I still haven't found the reason for the NPE in my post filter when it runs
against a sharded collection, so I'm posting my code in the hopes that a
seasoned Solr pro might notice something. I thought perhaps not treating the
doc values as multi doc values when indexes are segmented might have been
the issue. But I optimized my test collection to merge the segments and the
search fails in the same spot....
ERROR - 2016-08-10 09:03:20.249; [ShardTest1 shard1_0 core_node3
ShardTest1_shard1_0_replica1] org.apache.solr.common.SolrException;
null:java.lang.NullPointerException
at
org.apache.solr.handler.component.QueryComponent.returnFields(QueryComponent.java:1305)
at
org.apache.solr.handler.component.QueryComponent.handleRegularResponses(QueryComponent.java:758)
at
org.apache.solr.handler.component.QueryComponent.handleResponses(QueryComponent.java:729)
at
org.apache.solr.handler.component.SearchHandler.handleRequestBody(SearchHandler.java:388)
public class DocumentCollapsingCollector extends DelegatingCollector {
static final String AGGR_STATS = "AggregationStats";
static final String SORT_BY_SCORE = "SortByScore";
private static final String TOTAL_DOCS_STAT = "totalDocCount";
private final SolrQueryRequest req;
private final ResponseBuilder rb;
private final LeafReaderContext[] contexts;
private final FixedBitSet collapsedSet;
private final List<SortedDocValues> fieldValues;
private final NumericDocValues spendValues;
private final Map<FieldOrdinals, AggregationStats> aggregatedDocs;
private int docBase;
private final int maxDoc;
private final int numberOfFields;
private int totalDocs;
private final SearchPreProcessor.SortBy sortBy;
DocumentCollapsingCollector(int maxDoc, int segments,
List<SortedDocValues>
docValues, NumericDocValues spendValues,
SolrQueryRequest req, ResponseBuilder rb) {
aggregatedDocs = new HashMap<>();
this.maxDoc = maxDoc;
contexts = new LeafReaderContext[segments];
collapsedSet = new FixedBitSet(maxDoc);
fieldValues = docValues;
numberOfFields = docValues.size();
this.spendValues = spendValues;
this.req = req;
this.rb = rb;
sortBy = (SearchPreProcessor.SortBy)
req.getContext().get(SORT_BY_SCORE);
}
@Override
public void collect(int doc) throws IOException {
int globalDoc = doc + docBase;
int[] ords = new int[numberOfFields];
int i=0;
for (SortedDocValues vals : fieldValues) {
ords[i++] = vals.getOrd(globalDoc);
}
FieldOrdinals ordinals = new FieldOrdinals(ords);
AggregationStats stats = aggregatedDocs.get(ordinals);
if (stats != null) {
stats.bumpCount();
stats.addSpend(Double.longBitsToDouble(spendValues.get(globalDoc)));
} else {
aggregatedDocs.put(ordinals, new
AggregationStats(globalDoc,
Double.longBitsToDouble(spendValues.get(globalDoc))));
}
totalDocs++;
}
@Override
public boolean needsScores() {
return sortBy != null;
}
@Override
protected void doSetNextReader(LeafReaderContext context) throws
IOException {
contexts[context.ord] = context;
docBase = context.docBase;
}
@Override
public void finish() throws IOException {
if (contexts.length == 0) {
return;
}
for (AggregationStats docStats : aggregatedDocs.values()) {
collapsedSet.set(docStats.getDocId());
}
// saving the stats to the request context so that a doc
transformer can
pick them up
AggregationStatsArray stats = new
AggregationStatsArray(aggregatedDocs.values());
ImmutableSparseArray<AggregationStats> statsArray = new
ImmutableSparseArray<AggregationStats>(stats);
req.getContext().put(AGGR_STATS, statsArray);
int currentContext = 0;
int currentDocBase = 0;
int nextDocBase = currentContext+1 < contexts.length ?
contexts[currentContext+1].docBase : maxDoc;
super.leafDelegate =
super.delegate.getLeafCollector(contexts[currentContext]);
DummyScorer dummy = new DummyScorer();
super.leafDelegate.setScorer(dummy);
BitSetIterator it = new BitSetIterator(collapsedSet, 0L);
int docId = -1;
while ((docId = it.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS)
{
if (SearchPreProcessor.SortBy.COUNT.equals(sortBy)) {
dummy.score = statsArray.get(docId).getCount();
} else if
(SearchPreProcessor.SortBy.SPEND.equals(sortBy)) {
dummy.score = (float)
statsArray.get(docId).getSpend();
}
while (docId >= nextDocBase) {
currentContext++;
currentDocBase =
contexts[currentContext].docBase;
nextDocBase = currentContext+1 <
contexts.length ?
contexts[currentContext+1].docBase : maxDoc;
super.leafDelegate =
super.delegate.getLeafCollector(contexts[currentContext]);
super.leafDelegate.setScorer(dummy);
}
int contextDoc = docId-currentDocBase;
dummy.docId = contextDoc;
super.leafDelegate.collect(contextDoc);
}
rb.rsp.add(TOTAL_DOCS_STAT, Integer.valueOf(totalDocs));
if (super.delegate instanceof DelegatingCollector) {
((DelegatingCollector) super.delegate).finish();
}
}
private class FieldOrdinals {
private final int[] ords;
FieldOrdinals(int[] ords) {
this.ords = ords;
}
int[] getOrds() {
return ords;
}
@Override
public int hashCode() {
return Arrays.hashCode(ords);
}
@Override
public boolean equals(Object obj) {
return Arrays.equals(ords,
((FieldOrdinals)obj).getOrds());
}
}
private class DummyScorer extends Scorer {
float score;
int docId;
DummyScorer() {
super(null);
}
@Override
public float score() throws IOException {
return score;
}
@Override
public int freq() throws IOException {
return 0;
}
@Override
public int advance(int i) throws IOException {
return -1;
}
@Override
public long cost() {
return 0;
}
@Override
public int docID() {
return docId;
}
@Override
public int nextDoc() throws IOException {
return 0;
}
}
}
--
View this message in context:
http://lucene.472066.n3.nabble.com/AnalyticsQuery-fails-on-a-sharded-collection-tp4289274p4291180.html
Sent from the Solr - User mailing list archive at Nabble.com.
