Catmandu-RDF-0.32 000755 001750 001750 0 13151247400 12357 5 ustar 00voj voj 000000 000000 README 100644 001750 001750 3653 13151247400 13327 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 NAME
Catmandu::RDF - Modules for handling RDF data within the Catmandu
framework
SYNOPSIS
Command line client "catmandu":
catmandu convert RDF --url http://dx.doi.org/10.2474/trol.7.147
--fix 'aref_query(dct_title,title)' to YAML
catmandu convert RDF --file rdfdump.ttl to RDF --type turtle
# For big file the only efficient option to convert RDF is by
# transforming the input stream into triples and writing to NTriples
# in the output
catmandu convert convert RDF --triples 1 --type ttl to RDF --type NTriples < rdfdump.ttl
See documentation of modules for more examples.
DESCRIPTION
Catmandu::RDF contains modules for handling RDF data within the Catmandu
framework. RDF data is encoded/decoded in aREF
as implemented with RDF::aREF. Please keep
in mind that RDF is a graph-based data structuring format with
specialized technologies such as SPARQL and triple stores. Using
Catmandu::RDF to transform RDF to RDF (e.g. conversion from one RDF
serialization to another) is possible but probably less performant than
decent RDF tools. Catmandu::RDF, however, is more conventient to convert
between RDF and other data formats.
AVAILABLE MODULES
Catmandu::Exporter::RDF
Serialize RDF data (as RDF/XML, RDF/JSON, Turtle, NTriples, RDFa...)
Catmandu::Importer::RDF
Parse RDF data (RDF/XML, RDF/JSON, Turtle, NTriples...) or import
from a SPARQL endpoint
Catmandu::Fix::aref_query
Copy values of RDF data in aREF format to a new field
SEE ALSO
This module is based on Catmandu, RDF::aREF, RDF::Trine, and RDF::NS.
COPYRIGHT AND LICENSE
Copyright Jakob Voß, 2014-
This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.
CONTRIBUTORS
Jakob Voß, Patrick Hochstenbach
Changes 100644 001750 001750 4670 13151247400 13742 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 Changelog for Catmandu-RDF
0.32 2017-08-29 13:23:32 CEST
- Fixing SPARQL examples with latest RDF::LDF
- Better support for streaming RDF input
- Adding a --speed option to the Catmandu::Importer::RDF
0.31 2016-04-13 10:24:55 CEST
- Fix test failure caused by RDF::NS (#29)
0.30 2016-04-03 13:30:18 CEST
- increase RDF::LDF version (#28)
0.29 2016-03-30 14:28:27 CEST
- provide caching support for HTTP access
0.28 2015-11-25 11:35:42 CET
- streaming export in NTriples format by default (issue #25)
0.27 2015-05-30 14:15:45 CEST
- added sparql file option (issue #19)
0.26 2015-05-21 10:38:12 CEST
- added support of Linked Data Fragments
0.25 2015-03-27 13:53:59 CET
- support streaming of NTriple data
0.24 2015-03-09 13:20:23 CET
- added support of SPARQL
- fixed some unit tests
- rewrote aref_query fix
0.23 2014-12-11 16:41:22 CET
- fix bnode mapping bug
- simplify calling syntax of aref_query fix
0.22 2014-12-11 15:01:15 CET
- align with RDF::aREF 0.22, new options predicate_map
0.20 2014-12-10 15:13:40 CET
- tried to fix import from URL encoding (issue #9)
0.19 2014-12-10 14:17:59 CET
- add triples importer mode (issue #5)
- disable namespaces with ns=0 (issue #8)
- support importing from string reference
0.18 2014-10-14 12:53:01 CEST
- add field _url on import from url (issue #9)
- started fix function aref_query
0.17 2014-10-02 14:26:35 CEST
- Migrate to Dist::Milla
- Adjust to aREF 0.19
0.15 2014-07-17T11:35:04
- document and test count method
- started importer
0.14 2014-01-22T07:18:56
- internally use RDF::Trine::Model
- bug detected (issue #3?)
- use RDF::aREF 0.09
0.13 2014-01-15T12:15:56
- Merge release
- use RDF::aREF 0.08
0.12 2014-01-12T16:39:03
- release 0.12 with fixed dependencies
- update dependencies
- fixed dist.ini
- fixed dependency
0.11 2013-12-02T14:17:01
- documentation
- fixed cpanfile
- don't test ob Perl 5.10
- split RDF::aREF as independent module
0.10 2013-11-15T11:18:20
- started to support nested input documents
- renamed aRef to aREF
0.09 2013-11-13T14:29:24
- migrated from RDF/JSON to aRef
- fix link
0.03 2013-09-20T12:42:10
- auto-expand prefixed object-uris
- support 'a' as shortcut for 'rdf:type'
- extended documentation
- implemented basic Exporter
- support a subset of JSON-LD
- use dzil and travis
0.02 2013-09-06T09:14:51
- documentation
0.01 2013-09-05T09:39:00
- basic RDF Exporter
- first draft
t 000755 001750 001750 0 13151247400 12543 5 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 url.t 100644 001750 001750 6646 13151247400 13706 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t use strict;
use warnings;
use open ':std', ':encoding(utf8)';
use Test::More;
use Catmandu -all;
use Catmandu::RDF;
use RDF::Trine;
use Encode;
use HTTP::Response;
use Test::LWP::UserAgent;
use utf8;
RDF::Trine->default_useragent(user_agent());
{
note("importing turtle");
my $importer = importer('RDF', url => 'http://www.w3.org/TR/examples/example1.ttl', type => 'turtle');
my $aref = $importer->first;
is $aref->{'http://www.w3.org/TR/rdf-syntax-grammar'}->{dc_title},
'RDF/XML Syntax Specification (Revised)@', 'Import from URL';
}
{
note("importing rdf/xml");
my $importer = importer('RDF', url => 'http://www.w3.org/TR/examples/example2.rdf', type => 'xml');
my $aref = $importer->first;
is $aref->{'http://www.w3.org/TR/rdf-syntax-grammar'}->{dc_title},
'RDF/XML Syntax Specification (Revised)@', 'Import from URL';
}
{
note("importing NTriples");
my $importer = importer('RDF', url => 'http://www.w3.org/TR/examples/example3.nt', type => 'NTriples');
my $aref = $importer->first;
is $aref->{'http://www.w3.org/TR/rdf-syntax-grammar'}->{dc_title},
'RDF/XML Syntax Specification (Revised)@', 'Import from URL';
}
done_testing;
sub user_agent {
my $ua = Test::LWP::UserAgent->new( agent => "Catmandu::RDF/$Catmandu::RDF::VERSION" );
my $example =< .
\@prefix dc: .
\@prefix ex: .
dc:title "RDF/XML Syntax Specification (Revised)" ;
ex:editor [
ex:fullname "Dave Beckett";
ex:homePage
] .
