->rdf_triple($elem, $identifier, RDF_TYPE, AWOL_NS.'Generator'); # name { my $lang = $self->get_node_lang($elem); $self->rdf_triple_literal($elem, $identifier, AWOL_NS.'name', $elem->textContent, undef, $lang); } # uri if ($elem->hasAttribute('uri')) { my $link = $self->uri($elem->getAttribute('uri'), $elem); $self->rdf_triple($elem, $identifier, AWOL_NS.'uri', $link); } # version if ($elem->hasAttribute('uri')) { $self->rdf_triple($elem, $identifier, AWOL_NS.'version', $elem->getAttribute('version')); } return $identifier; } sub consume_inreplyto { my $self = shift; my $link = shift; my $id = $self->bnode($link); $self->rdf_triple($link, $id, RDF_TYPE, AWOL_NS.'Entry'); if ($link->hasAttribute('ref')) { $self->rdf_triple_literal($link, $id, AWOL_NS.'id', $link->getAttribute('ref'), XSD_NS.'anyURI'); } if ($link->hasAttribute('href')) { my $href = $self->uri($link->getAttribute('href'), $link); $self->rdf_triple($link, $id, IANA_NS.'self', $href); } # TODO: "type". if ($link->hasAttribute('source')) { my $fid = $self->bnode; my $href = $self->uri($link->getAttribute('href'), $link); $self->rdf_triple($link, $id, AWOL_NS.'source', $fid); $self->rdf_triple($link, $fid, RDF_TYPE, AWOL_NS.'Feed'); $self->rdf_triple($link, $fid, IANA_NS.'self', $href); } return $id; } sub consume_link { my $self = shift; my $link = shift; my $subject = shift || undef; # Link my $link_identifier = $self->bnode($link); $self->rdf_triple($link, $link_identifier, RDF_TYPE, AWOL_NS.'Link'); # Destination my $destination_identifier = $self->bnode; $self->rdf_triple($link, $destination_identifier, RDF_TYPE, AWOL_NS.'Content'); $self->rdf_triple($link, $link_identifier, AWOL_NS.'to', $destination_identifier); # rel { my $rel = HTTP::Link::Parser::relationship_uri( $link->hasAttribute('rel') ? $link->getAttribute('rel') : 'alternate'); $self->rdf_triple($link, $link_identifier, AWOL_NS.'rel', $rel); if ($link->hasAttribute('href') and defined $subject) { my $href = $self->uri($link->getAttribute('href'), $link); $self->rdf_triple($link, $subject, $rel, $href); } } # href if ($link->hasAttribute('href')) { my $href = $self->uri($link->getAttribute('href'), $link); $self->rdf_triple($link, $destination_identifier, AWOL_NS.'src', $href); } # hreflang if ($link->hasAttribute('hreflang')) { my $hreflang = $link->getAttribute('hreflang'); $self->rdf_triple_literal($link, $destination_identifier, AWOL_NS.'lang', $hreflang); } # length if ($link->hasAttribute('length')) { my $length = $link->getAttribute('length'); $self->rdf_triple_literal($link, $destination_identifier, AWOL_NS.'length', $length, XSD_NS.'integer'); } # type if ($link->hasAttribute('type')) { my $type = $link->getAttribute('type'); $self->rdf_triple_literal($link, $destination_identifier, AWOL_NS.'type', $type); } # title: TODO - check this uses AWOL properly. if ($link->hasAttribute('title')) { my $lang = $self->get_node_lang($link); my $title = $link->getAttribute('title'); $self->rdf_triple_literal($link, $link_identifier, AWOL_NS.'title', $title, undef, $lang); } # thr:count if ($link->hasAttributeNS(THR_NS, 'count')) { my $count = $link->getAttributeNS(THR_NS, 'count'); $self->rdf_triple_literal($link, $link_identifier, AX_NS.'count', $count, XSD_NS.'integer'); } # thr:updated if ($link->hasAttributeNS(THR_NS, 'updated')) { my $u = $link->getAttributeNS(THR_NS, 'updated'); $self->rdf_triple_literal($link, $link_identifier, AX_NS.'updated', $u, XSD_NS.'dateTime'); } return $link_identifier; } sub consume_category { my $self = shift; my $elem = shift; # Link my $id = $self->bnode($elem); $self->rdf_triple($elem, $id, RDF_TYPE, AWOL_NS.'Category'); # term if ($elem->hasAttribute('term')) { $self->rdf_triple_literal($elem, $id, AWOL_NS.'term', $elem->getAttribute('term')); } # label if ($elem->hasAttribute('label')) { my $lang = $self->get_node_lang($elem); $self->rdf_triple_literal($elem, $id, AWOL_NS.'label', $elem->getAttribute('label'), undef, $lang); } # scheme if ($elem->hasAttribute('scheme')) { my $link = $self->uri($elem->getAttribute('scheme'), $elem); $self->rdf_triple($elem, $id, AWOL_NS.'scheme', $link); } return $id; } sub xmlify # Function only used internally. { my $this = shift; my $dom = shift; my $lang = shift; my $rv; $lang = $this->get_node_lang($dom) unless $lang; foreach my $kid ($dom->childNodes) { my $fakelang = 0; if (($kid->nodeType == XML_ELEMENT_NODE) && defined $lang) { unless ($kid->hasAttributeNS(XML_XML_NS, 'lang')) { $kid->setAttributeNS(XML_XML_NS, 'lang', $lang); $fakelang++; } } $rv .= $kid->toStringEC14N(1); if ($fakelang) { $kid->removeAttributeNS(XML_XML_NS, 'lang'); } } return $rv; } sub xmlify_inclusive # Function only used internally. { my $this = shift; my $dom = shift; my $lang = shift; my $rv; $lang = $this->get_node_lang($dom) unless $lang; my $fakelang = 0; if (($dom->nodeType == XML_ELEMENT_NODE) && defined $lang) { unless ($dom->hasAttributeNS(XML_XML_NS, 'lang')) { $dom->setAttributeNS(XML_XML_NS, 'lang', $lang); $fakelang++; } } $rv = $dom->toStringEC14N(1); if ($fakelang) { $dom->removeAttributeNS(XML_XML_NS, 'lang'); } return $rv; } sub get_node_lang { my $this = shift; my $node = shift; if ($node->hasAttributeNS(XML_XML_NS, 'lang')) { return valid_lang($node->getAttributeNS(XML_XML_NS, 'lang')) ? $node->getAttributeNS(XML_XML_NS, 'lang'): undef; } if ($node != $this->{'DOM'}->documentElement && defined $node->parentNode && $node->parentNode->nodeType == XML_ELEMENT_NODE) { return $this->get_node_lang($node->parentNode); } return undef; } sub get_node_base { my $this = shift; my $node = shift; my @base; while (1) { push @base, $node->getAttributeNS(XML_XML_NS, 'base') if $node->hasAttributeNS(XML_XML_NS, 'base'); $node = $node->parentNode; last unless blessed($node) && $node->isa('XML::LibXML::Element'); } my $rv = URI->new($this->uri); # document URI. while (my $b = pop @base) { $rv = URI->new($b)->abs($rv); } return $rv->as_string; } sub rdf_triple # Function only used internally. { my $this = shift; my $suppress_triple = 0; $suppress_triple = $this->{'sub'}->{'pretriple_resource'}($this, @_) if defined $this->{'sub'}->{'pretriple_resource'}; return if $suppress_triple; my $element = shift; # A reference to the XML::LibXML element being parsed my $subject = shift; # Subject URI or bnode my $predicate = shift; # Predicate URI my $object = shift; # Resource URI or bnode my $graph = shift; # Graph URI or bnode (if named graphs feature is enabled) # First make sure the object node type is ok. my $to; if ($object =~ m/^_:(.*)/) { $to = RDF::Trine::Node::Blank->new($1); } else { $to = RDF::Trine::Node::Resource->new($object); } # Run the common function return $this->rdf_triple_common($element, $subject, $predicate, $to, $graph); } sub rdf_triple_literal # Function only used internally. { my $this = shift; my $suppress_triple = 0; $suppress_triple = $this->{'sub'}->{'pretriple_literal'}($this, @_) if defined $this->{'sub'}->{'pretriple_literal'}; return if $suppress_triple; my $element = shift; # A reference to the XML::LibXML element being parsed my $subject = shift; # Subject URI or bnode my $predicate = shift; # Predicate URI my $object = shift; # Resource Literal my $datatype = shift; # Datatype URI (possibly undef or '') my $language = shift; # Language (possibly undef or '') my $graph = shift; # Graph URI or bnode (if named graphs feature is enabled) # Now we know there's a literal my $to; # Work around bad Unicode