Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-23 21:18:58 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Index query builder automatically ignores redundant predicates.

Browse Source
This commit is contained in:
Viktor Lofgren 2023-04-02 12:04:26 +02:00
parent 1e4157017d
commit 105d93cd85
2 changed files with 34 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
code/features-index/index-query/src/main/java/nu/marginalia/index/query/IndexQueryBuilder.java
View File

@ -2,6 +2,10 @@ package nu.marginalia.index.query;
import nu.marginalia.index.query.filter.QueryFilterStepIf;
/** Builds a query.
* <p />
* Note: The query builder may omit predicates that are deemed redundant.
*/
public interface IndexQueryBuilder {
/** Filters documents that also contain termId, within the full index.
*/

33
code/services-core/index-service/src/main/java/nu/marginalia/index/index/SearchIndexQueryBuilder.java
View File

@ -1,5 +1,6 @@
package nu.marginalia.index.index;
import gnu.trove.set.hash.TIntHashSet;
import nu.marginalia.index.priority.ReverseIndexPriorityReader;
import nu.marginalia.index.query.IndexQuery;
import nu.marginalia.index.query.IndexQueryBuilder;
@ -14,18 +15,39 @@ public class SearchIndexQueryBuilder implements IndexQueryBuilder {
private final ReverseIndexFullReader reverseIndexFullReader;
private final ReverseIndexPriorityReader reverseIndexPrioReader;
/* Keep track of already added include terms to avoid redundant checks.
*
* Warning: This may cause unexpected behavior if for example attempting to
* first check one index and then another for the same term. At the moment, that
* makes no sense, but in the future, that might be a thing one might want to do.
* */
private final TIntHashSet alreadyConsideredTerms = new TIntHashSet();
SearchIndexQueryBuilder(ReverseIndexFullReader reverseIndexFullReader,
ReverseIndexPriorityReader reverseIndexPrioReader,
IndexQuery query)
IndexQuery query, int... sourceTerms)
{
this.query = query;
this.reverseIndexFullReader = reverseIndexFullReader;
this.reverseIndexPrioReader = reverseIndexPrioReader;
alreadyConsideredTerms.addAll(sourceTerms);
}
public IndexQueryBuilder alsoFull(int termId) {
query.addInclusionFilter(reverseIndexFullReader.also(termId));
if (alreadyConsideredTerms.add(termId)) {
query.addInclusionFilter(reverseIndexFullReader.also(termId));
}
return this;
}
public IndexQueryBuilder alsoPrio(int termId) {
if (alreadyConsideredTerms.add(termId)) {
query.addInclusionFilter(reverseIndexPrioReader.also(termId));
}
return this;
}
@ -38,12 +60,17 @@ public class SearchIndexQueryBuilder implements IndexQueryBuilder {
step = QueryFilterStepIf.noPass();
}
else if (termIds.length == 1) {
step = reverseIndexPrioReader.also(termIds[0]);
return alsoPrio(termIds[0]);
}
else {
var steps = IntStream.of(termIds)
.filter(alreadyConsideredTerms::add)
.mapToObj(reverseIndexPrioReader::also)
.collect(Collectors.toList());
if (steps.isEmpty())
return this;
step = QueryFilterStepIf.anyOf(steps);
}