EOF
add_response(
$ua,
'http://www.w3.org/TR/examples/example1.ttl',
'text/turtle; charset=utf-8',
$example
);
my $example2 =<
EOF
add_response(
$ua,
'http://www.w3.org/TR/examples/example2.rdf',
'application/rdf+xml; charset=utf-8',
$example2
);
my $example3 =< "RDF/XML Syntax Specification (Revised)".
_:b1 .
_:b1 "Dave Beckett" .
_:b1 .
EOF
add_response(
$ua,
'http://www.w3.org/TR/examples/example3.nt',
'text/plain; charset=utf-8',
$example3
);
return $ua;
}
sub add_response {
my $ua = shift;
my $url = shift;
my $content_type = shift;
my $content = shift;
$ua->map_response(
qr{^\Q$url\E$},
HTTP::Response->new(
'200',
'OK',
['Content-Type' => $content_type ],
Encode::encode_utf8($content)
)
);
}
LICENSE 100644 001750 001750 43617 13151247400 13500 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 This software is copyright (c) 2014- by -.
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 -.
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 -.
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
cpanfile 100644 001750 001750 603 13151247400 14123 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 requires 'perl', 'v5.13.1';
requires 'Catmandu', '0.9209';
requires 'RDF::LDF', '0.23';
requires 'RDF::NS', '20140910';
requires 'RDF::Query', '2.913';
requires 'RDF::Trine', '1.013';
requires 'RDF::aREF', '0.25';
requires 'IRI', '>=0.008';
test_requires 'Test::More', '0.99';
test_requires 'Test::LWP::UserAgent', '0.025';
test_requires 'Test::Pod', '0';
test_requires 'Encode', '0';
dist.ini 100644 001750 001750 33 13151247400 14040 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 author=Jakob Voß
[@Milla]
Build.PL 100644 001750 001750 261 13151247400 13713 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 # This Build.PL for Catmandu-RDF was generated by Dist::Zilla::Plugin::ModuleBuildTiny 0.014.
use strict;
use warnings;
use v5.13.1;
use Module::Build::Tiny 0.034;
Build_PL();
META.yml 100644 001750 001750 2056 13151247400 13714 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 ---
abstract: 'Modules for handling RDF data within the Catmandu framework'
author:
- 'Jakob Voß'
build_requires:
Encode: '0'
Test::LWP::UserAgent: '0.025'
Test::More: '0.99'
Test::Pod: '0'
configure_requires:
Module::Build::Tiny: '0.034'
dynamic_config: 0
generated_by: 'Dist::Zilla version 5.035, Dist::Milla version v1.0.8, CPAN::Meta::Converter version 2.150001'
license: perl
meta-spec:
url: http://module-build.sourceforge.net/META-spec-v1.4.html
version: '1.4'
name: Catmandu-RDF
no_index:
directory:
- t
- xt
- inc
- share
- eg
- examples
requires:
Catmandu: '0.9209'
IRI: '0.008'
RDF::LDF: '0.23'
RDF::NS: '20140910'
RDF::Query: '2.913'
RDF::Trine: '1.013'
RDF::aREF: '0.25'
perl: v5.13.1
resources:
bugtracker: https://github.com/LibreCat/Catmandu-RDF/issues
homepage: https://github.com/LibreCat/Catmandu-RDF
repository: https://github.com/LibreCat/Catmandu-RDF.git
version: '0.32'
x_contributors:
- 'Jakob Voß '
- 'Patrick Hochstenbach '
MANIFEST 100644 001750 001750 763 13151247400 13557 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 # This file was automatically generated by Dist::Zilla::Plugin::Manifest v5.035.
Build.PL
Changes
LICENSE
MANIFEST
META.json
META.yml
README
cpanfile
dist.ini
lib/Catmandu/Exporter/RDF.pm
lib/Catmandu/Fix/aref_query.pm
lib/Catmandu/Fix/rdf_ldf_statements.pm
lib/Catmandu/Importer/RDF.pm
lib/Catmandu/RDF.pm
t/aref_query.t
t/example.rdf
t/example.ttl
t/example.yml
t/exporter-add.t
t/exporter.t
t/importer.t
t/issue-3.t
t/query.sparql
t/rdf_ldf_statements.t
t/release-pod-syntax.t
t/sparql.t
t/url.t
META.json 100644 001750 001750 3635 13151247400 14070 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32 {
"abstract" : "Modules for handling RDF data within the Catmandu framework",
"author" : [
"Jakob Voß"
],
"dynamic_config" : 0,
"generated_by" : "Dist::Zilla version 5.035, Dist::Milla version v1.0.8, CPAN::Meta::Converter version 2.150001",
"license" : [
"perl_5"
],
"meta-spec" : {
"url" : "http://search.cpan.org/perldoc?CPAN::Meta::Spec",
"version" : 2
},
"name" : "Catmandu-RDF",
"no_index" : {
"directory" : [
"t",
"xt",
"inc",
"share",
"eg",
"examples"
]
},
"prereqs" : {
"configure" : {
"requires" : {
"Module::Build::Tiny" : "0.034"
}
},
"develop" : {
"requires" : {
"Dist::Milla" : "v1.0.8",
"Test::Pod" : "1.41"
}
},
"runtime" : {
"requires" : {
"Catmandu" : "0.9209",
"IRI" : "0.008",
"RDF::LDF" : "0.23",
"RDF::NS" : "20140910",
"RDF::Query" : "2.913",
"RDF::Trine" : "1.013",
"RDF::aREF" : "0.25",
"perl" : "v5.13.1"
}
},
"test" : {
"requires" : {
"Encode" : "0",
"Test::LWP::UserAgent" : "0.025",
"Test::More" : "0.99",
"Test::Pod" : "0"
}
}
},
"release_status" : "stable",
"resources" : {
"bugtracker" : {
"web" : "https://github.com/LibreCat/Catmandu-RDF/issues"
},
"homepage" : "https://github.com/LibreCat/Catmandu-RDF",
"repository" : {
"type" : "git",
"url" : "https://github.com/LibreCat/Catmandu-RDF.git",
"web" : "https://github.com/LibreCat/Catmandu-RDF"
}
},
"version" : "0.32",
"x_contributors" : [
"Jakob Voß ",
"Patrick Hochstenbach "
]
}
sparql.t 100644 001750 001750 27325 13151247400 14423 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t use strict;
use warnings;
use open ':std', ':encoding(utf8)';
use Test::More;
use Catmandu -all;
use Catmandu::RDF;
use RDF::Trine;
use Encode;
use HTTP::Response;
use Test::LWP::UserAgent;
use utf8;
RDF::Trine->default_useragent(user_agent());
{
note("importing from sparql endpoint");
my $sparql =<
SELECT * WHERE { ?book dc:title ?title . }
END
my $url = 'http://sparql.org/books/sparql';
my $importer = importer('RDF', url => $url, sparql => $sparql);
is $importer->sparql, $sparql, "SPARQL";
$importer = importer('RDF', url => $url,
sparql => "SELECT * WHERE { ?book dc:title ?title . }\n");
is $importer->sparql, $sparql, "SPARQL, PREFIX added";
my $ref = $importer->first;
ok $ref->{title} , 'got a title';
ok $ref->{book} , 'got a book';
}
{
note("importing from ldf endpoint");
my $sparql =< }
EOF
my $url = 'http://fragments.dbpedia.org/2014/en';
my $importer = importer('RDF', url => $url, sparql => $sparql);
my $ref = $importer->first;
ok $ref->{film} , 'got a film';
}
{
note("importing from ldf endpoint (utf8)");
my $url = 'http://fragments.dbpedia.org/2014/en';
my $importer = importer('RDF', url => $url, sparql => 't/query.sparql');
my $ref = $importer->first;
ok $ref->{name} , 'got a name (file sparql)';
like $ref->{name} , qr/François Schuiten/ , 'utf8 test';
}
done_testing;
sub user_agent {
my $ua = Test::LWP::UserAgent->new( agent => "Catmandu::RDF/${Catmandu::RDF::VERSION}" );
my $example =<
http://example.org/book/book7
Harry Potter and the Deathly Hallows
EOF
add_response(
$ua,
'http://sparql.org/books/sparql?query=PREFIX%20dc%3A%20%3Chttp%3A%2F%2Fpurl.org%2Fdc%2Felements%2F1.1%2F%3E%0ASELECT%20%2A%20WHERE%20%7B%20%3Fbook%20dc%3Atitle%20%3Ftitle%20.%20%7D%0A',
'application/sparql-results+xml; charset=utf-8',
$example
);
my $example2 =<.
