use of org.apache.lucene.search.DisjunctionMaxQuery in project lucene-solr by apache.
the class TestClassicSimilarity method testDMQHit.
public void testDMQHit() throws IOException {
Query query = new DisjunctionMaxQuery(Arrays.asList(new TermQuery(new Term("test", "hit"))), 0);
TopDocs topDocs = indexSearcher.search(query, 1);
assertEquals(1, topDocs.totalHits);
assertEquals(1, topDocs.scoreDocs.length);
assertTrue(topDocs.scoreDocs[0].score != 0);
}
use of org.apache.lucene.search.DisjunctionMaxQuery in project lucene-solr by apache.
the class WeightedSpanTermExtractor method extract.
/**
* Fills a <code>Map</code> with {@link WeightedSpanTerm}s using the terms from the supplied <code>Query</code>.
*
* @param query
* Query to extract Terms from
* @param terms
* Map to place created WeightedSpanTerms in
* @throws IOException If there is a low-level I/O error
*/
protected void extract(Query query, float boost, Map<String, WeightedSpanTerm> terms) throws IOException {
if (query instanceof BoostQuery) {
BoostQuery boostQuery = (BoostQuery) query;
extract(boostQuery.getQuery(), boost * boostQuery.getBoost(), terms);
} else if (query instanceof BooleanQuery) {
for (BooleanClause clause : (BooleanQuery) query) {
if (!clause.isProhibited()) {
extract(clause.getQuery(), boost, terms);
}
}
} else if (query instanceof PhraseQuery) {
PhraseQuery phraseQuery = ((PhraseQuery) query);
Term[] phraseQueryTerms = phraseQuery.getTerms();
if (phraseQueryTerms.length == 1) {
extractWeightedSpanTerms(terms, new SpanTermQuery(phraseQueryTerms[0]), boost);
} else {
SpanQuery[] clauses = new SpanQuery[phraseQueryTerms.length];
for (int i = 0; i < phraseQueryTerms.length; i++) {
clauses[i] = new SpanTermQuery(phraseQueryTerms[i]);
}
// sum position increments beyond 1
int positionGaps = 0;
int[] positions = phraseQuery.getPositions();
if (positions.length >= 2) {
// positions are in increasing order. max(0,...) is just a safeguard.
positionGaps = Math.max(0, positions[positions.length - 1] - positions[0] - positions.length + 1);
}
//if original slop is 0 then require inOrder
boolean inorder = (phraseQuery.getSlop() == 0);
SpanNearQuery sp = new SpanNearQuery(clauses, phraseQuery.getSlop() + positionGaps, inorder);
extractWeightedSpanTerms(terms, sp, boost);
}
} else if (query instanceof TermQuery || query instanceof SynonymQuery) {
extractWeightedTerms(terms, query, boost);
} else if (query instanceof SpanQuery) {
extractWeightedSpanTerms(terms, (SpanQuery) query, boost);
} else if (query instanceof ConstantScoreQuery) {
final Query q = ((ConstantScoreQuery) query).getQuery();
if (q != null) {
extract(q, boost, terms);
}
} else if (query instanceof CommonTermsQuery) {
// specialized since rewriting would change the result query
// this query is TermContext sensitive.
