private void InitBlock(AnonymousClassAnalyzer1 enclosingInstance)
{
this.enclosingInstance = enclosingInstance;
termAtt = (TermAttribute)AddAttribute(typeof(TermAttribute));
payloadAtt = (PayloadAttribute)AddAttribute(typeof(PayloadAttribute));
posIncrAtt = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
}
private void InitBlock(AnonymousClassAnalyzer1 enclosingInstance)
{
this.enclosingInstance = enclosingInstance;
termAtt = (TermAttribute) AddAttribute(typeof(TermAttribute));
payloadAtt = (PayloadAttribute) AddAttribute(typeof(PayloadAttribute));
posIncrAtt = (PositionIncrementAttribute) AddAttribute(typeof(PositionIncrementAttribute));
}
private void InitBlock(AnonymousClassAnalyzer1 enclosingInstance)
{
this.enclosingInstance = enclosingInstance;
termAtt = AddAttribute<ITermAttribute>();
payloadAtt = AddAttribute<IPayloadAttribute>();
posIncrAtt = AddAttribute<IPositionIncrementAttribute>();
}
public virtual void TestTokenReuse()
{
Analyzer analyzer = new AnonymousClassAnalyzer1(this);
IndexWriter writer = new IndexWriter(dir, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("f1", "a 5 a a", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
writer.Flush();
SegmentInfo info = writer.NewestSegment();
writer.Close();
SegmentReader reader = SegmentReader.Get(info);
TermPositions termPositions = reader.TermPositions(new Term("f1", "a"));
Assert.IsTrue(termPositions.Next());
int freq = termPositions.Freq();
Assert.AreEqual(3, freq);
Assert.AreEqual(0, termPositions.NextPosition());
Assert.AreEqual(true, termPositions.IsPayloadAvailable());
Assert.AreEqual(6, termPositions.NextPosition());
Assert.AreEqual(false, termPositions.IsPayloadAvailable());
Assert.AreEqual(7, termPositions.NextPosition());
Assert.AreEqual(false, termPositions.IsPayloadAvailable());
}
private void InitBlock(AnonymousClassAnalyzer1 enclosingInstance)
{
this.enclosingInstance = enclosingInstance;
termAtt = AddAttribute <ITermAttribute>();
payloadAtt = AddAttribute <IPayloadAttribute>();
posIncrAtt = AddAttribute <IPositionIncrementAttribute>();
}
public virtual void TestTokenReuse()
{
Analyzer analyzer = new AnonymousClassAnalyzer1(this);
IndexWriter writer = new IndexWriter(dir, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("f1", "a 5 a a", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
writer.Flush();
SegmentInfo info = writer.NewestSegment();
writer.Close();
SegmentReader reader = SegmentReader.Get(info);
TermPositions termPositions = reader.TermPositions(new Term("f1", "a"));
Assert.IsTrue(termPositions.Next());
int freq = termPositions.Freq();
Assert.AreEqual(3, freq);
Assert.AreEqual(0, termPositions.NextPosition());
Assert.AreEqual(true, termPositions.IsPayloadAvailable());
Assert.AreEqual(6, termPositions.NextPosition());
Assert.AreEqual(false, termPositions.IsPayloadAvailable());
Assert.AreEqual(7, termPositions.NextPosition());
Assert.AreEqual(false, termPositions.IsPayloadAvailable());
}
internal AnonymousClassTokenFilter(AnonymousClassAnalyzer1 enclosingInstance, Lucene.Net.Analysis.TokenStream Param1):base(Param1)
{
InitBlock(enclosingInstance);
}
internal AnonymousClassTokenFilter(AnonymousClassAnalyzer1 enclosingInstance, Lucene.Net.Analysis.TokenStream Param1) : base(Param1)
{
InitBlock(enclosingInstance);
}
public virtual void TestDocumentsWriterExceptions()
{
Analyzer analyzer = new AnonymousClassAnalyzer1(this);
for (int i = 0; i < 2; i++)
{
MockRAMDirectory dir = new MockRAMDirectory();
IndexWriter writer = new IndexWriter(dir, analyzer);
//writer.setInfoStream(System.out);
Document doc = new Document();
doc.Add(new Field("contents", "here are some contents", Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
writer.AddDocument(doc);
writer.AddDocument(doc);
doc.Add(new Field("crash", "this should crash after 4 terms", Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
doc.Add(new Field("other", "this will not get indexed", Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
try
{
writer.AddDocument(doc);
Assert.Fail("did not hit expected exception");
}
catch (System.IO.IOException)
{
}
if (0 == i)
{
doc = new Document();
doc.Add(new Field("contents", "here are some contents", Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
writer.AddDocument(doc);
writer.AddDocument(doc);
}
writer.Close();