\@prefix rdfs: .
\@prefix xsd: .
\@prefix dc: .
\@prefix foaf: .
\@prefix dbpedia: .
\@prefix dbpedia-owl: .
\@prefix dbpprop: .
\@prefix hydra: .
\@prefix void: .
hydra:member .
a void:Dataset, hydra:Collection;
void:subset ;
void:uriLookupEndpoint "http://fragments.dbpedia.org/2014/en{?subject,predicate,object}";
hydra:search _:triplePattern.
_:triplePattern hydra:template "http://fragments.dbpedia.org/2014/en{?subject,predicate,object}";
hydra:mapping _:subject, _:predicate, _:object.
_:subject hydra:variable "subject";
hydra:property rdf:subject.
_:predicate hydra:variable "predicate";
hydra:property rdf:predicate.
_:object hydra:variable "object";
hydra:property rdf:object.
, , .
"literal1", "literalA", "literalB", "literalC";
, .
"literal2".
void:subset ;
a hydra:Collection, hydra:PagedCollection;
dc:title "Linked Data Fragment of Test"\@en;
dc:description "Triple Pattern Fragment of the 'Test' dataset containing triples matching the pattern { ?s ?p ?o }."\@en;
dc:source ;
hydra:totalItems "10"^^xsd:integer;
void:triples "10"^^xsd:integer;
hydra:itemsPerPage "100"^^xsd:integer;
hydra:firstPage .
EOF
add_response(
$ua,
'http://fragments.dbpedia.org/2014/en',
'text/turtle; charset=utf-8',
$example2
);
my $example2b =<.
\@prefix rdfs: .
\@prefix owl: .
\@prefix skos: .
\@prefix xsd: .
\@prefix dc: .
\@prefix dcterms: .
\@prefix dc11: .
\@prefix foaf: .
\@prefix geo: .
\@prefix dbpedia: .
\@prefix dbpedia-owl: .
\@prefix dbpprop: .
\@prefix hydra: .
\@prefix void: .
hydra:member .
a void:Dataset, hydra:Collection;
void:subset , ;
void:uriLookupEndpoint "http://fragments.dbpedia.org/2014/en{?subject,predicate,object}";
hydra:search _:triplePattern.
_:triplePattern hydra:template "http://fragments.dbpedia.org/2014/en{?subject,predicate,object}";
hydra:mapping _:subject, _:predicate, _:object.
_:subject hydra:variable "subject";
hydra:property rdf:subject.
_:predicate hydra:variable "predicate";
hydra:property rdf:predicate.
_:object hydra:variable "object";
hydra:property rdf:object.
dcterms:subject .
void:subset .
a hydra:Collection, hydra:PagedCollection;
dcterms:title "Linked Data Fragment of DBpedia 2014"\@en;
dcterms:description "Triple Pattern Fragment of the 'DBpedia 2014' dataset containing triples matching the pattern { ?s }."\@en;
dcterms:source ;
hydra:totalItems "1"^^xsd:integer;
void:triples "1"^^xsd:integer;
hydra:itemsPerPage "100"^^xsd:integer;
hydra:firstPage ;
hydra:nextPage .
EOF
add_response(
$ua,
'http://fragments.dbpedia.org/2014/en?predicate=http%3A%2F%2Fpurl.org%2Fdc%2Fterms%2Fsubject&object=http%3A%2F%2Fdbpedia.org%2Fresource%2FCategory%3AFrench_films',
'text/turtle; charset=utf-8',
$example2b
);
my $example3=<.
\@prefix rdfs: .
\@prefix owl: .
\@prefix skos: .
\@prefix xsd: .
\@prefix dc: .
\@prefix dcterms: .
\@prefix dc11: .
\@prefix foaf: .
\@prefix geo: .
\@prefix dbpedia: .
\@prefix dbpedia-owl: .
\@prefix dbpprop: .
\@prefix hydra: .
\@prefix void: .
hydra:member .
a void:Dataset, hydra:Collection;
void:subset ;
void:uriLookupEndpoint "http://fragments.dbpedia.org/2014/en{?subject,predicate,object}";
hydra:search _:triplePattern.
_:triplePattern hydra:template "http://fragments.dbpedia.org/2014/en{?subject,predicate,object}";
hydra:mapping _:subject, _:predicate, _:object.
_:subject hydra:variable "subject";
hydra:property rdf:subject.
_:predicate hydra:variable "predicate";
hydra:property rdf:predicate.
