// LUCENE-1448
// TODO: instead of testing it this way, we can test
// with BaseTokenStreamTestCase now...
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception
public virtual void testEndOffsetPositionWithTeeSinkTokenFilter()
{
Directory dir = newDirectory();
Analyzer analyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false);
IndexWriter w = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
Document doc = new Document();
TokenStream tokenStream = analyzer.tokenStream("field", "abcd ");
TeeSinkTokenFilter tee = new TeeSinkTokenFilter(tokenStream);
TokenStream sink = tee.newSinkTokenStream();
FieldType ft = new FieldType(TextField.TYPE_NOT_STORED);
ft.StoreTermVectors = true;
ft.StoreTermVectorOffsets = true;
ft.StoreTermVectorPositions = true;
Field f1 = new Field("field", tee, ft);
Field f2 = new Field("field", sink, ft);
doc.add(f1);
doc.add(f2);
w.addDocument(doc);
w.close();
IndexReader r = DirectoryReader.open(dir);
Terms vector = r.getTermVectors(0).terms("field");
assertEquals(1, vector.size());
TermsEnum termsEnum = vector.iterator(null);
termsEnum.next();
assertEquals(2, termsEnum.totalTermFreq());
DocsAndPositionsEnum positions = termsEnum.docsAndPositions(null, null);
assertTrue(positions.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
assertEquals(2, positions.freq());
positions.nextPosition();
assertEquals(0, positions.startOffset());
assertEquals(4, positions.endOffset());
positions.nextPosition();
assertEquals(8, positions.startOffset());
assertEquals(12, positions.endOffset());
assertEquals(DocIdSetIterator.NO_MORE_DOCS, positions.nextDoc());
r.close();
dir.close();
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: private void addPositions(final org.apache.lucene.index.DocsAndPositionsEnum in, final org.apache.lucene.store.IndexOutput out) throws java.io.IOException
//JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
internal virtual void addPositions(DocsAndPositionsEnum @in, IndexOutput @out)
{
int freq = @in.freq();
@out.writeVInt(freq);
int previousPosition = 0;
int previousEndOffset = 0;
for (int i = 0; i < freq; i++)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int pos = in.nextPosition();
int pos = @in.nextPosition();
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.util.BytesRef payload = in.getPayload();
BytesRef payload = @in.Payload;
// The low-order bit of token is set only if there is a payload, the
// previous bits are the delta-encoded position.
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int token = (pos - previousPosition) << 1 | (payload == null ? 0 : 1);
int token = (pos - previousPosition) << 1 | (payload == null ? 0 : 1);
@out.writeVInt(token);
previousPosition = pos;
if (storeOffsets) // don't encode offsets if they are not stored
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int startOffset = in.startOffset();
int startOffset = @in.startOffset();
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int endOffset = in.endOffset();
int endOffset = @in.endOffset();
@out.writeVInt(startOffset - previousEndOffset);
@out.writeVInt(endOffset - startOffset);
previousEndOffset = endOffset;
}
if (payload != null)
{
@out.writeVInt(payload.length);
@out.writeBytes(payload.bytes, payload.offset, payload.length);
}
}
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: private void addPositions(final org.apache.lucene.index.DocsAndPositionsEnum in, final org.apache.lucene.store.IndexOutput out) throws java.io.IOException
//JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
internal virtual void addPositions(DocsAndPositionsEnum @in, IndexOutput @out)
{
int freq = @in.freq();
@out.writeVInt(freq);
int previousPosition = 0;
int previousEndOffset = 0;
for (int i = 0; i < freq; i++)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int pos = in.nextPosition();
int pos = @in.nextPosition();
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.util.BytesRef payload = in.getPayload();
BytesRef payload = @in.Payload;
// The low-order bit of token is set only if there is a payload, the
// previous bits are the delta-encoded position.
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int token = (pos - previousPosition) << 1 | (payload == null ? 0 : 1);
int token = (pos - previousPosition) << 1 | (payload == null ? 0 : 1);
@out.writeVInt(token);
previousPosition = pos;
if (storeOffsets) // don't encode offsets if they are not stored
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int startOffset = in.startOffset();
int startOffset = @in.startOffset();
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int endOffset = in.endOffset();
int endOffset = @in.endOffset();
@out.writeVInt(startOffset - previousEndOffset);
@out.writeVInt(endOffset - startOffset);
previousEndOffset = endOffset;
}
if (payload != null)
{
@out.writeVInt(payload.length);
@out.writeBytes(payload.bytes, payload.offset, payload.length);
}
}
}
/// <summary>
/// Make sure we skip wicked long terms.
/// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testWickedLongTerm() throws java.io.IOException
public virtual void testWickedLongTerm()
{
RAMDirectory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, new ClassicAnalyzer(TEST_VERSION_CURRENT)));
char[] chars = new char[IndexWriter.MAX_TERM_LENGTH];
Arrays.fill(chars, 'x');
Document doc = new Document();
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final String bigTerm = new String(chars);
string bigTerm = new string(chars);
// This produces a too-long term:
string contents = "abc xyz x" + bigTerm + " another term";
doc.add(new TextField("content", contents, Field.Store.NO));
writer.addDocument(doc);
// Make sure we can add another normal document
doc = new Document();
doc.add(new TextField("content", "abc bbb ccc", Field.Store.NO));
writer.addDocument(doc);
writer.close();
IndexReader reader = IndexReader.open(dir);
// Make sure all terms < max size were indexed
assertEquals(2, reader.docFreq(new Term("content", "abc")));
assertEquals(1, reader.docFreq(new Term("content", "bbb")));
assertEquals(1, reader.docFreq(new Term("content", "term")));
assertEquals(1, reader.docFreq(new Term("content", "another")));
// Make sure position is still incremented when
// massive term is skipped:
DocsAndPositionsEnum tps = MultiFields.getTermPositionsEnum(reader, MultiFields.getLiveDocs(reader), "content", new BytesRef("another"));
assertTrue(tps.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
assertEquals(1, tps.freq());
assertEquals(3, tps.nextPosition());
// Make sure the doc that has the massive term is in
// the index:
assertEquals("document with wicked long term should is not in the index!", 2, reader.numDocs());
reader.close();
// Make sure we can add a document with exactly the
// maximum length term, and search on that term:
doc = new Document();
doc.add(new TextField("content", bigTerm, Field.Store.NO));
ClassicAnalyzer sa = new ClassicAnalyzer(TEST_VERSION_CURRENT);
sa.MaxTokenLength = 100000;
writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, sa));
writer.addDocument(doc);
writer.close();
reader = IndexReader.open(dir);
assertEquals(1, reader.docFreq(new Term("content", bigTerm)));
reader.close();
dir.close();
}