handling in RDF::Trine. $object = encode_utf8($object); if (defined $datatype) { if ($datatype eq 'http://www.w3.org/1999/02/22-rdf-syntax-ns#XMLLiteral') { if ($this->{'options'}->{'use_rtnlx'}) { eval { require RDF::Trine::Node::Literal::XML; $to = RDF::Trine::Node::Literal::XML->new($element->childNodes); }; } if ( $@ || !defined $to) { my $orig = $RDF::Trine::Node::Literal::USE_XMLLITERALS; $RDF::Trine::Node::Literal::USE_XMLLITERALS = 0; $to = RDF::Trine::Node::Literal->new($object, undef, $datatype); $RDF::Trine::Node::Literal::USE_XMLLITERALS = $orig; } } else { $to = RDF::Trine::Node::Literal->new($object, undef, $datatype); } } else { $to = RDF::Trine::Node::Literal->new($object, $language, undef); } # Run the common function $this->rdf_triple_common($element, $subject, $predicate, $to, $graph); } sub rdf_triple_common # Function only used internally. { my $this = shift; # A reference to the Parser object my $element = shift; # A reference to the XML::LibXML element being parsed my $subject = shift; # Subject URI or bnode my $predicate = shift; # Predicate URI my $to = shift; # RDF::Trine::Node Resource URI or bnode my $graph = shift; # Graph URI or bnode (if named graphs feature is enabled) # First, make sure subject and predicates are the right kind of nodes my $tp = RDF::Trine::Node::Resource->new($predicate); my $ts; if ($subject =~ m/^_:(.*)/) { $ts = RDF::Trine::Node::Blank->new($1); } else { $ts = RDF::Trine::Node::Resource->new($subject); } my $statement; # If we are configured for it, and graph name can be found, add it. if (ref($this->{'options'}->{'named_graphs'}) && ($graph)) { $this->{Graphs}->{$graph}++; my $tg; if ($graph =~ m/^_:(.*)/) { $tg = RDF::Trine::Node::Blank->new($1); } else { $tg = RDF::Trine::Node::Resource->new($graph); } $statement = RDF::Trine::Statement::Quad->new($ts, $tp, $to, $tg); } else { $statement = RDF::Trine::Statement->new($ts, $tp, $to); } my $suppress_triple = 0; $suppress_triple = $this->{'sub'}->{'ontriple'}($this, $element, $statement) if ($this->{'sub'}->{'ontriple'}); return if $suppress_triple; $this->{RESULTS}->add_statement($statement); } sub bnode # Function only used internally. { my $this = shift; my $element = shift; if (defined $this->{'bnode_generator'}) { return $this->{'bnode_generator'}->bnode($element); } return sprintf('_:AwolAutoNode%03d', $this->{bnodes}++); } sub valid_lang { my $value_to_test = shift; return 1 if (defined $value_to_test) && ($value_to_test eq ''); return 0 unless defined $value_to_test; # Regex for recognizing RFC 4646 well-formed tags # http://www.rfc-editor.org/rfc/rfc4646.txt # http://tools.ietf.org/html/draft-ietf-ltru-4646bis-21 # The structure requires no forward references, so it reverses the order. # It uses Java/Perl syntax instead of the old ABNF # The uppercase comments are fragments copied from RFC 4646 # Note: the tool requires that any real "=" or "#" or ";" in the regex be escaped. my $alpha = '[a-z]'; # ALPHA my $digit = '[0-9]'; # DIGIT my $alphanum = '[a-z0-9]'; # ALPHA / DIGIT my $x = 'x'; # private use singleton my $singleton = '[a-wyz]'; # other singleton my $s = '[_-]'; # separator -- lenient parsers will use [_-] -- strict will use [-] # Now do the components. The structure is slightly different to allow for capturing the right components. # The notation (?:....) is a non-capturing version of (...): so the "?:" can be deleted if someone doesn't care about capturing. my $language = '([a-z]{2,8}) | ([a-z]{2,3} $s [a-z]{3})'; # ABNF (2*3ALPHA) / 4ALPHA / 5*8ALPHA --- note: because of how | works in regex, don't use $alpha{2,3} | $alpha{4,8} # We don't have to have the general case of extlang, because there can be only one extlang (except