_:object hydra:variable "object";
hydra:property rdf:object.
rdfs:label "François Schuiten"\@de, "François Schuiten"\@en, "François Schuiten"\@es, "François Schuiten"\@fr, "François Schuiten"\@it, "François Schuiten"\@nl, "フランソワ・スクイテン"\@ja.
void:subset ;
a hydra:Collection, hydra:PagedCollection;
dcterms:title "Linked Data Fragment of DBpedia 2014"\@en;
dcterms:description "Triple Pattern Fragment of the 'DBpedia 2014' dataset containing triples matching the pattern { ?o }."\@en;
dcterms:source ;
hydra:totalItems "7"^^xsd:integer;
void:triples "7"^^xsd:integer;
hydra:itemsPerPage "100"^^xsd:integer;
hydra:firstPage
EOF
add_response(
$ua,
'http://fragments.dbpedia.org/2014/en?subject=http%3A%2F%2Fdbpedia.org%2Fresource%2FFran%C3%A7ois_Schuiten&predicate=http%3A%2F%2Fwww.w3.org%2F2000%2F01%2Frdf-schema%23label',
'text/turtle; charset=utf-8',
$example3
);
return $ua;
}
sub add_response {
my $ua = shift;
my $url = shift;
my $content_type = shift;
my $content = shift;
$ua->map_response(
qr{^\Q$url\E$},
HTTP::Response->new(
'200',
'OK',
['Content-Type' => $content_type ],
Encode::encode_utf8($content)
)
);
} issue-3.t 100644 001750 001750 1341 13151247400 14357 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t use strict;
use warnings;
use Test::More;
use Catmandu::Exporter::RDF;
my $turtle;
my $exporter = Catmandu::Exporter::RDF->new(file => \$turtle, type => 'ttl');
my @arefs = (
{
"http://x.org/alice" => { "foaf_knows" => "" },
"http://x.org/bob" => { "a" => "foaf_Person", }
},
{
"http://x.org/alice" => { "foaf_knows" => "" },
}
);
$exporter->add($_) for @arefs;
$exporter->commit;
$turtle =~ s/ \./ ;/smg;
is_deeply [ sort split "\n", $turtle ], [
' , ;',
' a ;'
];
print $turtle;
done_testing;
exporter.t 100644 001750 001750 3073 13151247400 14743 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t use strict;
use warnings;
use Test::More;
my $pkg;
BEGIN { use_ok $pkg = 'Catmandu::Exporter::RDF'; }
require_ok $pkg;
my $file = "";
my $data = { # example copied from RDF::Trine::Model
"http://example.com/subject1" => {
"http://example.com/predicate1" => [
'Foo@en',
"Bar^"
],
},
"_:bnode1" => {
"http://example.com/predicate2" => [
"http://example.com/object2",
],
"http://example.com/predicate2" => [
"_:bnode3",
],
},
};
my $exporter = $pkg->new(file => \$file, type => 'ttl');
isa_ok $exporter, $pkg;
is $exporter->count, 0, 'count is zero';
$exporter->add($data);
$exporter->commit;
# normalize
$file =~ s/("Foo".+), ("Bar".+) ./$2, $1 ./;
$file = join "\n", sort split "\n", "$file";
$file .= "\n" unless $file =~ /\n$/m;
is $file, <<'RDF', 'serialize Turtle';
"Bar"^^, "Foo"@en .
[] [] .
RDF
is $exporter->count, 1, 'count is always one';
$file = "";
$exporter = $pkg->new(file => \$file);
$exporter->add( { _id => '', foaf_knows => { foaf_name => 'alice' } } );
is $file, < _:b1 .
_:b1 "alice" .
NTRIPLES
$exporter->add( { _id => '', foaf_knows => { foaf_name => 'alice' } } );
$exporter->commit;
is scalar(split "\n", $file), 4, 'keep blank nodes separated';
is $exporter->count, 2, 'count is 2';
done_testing;
importer.t 100644 001750 001750 4156 13151247400 14737 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t use strict;
use warnings;
use Test::More;
use Catmandu -all;
my $pkg;
BEGIN { use_ok $pkg = 'Catmandu::Importer::RDF'; }
require_ok $pkg;
isa_ok $pkg->new, $pkg;
my $aref = importer('YAML', file => 't/example.yml')->first;
my $expect = {
'http://example.org' => {
a => '',
'http://example.org/foo' => "b\x{e4}r\@en",
'http://purl.org/dc/elements/1.1/title' => "B\x{c4}R@",
'http://purl.org/dc/elements/1.1/extent' =>
'42^',
}
};
is_deeply importer('RDF', ns => 0, file => 't/example.ttl')->first,
$expect, 'disable namespace prefixes';
foreach my $file (qw(t/example.ttl t/example.rdf)) {
is_deeply importer('RDF', file => $file, ns => 20150725)->first,
$aref, "default namespace prefixes ($file)";
}
{
use utf8;
my $ttl = ' "bär"@en .';
my $importer = importer('RDF', type => 'turtle', file => \$ttl, ns => 20150725);
my $aref = $importer->first;
is_deeply $aref->{'http://example.org'}->{'http://example.org/foo'},
'bär@en', 'import from scalar with Unicode';
}
{
my $importer = importer('RDF', file => 't/example.ttl', triples => 1, predicate_map => 1, ns => 20150725);
my $aref = $importer->to_array;
is_deeply [
sort {
my (undef,$x) = sort keys %$a;
my (undef,$y) = sort keys %$b;
$x cmp $y
} @$aref
], [
{ _id => 'http://example.org', a => 'rdfs_Resource' },
{ _id => 'http://example.org', dc_extent => '42^xs_integer' },
{ _id => 'http://example.org', dc_title => "B\x{c4}R@" },
{ _id => 'http://example.org', 'http://example.org/foo' => "b\x{e4}r\@en" }
], 'import triples';
my $nt = "";
my $exporter = exporter('RDF', type => 'ntriples', file => \$nt);
$exporter->add_many($aref);
$exporter->commit;
$importer = importer('RDF', type => 'ntriples', file => \$nt, ns => 0);
is_deeply $importer->first, $expect, 'round-trip export-import-export';
}
done_testing;
example.rdf 100644 001750 001750 1460 13151247400 15034 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t
bär
BÄR
42
example.ttl 100644 001750 001750 362 13151247400 15044 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t @prefix rdfs: .
a rdfs:Resource ;
"b\u00e4r"@en ;
"B\u00c4R" ;
42 .
example.yml 100644 001750 001750 212 13151247400 15034 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t ---
'http://example.org':
a: rdfs_Resource
dc_title: BÄR@
dc_extent: 42^xs_integer
'http://example.org/foo': bär@en
...
aref_query.t 100644 001750 001750 1630 13151247400 15232 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t use strict;
use warnings;
use Test::More;
use Catmandu ':all';
use Catmandu::Fix;
use Catmandu::Fix::aref_query as => 'my_query';
{
my $fixer = Catmandu::Fix->new( fixes => ['aref_query(dc_title,title)'] );
my $rdf = importer('RDF', file => 't/example.ttl')->first;
($rdf->{_uri}) = keys %$rdf;
$fixer->fix($rdf);
delete $rdf->{ $rdf->{_uri} };
is_deeply $rdf, {
'_uri' => 'http://example.org',
title => "B\x{c4}R",
}, 'simple RDF fix';
}
my $rdf = importer('RDF', file => 't/example.ttl')->first;
sub fix {
my $rdf = shift;
my_query($rdf, @_);
delete $rdf->{$_[-1]};
}
is fix($rdf,'http://example.org','dc_title','label'), "B\x{c4}R";
is fix($rdf,'dc_title','label'), undef;
$rdf->{_url} = 'http://example.org';
is fix($rdf,'dc_title','label'), "B\x{c4}R", 'respect _url field';
is fix($rdf,'http://example.com','dc_title','label'), undef;
done_testing;
query.sparql 100644 001750 001750 200 13151247400 15244 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t SELECT ?name WHERE {
?name .
