// 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: SortingDocsAndPositionsEnum(int maxDoc, SortingDocsAndPositionsEnum reuse, final org.apache.lucene.index.DocsAndPositionsEnum in, Sorter.DocMap docMap, boolean storeOffsets) throws java.io.IOException
//JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
internal SortingDocsAndPositionsEnum(int maxDoc, SortingDocsAndPositionsEnum reuse, DocsAndPositionsEnum @in, Sorter.DocMap docMap, bool storeOffsets) : base(@in)
{
this.maxDoc = maxDoc;
this.storeOffsets = storeOffsets;
if (reuse != null)
{
docs = reuse.docs;
offsets = reuse.offsets;
payload = reuse.payload;
file = reuse.file;
if (reuse.maxDoc == maxDoc)
{
sorter = reuse.sorter;
}
else
{
sorter = new DocOffsetSorter(maxDoc);
}
}
else
{
docs = new int[32];
offsets = new long[32];
payload = new BytesRef(32);
file = new RAMFile();
sorter = new DocOffsetSorter(maxDoc);
}
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.store.IndexOutput out = new org.apache.lucene.store.RAMOutputStream(file);
IndexOutput @out = new RAMOutputStream(file);
int doc;
int i = 0;
while ((doc = @in.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS)
{
if (i == docs.Length)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int newLength = org.apache.lucene.util.ArrayUtil.oversize(i + 1, 4);
int newLength = ArrayUtil.oversize(i + 1, 4);
docs = Arrays.copyOf(docs, newLength);
offsets = Arrays.copyOf(offsets, newLength);
}
docs[i] = docMap.oldToNew(doc);
offsets[i] = @out.FilePointer;
addPositions(@in, @out);
i++;
}
upto = i;
sorter.reset(docs, offsets);
sorter.sort(0, upto);
@out.close();
this.postingInput = new RAMInputStream("", file);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: SortingDocsAndPositionsEnum(int maxDoc, SortingDocsAndPositionsEnum reuse, final org.apache.lucene.index.DocsAndPositionsEnum in, Sorter.DocMap docMap, boolean storeOffsets) throws java.io.IOException
//JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
internal SortingDocsAndPositionsEnum(int maxDoc, SortingDocsAndPositionsEnum reuse, DocsAndPositionsEnum @in, Sorter.DocMap docMap, bool storeOffsets)
: base(@in)
{
this.maxDoc = maxDoc;
this.storeOffsets = storeOffsets;
if (reuse != null)
{
docs = reuse.docs;
offsets = reuse.offsets;
payload = reuse.payload;
file = reuse.file;
if (reuse.maxDoc == maxDoc)
{
sorter = reuse.sorter;
}
else
{
sorter = new DocOffsetSorter(maxDoc);
}
}
else
{
docs = new int[32];
offsets = new long[32];
payload = new BytesRef(32);
file = new RAMFile();
sorter = new DocOffsetSorter(maxDoc);
}
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.store.IndexOutput out = new org.apache.lucene.store.RAMOutputStream(file);
IndexOutput @out = new RAMOutputStream(file);
int doc;
int i = 0;
while ((doc = @in.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS)
{
if (i == docs.Length)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int newLength = org.apache.lucene.util.ArrayUtil.oversize(i + 1, 4);
int newLength = ArrayUtil.oversize(i + 1, 4);
docs = Arrays.copyOf(docs, newLength);
offsets = Arrays.copyOf(offsets, newLength);
}
docs[i] = docMap.oldToNew(doc);
offsets[i] = @out.FilePointer;
addPositions(@in, @out);
i++;
}
upto = i;
sorter.reset(docs, offsets);
sorter.sort(0, upto);
@out.close();
this.postingInput = new RAMInputStream("", file);
}
/// <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();
}