risdenk commented on code in PR #1184:
URL: https://github.com/apache/solr/pull/1184#discussion_r1029373164
##########
solr/core/src/java/org/apache/solr/search/SolrIndexSearcher.java:
##########
@@ -1190,38 +1192,52 @@ public ProcessedFilter getProcessedFilter(DocSet
setFilter, List<Query> queries)
}
Query posQuery = QueryUtils.getAbs(q);
- sets[end] = getPositiveDocSet(posQuery);
+ DocSet docSet = getPositiveDocSet(posQuery);
// Negative query if absolute value different from original
if (Objects.equals(q, posQuery)) {
- neg[end] = false;
- // keep track of the smallest positive set.
- // This optimization is only worth it if size() is cached, which it
would
- // be if we don't do any set operations.
- int sz = sets[end].size();
- if (sz < smallestCount) {
- smallestCount = sz;
- smallestIndex = end;
- answer = sets[end];
+ // keep track of the smallest positive set; use "answer" for this.
+ if (answer == null) {
+ answer = docSet;
+ continue;
}
+ // note: assume that size() is cached. It generally comes from the
cache, so should be.
+ if (docSet.size() < answer.size()) {
+ // swap answer & docSet so that answer is smallest
+ DocSet tmp = answer;
+ answer = docSet;
+ docSet = tmp;
+ }
+ neg[end] = false;
} else {
neg[end] = true;
}
+ sets[end++] = docSet;
+ } // end of queries
- end++;
- }
+ if (end > 0) {
+ // Are all of our normal cached filters negative?
+ if (answer == null) {
+ answer = getLiveDocSet();
+ }
- // Are all of our normal cached filters negative?
- if (end > 0 && answer == null) {
- answer = getLiveDocSet();
- }
+ // This optimizes for the case where we have more than 2 filters and
instead
+ // of copying the bitsets we make one mutable bitset. We should only do
this
+ // for BitDocSet since it clones the backing bitset for andNot and
intersection.
+ if (end > 1 && answer instanceof BitDocSet) {
+ answer = MutableBitDocSet.fromBitDocSet((BitDocSet) answer);
+ }
- // do negative queries first to shrink set size
- for (int i = 0; i < end; i++) {
- if (neg[i]) answer = answer.andNot(sets[i]);
- }
+ // do negative queries first to shrink set size
+ for (int i = 0; i < end; i++) {
+ if (neg[i]) answer = answer.andNot(sets[i]);
+ }
+
+ for (int i = 0; i < end; i++) {
+ if (!neg[i]) answer = answer.intersection(sets[i]);
+ }
- for (int i = 0; i < end; i++) {
- if (!neg[i] && i != smallestIndex) answer = answer.intersection(sets[i]);
+ // Make sure to keep answer as an immutable DocSet if we made it mutable
+ answer = MutableBitDocSet.unwrapIfMutable(answer);
}
// ignore "answer" if it simply matches all docs
Review Comment:
so in theory you are probably correct. in practice don't plan on tackling
this here :)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
