[
https://issues.apache.org/jira/browse/RYA-260?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15977552#comment-15977552
]
ASF GitHub Bot commented on RYA-260:
------------------------------------
Github user meiercaleb commented on a diff in the pull request:
https://github.com/apache/incubator-rya/pull/156#discussion_r112546328
--- Diff:
extras/rya.pcj.fluo/pcj.fluo.app/src/main/java/org/apache/rya/indexing/pcj/fluo/app/observers/TripleObserver.java
---
@@ -62,85 +66,113 @@ public ObservedColumn getObservedColumn() {
@Override
public void process(final TransactionBase tx, final Bytes brow, final
Column column) {
- //get string representation of triple
- String row = brow.toString();
- final String triple = IncUpdateDAO.getTripleString(brow);
- String visibility = tx.gets(row, FluoQueryColumns.TRIPLES, "");
-
- //get variable metadata for all SP in table
- RowScanner rscanner =
tx.scanner().over(Span.prefix(SP_PREFIX)).fetch(FluoQueryColumns.STATEMENT_PATTERN_VARIABLE_ORDER).byRow().build();
-
+ // Get string representation of triple.
+ final RyaStatement ryaStatement =
IncUpdateDAO.deserializeTriple(brow);
+ log.trace(
+ "Transaction ID: " + tx.getStartTimestamp() + "\n" +
+ "Rya Statement: " + ryaStatement + "\n");
- //see if triple matches conditions of any of the SP
+ final String triple = IncUpdateDAO.getTripleString(ryaStatement);
- for (ColumnScanner colScanner : rscanner) {
+ // Iterate over each of the Statement Patterns that are being
matched against.
+ final RowScanner spScanner = tx.scanner()
+ .over(Span.prefix(SP_PREFIX))
+
+ // Only fetch rows that have the pattern in them. There
will only be a single row with a pattern per SP.
+ .fetch(FluoQueryColumns.STATEMENT_PATTERN_PATTERN)
+ .byRow()
+ .build();
+
+ //see if triple matches conditions of any of the SP
+ for (final ColumnScanner colScanner : spScanner) {
+ // Get the Statement Pattern's node id.
final String spID = colScanner.getsRow();
- final StatementPatternMetadata spMetadata =
QUERY_DAO.readStatementPatternMetadata(tx, spID);
+ // Fetch its metadata.
+ final StatementPatternMetadata spMetadata =
QUERY_METADATA_DAO.readStatementPatternMetadata(tx, spID);
+
+ // Attempt to match the triple against the pattern.
final String pattern = spMetadata.getStatementPattern();
-
- for (ColumnValue cv : colScanner) {
- final String varOrders = cv.getsValue();
- final VariableOrder varOrder = new
VariableOrder(varOrders);
- final String bindingSetString = getBindingSet(triple,
pattern, varOrders);
-
- //Statement matches to a binding set
- if(bindingSetString.length() != 0) {
- final VisibilityBindingSet bindingSet = new
VisibilityBindingSet(
- CONVERTER.convert(bindingSetString, varOrder),
- visibility);
- final String valueString =
CONVERTER.convert(bindingSet, varOrder);
- tx.set(spID + NODEID_BS_DELIM + bindingSetString,
FluoQueryColumns.STATEMENT_PATTERN_BINDING_SET, valueString);
+ final VariableOrder varOrder = spMetadata.getVariableOrder();
+ final String bindingSetString = getBindingSet(triple, pattern,
varOrder);
+
+ // Statement matches to a binding set.
+ if(bindingSetString.length() != 0) {
+ // Fetch the triple's visibility label.
+ final String visibility = tx.gets(brow.toString(),
FluoQueryColumns.TRIPLES, "");
+
+ // Create the Row ID for the emitted binding set. It does
not contain visibilities.
+ final String row = spID + NODEID_BS_DELIM +
bindingSetString;
+ final Bytes rowBytes = Bytes.of(
row.getBytes(Charsets.UTF_8) );
+
+ // If this is a new Binding Set, then emit it.
+ if(tx.get(rowBytes,
FluoQueryColumns.STATEMENT_PATTERN_BINDING_SET) == null) {
--- End diff --
This is a worthwhile optimization.
> Add Aggregation support for Fluo/PCJ app
> ----------------------------------------
>
> Key: RYA-260
> URL: https://issues.apache.org/jira/browse/RYA-260
> Project: Rya
> Issue Type: New Feature
> Reporter: Andrew Smith
> Assignee: Kevin Chilton
>
> A user must be able to submit a PCJ query that contains the following
> aggregation functions from SPARQL:
> * Sum
> * Count
> * Average
> * Min
> * Max
> This task does not include any aggregations that appear within a GroupBy
> clause. We only need to support queries that have the aggregation within the
> SELECT section.
> For example, the following query should be processed:
> {code}
> SELECT (avg(?price) as ?averagePrice)
> {
> urn:BookA urn:price ?price.
> }
> {code}
> And the following query should not be processed because it requires a group
> by:
> {code}
> SELECT ?title (avg(?price) as ?averagePrice)
> {
> ?title urn:price ?price.
> }
> GROUP BY ?title
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