}
exporter-add.t 100644 001750 001750 5554 13151247400 15477 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t use strict;
use warnings;
use Test::More;
use Catmandu::Exporter::RDF;
sub check_add(@) { ## no critic
my $options = shift;
my $data = shift;
my $result = shift;
my $file = "";
my $exporter = Catmandu::Exporter::RDF->new(file => \$file, %$options);
$exporter->add($data);
$exporter->commit;
if (ref $result) {
$result->($file);
} else {
is $file, $result, $_[0];
}
}
check_add { type => 'ttl', ns => '20130816' }, {
_id => 'http://example.org/',
dc_title => 'Subject',
} => " \"Subject\" .\n",
'expand predicate URI';
check_add { type => 'ttl', ns => '20130816' }, {
_id => 'http://example.org/',
dc_title => 'Subject@',
} => " \"Subject\" .\n",
'literal object';
check_add { type => 'ttl', ns => '20130816' }, {
_id => 'http://example.org/',
dct_extent => '42^xsd_integer',
} => " 42 .\n",
'literal object with datatype';
check_add { type => 'ttl', ns => '20130816' }, {
_id => 'http://example.org/',
'http://example.org/predicate' => { '_id' => 'http://example.com/object' },
} => " .\n",
'uri object';
check_add { type => 'ttl', ns => '20130816' }, {
_id => 'http://example.org/',
a => 'foaf_Organization',
} => " a .\n",
'"a" for rdf:type';
=todo
check_add { type => 'ttl', ns => '20130816' }, {
'_id' => 'http://example.org/',
'http://example.org/predicate' => { },
} => " _:b1 .\n",
'blank node object';
=cut
check_add { type => 'ttl', ns => '20130816' }, {
_id => 'http://www.gbv.de/',
geo_location => {
geo_lat => '9.93492',
geo_long => '51.5393710',
}
} => sub {
my $ttl = shift;
ok $ttl =~ qr{_:[a-zA-Z0-9]+ "9.93492"}
&& $ttl =~ qr{ "51.5393710"}
&& $ttl =~ qr{ _:[a-zA-Z0-9]+},
'nested RDF';
};
## fixes
check_add { type => 'ttl', ns => '20130816',
fix => ["move_field('_id','\_id')","prepend('\_id','http://example.org/');"]
}, {
_id => 123,
dc_title => 'Foo',
} => " \"Foo\" .\n",
'fix subject URI';
check_add { type => 'ttl', ns => '20130816',
fix => [
"append('dc:extent','^xsd:integer');"
]
}, {
_id => 'http://example.org/',
dc_extent => 42,
} => " \"42\" .\n",
'fix predicate';
done_testing;
Catmandu 000755 001750 001750 0 13151247400 14602 5 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib RDF.pm 100644 001750 001750 5710 13151247400 15716 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib/Catmandu package Catmandu::RDF;
use namespace::clean;
use Catmandu::Sane;
use Catmandu::Util qw(is_instance);
use Moo::Role;
use RDF::NS;
our $VERSION = '0.32';
our %TYPE_ALIAS = (
Ttl => 'Turtle',
N3 => 'Notation3',
Xml => 'RDFXML',
XML => 'RDFXML',
Json => 'RDFJSON',
);
has type => (
is => 'ro',
coerce => sub { my $t = ucfirst($_[0]); $TYPE_ALIAS{$t} // $t },
);
has ns => (
is => 'ro',
default => sub { RDF::NS->new },
coerce => sub {
return $_[0] if is_instance($_[0],'RDF::NS');
return $_[0] if !$_[0];
return RDF::NS->new($_[0]);
},
handles => ['uri'],
);
1;
__END__
=encoding utf8
=head1 NAME
Catmandu::RDF - Modules for handling RDF data within the Catmandu framework
=begin markdown
# STATUS
[](https://travis-ci.org/LibreCat/Catmandu-RDF)
[](https://coveralls.io/r/LibreCat/Catmandu-RDF)
[](http://cpants.cpanauthors.org/dist/Catmandu-RDF)
=end markdown
=head1 SYNOPSIS
Command line client C:
catmandu convert RDF --url http://dx.doi.org/10.2474/trol.7.147
--fix 'aref_query(dct_title,title)' to YAML
catmandu convert RDF --file rdfdump.ttl to RDF --type turtle
# For big file the only efficient option to convert RDF is by
# transforming the input stream into triples and writing to NTriples
# in the output
catmandu convert convert RDF --triples 1 --type ttl to RDF --type NTriples < rdfdump.ttl
See documentation of modules for more examples.
=head1 DESCRIPTION
Catmandu::RDF contains modules for handling RDF data within the L
framework. RDF data is encoded/decoded in L as
implemented with L. Please keep in mind that RDF is a graph-based
data structuring format with specialized technologies such as SPARQL and triple
stores. Using Catmandu::RDF to transform RDF to RDF (e.g. conversion from one
RDF serialization to another) is possible but probably less performant than
decent RDF tools. Catmandu::RDF, however, is more conventient to convert
between RDF and other data formats.
=head1 AVAILABLE MODULES
=over
=item L
Serialize RDF data (as RDF/XML, RDF/JSON, Turtle, NTriples, RDFa...)
=item L
Parse RDF data (RDF/XML, RDF/JSON, Turtle, NTriples...) or import from a SPARQL
endpoint
=item L
Copy values of RDF data in aREF format to a new field
=back
=head1 SEE ALSO
This module is based on L, L, L, and
L.
=head1 COPYRIGHT AND LICENSE
Copyright Jakob Voß, 2014-
This is free software; you can redistribute it and/or modify it under the same
terms as the Perl 5 programming language system itself.
=head1 CONTRIBUTORS
Jakob Voß, Patrick Hochstenbach
=cut
rdf_ldf_statements.t 100644 001750 001750 313 13151247400 16714 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t #!/usr/bin/env perl
use strict;
use warnings;
use Test::More;
use Test::Exception;
my $pkg;
BEGIN {
$pkg = 'Catmandu::Fix::rdf_ldf_statements';
use_ok $pkg;
}
require_ok $pkg;
done_testing;
release-pod-syntax.t 100644 001750 001750 456 13151247400 16601 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/t #!perl
BEGIN {
unless ($ENV{RELEASE_TESTING}) {
require Test::More;
Test::More::plan(skip_all => 'these tests are for release candidate testing');
}
}
# This file was automatically generated by Dist::Zilla::Plugin::PodSyntaxTests.
use Test::More;
use Test::Pod 1.41;
all_pod_files_ok();
Exporter 000755 001750 001750 0 13151247400 16412 5 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib/Catmandu RDF.pm 100644 001750 001750 7124 13151247400 17527 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib/Catmandu/Exporter package Catmandu::Exporter::RDF;
use namespace::clean;
use Catmandu::Sane;
use Moo;
use RDF::Trine::Serializer;
use RDF::Trine::Model;
use RDF::aREF;
our $VERSION = '0.32';
with 'Catmandu::RDF';
with 'Catmandu::Exporter';
# internal attributes
has decoder => (
is => 'lazy'
);
has serializer => (
is => 'lazy'
);
has model => (
is => 'lazy'
);
sub _build_decoder {
RDF::aREF::Decoder->new(
ns => $_[0]->ns // ($_[0]->ns eq 0 ? { } : RDF::NS->new),
callback => $_[0]->model
);
}
sub _build_serializer {
RDF::Trine::Serializer->new($_[0]->type // 'ntriples');
}
sub _build_model {
my $self = shift;
# Streaming output when we have type => NTriples
if (lc($self->type // 'ntriples') eq 'ntriples') {
sub {
require RDF::Trine::Statement;
eval {
my $st = RDF::aREF::Decoder::trine_statement(@_);
$self->fh->print($self->serializer->statement_as_string($st));
};
$self->decoder->error($@) if $@;
};
}
else {
RDF::Trine::Model->new;
}
}
sub add {
my ($self, $aref) = @_;
$self->decoder->decode($aref, keep_bnode_map => 1);
}
sub commit {
my ($self) = @_;
if (ref $self->model eq 'RDF::Trine::Model') {
$self->model->end_bulk_ops;
$self->decoder->clean_bnodes;
$self->serializer->serialize_model_to_file( $self->fh, $self->model );
}
}
1;
__END__
=head1 NAME
Catmandu::Exporter::RDF - serialize RDF data
=head1 SYNOPSIS
In Perl code:
use Catmandu -all;
my $exporter = exporter('RDF',
file => 'export.rdf',
type => 'XML',
fix => 'rdf.fix'
);
$exporter->add( $aref ); # pass RDF data in aREF encoding
$exporter->commit;
=head1 DESCRIPTION
This L exports RDF data in different RDF serializations.
=head1 CONFIGURATION
=over
=item file
=item fh
=item encoding
=item fix
Default configuration options of L. The option C is
supported as derived from L. For every C or for every
item in C the given fixes will be applied first.
=item type
A serialization form can be set with option C with default value
C. The option must refer to a subclass of L,
for instance C for RDF/Turtle with L.
The first letter is transformed uppercase, so C<< format => 'turtle' >> will
work as well. In addition there are aliases C for C, C for
C, C and C for C, C for C.
When the option C is set to 'NTriples' the export can be streamed in all
other cases the results are exported in bulk after C.
=item ns
The option C can refer to an instance of or to a constructor argument of
L. Use a fixed date, such as "C<20130816>" to make sure your URI
namespace prefixes are stable.
=back
=head1 METHODS
See also L.
=head2 add( ... )
RDF data is added given in B as
implemented with L and defined at L.
=head2 count
Returns the number of times C has been called. In contrast to other
Catmandu exporters, this does not reflect the number of exporter records
because RDF data is always merged to one RDF graph.
=head2 uri( $uri )
Expand and abbreviated with L. For instance "C" is expanded
to "C".
=cut
=head1 SEE ALSO
Serialization is based on L.
=encoding utf8
=cut
Importer 000755 001750 001750 0 13151247400 16403 5 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib/Catmandu RDF.pm 100644 001750 001750 30661 13151247400 17542 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib/Catmandu/Importer package Catmandu::Importer::RDF;
use open ':std', ':encoding(utf8)';
use namespace::clean;
use Catmandu::Sane;
use Moo;
use RDF::Trine::Parser;
use RDF::Trine::Model;
use RDF::Trine::Store::SPARQL;
use RDF::Trine::Store::LDF;
use RDF::Trine::Store;
use RDF::Query;
use RDF::LDF;
use RDF::aREF;
use RDF::aREF::Encoder;
use RDF::NS;
use IO::Pipe;
use JSON;
use LWP::UserAgent::CHICaching;
our $VERSION = '0.32';
with 'Catmandu::RDF';
with 'Catmandu::Importer';
has url => (
is => 'ro'
);
has base => (
is => 'ro',
lazy => 1,
builder => sub {
defined $_[0]->file ? "file://".$_[0]->file : "http://example.org/";
}
);
has encoder => (
is => 'ro',
lazy => 1,
builder => sub {
my $ns = $_[0]->ns;
RDF::aREF::Encoder->new(
ns => (($ns // 1) ? $ns : { }),
subject_map => !$_[0]->predicate_map,
);
}
);
has sparql => (
is => 'ro',
lazy => 1,
trigger => sub {
my ($sparql, $ns) = ($_[1], $_[0]->ns);
$sparql = do { local (@ARGV,$/) = $sparql; <> } if $sparql =~ /^\S+$/ && -r $sparql;
my %prefix;
# guess requires prefixes (don't override existing). Don't mind false positives
$prefix{$_} = 1 for ($sparql =~ /\s([a-z][a-z0-0_-]*):/mig);
delete $prefix{$_} for ($sparql =~ /PREFIX\s+([^:]+):/mg);
$_[0]->{sparql} = join "\n", (map { $ns->SPARQL($_) } keys %prefix), $sparql;
}
);
has sparql_result => (
is => 'ro',
default => sub { 'simple' }
);
has predicate_map => (
is => 'ro',
);
has triples => (
is => 'ro',
);
has cache => (
is => 'ro',
default => sub { 0 }
);
has cache_options => (
is => 'ro',
default => sub { +{
driver => 'Memory',
global => 1 ,
max_size => 1024*1024
} }
);
has speed => (
is => 'ro',
);
sub BUILD {
my ($self) = @_;
if ($self->cache) {
my $options = $self->cache_options // {};
my $cache = CHI->new( %$options );
my $ua = LWP::UserAgent::CHICaching->new(cache => $cache);
RDF::Trine->default_useragent($ua);
}
}
sub generator {
my ($self) = @_;
if ($self->sparql) {
return $self->sparql_generator;
} else {
return $self->rdf_generator;
}
}
sub sparql_generator {
my ($self) = @_;