IndexReader reader = IndexReader.Open(dir);
int expected = 3 + (1 - i) * 2;
Assert.AreEqual(expected, reader.DocFreq(new Term("contents", "here")));
Assert.AreEqual(expected, reader.MaxDoc());
int numDel = 0;
for (int j = 0; j < reader.MaxDoc(); j++)
{
if (reader.IsDeleted(j))
numDel++;
else
reader.Document(j);
reader.GetTermFreqVectors(j);
}
reader.Close();
Assert.AreEqual(1, numDel);
writer = new IndexWriter(dir, analyzer);
writer.SetMaxBufferedDocs(10);
doc = new Document();
doc.Add(new Field("contents", "here are some contents", Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
for (int j = 0; j < 17; j++)
writer.AddDocument(doc);
writer.Optimize();
writer.Close();
reader = IndexReader.Open(dir);
expected = 19 + (1 - i) * 2;
Assert.AreEqual(expected, reader.DocFreq(new Term("contents", "here")));
Assert.AreEqual(expected, reader.MaxDoc());
numDel = 0;
for (int j = 0; j < reader.MaxDoc(); j++)
{
if (reader.IsDeleted(j))
numDel++;
else
reader.Document(j);
reader.GetTermFreqVectors(j);
}
reader.Close();
Assert.AreEqual(0, numDel);
dir.Close();
}
}
public virtual void TestSetPosition()
{
Analyzer analyzer = new AnonymousClassAnalyzer(this);
RAMDirectory store = new RAMDirectory();
IndexWriter writer = new IndexWriter(store, analyzer, true);
Document d = new Document();
d.Add(new Field("field", "bogus", Field.Store.YES, Field.Index.TOKENIZED));
writer.AddDocument(d);
writer.Optimize();
writer.Close();
IndexSearcher searcher = new IndexSearcher(store);
PhraseQuery q;
Hits hits;
q = new PhraseQuery();
q.Add(new Term("field", "1"));
q.Add(new Term("field", "2"));
hits = searcher.Search(q);
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);
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);
Assert.AreEqual(1, hits.Length());
q = new PhraseQuery();
q.Add(new Term("field", "2"));
q.Add(new Term("field", "3"));
hits = searcher.Search(q);
Assert.AreEqual(1, hits.Length());
q = new PhraseQuery();
q.Add(new Term("field", "3"));
q.Add(new Term("field", "4"));
hits = searcher.Search(q);
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);
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);
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);
Assert.AreEqual(1, hits.Length());
q = new PhraseQuery();
q.Add(new Term("field", "2"));
q.Add(new Term("field", "4"));
hits = searcher.Search(q);
Assert.AreEqual(1, hits.Length());
q = new PhraseQuery();
q.Add(new Term("field", "3"));
q.Add(new Term("field", "5"));
hits = searcher.Search(q);
Assert.AreEqual(1, hits.Length());
q = new PhraseQuery();
q.Add(new Term("field", "4"));
q.Add(new Term("field", "5"));
hits = searcher.Search(q);
Assert.AreEqual(1, hits.Length());
q = new PhraseQuery();
q.Add(new Term("field", "2"));
q.Add(new Term("field", "5"));
hits = searcher.Search(q);
Assert.AreEqual(0, hits.Length());
// analyzer to introduce stopwords and increment gaps
Analyzer stpa = new AnonymousClassAnalyzer1(this);
// should not find "1 2" because there is a gap of 1 in the index
Lucene.Net.QueryParsers.QueryParser qp = new Lucene.Net.QueryParsers.QueryParser("field", stpa);
q = (PhraseQuery) qp.Parse("\"1 2\"");
hits = searcher.Search(q);
Assert.AreEqual(0, hits.Length());
// omitted stop word cannot help because stop filter swallows the increments.
q = (PhraseQuery) qp.Parse("\"1 stop 2\"");
hits = searcher.Search(q);
Assert.AreEqual(0, hits.Length());
// query parser alone won't help, because stop filter swallows the increments.
qp.SetEnablePositionIncrements(true);
q = (PhraseQuery) qp.Parse("\"1 stop 2\"");
hits = searcher.Search(q);
Assert.AreEqual(0, hits.Length());
bool dflt = StopFilter.GetEnablePositionIncrementsDefault();
try
{
// stop filter alone won't help, because query parser swallows the increments.
qp.SetEnablePositionIncrements(false);
StopFilter.SetEnablePositionIncrementsDefault(true);
q = (PhraseQuery) qp.Parse("\"1 stop 2\"");
hits = searcher.Search(q);
Assert.AreEqual(0, hits.Length());
// when both qp qnd stopFilter propagate increments, we should find the doc.
qp.SetEnablePositionIncrements(true);
q = (PhraseQuery) qp.Parse("\"1 stop 2\"");
hits = searcher.Search(q);
Assert.AreEqual(1, hits.Length());
}
finally
{
StopFilter.SetEnablePositionIncrementsDefault(dflt);
}
}
private void InitBlock(AnonymousClassAnalyzer1 enclosingInstance)
{
this.enclosingInstance = enclosingInstance;
}
