use of org.apache.lucene.document.TextField in project lucene-solr by apache.
the class TestJoinUtil method testSimple.
public void testSimple() throws Exception {
final String idField = "id";
final String toField = "productId";
Directory dir = newDirectory();
RandomIndexWriter w = new RandomIndexWriter(random(), dir, newIndexWriterConfig(new MockAnalyzer(random())).setMergePolicy(newLogMergePolicy()));
// 0
Document doc = new Document();
doc.add(new TextField("description", "random text", Field.Store.NO));
doc.add(new TextField("name", "name1", Field.Store.NO));
doc.add(new TextField(idField, "1", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("1")));
w.addDocument(doc);
// 1
doc = new Document();
doc.add(new TextField("price", "10.0", Field.Store.NO));
doc.add(new TextField(idField, "2", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("2")));
doc.add(new TextField(toField, "1", Field.Store.NO));
doc.add(new SortedDocValuesField(toField, new BytesRef("1")));
w.addDocument(doc);
// 2
doc = new Document();
doc.add(new TextField("price", "20.0", Field.Store.NO));
doc.add(new TextField(idField, "3", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("3")));
doc.add(new TextField(toField, "1", Field.Store.NO));
doc.add(new SortedDocValuesField(toField, new BytesRef("1")));
w.addDocument(doc);
// 3
doc = new Document();
doc.add(new TextField("description", "more random text", Field.Store.NO));
doc.add(new TextField("name", "name2", Field.Store.NO));
doc.add(new TextField(idField, "4", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("4")));
w.addDocument(doc);
w.commit();
// 4
doc = new Document();
doc.add(new TextField("price", "10.0", Field.Store.NO));
doc.add(new TextField(idField, "5", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("5")));
doc.add(new TextField(toField, "4", Field.Store.NO));
doc.add(new SortedDocValuesField(toField, new BytesRef("4")));
w.addDocument(doc);
// 5
doc = new Document();
doc.add(new TextField("price", "20.0", Field.Store.NO));
doc.add(new TextField(idField, "6", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("6")));
doc.add(new TextField(toField, "4", Field.Store.NO));
doc.add(new SortedDocValuesField(toField, new BytesRef("4")));
w.addDocument(doc);
IndexSearcher indexSearcher = new IndexSearcher(w.getReader());
w.close();
// Search for product
Query joinQuery = JoinUtil.createJoinQuery(idField, false, toField, new TermQuery(new Term("name", "name2")), indexSearcher, ScoreMode.None);
TopDocs result = indexSearcher.search(joinQuery, 10);
assertEquals(2, result.totalHits);
assertEquals(4, result.scoreDocs[0].doc);
assertEquals(5, result.scoreDocs[1].doc);
joinQuery = JoinUtil.createJoinQuery(idField, false, toField, new TermQuery(new Term("name", "name1")), indexSearcher, ScoreMode.None);
result = indexSearcher.search(joinQuery, 10);
assertEquals(2, result.totalHits);
assertEquals(1, result.scoreDocs[0].doc);
assertEquals(2, result.scoreDocs[1].doc);
// Search for offer
joinQuery = JoinUtil.createJoinQuery(toField, false, idField, new TermQuery(new Term("id", "5")), indexSearcher, ScoreMode.None);
result = indexSearcher.search(joinQuery, 10);
assertEquals(1, result.totalHits);
assertEquals(3, result.scoreDocs[0].doc);
indexSearcher.getIndexReader().close();
dir.close();
}
use of org.apache.lucene.document.TextField in project lucene-solr by apache.
the class TestMemoryIndex method testDocValuesDoNotAffectBoostPositionsOrOffset.
