//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void test10kPulsed() throws Exception
public virtual void test10kPulsed()
{
// we always run this test with pulsing codec.
Codec cp = TestUtil.alwaysPostingsFormat(new Pulsing41PostingsFormat(1));
File f = createTempDir("10kpulsed");
BaseDirectoryWrapper dir = newFSDirectory(f);
dir.CheckIndexOnClose = false; // we do this ourselves explicitly
RandomIndexWriter iw = new RandomIndexWriter(random(), dir, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random())).setCodec(cp));
Document document = new Document();
FieldType ft = new FieldType(TextField.TYPE_STORED);
switch (TestUtil.Next(random(), 0, 2))
{
case 0:
ft.IndexOptions = IndexOptions.DOCS_ONLY;
break;
case 1:
ft.IndexOptions = IndexOptions.DOCS_AND_FREQS;
break;
default:
ft.IndexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
break;
}
Field field = newField("field", "", ft);
document.add(field);
NumberFormat df = new DecimalFormat("00000", new DecimalFormatSymbols(Locale.ROOT));
for (int i = 0; i < 10050; i++)
{
field.StringValue = df.format(i);
iw.addDocument(document);
}
IndexReader ir = iw.Reader;
iw.close();
TermsEnum te = MultiFields.getTerms(ir, "field").iterator(null);
DocsEnum de = null;
for (int i = 0; i < 10050; i++)
{
string expected = df.format(i);
assertEquals(expected, te.next().utf8ToString());
de = TestUtil.docs(random(), te, null, de, DocsEnum.FLAG_NONE);
assertTrue(de.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
assertEquals(DocIdSetIterator.NO_MORE_DOCS, de.nextDoc());
}
ir.close();
TestUtil.checkIndex(dir);
dir.close();
}
/// <summary>
/// a variant, that uses pulsing, but uses a high TF to force pass thru to the underlying codec
/// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void test10kNotPulsed() throws Exception
public virtual void test10kNotPulsed()
{
// we always run this test with pulsing codec.
int freqCutoff = TestUtil.Next(random(), 1, 10);
Codec cp = TestUtil.alwaysPostingsFormat(new Pulsing41PostingsFormat(freqCutoff));
File f = createTempDir("10knotpulsed");
BaseDirectoryWrapper dir = newFSDirectory(f);
dir.CheckIndexOnClose = false; // we do this ourselves explicitly
RandomIndexWriter iw = new RandomIndexWriter(random(), dir, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random())).setCodec(cp));
Document document = new Document();
FieldType ft = new FieldType(TextField.TYPE_STORED);
switch (TestUtil.Next(random(), 0, 2))
{
case 0:
ft.IndexOptions = IndexOptions.DOCS_ONLY;
break;
case 1:
ft.IndexOptions = IndexOptions.DOCS_AND_FREQS;
break;
default:
ft.IndexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
break;
}
Field field = newField("field", "", ft);
document.add(field);
NumberFormat df = new DecimalFormat("00000", new DecimalFormatSymbols(Locale.ROOT));
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final int freq = freqCutoff + 1;
int freq = freqCutoff + 1;
for (int i = 0; i < 10050; i++)
{
StringBuilder sb = new StringBuilder();
for (int j = 0; j < freq; j++)
{
sb.Append(df.format(i));
sb.Append(' '); // whitespace
}
field.StringValue = sb.ToString();
iw.addDocument(document);
}
IndexReader ir = iw.Reader;
iw.close();
TermsEnum te = MultiFields.getTerms(ir, "field").iterator(null);
DocsEnum de = null;
for (int i = 0; i < 10050; i++)
{
string expected = df.format(i);
assertEquals(expected, te.next().utf8ToString());
de = TestUtil.docs(random(), te, null, de, DocsEnum.FLAG_NONE);
assertTrue(de.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
assertEquals(DocIdSetIterator.NO_MORE_DOCS, de.nextDoc());
}
ir.close();
TestUtil.checkIndex(dir);
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();
}