warn "--triples not active for sparql queries" if ($self->triples);
warn "--predicate_map not active for sparql queries" if ($self->predicate_map);
my $encoder = RDF::aREF::Encoder->new( ns => {} ); # never return qnames
sub {
state $stream = $self->_sparql_stream;
if (defined($stream) && defined(my $row = $stream->next)) {
if (ref $row eq 'RDF::Query::VariableBindings' || ref $row eq 'RDF::Trine::VariableBindings') {
my $ref = {};
for (keys %$row) {
my $val = $row->{$_};
$ref->{$_} = $self->sparql_result eq 'aref'
? $encoder->object($val) : do { # TODO: clean up
if ( $val->is_resource ) {
$val->uri_value;
} elsif ( $val->is_literal) {
$val->literal_value;
} else {
$val->as_string
}
};
}
return $ref;
} else {
die "Expected a RDF::Query::VariableBindings or RDF::Trine::VariableBindings but got a " . ref($row);
}
} else {
return ($stream = undef);
}
};
}
sub rdf_generator {
my ($self) = @_;
sub {
state $stream = $self->_hashref_stream;
return unless $stream;
my $aref = { };
if ($self->triples) {
if (my $hashref = $stream->()) {
$self->encoder->add_hashref($hashref, $aref);
}
else {
return ($stream = undef);
}
}
else {
# TODO: include namespace mappings if requested
while (my $hashref = $stream->()) {
$self->encoder->add_hashref(
$hashref,
$aref
);
}
if ($self->url) {
$aref->{_url} = $self->url;
}
$stream = undef;
}
if ($self->url) {
# RDF::Trine::Parser parses data from URL to UTF-8
# but we want internal character sequences
_utf8_decode($aref);
}
return $aref;
};
}
sub _utf8_decode {
if (ref $_[0] eq 'HASH') {
# FIXME: UTF-8 in property values
foreach (values %{$_[0]}) {
ref($_) ? _utf8_decode($_) : utf8::decode($_);
}
} else {
foreach (@{$_[0]}) {
ref($_) ? _utf8_decode($_) : utf8::decode($_);
}
}
}
sub _sparql_stream {
my ($self) = @_;
die "need an url" unless $self->url;
$self->log->info("parsing: " . $self->sparql);
my $store;
# Check if this server is an LDF server
my $ldf_client = RDF::LDF->new(url => $self->url);
if ($ldf_client->is_fragment_server) {
$store = RDF::Trine::Store->new_with_config({
storetype => 'LDF',
url => $self->url
});
}
else {
$store = RDF::Trine::Store->new_with_config({
storetype => 'SPARQL',
url => $self->url
});
}
unless ($store) {
$self->log->error("failed to connect to " . $self->url);
return;
}
my $model = RDF::Trine::Model->new($store);
my $rdf_query = RDF::Query->new($self->sparql);
unless ($rdf_query) {
$self->log->error("failed to parse " . $self->sparql);
return;
}
my $iterator = $rdf_query->execute($model);
unless ($iterator) {
$self->log->error("failed to execute " . $self->sparql . " at " . $self->url);
return;
}
}
sub _hashref_stream {
my ($self) = @_;
# Create a pipe stream to convert a callback handler into an iterator
my $pipe = IO::Pipe->new();
if (my $pid = fork()) {
# parent
$pipe->reader();
binmode($pipe,':encoding(UTF-8)');
return sub {
state $line = <$pipe>;
return decode_json($line) if defined($line);
waitpid($pid,0);
return undef;
};
}
else {
# child
$pipe->writer();
binmode($pipe,':encoding(UTF-8)');
my $parser = $self->type
? RDF::Trine::Parser->new( $self->type ) : 'RDF::Trine::Parser';
my $handler = sub {
my $triple = shift;
state $start = time;
state $count = 0;
my $subject = $triple->subject->is_blank ?
'_:' . $triple->subject->blank_identifier :
$triple->subject->uri_value;
my $predicate = $triple->predicate->is_blank ?
'_:' . $triple->predicate->blank_identifier :
$triple->predicate->value;
my $value = $triple->object->is_literal ?
$triple->object->literal_value :
$triple->object->is_blank ?
'_:' . $triple->object->blank_identifier :
$triple->object->uri_value;
my $type = lc $triple->object->type;
$type = 'bnode' if $type eq 'blank';
my $lang = $triple->object->is_literal ? $triple->object->literal_value_language : undef;
my $datatype = $triple->object->is_literal ? $triple->object->literal_datatype : undef;
# Create the RDF::Trine type RDF/JSON RDF::aREF can parse
my $hashref = {};
$hashref->{$subject}->{$predicate}->[0]->{type} = $type;
$hashref->{$subject}->{$predicate}->[0]->{datatype} = $datatype if $datatype;
$hashref->{$subject}->{$predicate}->[0]->{lang} = $lang if $lang;
$hashref->{$subject}->{$predicate}->[0]->{value} = $value;
print $pipe encode_json($hashref) , "\n";
$count++;
if ($self->speed && ($count % 100 == 0) && (my $elapsed = time - $start) ) {
printf STDERR "triples %9d (%d/sec)\n" , $count , $count/$elapsed;
}
};
if ($self->url) {
$parser->parse_url( $self->url, $handler);
}
else {
my $from_scalar = (ref $self->file // '') eq 'SCALAR';
if (!$self->type and $self->file and !$from_scalar) {
$parser = $parser->guess_parser_by_filename($self->file)->new;
}
if ($from_scalar) {
$parser->parse( $self->base, ${$self->file}, $handler );
}
else {
$parser->parse_file( $self->base, $self->file // $self->fh, $handler );
}
}
exit(0);
}
}
1;
__END__
=head1 NAME
Catmandu::Importer::RDF - parse RDF data
=head1 SYNOPSIS
Command line client C:
catmandu convert RDF --url http://d-nb.info/gnd/4151473-7 to YAML
catmandu convert RDF --file rdfdump.ttl to JSON
# Parse the input into on JSON document per triplet. This is the
# most memory efficient (and fastest) way to parse RDF input.
catmandu convert RDF --triples 1 --file rdfdump.ttl to JSON
# Transform back into NTriples (conversions to and from triples is the
# most efficient way to process RDF)
catmandu convert RDF --triples 1 --file rdfdump.ttl to RDF --type NTriples
# Query a SPARQL endpoint
catmandu convert RDF --url http://dbpedia.org/sparql
--sparql "SELECT ?film WHERE { ?film dct:subject }"
catmandu convert RDF --url http://example.org/sparql --sparql query.rq
# Query a Linked Data Fragment endpoint
catmandu convert RDF --url http://fragments.dbpedia.org/2014/en
--sparql "SELECT ?film WHERE { ?film dct:subject }"
In Perl code:
use Catmandu::Importer::RDF;
my $url = "http://dx.doi.org/10.2474/trol.7.147";
my $rdf = Catmandu::Importer::RDF->new( url => $url )->first;
=head1 DESCRIPTION
This L can be use to import RDF data from URLs, files or
input streams, SPARQL endpoints, and Linked Data Fragment endpoints.
By default an RDF graph is imported as single item in aREF format (see
L).
=head1 CONFIGURATION
=over
=item url
URL to retrieve RDF from.
=item type
RDF serialization type (e.g. C for RDF/Turtle).