public void testDocValuesDoNotAffectBoostPositionsOrOffset() throws Exception {
Document doc = new Document();
doc.add(new BinaryDocValuesField("text", new BytesRef("quick brown fox")));
doc.add(new TextField("text", "quick brown fox", Field.Store.NO));
MemoryIndex mi = MemoryIndex.fromDocument(doc, analyzer, true, true);
LeafReader leafReader = mi.createSearcher().getIndexReader().leaves().get(0).reader();
TermsEnum tenum = leafReader.terms("text").iterator();
assertEquals("brown", tenum.next().utf8ToString());
PostingsEnum penum = tenum.postings(null, PostingsEnum.OFFSETS);
assertEquals(0, penum.nextDoc());
assertEquals(1, penum.freq());
assertEquals(1, penum.nextPosition());
assertEquals(6, penum.startOffset());
assertEquals(11, penum.endOffset());
assertEquals("fox", tenum.next().utf8ToString());
penum = tenum.postings(penum, PostingsEnum.OFFSETS);
assertEquals(0, penum.nextDoc());
assertEquals(1, penum.freq());
assertEquals(2, penum.nextPosition());
assertEquals(12, penum.startOffset());
assertEquals(15, penum.endOffset());
assertEquals("quick", tenum.next().utf8ToString());
penum = tenum.postings(penum, PostingsEnum.OFFSETS);
assertEquals(0, penum.nextDoc());
assertEquals(1, penum.freq());
assertEquals(0, penum.nextPosition());
assertEquals(0, penum.startOffset());
assertEquals(5, penum.endOffset());
BinaryDocValues binaryDocValues = leafReader.getBinaryDocValues("text");
assertEquals(0, binaryDocValues.nextDoc());
assertEquals("quick brown fox", binaryDocValues.binaryValue().utf8ToString());
}
use of org.apache.lucene.document.TextField in project lucene-solr by apache.
the class TestJoinUtil method testInsideBooleanQuery.
/** LUCENE-5487: verify a join query inside a SHOULD BQ
* will still use the join query's optimized BulkScorers */
public void testInsideBooleanQuery() throws Exception {
final String idField = "id";
final String toField = "productId";
Directory dir = newDirectory();
RandomIndexWriter w = new RandomIndexWriter(random(), dir, newIndexWriterConfig(new MockAnalyzer(random())).setMergePolicy(newLogMergePolicy()));
// 0
Document doc = new Document();
doc.add(new TextField("description", "random text", Field.Store.NO));
doc.add(new TextField("name", "name1", Field.Store.NO));
doc.add(new TextField(idField, "7", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("7")));
w.addDocument(doc);
// 1
doc = new Document();
doc.add(new TextField("price", "10.0", Field.Store.NO));
doc.add(new TextField(idField, "2", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("2")));
doc.add(new TextField(toField, "7", Field.Store.NO));
w.addDocument(doc);
// 2
doc = new Document();
doc.add(new TextField("price", "20.0", Field.Store.NO));
doc.add(new TextField(idField, "3", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("3")));
doc.add(new TextField(toField, "7", Field.Store.NO));
w.addDocument(doc);
// 3
doc = new Document();
doc.add(new TextField("description", "more random text", Field.Store.NO));
doc.add(new TextField("name", "name2", Field.Store.NO));
doc.add(new TextField(idField, "0", Field.Store.NO));
w.addDocument(doc);
w.commit();
// 4
doc = new Document();
doc.add(new TextField("price", "10.0", Field.Store.NO));
doc.add(new TextField(idField, "5", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("5")));
doc.add(new TextField(toField, "0", Field.Store.NO));
w.addDocument(doc);
// 5
doc = new Document();
doc.add(new TextField("price", "20.0", Field.Store.NO));
doc.add(new TextField(idField, "6", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("6")));
doc.add(new TextField(toField, "0", Field.Store.NO));
w.addDocument(doc);
w.forceMerge(1);
IndexSearcher indexSearcher = new IndexSearcher(w.getReader());
w.close();
// Search for product
Query joinQuery = JoinUtil.createJoinQuery(idField, false, toField, new TermQuery(new Term("description", "random")), indexSearcher, ScoreMode.Avg);
BooleanQuery.Builder bq = new BooleanQuery.Builder();
bq.add(joinQuery, BooleanClause.Occur.SHOULD);
bq.add(new TermQuery(new Term("id", "3")), BooleanClause.Occur.SHOULD);
indexSearcher.search(bq.build(), new SimpleCollector() {
boolean sawFive;
@Override
public void collect(int docID) {
// appending to head of linked list):
if (docID == 5) {
sawFive = true;
} else if (docID == 1) {
assertFalse("optimized bulkScorer was not used for join query embedded in boolean query!", sawFive);
}
}
@Override
public boolean needsScores() {
return false;
}
});
indexSearcher.getIndexReader().close();
dir.close();
}
use of org.apache.lucene.document.TextField in project lucene-solr by apache.
