[redland-dev] Creating additional storage hashes
Jason Johnston
redland at lojjic.net
Sun Jun 15 16:14:31 BST 2003
Dave Beckett wrote:
>>So... is there a simple way to create a s2po hash? And, if not, is
>>there a difficult way to create it? ;-) I'm not opposed to modifying
>>the C source to accomplish what I need.
>
> Oh yes :)
>
> Let me enter tutorial mode.
>
> [snip fantastic tutorial]
Thanks so much for your detailed instructions, they were a great help!
From them, I was able to successfully create a s2po indexed hash. It
did take some extra work than you gave in your walkthrough to make
find_statements use the new hash (there are several places where it
forks the codepath depending on what nodes are provided so I needed to
add a fork), but luckily there was already code for the optional p2so
hash so I copied that everywhere it appeared. It appeared to work when
I tested find_statements with only the subject node known on the new set
of BDB hashes.
However, when I tried repeating the find_statements call over a list of
several subject nodes, it fails. Sometimes I just get "Segmentation
fault", and the most detailed error I've gotten is:
rdf_node.c:381:librdf_node_from_node: fatal error: Do not know how to
copy node type 0
I'm at a loss where to begin tracking down what's going wrong, perhaps
I'm missing something or there's another part of the library that
expects one of the three normal hashes? It just seems strange that it
can work once or twice and fail after that. I can send you the
particular files and scripts I'm using via your personal email if it
would help track it down.
Thanks again for your assistance.
--Jason Johnston
--------------------------------------------------
Here's the patch I'm using (sorry if it wraps, I can send it to you
separately if you need):
diff -u -r1.49 rdf_storage_hashes.c
--- librdf/rdf_storage_hashes.c 15 Apr 2003 22:26:13 -0000 1.49
+++ librdf/rdf_storage_hashes.c 16 May 2003 02:19:04 -0000
@@ -52,10 +52,13 @@
{"po2s",
LIBRDF_STATEMENT_PREDICATE|LIBRDF_STATEMENT_OBJECT,
LIBRDF_STATEMENT_SUBJECT}, /* For 'get sources' */
- {"so2p",
+ {"so2p",
LIBRDF_STATEMENT_SUBJECT|LIBRDF_STATEMENT_OBJECT,
LIBRDF_STATEMENT_PREDICATE}, /* For 'get arcs' */
- {"p2so",
+ {"s2po",
+ LIBRDF_STATEMENT_SUBJECT,
+ LIBRDF_STATEMENT_PREDICATE|LIBRDF_STATEMENT_OBJECT}, /* For '(s, ?,
?)' */
+ {"p2so",
LIBRDF_STATEMENT_PREDICATE,
LIBRDF_STATEMENT_SUBJECT|LIBRDF_STATEMENT_OBJECT}, /* For '(?, p,
?)' */
{"contexts",
@@ -107,6 +110,7 @@
int targets_index;
int p2so_index;
+ int s2po_index;
/* If this is non-0, contexts are being used */
int index_contexts;
@@ -244,7 +248,7 @@
context->options=options;
/* Work out the number of hashes for allocating stuff below */
- hash_count=3;
+ hash_count=4;
if((index_contexts=librdf_hash_get_as_boolean(options, "contexts"))<0)
index_contexts=0; /* default is no contexts */
@@ -278,7 +282,7 @@
return 1;
}
- for(i=0; i<3; i++) {
+ for(i=0; i<4; i++) {
status=librdf_storage_hashes_register(storage, name,
&librdf_storage_hashes_descriptions[i]);
if(status)
@@ -299,6 +303,7 @@
context->arcs_index= -1;
context->targets_index= -1;
context->p2so_index= -1;
+ context->s2po_index= -1;
/* and index for contexts (no key or value fields) */
context->contexts_index= -1;
@@ -325,6 +330,9 @@
} else if(key_fields == LIBRDF_STATEMENT_PREDICATE &&
value_fields ==
(LIBRDF_STATEMENT_SUBJECT|LIBRDF_STATEMENT_OBJECT)) {
context->p2so_index=i;
+ } else if(key_fields == LIBRDF_STATEMENT_SUBJECT &&
+ value_fields ==
(LIBRDF_STATEMENT_PREDICATE|LIBRDF_STATEMENT_OBJECT)) {
+ context->s2po_index=i;
} else if(!key_fields || !value_fields) {
context->contexts_index=i;
}
@@ -984,6 +992,16 @@
context->p2so_index,
librdf_statement_get_predicate(statement),
LIBRDF_STATEMENT_SUBJECT|LIBRDF_STATEMENT_OBJECT);
+ } else if(librdf_statement_get_subject(statement) &&
+ !librdf_statement_get_predicate(statement) &&
+ !librdf_statement_get_object(statement) &&
+ context->s2po_index >= 0) {
+ /* (s ? ?) -> (s p o) wanted */
+ stream=librdf_storage_hashes_serialise_common(storage,
+ context->s2po_index,
+
librdf_statement_get_subject(statement),
+
LIBRDF_STATEMENT_PREDICATE|LIBRDF_STATEMENT_OBJECT);
+
} else {
statement=librdf_new_statement_from_statement(statement);
if(!statement)
@@ -1089,13 +1107,20 @@
librdf_free_node(node);
break;
+ case (LIBRDF_STATEMENT_PREDICATE|LIBRDF_STATEMENT_OBJECT): /* s2po */
+ if((node=librdf_statement_get_predicate(&context->statement)))
+ librdf_free_node(node);
+ if((node=librdf_statement_get_object(&context->statement)))
+ librdf_free_node(node);
+ break;
+
case (LIBRDF_STATEMENT_SUBJECT|LIBRDF_STATEMENT_OBJECT): /* p2so */
if((node=librdf_statement_get_subject(&context->statement)))
librdf_free_node(node);
@@ -1124,6 +1149,17 @@
node=librdf_statement_get_object(&context->statement);
break;
+ case (LIBRDF_STATEMENT_PREDICATE|LIBRDF_STATEMENT_OBJECT): /* s2po */
+ /* fill in the only blank from the node stored in our context */
+ node=librdf_new_node_from_node(context->search_node);
+ if(!node)
+ return NULL;
+ librdf_statement_set_subject(&context->statement2, node);
+ librdf_statement_set_predicate(&context->statement2,
librdf_statement_get_predicate(&context->statement));
+ librdf_statement_set_object(&context->statement2,
librdf_statement_get_object(&context->statement));
+ return (void*)&context->statement2;
+ break;
+
case (LIBRDF_STATEMENT_SUBJECT|LIBRDF_STATEMENT_OBJECT): /* p2so */
librdf_statement_set_subject(&context->statement2,
librdf_statement_get_subject(&context->statement));
/* fill in the only blank from the node stored in our context */
@@ -1237,6 +1273,11 @@
librdf_statement_set_predicate(&icontext->statement, node2);
break;
+ case (LIBRDF_STATEMENT_PREDICATE|LIBRDF_STATEMENT_OBJECT): /* s2po */
+ icontext->search_node=librdf_new_node_from_node(node1);
+ librdf_statement_set_subject(&icontext->statement, node1);
+ break;
+
case (LIBRDF_STATEMENT_SUBJECT|LIBRDF_STATEMENT_OBJECT): /* p2so */
icontext->search_node=librdf_new_node_from_node(node1);
librdf_statement_set_predicate(&icontext->statement, node1);
More information about the redland-dev
mailing list