---++Virtuoso RDF Graph Dump based on Inference Rule Utility
The graph_dump procedure below can be used to export triples from Named RDF Graphs in N3 triple format to file, filtering based on the specified Inference rule and predicate/property URI:
Params:
* in srcgraph varchar - source graph
* in format varchar - output format N3 is supported for now
* in inf varchar - inference name
* in pred varchar - predicate to filter
* in out_file varchar - output file prefix
* in file_llength_llimit := 1000000000 - maximum size of files data is dumped in
create procedure graph_dump (in srcgraph varchar, in format varchar := 'N3', in inf varchar := null, in pred varchar := null,
in out_file varchar, in file_length_limit integer := 1000000000)
{
declare qr, file_name varchar;
declare env, ses, meta, data, h any;
declare ses_len, max_ses_len, file_len, file_idx integer;
set isolation = 'uncommitted';
max_ses_len := 10000000;
file_len := 0;
file_idx := 1;
if (format <> 'N3')
signal ('22023', 'The output format is not supported');
file_name := sprintf ('%s%06d.ttl', out_file, file_idx);
string_to_file (file_name || '.graph', srcgraph, -2);
string_to_file (file_name, sprintf ('# Dump of graph <%s>, as of %s\n', srcgraph, cast (now() as varchar)), -2);
--env := vector (dict_new (16000), 0, '', '', '', 0, 0);
env := vector (dict_new (16000), 0, '', '', '', 0, 0, 0, 0);
ses := string_output ();
if (inf is not null)
inf := sprintf ('define input:inference "%s"', inf);
else
inf := '';
if (pred is not null)
pred := sprintf ('<%s>', pred);
else
pred := '?p';
qr := sprintf ('select * from (sparql define input:storage "" %s select ?s %s as ?p ?o { graph <%S> { ?s %s ?o } } ) as sub option (loop)',
inf, pred, srcgraph, pred);
exec (qr, null, null, vector (), 0, null, null, h);
while (0 = exec_next (h, null, null, data))
{
declare "s", "p", "o" any;
"s" := data[0];
"p" := data[1];
"o" := data[2];
http_ttl_triple (env, "s", "p", "o", ses);
ses_len := length (ses);
if (ses_len > max_ses_len)
{
file_len := file_len + ses_len;
if (file_len > file_length_limit)
{
http (' .\n', ses);
string_to_file (file_name, ses, -1);
file_len := 0;
file_idx := file_idx + 1;
file_name := sprintf ('%s%06d.ttl', out_file, file_idx);
string_to_file (file_name, sprintf ('# Dump of graph <%s>, as of %s (part %d)\n', srcgraph, cast (now() as varchar), file_idx), -2);
env := vector (dict_new (16000), 0, '', '', '', 0, 0);
}
else
string_to_file (file_name, ses, -1);
ses := string_output ();
}
}
exec_close (h);
if (length (ses))
{
http (' .\n', ses);
string_to_file (file_name, ses, -1);
}
}
;
---+++Example
[[http://www.ontologyportal.org/][SUMO ontology]] was recently mapped to DBpedia by its creators using RDF/XML and loaded into the [[http://dbpedia.org/sparql][DBpedia SPARQL Endpoint]].
Issues:
* To add to DBpedia data sets, N3 is preferred format.
* Cross Links needed i.e. mapping <#dbpediaURI> owl:sameAs <#SumoURI> in addition to the authors links which are solely, <#SumoURI> owl:sameAs <#DBpediaURI>
Solution:
* Make an inference rules graph where owl:sameAs is explicitly asserted to be an owl:SymmetricalProperty type.
ttlp('owl:sameAs a owl:SymmetricalProperty .', '', 'rule_graph');
* Make a Named Rule that's associated the the Named Graph in step above.
rdfs_rule_set ('sas', 'rule_graph');
* Run the graph_dump export procedure with the inference rule parameter and predicate/property filter option to export the data to file, in N3 format and with necessary owl:sameas cross links.
graph_dump ('http://www.ontologyportal.org/SUMO#', 'N3', 'sas', 'http://www.w3.org/2002/07/owl#sameAs', 'sumo_');