/// <summary>
/// Set up a new index in RAM with three test phrases and the supplied Analyzer.
/// </summary>
/// <exception cref="Exception"> if an error occurs with index writer or searcher </exception>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public void setUp() throws Exception
public override void setUp()
{
base.setUp();
analyzer = new ShingleAnalyzerWrapper(new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false), 2);
directory = newDirectory();
IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
Document doc;
doc = new Document();
doc.add(new TextField("content", "please divide this sentence into shingles", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("content", "just another test sentence", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("content", "a sentence which contains no test", Field.Store.YES));
writer.addDocument(doc);
writer.close();
reader = DirectoryReader.open(directory);
searcher = newSearcher(reader);
}
/// <summary>
/// Set up a new index in RAM with three test phrases and the supplied Analyzer.
/// </summary>
/// <exception cref="Exception"> if an error occurs with index writer or searcher </exception>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public void setUp() throws Exception
public override void setUp()
{
base.setUp();
analyzer = new ShingleAnalyzerWrapper(new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false), 2);
directory = newDirectory();
IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
Document doc;
doc = new Document();
doc.add(new TextField("content", "please divide this sentence into shingles", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("content", "just another test sentence", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("content", "a sentence which contains no test", Field.Store.YES));
writer.addDocument(doc);
writer.close();
reader = DirectoryReader.open(directory);
searcher = newSearcher(reader);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public void setUp() throws Exception
public override void setUp()
{
base.setUp();
directory = newDirectory();
IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(TEST_VERSION_CURRENT, new SimpleAnalyzer(TEST_VERSION_CURRENT)));
Document doc = new Document();
doc.add(new StringField("partnum", "Q36", Field.Store.YES));
doc.add(new TextField("description", "Illidium Space Modulator", Field.Store.YES));
writer.addDocument(doc);
writer.close();
reader = DirectoryReader.open(directory);
searcher = newSearcher(reader);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public void setUp() throws Exception
public override void setUp()
{
base.setUp();
directory = newDirectory();
IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(TEST_VERSION_CURRENT, new SimpleAnalyzer(TEST_VERSION_CURRENT)));
Document doc = new Document();
doc.add(new StringField("partnum", "Q36", Field.Store.YES));
doc.add(new TextField("description", "Illidium Space Modulator", Field.Store.YES));
writer.addDocument(doc);
writer.close();
reader = DirectoryReader.open(directory);
searcher = newSearcher(reader);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public void setUp() throws Exception
public override void setUp()
{
base.setUp();
dir = new RAMDirectory();
appAnalyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false);
IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, appAnalyzer));
int numDocs = 200;
for (int i = 0; i < numDocs; i++)
{
Document doc = new Document();
string variedFieldValue = variedFieldValues[i % variedFieldValues.Length];
string repetitiveFieldValue = repetitiveFieldValues[i % repetitiveFieldValues.Length];
doc.add(new TextField("variedField", variedFieldValue, Field.Store.YES));
doc.add(new TextField("repetitiveField", repetitiveFieldValue, Field.Store.YES));
writer.addDocument(doc);
}
writer.close();
reader = DirectoryReader.open(dir);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public void setUp() throws Exception
public override void setUp()
{
base.setUp();
dir = new RAMDirectory();
appAnalyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false);
IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, appAnalyzer));
int numDocs = 200;
for (int i = 0; i < numDocs; i++)
{
Document doc = new Document();
string variedFieldValue = variedFieldValues[i % variedFieldValues.Length];
string repetitiveFieldValue = repetitiveFieldValues[i % repetitiveFieldValues.Length];
doc.add(new TextField("variedField", variedFieldValue, Field.Store.YES));
doc.add(new TextField("repetitiveField", repetitiveFieldValue, Field.Store.YES));
writer.addDocument(doc);
}
writer.close();
reader = DirectoryReader.open(dir);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testIndexWriter_LUCENE4656() throws java.io.IOException
public virtual void testIndexWriter_LUCENE4656()
{
Directory directory = newDirectory();
IndexWriter writer = new IndexWriter(directory, newIndexWriterConfig(TEST_VERSION_CURRENT, null));
TokenStream ts = new EmptyTokenStream();
