public override void BeforeClass()
{
base.BeforeClass();
directory = NewDirectory();
Analyzer analyzer = new AnalyzerAnonymousClass();
RandomIndexWriter writer = new RandomIndexWriter(
#if FEATURE_INSTANCE_TESTDATA_INITIALIZATION
this,
#endif
Random, directory, analyzer);
Documents.Document doc = new Documents.Document();
doc.Add(NewTextField("field", "one two three four five", Field.Store.YES));
doc.Add(NewTextField("repeated", "this is a repeated field - first part", Field.Store.YES));
IIndexableField repeatedField = NewTextField("repeated", "second part of a repeated field", Field.Store.YES);
doc.Add(repeatedField);
doc.Add(NewTextField("palindrome", "one two three two one", Field.Store.YES));
writer.AddDocument(doc);
doc = new Documents.Document();
doc.Add(NewTextField("nonexist", "phrase exist notexist exist found", Field.Store.YES));
writer.AddDocument(doc);
doc = new Documents.Document();
doc.Add(NewTextField("nonexist", "phrase exist notexist exist found", Field.Store.YES));
writer.AddDocument(doc);
reader = writer.GetReader();
writer.Dispose();
searcher = NewSearcher(reader);
}
public virtual void TestCrossPlaneNormalization()
{
var analyzer = new AnalyzerAnonymousClass();
var num = 1000 * RandomMultiplier;
for (var i = 0; i < num; i++)
{
var s = TestUtil.RandomUnicodeString(Random);
var ts = analyzer.GetTokenStream("foo", s);
try
{
ts.Reset();
var offsetAtt = ts.AddAttribute <IOffsetAttribute>();
while (ts.IncrementToken())
{
var highlightedText = s.Substring(offsetAtt.StartOffset, offsetAtt.EndOffset - offsetAtt.StartOffset);
for (int j = 0, cp = 0; j < highlightedText.Length; j += Character.CharCount(cp))
{
cp = highlightedText.CodePointAt(j);
assertTrue("non-letter:" + cp.ToString("x"), Character.IsLetter(cp));
}
}
ts.End();
}
finally
{
IOUtils.DisposeWhileHandlingException(ts);
}
}
// just for fun
CheckRandomData(Random, analyzer, num);
}
public virtual void TestPositionIncrementGap()
{
Analyzer analyzer = new AnalyzerAnonymousClass();
IndexWriter writer = new IndexWriter(dir, NewIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
Document doc = new Document();
doc.Add(NewTextField("repeated", "repeated one", Field.Store.YES));
doc.Add(NewTextField("repeated", "repeated two", Field.Store.YES));
writer.AddDocument(doc);
writer.Commit();
SegmentCommitInfo info = writer.NewestSegment();
writer.Dispose();
SegmentReader reader = new SegmentReader(info, DirectoryReader.DEFAULT_TERMS_INDEX_DIVISOR, NewIOContext(Random));
DocsAndPositionsEnum termPositions = MultiFields.GetTermPositionsEnum(reader, MultiFields.GetLiveDocs(reader), "repeated", new BytesRef("repeated"));
Assert.IsTrue(termPositions.NextDoc() != DocIdSetIterator.NO_MORE_DOCS);
int freq = termPositions.Freq;
Assert.AreEqual(2, freq);
Assert.AreEqual(0, termPositions.NextPosition());
Assert.AreEqual(502, termPositions.NextPosition());
reader.Dispose();
}
internal virtual void AddDocs(Random random, Directory dir, int ndocs, string field, string val, int maxTF, float percentDocs)
{
Analyzer analyzer = new AnalyzerAnonymousClass(random, val, maxTF, percentDocs);
Document doc = new Document();
doc.Add(NewStringField(field, val, Field.Store.NO));
IndexWriter writer = new IndexWriter(dir, NewIndexWriterConfig(TEST_VERSION_CURRENT, analyzer).SetOpenMode(OpenMode.CREATE).SetMaxBufferedDocs(100).SetMergePolicy(NewLogMergePolicy(100)));
for (int i = 0; i < ndocs; i++)
{
writer.AddDocument(doc);
}
writer.ForceMerge(1);
writer.Dispose();
}
public virtual void TestSetPosition()
{
Analyzer analyzer = new AnalyzerAnonymousClass(this);
Directory store = NewDirectory();
RandomIndexWriter writer = new RandomIndexWriter(Random, store, analyzer);
Document d = new Document();
d.Add(NewTextField("field", "bogus", Field.Store.YES));
writer.AddDocument(d);
IndexReader reader = writer.GetReader();
writer.Dispose();
IndexSearcher searcher = NewSearcher(reader);
DocsAndPositionsEnum pos = MultiFields.GetTermPositionsEnum(searcher.IndexReader, MultiFields.GetLiveDocs(searcher.IndexReader), "field", new BytesRef("1"));
pos.NextDoc();
// first token should be at position 0
Assert.AreEqual(0, pos.NextPosition());
pos = MultiFields.GetTermPositionsEnum(searcher.IndexReader, MultiFields.GetLiveDocs(searcher.IndexReader), "field", new BytesRef("2"));
pos.NextDoc();
// second token should be at position 2
Assert.AreEqual(2, pos.NextPosition());
PhraseQuery q;
ScoreDoc[] hits;
q = new PhraseQuery();
q.Add(new Term("field", "1"));
q.Add(new Term("field", "2"));
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(0, hits.Length);
// same as previous, just specify positions explicitely.
q = new PhraseQuery();
q.Add(new Term("field", "1"), 0);
q.Add(new Term("field", "2"), 1);
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(0, hits.Length);
// specifying correct positions should find the phrase.
q = new PhraseQuery();
q.Add(new Term("field", "1"), 0);
q.Add(new Term("field", "2"), 2);
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(1, hits.Length);
q = new PhraseQuery();
q.Add(new Term("field", "2"));
q.Add(new Term("field", "3"));
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(1, hits.Length);
q = new PhraseQuery();
q.Add(new Term("field", "3"));
q.Add(new Term("field", "4"));
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(0, hits.Length);
// phrase query would find it when correct positions are specified.
q = new PhraseQuery();
q.Add(new Term("field", "3"), 0);
q.Add(new Term("field", "4"), 0);
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(1, hits.Length);
// phrase query should fail for non existing searched term
// even if there exist another searched terms in the same searched position.
q = new PhraseQuery();
q.Add(new Term("field", "3"), 0);
q.Add(new Term("field", "9"), 0);
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(0, hits.Length);
// multi-phrase query should succed for non existing searched term
// because there exist another searched terms in the same searched position.
MultiPhraseQuery mq = new MultiPhraseQuery();
mq.Add(new Term[] { new Term("field", "3"), new Term("field", "9") }, 0);
hits = searcher.Search(mq, null, 1000).ScoreDocs;
Assert.AreEqual(1, hits.Length);
q = new PhraseQuery();
q.Add(new Term("field", "2"));
q.Add(new Term("field", "4"));
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(1, hits.Length);
q = new PhraseQuery();
q.Add(new Term("field", "3"));
q.Add(new Term("field", "5"));
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(1, hits.Length);
q = new PhraseQuery();
q.Add(new Term("field", "4"));
q.Add(new Term("field", "5"));
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(1, hits.Length);
q = new PhraseQuery();
q.Add(new Term("field", "2"));
q.Add(new Term("field", "5"));
hits = searcher.Search(q, null, 1000).ScoreDocs;
Assert.AreEqual(0, hits.Length);
reader.Dispose();
store.Dispose();
}