extractWeightedTerms(terms, query, boost);
} else if (query instanceof DisjunctionMaxQuery) {
for (Query clause : ((DisjunctionMaxQuery) query)) {
extract(clause, boost, terms);
}
} else if (query instanceof ToParentBlockJoinQuery) {
extract(((ToParentBlockJoinQuery) query).getChildQuery(), boost, terms);
} else if (query instanceof ToChildBlockJoinQuery) {
extract(((ToChildBlockJoinQuery) query).getParentQuery(), boost, terms);
} else if (query instanceof MultiPhraseQuery) {
final MultiPhraseQuery mpq = (MultiPhraseQuery) query;
final Term[][] termArrays = mpq.getTermArrays();
final int[] positions = mpq.getPositions();
if (positions.length > 0) {
int maxPosition = positions[positions.length - 1];
for (int i = 0; i < positions.length - 1; ++i) {
if (positions[i] > maxPosition) {
maxPosition = positions[i];
}
}
@SuppressWarnings({ "unchecked", "rawtypes" }) final List<SpanQuery>[] disjunctLists = new List[maxPosition + 1];
int distinctPositions = 0;
for (int i = 0; i < termArrays.length; ++i) {
final Term[] termArray = termArrays[i];
List<SpanQuery> disjuncts = disjunctLists[positions[i]];
if (disjuncts == null) {
disjuncts = (disjunctLists[positions[i]] = new ArrayList<>(termArray.length));
++distinctPositions;
}
for (Term aTermArray : termArray) {
disjuncts.add(new SpanTermQuery(aTermArray));
}
}
int positionGaps = 0;
int position = 0;
final SpanQuery[] clauses = new SpanQuery[distinctPositions];
for (List<SpanQuery> disjuncts : disjunctLists) {
if (disjuncts != null) {
clauses[position++] = new SpanOrQuery(disjuncts.toArray(new SpanQuery[disjuncts.size()]));
} else {
++positionGaps;
}
}
if (clauses.length == 1) {
extractWeightedSpanTerms(terms, clauses[0], boost);
} else {
final int slop = mpq.getSlop();
final boolean inorder = (slop == 0);
SpanNearQuery sp = new SpanNearQuery(clauses, slop + positionGaps, inorder);
extractWeightedSpanTerms(terms, sp, boost);
}
}
} else if (query instanceof MatchAllDocsQuery) {
//nothing
} else if (query instanceof CustomScoreQuery) {
extract(((CustomScoreQuery) query).getSubQuery(), boost, terms);
} else if (isQueryUnsupported(query.getClass())) {
// nothing
} else {
if (query instanceof MultiTermQuery && (!expandMultiTermQuery || !fieldNameComparator(((MultiTermQuery) query).getField()))) {
return;
}
Query origQuery = query;
final IndexReader reader = getLeafContext().reader();
Query rewritten;
if (query instanceof MultiTermQuery) {
rewritten = MultiTermQuery.SCORING_BOOLEAN_REWRITE.rewrite(reader, (MultiTermQuery) query);
} else {
rewritten = origQuery.rewrite(reader);
}
if (rewritten != origQuery) {
// only rewrite once and then flatten again - the rewritten query could have a special treatment
// if this method is overwritten in a subclass or above in the next recursion
extract(rewritten, boost, terms);
} else {
extractUnknownQuery(query, terms);
}
}
}
use of org.apache.lucene.search.DisjunctionMaxQuery in project lucene-solr by apache.
the class FieldQuery method flatten.
void flatten(Query sourceQuery, IndexReader reader, Collection<Query> flatQueries, float boost) throws IOException {
while (sourceQuery instanceof BoostQuery) {
BoostQuery bq = (BoostQuery) sourceQuery;
sourceQuery = bq.getQuery();
boost *= bq.getBoost();
}
if (sourceQuery instanceof BooleanQuery) {
BooleanQuery bq = (BooleanQuery) sourceQuery;
for (BooleanClause clause : bq) {
if (!clause.isProhibited()) {
flatten(clause.getQuery(), reader, flatQueries, boost);
}
}
} else if (sourceQuery instanceof DisjunctionMaxQuery) {
DisjunctionMaxQuery dmq = (DisjunctionMaxQuery) sourceQuery;
for (Query query : dmq) {