the class TestJoinUtil method test300spartans.
void test300spartans(boolean multipleValues, ScoreMode scoreMode) throws Exception {
final String idField = "id";
final String toField = "productId";
Directory dir = newDirectory();
RandomIndexWriter w = new RandomIndexWriter(random(), dir, newIndexWriterConfig(new MockAnalyzer(random())).setMergePolicy(newLogMergePolicy()));
// 0
Document doc = new Document();
doc.add(new TextField("description", "random text", Field.Store.NO));
doc.add(new TextField("name", "name1", Field.Store.NO));
doc.add(new TextField(idField, "0", Field.Store.NO));
doc.add(new SortedDocValuesField(idField, new BytesRef("0")));
w.addDocument(doc);
doc = new Document();
doc.add(new TextField("price", "10.0", Field.Store.NO));
if (multipleValues) {
for (int i = 0; i < 300; i++) {
doc.add(new SortedSetDocValuesField(toField, new BytesRef("" + i)));
}
} else {
doc.add(new SortedDocValuesField(toField, new BytesRef("0")));
}
w.addDocument(doc);
IndexSearcher indexSearcher = new IndexSearcher(w.getReader());
w.close();
// Search for product
Query joinQuery = JoinUtil.createJoinQuery(toField, multipleValues, idField, new TermQuery(new Term("price", "10.0")), indexSearcher, scoreMode);
TopDocs result = indexSearcher.search(joinQuery, 10);
assertEquals(1, result.totalHits);
assertEquals(0, result.scoreDocs[0].doc);
indexSearcher.getIndexReader().close();
dir.close();
}
use of org.apache.lucene.document.TextField in project lucene-solr by apache.
the class TestMemoryIndex method testPointValuesDoNotAffectPositionsOrOffset.
public void testPointValuesDoNotAffectPositionsOrOffset() throws Exception {
MemoryIndex mi = new MemoryIndex(true, true);
mi.addField(new TextField("text", "quick brown fox", Field.Store.NO), analyzer);
mi.addField(new BinaryPoint("text", "quick".getBytes(StandardCharsets.UTF_8)), analyzer);
mi.addField(new BinaryPoint("text", "brown".getBytes(StandardCharsets.UTF_8)), analyzer);
LeafReader leafReader = mi.createSearcher().getIndexReader().leaves().get(0).reader();
TermsEnum tenum = leafReader.terms("text").iterator();
assertEquals("brown", tenum.next().utf8ToString());
PostingsEnum penum = tenum.postings(null, PostingsEnum.OFFSETS);
assertEquals(0, penum.nextDoc());
assertEquals(1, penum.freq());
assertEquals(1, penum.nextPosition());
assertEquals(6, penum.startOffset());
assertEquals(11, penum.endOffset());
assertEquals("fox", tenum.next().utf8ToString());
penum = tenum.postings(penum, PostingsEnum.OFFSETS);
assertEquals(0, penum.nextDoc());
assertEquals(1, penum.freq());
assertEquals(2, penum.nextPosition());
assertEquals(12, penum.startOffset());
assertEquals(15, penum.endOffset());
assertEquals("quick", tenum.next().utf8ToString());
penum = tenum.postings(penum, PostingsEnum.OFFSETS);
assertEquals(0, penum.nextDoc());
assertEquals(1, penum.freq());
assertEquals(0, penum.nextPosition());
assertEquals(0, penum.startOffset());
assertEquals(5, penum.endOffset());
IndexSearcher indexSearcher = mi.createSearcher();
assertEquals(1, indexSearcher.count(BinaryPoint.newExactQuery("text", "quick".getBytes(StandardCharsets.UTF_8))));
assertEquals(1, indexSearcher.count(BinaryPoint.newExactQuery("text", "brown".getBytes(StandardCharsets.UTF_8))));
assertEquals(0, indexSearcher.count(BinaryPoint.newExactQuery("text", "jumps".getBytes(StandardCharsets.UTF_8))));
}
Aggregations