for zh-min-nan). # Note: extlang invalid in Unicode language tags my $script = '[a-z]{4}' ; # 4ALPHA my $region = '(?: [a-z]{2}|[0-9]{3})' ; # 2ALPHA / 3DIGIT my $variant = '(?: [a-z0-9]{5,8} | [0-9] [a-z0-9]{3} )' ; # 5*8alphanum / (DIGIT 3alphanum) my $extension = '(?: [a-wyz] (?: [_-] [a-z0-9]{2,8} )+ )' ; # singleton 1*("-" (2*8alphanum)) my $privateUse = '(?: x (?: [_-] [a-z0-9]{1,8} )+ )' ; # "x" 1*("-" (1*8alphanum)) # Define certain grandfathered codes, since otherwise the regex is pretty useless. # Since these are limited, this is safe even later changes to the registry -- # the only oddity is that it might change the type of the tag, and thus # the results from the capturing groups. # http://www.iana.org/assignments/language-subtag-registry # Note that these have to be compared case insensitively, requiring (?i) below. my $grandfathered = '(?: (en [_-] GB [_-] oed) | (i [_-] (?: ami | bnn | default | enochian | hak | klingon | lux | mingo | navajo | pwn | tao | tay | tsu )) | (no [_-] (?: bok | nyn )) | (sgn [_-] (?: BE [_-] (?: fr | nl) | CH [_-] de )) | (zh [_-] min [_-] nan) )'; # old: | zh $s (?: cmn (?: $s Hans | $s Hant )? | gan | min (?: $s nan)? | wuu | yue ); # For well-formedness, we don't need the ones that would otherwise pass. # For validity, they need to be checked. # $grandfatheredWellFormed = (?: # art $s lojban # | cel $s gaulish # | zh $s (?: guoyu | hakka | xiang ) # ); # Unicode locales: but we are shifting to a compatible form # $keyvalue = (?: $alphanum+ \= $alphanum+); # $keywords = ($keyvalue (?: \; $keyvalue)*); # We separate items that we want to capture as a single group my $variantList = $variant . '(?:' . $s . $variant . ')*' ; # special for multiples my $extensionList = $extension . '(?:' . $s . $extension . ')*' ; # special for multiples my $langtag = " ($language) ($s ( $script ) )? ($s ( $region ) )? ($s ( $variantList ) )? ($s ( $extensionList ) )? ($s ( $privateUse ) )? "; # Here is the final breakdown, with capturing groups for each of these components # The variants, extensions, grandfathered, and private-use may have interior '-' my $r = ($value_to_test =~ /^( ($langtag) | ($privateUse) | ($grandfathered) )$/xi); return $r; } 'A man, a plan, a canal: Panama'; # E, r u true? __END__ =head1 NAME XML::Atom::OWL - parse an Atom file into RDF =head1 SYNOPSIS use XML::Atom::OWL; $parser = XML::Atom::OWL->new($xml, $baseuri); $graph = $parser->graph; =head1 DESCRIPTION This has a pretty similar interface to L. =head2 Constructor =over 4 =item C<< new($xml, $baseuri, \%options, $storage) >> This method creates a new XML::Atom::OWL object and returns it. The $xml variable may contain an XML (Atom) string, or an L object. If a string, the document is parsed using L, which will throw an exception if it is not well-formed. XML::Atom::OWL does not catch the exception. The base URI is used to resolve relative URIs found in the document. Currently only one option is defined, 'no_fetch_content_src', a boolean indicating whether URLs should be automatically fetched and added to the model as if inline content had been provided. They are fetched by default, but it's pretty rare for feeds to include this attribute. $storage is an RDF::Trine::Storage object. If undef, then a new temporary store is created. =back =head2 Public Methods =over 4 =item C<< uri >> Returns the base URI of the document being parsed. This will usually be the same as the base URI provided to the constructor. Optionally it may be passed a parameter - an absolute or relative URI - in which case it returns the same URI which it was passed as a parameter, but as an absolute URI, resolved relative to the document's base URI. This seems like two unrelated