flatten(query, reader, flatQueries, boost);
}
} else if (sourceQuery instanceof TermQuery) {
if (boost != 1f) {
sourceQuery = new BoostQuery(sourceQuery, boost);
}
if (!flatQueries.contains(sourceQuery))
flatQueries.add(sourceQuery);
} else if (sourceQuery instanceof SynonymQuery) {
SynonymQuery synQuery = (SynonymQuery) sourceQuery;
for (Term term : synQuery.getTerms()) {
flatten(new TermQuery(term), reader, flatQueries, boost);
}
} else if (sourceQuery instanceof PhraseQuery) {
PhraseQuery pq = (PhraseQuery) sourceQuery;
if (pq.getTerms().length == 1)
sourceQuery = new TermQuery(pq.getTerms()[0]);
if (boost != 1f) {
sourceQuery = new BoostQuery(sourceQuery, boost);
}
flatQueries.add(sourceQuery);
} else if (sourceQuery instanceof ConstantScoreQuery) {
final Query q = ((ConstantScoreQuery) sourceQuery).getQuery();
if (q != null) {
flatten(q, reader, flatQueries, boost);
}
} else if (sourceQuery instanceof CustomScoreQuery) {
final Query q = ((CustomScoreQuery) sourceQuery).getSubQuery();
if (q != null) {
flatten(q, reader, flatQueries, boost);
}
} else if (sourceQuery instanceof ToParentBlockJoinQuery) {
Query childQuery = ((ToParentBlockJoinQuery) sourceQuery).getChildQuery();
if (childQuery != null) {
flatten(childQuery, reader, flatQueries, boost);
}
} else if (reader != null) {
Query query = sourceQuery;
Query rewritten;
if (sourceQuery instanceof MultiTermQuery) {
rewritten = new MultiTermQuery.TopTermsScoringBooleanQueryRewrite(MAX_MTQ_TERMS).rewrite(reader, (MultiTermQuery) query);
} else {
rewritten = query.rewrite(reader);
}
if (rewritten != query) {
// only rewrite once and then flatten again - the rewritten query could have a speacial treatment
// if this method is overwritten in a subclass.
flatten(rewritten, reader, flatQueries, boost);
}
// if the query is already rewritten we discard it
}
// else discard queries
}
use of org.apache.lucene.search.DisjunctionMaxQuery in project lucene-solr by apache.
the class TestExtendedDismaxParser method containsClause.
private boolean containsClause(Query query, String field, String value, int boost, boolean fuzzy) {
float queryBoost = 1f;
if (query instanceof BoostQuery) {
BoostQuery bq = (BoostQuery) query;
query = bq.getQuery();
queryBoost = bq.getBoost();
}
if (query instanceof BooleanQuery) {
return containsClause((BooleanQuery) query, field, value, boost, fuzzy);
}
if (query instanceof DisjunctionMaxQuery) {
return containsClause((DisjunctionMaxQuery) query, field, value, boost, fuzzy);
}
if (boost != queryBoost) {
return false;
}
if (query instanceof TermQuery && !fuzzy) {
return containsClause((TermQuery) query, field, value);
}
if (query instanceof FuzzyQuery && fuzzy) {
return containsClause((FuzzyQuery) query, field, value);
}
return false;
}
use of org.apache.lucene.search.DisjunctionMaxQuery in project lucene-solr by apache.
the class SolrPluginUtilsTest method testDisjunctionMaxQueryParser.
@Test
public void testDisjunctionMaxQueryParser() throws Exception {
Query out;
String t;
SolrQueryRequest req = req("df", "text");
QParser qparser = QParser.getParser("hi", "dismax", req);
DisjunctionMaxQueryParser qp = new SolrPluginUtils.DisjunctionMaxQueryParser(qparser, req.getParams().get("df"));
qp.addAlias("hoss", 0.01f, SolrPluginUtils.parseFieldBoosts("title^2.0 title_stemmed name^1.2 subject^0.5"));
qp.addAlias("test", 0.01f, SolrPluginUtils.parseFieldBoosts("text^2.0"));
qp.addAlias("unused", 1.0f, SolrPluginUtils.parseFieldBoosts("subject^0.5 sind^1.5"));
/* first some sanity tests that don't use aliasing at all */
t = "XXXXXXXX";
out = qp.parse(t);
assertNotNull(t + " sanity test gave back null", out);