=item base
Base URL. By default derived from the URL or file name.
=item ns
Use default namespace prefixes as provided by L to abbreviate
predicate and datatype URIs. Set to C<0> to disable abbreviating URIs.
Set to a specific date to get stable namespace prefix mappings.
=item triples
Import each RDF triple as one aREF subject map (default) or predicate map
(option C), if enabled. This is the most efficient way to
process large input files. All the processing can be streamed.
=item predicate_map
Import RDF as aREF predicate map, if possible.
=item file
=item fh
=item encoding
=item fix
Default configuration options of L.
=item sparql
The SPARQL query to be executed on the URL endpoint (currectly only SELECT is
supported). The query can be supplied as string or as filename. The importer
tries to automatically add missing PREFIX statements from the default namespace
prefixes.
=item sparql_result
Encoding of SPARQL result values. With C, query results are encoded in
aREF format, with URIs in C> and C> (no qNames) and literal nodes
appended by C<@> and optional language code. By default (value C), all
RDF nodes are simplfied to their literal form.
=item cache
Set to a true value to cache repeated URL responses in a L based backend.
=item cache_options
Provide the L based options for caching result sets. By default a memory store of
1MB size is used. This is equal to:
Catamandu::Importer::RDF->new( ...,
cache => 1,
cache_options => {
driver => 'Memory',
global => 1,
max_size => 1024*1024
});
=item speed
If set to a true value, then write RDF file processing speed on the STDERR as
number of triples parsed per second.
=back
=head1 METHODS
See L.
=head1 SEE ALSO
L, L
=encoding utf8
=cut
Fix 000755 001750 001750 0 13151247400 15330 5 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib/Catmandu aref_query.pm 100644 001750 001750 5201 13151247400 20166 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib/Catmandu/Fix package Catmandu::Fix::aref_query;
use Catmandu::Sane;
use Moo;
use Catmandu::Fix;
our $VERSION = '0.32';
with 'Catmandu::Fix::Base';
has query => (
is => 'ro',
coerce => sub { RDF::aREF::Query->new( query => $_[0] ) } # TODO: ns
);
has path => (
is => 'ro',
);
has subject => (
is => 'ro',
);
around 'BUILDARGS', sub {
my $orig = shift;
my $self = shift;
if (@_ == 3) {
$orig->($self, subject => $_[0], query => $_[1], path => $_[2] );
} elsif (@_ == 2) {
$orig->($self, query => $_[0], path => $_[1] );
} else {
$orig->($self, @_);
}
};
sub emit {
my ($self, $fixer) = @_;
my $subject = defined $self->subject ? $fixer->emit_string($self->subject) : 'undef';
my $path = $fixer->split_path($self->path);
my $query = $fixer->capture($self->query);
# TODO: replace/append/single-value mode
my $var = $fixer->var;
my $origin = $fixer->generate_var;
my $values = $fixer->generate_var;
my $perl = join "\n",
"my ${origin} = ${subject} // ${var}->{_uri} // ${var}->{_url};",
"my ${values} = [ ${query}->apply( ${var}, ${origin} ) ];",
$fixer->emit_create_path( $var, $path, sub {
my $var = shift;
join "\n", map { " $_" } '',
"if (is_array_ref(${var})) {",
" push \@{${var}}, \@{${values}};",
"} else {",
" if (defined ${var}) {",
" unshift \@{${values}}, ${var};",
" }",
" ${var} = \@{${values}} > 1 ? ${values} : ${values}->[0];",
"}"
;
});
# print $perl."\n";
return $perl;
}
1;
__END__
=head1 NAME
Catmandu::Fix::aref_query - copy values of RDF in aREF to a new field
=head1 SYNOPSIS
In Catmandu Fix language
aref_query( dc_title => title )
aref_query( query => 'dc_title', field => 'title' )
aref_query( 'http://example.org/subject', dc_title => title )
In Perl code
use Catmandu::Fix::aref_query as => 'my_query';
use RDF::aREF;
my $rdf = encode_aref("example.ttl");
my_query( $rdf, dc_title => 'title' );
=head1 DESCRIPTION
This L can be used to map values of imported RDF, given in
L structure
=head1 ARGUMENTS
=over
=item subject
Optional subject URI (first argument). By default, the fields C<_uri> and
C<_uri> are used.
=item query
aREF query expression (first or second argument)
=item path
Field name to map RDF data to (last argument). Existing values are also kept.
=back
=head1 SEE ALSO
Function C in L
=cut
rdf_ldf_statements.pm 100644 001750 001750 4320 13151247400 21674 0 ustar 00voj voj 000000 000000 Catmandu-RDF-0.32/lib/Catmandu/Fix package Catmandu::Fix::rdf_ldf_statements;
use Catmandu::Sane;
use Moo;
use RDF::LDF;
use Catmandu::Fix::Has;
has path => (fix_arg => 1);
has subject => (fix_opt => 1, default => sub { undef });
has predicate => (fix_opt => 1, default => sub { undef });
has url => (fix_opt => 1, default => sub { undef });
has client => (is => 'lazy');
with 'Catmandu::Fix::SimpleGetValue';
sub _build_client {
my ($self) = @_;
my $url = $self->url // 'http://data.linkeddatafragments.org/viaf';
RDF::LDF->new(url => $url);
}
sub emit_value {
my ($self,$var,$fixer) = @_;
my $subject_var = $fixer->capture($self->subject);
my $predicate_var = $fixer->capture($self->predicate);
my $client_var = $fixer->capture($self->client);
my $it = $fixer->generate_var;
my $st = $fixer->generate_var;
my $perl = <get_statements(${subject_var},${predicate_var},${var});
if (${it}) {
${var} = [];
while (my ${st} = ${it}->()) {
push \@{${var}} , ${st}->subject->uri;
}
}
}
EOF
$perl;
}
=head1 NAME
Catmandu::Fix::rdf_ldf_statements - lookup an object into a LDF endpoint
=head1 SYNOPSIS
# Replace a name with an array of matching VIAF records
# name: "\"Einstein, Albert, 1879-1955\""
rdf_ldf_statements(name,url:"http://data.linkedatafragments.org/viaf",predicate:"http://schema.org/alternateName")
# name:
# - http://viaf.org/viaf/75121530
=head1 DESCRIPTION
This L can be used to find at a Linked Data Fragments endpoint
all subject URIs for which the object has a specific value found at a path. E.g.
rdf_ldf_statements(name,url:"http://data.linkedatafragments.org/viaf")
means, search at the endpoint http://data.linkedatafragments.org/viaf all the
subjects for which the object is the value found in 'name', and replace the name value
with all the found subjects.
=head1 ARGUMENTS
=over
=item subject
Optional subject URI to be used in the LDF query
=item predicate
Optional predicate URI to be used in the LDF query
=item url
Required URL to the Linked Data Fragments endpoint
=back
=head1 SEE ALSO
L
=cut
1;