functions, but if you consider the consequence of passing a relative URI consisting of a zero-length string, it in fact makes sense. =item C<< dom >> Returns the parsed XML::LibXML::Document. =item C<< graph >> This method will return an RDF::Trine::Model object with all statements of the full graph. This method automatically calls C. =item C<< root_identifier >> Returns the blank node or URI for the root element of the Atom document as an RDF::Trine::Node Calls C automatically. =item C<< set_callbacks(\%callbacks) >> Set callback functions for the parser to call on certain events. These are only necessary if you want to do something especially unusual. $p->set_callbacks({ 'pretriple_resource' => sub { ... } , 'pretriple_literal' => sub { ... } , 'ontriple' => undef , }); For details of the callback functions, see the section CALLBACKS. C must be used I C. C itself returns a reference to the parser object itself. =item C<< consume >> The document is parsed. Triples extracted from the document are passed to the callbacks as each one is found; triples are made available in the model returned by the C method. This function returns the parser object itself, making it easy to abbreviate several of XML::Atom::OWL's functions: my $iterator = XML::Atom::OWL->new(undef, $uri) ->consume->graph->as_stream; You probably only need to call this explicitly if you're using callbacks. =back =head1 CALLBACKS Several callback functions are provided. These may be set using the C function, which taskes a hashref of keys pointing to coderefs. The keys are named for the event to fire the callback on. =head2 pretriple_resource This is called when a triple has been found, but before preparing the triple for adding to the model. It is only called for triples with a non-literal object value. The parameters passed to the callback function are: =over 4 =item * A reference to the C object =item * A reference to the C being parsed =item * Subject URI or bnode (string) =item * Predicate URI (string) =item * Object URI or bnode (string) =item * Graph URI or bnode (string or undef) =back The callback should return 1 to tell the parser to skip this triple (not add it to the graph); return 0 otherwise. =head2 pretriple_literal This is the equivalent of pretriple_resource, but is only called for triples with a literal object value. The parameters passed to the callback function are: =over 4 =item * A reference to the C object =item * A reference to the C being parsed =item * Subject URI or bnode (string) =item * Predicate URI (string) =item * Object literal (string) =item * Datatype URI (string or undef) =item * Language (string or undef) =item * Graph URI or bnode (string or undef) =back Beware: sometimes both a datatype I a language will be passed. This goes beyond the normal RDF data model.) The callback should return 1 to tell the parser to skip this triple (not add it to the graph); return 0 otherwise. =head2 ontriple This is called once a triple is ready to be added to the graph. (After the pretriple callbacks.) The parameters passed to the callback function are: =over 4 =item * A reference to the C object =item * A reference to the C being parsed =item * An RDF::Trine::Statement object. =back The callback should return 1 to tell the parser to skip this triple (not add it to the graph); return 0 otherwise. The callback may modify the RDF::Trine::Statement object. =head1 BUGS Please report any bugs to L. =head1 SEE ALSO L, L. L. =head1 AUTHOR Toby Inkster Etobyink@cpan.orgE. =head1 COPYRIGHT AND LICENCE Copyright 2010-2011 Toby Inkster This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself. =head1 DISCLAIMER OF WARRANTIES THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.