assertTrue(t + " sanity test isn't TermQuery: " + out.getClass(), out instanceof TermQuery);
assertEquals(t + " sanity test is wrong field", qp.getDefaultField(), ((TermQuery) out).getTerm().field());
t = "subject:XXXXXXXX";
out = qp.parse(t);
assertNotNull(t + " sanity test gave back null", out);
assertTrue(t + " sanity test isn't TermQuery: " + out.getClass(), out instanceof TermQuery);
assertEquals(t + " sanity test is wrong field", "subject", ((TermQuery) out).getTerm().field());
/* field has untokenzied type, so this should be a term anyway */
t = "sind:\"simple phrase\"";
out = qp.parse(t);
assertNotNull(t + " sanity test gave back null", out);
assertTrue(t + " sanity test isn't TermQuery: " + out.getClass(), out instanceof TermQuery);
assertEquals(t + " sanity test is wrong field", "sind", ((TermQuery) out).getTerm().field());
t = "subject:\"simple phrase\"";
out = qp.parse(t);
assertNotNull(t + " sanity test gave back null", out);
assertTrue(t + " sanity test isn't PhraseQuery: " + out.getClass(), out instanceof PhraseQuery);
assertEquals(t + " sanity test is wrong field", "subject", ((PhraseQuery) out).getTerms()[0].field());
/* now some tests that use aliasing */
/* basic usage of single "term" */
t = "hoss:XXXXXXXX";
out = qp.parse(t);
assertNotNull(t + " was null", out);
assertTrue(t + " wasn't a DMQ:" + out.getClass(), out instanceof DisjunctionMaxQuery);
assertEquals(t + " wrong number of clauses", 4, countItems(((DisjunctionMaxQuery) out).iterator()));
/* odd case, but should still work, DMQ of one clause */
t = "test:YYYYY";
out = qp.parse(t);
assertNotNull(t + " was null", out);
assertTrue(t + " wasn't a DMQ:" + out.getClass(), out instanceof DisjunctionMaxQuery);
assertEquals(t + " wrong number of clauses", 1, countItems(((DisjunctionMaxQuery) out).iterator()));
/* basic usage of multiple "terms" */
t = "hoss:XXXXXXXX test:YYYYY";
out = qp.parse(t);
assertNotNull(t + " was null", out);
assertTrue(t + " wasn't a boolean:" + out.getClass(), out instanceof BooleanQuery);
{
BooleanQuery bq = (BooleanQuery) out;
List<BooleanClause> clauses = new ArrayList<>(bq.clauses());
assertEquals(t + " wrong number of clauses", 2, clauses.size());
Query sub = clauses.get(0).getQuery();
assertTrue(t + " first wasn't a DMQ:" + sub.getClass(), sub instanceof DisjunctionMaxQuery);
assertEquals(t + " first had wrong number of clauses", 4, countItems(((DisjunctionMaxQuery) sub).iterator()));
sub = clauses.get(1).getQuery();
assertTrue(t + " second wasn't a DMQ:" + sub.getClass(), sub instanceof DisjunctionMaxQuery);
assertEquals(t + " second had wrong number of clauses", 1, countItems(((DisjunctionMaxQuery) sub).iterator()));
}
/* a phrase, and a term that is a stop word for some fields */
t = "hoss:\"XXXXXX YYYYY\" hoss:the";
out = qp.parse(t);
assertNotNull(t + " was null", out);
assertTrue(t + " wasn't a boolean:" + out.getClass(), out instanceof BooleanQuery);
{
BooleanQuery bq = (BooleanQuery) out;
List<BooleanClause> clauses = new ArrayList<>(bq.clauses());
assertEquals(t + " wrong number of clauses", 2, clauses.size());
Query sub = clauses.get(0).getQuery();
assertTrue(t + " first wasn't a DMQ:" + sub.getClass(), sub instanceof DisjunctionMaxQuery);
assertEquals(t + " first had wrong number of clauses", 4, countItems(((DisjunctionMaxQuery) sub).iterator()));
sub = clauses.get(1).getQuery();
assertTrue(t + " second wasn't a DMQ:" + sub.getClass(), sub instanceof DisjunctionMaxQuery);
assertEquals(t + " second had wrong number of clauses (stop words)", 2, countItems(((DisjunctionMaxQuery) sub).iterator()));
}
}
Aggregations