Apache/lucene
1
0
Fork 0
mirror of https://github.com/apache/lucene.git synced 2025-02-20 08:56:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Added test for "no effect queries" compliancy in UnifiedHighlighter.

Browse Source
This commit is contained in:
Vincent Letard 2024-03-06 10:28:45 -05:00
parent 49db29e59f
commit 5b64e21572
No known key found for this signature in database
1 changed files with 51 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighter.java
View File

@ -38,11 +38,14 @@ import org.apache.lucene.document.FieldType;
import org.apache.lucene.index.IndexOptions;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queries.function.FunctionQuery;
import org.apache.lucene.queries.function.valuesource.ConstValueSource;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.DocIdSetIterator;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MatchAllDocsQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
@ -1662,4 +1665,52 @@ public class TestUnifiedHighlighter extends UnifiedHighlighterTestBase {
ir.close();
}
public void testPostingsOffsetStrategy() throws Exception {
if (this.fieldType.indexOptions() != IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS
|| this.fieldType.storeTermVectors())
// ignore if fieldType is not POSTINGS only
return;
RandomIndexWriter iw = newIndexOrderPreservingWriter();
Field body = new Field("body", "", fieldType);
Document doc = new Document();
doc.add(body);
body.setStringValue(
"This is a test. Just a test highlighting from postings. Feel free to ignore.");
iw.addDocument(doc);
body.setStringValue("Highlighting the first term. Hope it works.");
iw.addDocument(doc);
IndexReader ir = iw.getReader();
iw.close();
IndexSearcher searcher = newSearcher(ir);
UnifiedHighlighter highlighter = randomUnifiedHighlighter(searcher, indexAnalyzer);
Query query = new TermQuery(new Term("body", "highlighting"));
TopDocs topDocs = searcher.search(query, 10, Sort.INDEXORDER);
Set<Term> queryTerms = UnifiedHighlighter.extractTerms(query);
FieldHighlighter fieldHighlighter = highlighter.getFieldHighlighter("body", query, queryTerms, 1);
assertEquals(UnifiedHighlighter.OffsetSource.POSTINGS, fieldHighlighter.getOffsetSource()); // TermQuery is compatible with POSTINGS offset strategy
String[] snippets = highlighter.highlight("body", query, topDocs);
for (Query noEffectQuery: new Query[] {new MatchAllDocsQuery(), new FunctionQuery(new ConstValueSource(5))}) {
final Query booleanQuery = new BooleanQuery.Builder()
.add(noEffectQuery, BooleanClause.Occur.MUST)
.add(query, BooleanClause.Occur.MUST)
.build();
queryTerms = UnifiedHighlighter.extractTerms(booleanQuery);
fieldHighlighter = highlighter.getFieldHighlighter("body", booleanQuery, queryTerms, 1);
assertEquals(noEffectQuery.getClass().toString(), UnifiedHighlighter.OffsetSource.POSTINGS, fieldHighlighter.getOffsetSource()); // combining to a query with no effet (on highlighting) should lead to the same highlighter behavior
String[] bqSnippets = highlighter.highlight("body", query, topDocs);
assertArrayEquals(bqSnippets.toString(), snippets, bqSnippets); // ensuring that the combined query does produce the same output
}
ir.close();
}
}