assertFalse(ts.hasAttribute(typeof(TermToBytesRefAttribute)));
Document doc = new Document();
doc.add(new StringField("id", "0", Field.Store.YES));
doc.add(new TextField("description", ts));
// this should not fail because we have no TermToBytesRefAttribute
writer.addDocument(doc);
assertEquals(1, writer.numDocs());
writer.close();
directory.close();
}
/*
* public void testPerFieldAnalyzer() throws Exception {
* PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new SimpleAnalyzer(TEST_VERSION_CURRENT));
* analyzer.addAnalyzer("partnum", new KeywordAnalyzer());
*
* QueryParser queryParser = new QueryParser(TEST_VERSION_CURRENT, "description", analyzer);
* Query query = queryParser.parse("partnum:Q36 AND SPACE");
*
* ScoreDoc[] hits = searcher.search(query, null, 1000).scoreDocs;
* assertEquals("Q36 kept as-is",
* "+partnum:Q36 +space", query.toString("description"));
* assertEquals("doc found!", 1, hits.length);
* }
*/
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testMutipleDocument() throws Exception
public virtual void testMutipleDocument()
{
RAMDirectory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, new KeywordAnalyzer()));
Document doc = new Document();
doc.add(new TextField("partnum", "Q36", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("partnum", "Q37", Field.Store.YES));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
DocsEnum td = TestUtil.docs(random(), reader, "partnum", new BytesRef("Q36"), MultiFields.getLiveDocs(reader), null, 0);
assertTrue(td.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
td = TestUtil.docs(random(), reader, "partnum", new BytesRef("Q37"), MultiFields.getLiveDocs(reader), null, 0);
assertTrue(td.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testIndexWriter_LUCENE4656() throws java.io.IOException
public virtual void testIndexWriter_LUCENE4656()
{
Directory directory = newDirectory();
IndexWriter writer = new IndexWriter(directory, newIndexWriterConfig(TEST_VERSION_CURRENT, null));
TokenStream ts = new EmptyTokenStream();
assertFalse(ts.hasAttribute(typeof(TermToBytesRefAttribute)));
Document doc = new Document();
doc.add(new StringField("id", "0", Field.Store.YES));
doc.add(new TextField("description", ts));
// this should not fail because we have no TermToBytesRefAttribute
writer.addDocument(doc);
assertEquals(1, writer.numDocs());
writer.close();
directory.close();
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testLimitTokenCountIndexWriter() throws java.io.IOException
public virtual void testLimitTokenCountIndexWriter()
{
foreach (bool consumeAll in new bool[] {true, false})
{
Directory dir = newDirectory();
int limit = TestUtil.Next(random(), 50, 101000);
MockAnalyzer mock = new MockAnalyzer(random());
// if we are consuming all tokens, we can use the checks,
// otherwise we can't
mock.EnableChecks = consumeAll;
Analyzer a = new LimitTokenCountAnalyzer(mock, limit, consumeAll);
IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, a));
Document doc = new Document();
StringBuilder b = new StringBuilder();
for (int i = 1;i < limit;i++)
{
b.Append(" a");
}
b.Append(" x");
b.Append(" z");
doc.add(newTextField("field", b.ToString(), Field.Store.NO));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
Term t = new Term("field", "x");
assertEquals(1, reader.docFreq(t));
t = new Term("field", "z");
assertEquals(0, reader.docFreq(t));
reader.close();
dir.close();
}
}
/*
public void testPerFieldAnalyzer() throws Exception {
PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new SimpleAnalyzer(TEST_VERSION_CURRENT));
analyzer.addAnalyzer("partnum", new KeywordAnalyzer());
QueryParser queryParser = new QueryParser(TEST_VERSION_CURRENT, "description", analyzer);
Query query = queryParser.parse("partnum:Q36 AND SPACE");
ScoreDoc[] hits = searcher.search(query, null, 1000).scoreDocs;
assertEquals("Q36 kept as-is",
"+partnum:Q36 +space", query.toString("description"));
assertEquals("doc found!", 1, hits.length);
}
*/
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testMutipleDocument() throws Exception
public virtual void testMutipleDocument()
{
RAMDirectory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig(TEST_VERSION_CURRENT, new KeywordAnalyzer()));
Document doc = new Document();
doc.add(new TextField("partnum", "Q36", Field.Store.YES));
writer.addDocument(doc);
doc = new Document();
doc.add(new TextField("partnum", "Q37", Field.Store.YES));
writer.addDocument(doc);
writer.close();
IndexReader reader = DirectoryReader.open(dir);
DocsEnum td = TestUtil.docs(random(), reader, "partnum", new BytesRef("Q36"), MultiFields.getLiveDocs(reader), null, 0);
assertTrue(td.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
td = TestUtil.docs(random(), reader, "partnum", new BytesRef("Q37"), MultiFields.getLiveDocs(reader), null, 0);
assertTrue(td.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
}
/// <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();
}
// 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();
}
