Last active
July 5, 2019 02:36
-
-
Save dvcama/842b1aae9ef4a706239b to your computer and use it in GitHub Desktop.
virtuoso : export all graphs (triple dump) - virtuoso 6
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CREATE PROCEDURE dump_graphs | |
( IN dir VARCHAR := '{WRITE HERE YOUR EXPORT PATH (allowed dir in virtuoso.ini)}' , | |
IN file_length_limit INTEGER := 10000000000 | |
) | |
{ | |
DECLARE inx INT; | |
inx := 1; | |
SET ISOLATION = 'uncommitted'; | |
FOR ( SELECT * | |
FROM ( SPARQL DEFINE input:storage "" | |
SELECT DISTINCT ?g { GRAPH ?g { ?s ?p ?o } . | |
FILTER ( ?g != virtrdf: ) | |
} | |
) AS sub OPTION ( LOOP )) DO | |
{ | |
dbg_printf ('about to dump %s',"g"); | |
dump_one_graph ( "g", | |
sprintf ('%s/graph%06d_', dir, inx), | |
file_length_limit | |
); | |
dbg_printf ('dump done %s',"g"); | |
inx := inx + 1; | |
} | |
} | |
; | |
CREATE PROCEDURE dump_one_graph | |
( IN srcgraph VARCHAR , | |
IN out_file VARCHAR , | |
IN file_length_limit INTEGER := 1000000000 | |
) | |
{ | |
DECLARE file_name varchar; | |
DECLARE env, ses 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; | |
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, 0, 0); | |
ses := string_output (); | |
FOR (SELECT * FROM ( SPARQL DEFINE input:storage "" | |
SELECT ?s ?p ?o { GRAPH `iri(?:srcgraph)` { ?s ?p ?o } } | |
) AS sub OPTION (LOOP)) DO | |
{ | |
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, 0, 0); | |
} | |
ELSE | |
string_to_file (file_name, ses, -1); | |
ses := string_output (); | |
} | |
} | |
IF (LENGTH (ses)) | |
{ | |
http (' .\n', ses); | |
string_to_file (file_name, ses, -1); | |
} | |
} | |
; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment