public override void SetUp()
{
base.SetUp();
directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("field", "one two three four five", Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("sorter", "b", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
doc = new Document();
doc.Add(new Field("field", "one two three four", Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("sorter", "d", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
doc = new Document();
doc.Add(new Field("field", "one two three y", Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("sorter", "a", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
doc = new Document();
doc.Add(new Field("field", "one two x", Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("sorter", "c", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
writer.Optimize();
writer.Close();
searcher = new IndexSearcher(directory, true);
query = new TermQuery(new Term("field", "three"));
filter = NewStaticFilterB();
}
public virtual void TestAddSameDocTwice()
{
// LUCENE-5367: this was a problem with the previous code, making sure it
// works with the new code.
Directory indexDir = NewDirectory(), taxoDir = NewDirectory();
IndexWriter indexWriter = new IndexWriter(indexDir, NewIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(Random())));
DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
FacetsConfig facetsConfig = new FacetsConfig();
Document doc = new Document();
doc.Add(new FacetField("a", "b"));
doc = facetsConfig.Build(taxoWriter, doc);
// these two addDocument() used to fail
indexWriter.AddDocument(doc);
indexWriter.AddDocument(doc);
IOUtils.Close(indexWriter, taxoWriter);
DirectoryReader indexReader = DirectoryReader.Open(indexDir);
DirectoryTaxonomyReader taxoReader = new DirectoryTaxonomyReader(taxoDir);
IndexSearcher searcher = NewSearcher(indexReader);
FacetsCollector fc = new FacetsCollector();
searcher.Search(new MatchAllDocsQuery(), fc);
Facets facets = GetTaxonomyFacetCounts(taxoReader, facetsConfig, fc);
FacetResult res = facets.GetTopChildren(10, "a");
Assert.AreEqual(1, res.LabelValues.Length);
Assert.AreEqual(2, res.LabelValues[0].value);
IOUtils.Close(indexReader, taxoReader);
IOUtils.Close(indexDir, taxoDir);
}
public virtual void SetUp()
{
// Create an index writer.
directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
// oldest doc:
// Add the first document. text = "Document 1" dateTime = Oct 10 03:25:22 EDT 2007
writer.AddDocument(CreateDocument("Document 1", 633275835220000000L));
// Add the second document. text = "Document 2" dateTime = Oct 10 03:25:26 EDT 2007
writer.AddDocument(CreateDocument("Document 2", 633275835260000000L));
// Add the third document. text = "Document 3" dateTime = Oct 11 07:12:13 EDT 2007
writer.AddDocument(CreateDocument("Document 3", 633276835330000000L));
// Add the fourth document. text = "Document 4" dateTime = Oct 11 08:02:09 EDT 2007
writer.AddDocument(CreateDocument("Document 4", 633276865290000000L));
// latest doc:
// Add the fifth document. text = "Document 5" dateTime = Oct 12 13:25:43 EDT 2007
writer.AddDocument(CreateDocument("Document 5", 633277923430000000L));
//// oldest doc:
//// Add the first document. text = "Document 1" dateTime = Oct 10 03:25:22 EDT 2007
//writer.AddDocument(CreateDocument("Document 1", 1192001122000L));
//// Add the second document. text = "Document 2" dateTime = Oct 10 03:25:26 EDT 2007
//writer.AddDocument(CreateDocument("Document 2", 1192001126000L));
//// Add the third document. text = "Document 3" dateTime = Oct 11 07:12:13 EDT 2007
//writer.AddDocument(CreateDocument("Document 3", 1192101133000L));
//// Add the fourth document. text = "Document 4" dateTime = Oct 11 08:02:09 EDT 2007
//writer.AddDocument(CreateDocument("Document 4", 1192104129000L));
//// latest doc:
//// Add the fifth document. text = "Document 5" dateTime = Oct 12 13:25:43 EDT 2007
//writer.AddDocument(CreateDocument("Document 5", 1192209943000L));
writer.Optimize();
writer.Close();
}
public override void SetUp()
{
base.SetUp();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
for (int i = 0; i < 5137; ++i)
{
Document doc = new Document();
doc.Add(new Field(FIELD, "meaninglessnames", Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
{
Document doc = new Document();
doc.Add(new Field(FIELD, "tangfulin", Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
for (int i = 5138; i < 11377; ++i)
{
Document doc = new Document();
doc.Add(new Field(FIELD, "meaninglessnames", Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
{
Document doc = new Document();
doc.Add(new Field(FIELD, "tangfulin", Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
writer.Close();
}
void Index()
{
Lucene.Net.Index.IndexWriter wr = new Lucene.Net.Index.IndexWriter(dir, new Lucene.Net.Analysis.WhitespaceAnalyzer(), Lucene.Net.Index.IndexWriter.MaxFieldLength.UNLIMITED);
Lucene.Net.Documents.Document doc = null;
Lucene.Net.Documents.Field f = null;
doc = new Lucene.Net.Documents.Document();
f = new Lucene.Net.Documents.Field("field", "a b c d", Lucene.Net.Documents.Field.Store.NO, Lucene.Net.Documents.Field.Index.ANALYZED);
doc.Add(f);
wr.AddDocument(doc);
doc = new Lucene.Net.Documents.Document();
f = new Lucene.Net.Documents.Field("field", "a b a d", Lucene.Net.Documents.Field.Store.NO, Lucene.Net.Documents.Field.Index.ANALYZED);
doc.Add(f);
wr.AddDocument(doc);
doc = new Lucene.Net.Documents.Document();
f = new Lucene.Net.Documents.Field("field", "a b e f", Lucene.Net.Documents.Field.Store.NO, Lucene.Net.Documents.Field.Index.ANALYZED);
doc.Add(f);
wr.AddDocument(doc);
doc = new Lucene.Net.Documents.Document();
f = new Lucene.Net.Documents.Field("field", "x y z", Lucene.Net.Documents.Field.Store.NO, Lucene.Net.Documents.Field.Index.ANALYZED);
doc.Add(f);
wr.AddDocument(doc);
wr.Close();
}
public virtual void TestPhrasePrefix()
{
RAMDirectory indexStore = new RAMDirectory();
IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Document doc1 = new Document();
Document doc2 = new Document();
Document doc3 = new Document();
Document doc4 = new Document();
Document doc5 = new Document();
doc1.Add(new Field("body", "blueberry pie", Field.Store.YES, Field.Index.ANALYZED));
doc2.Add(new Field("body", "blueberry strudel", Field.Store.YES, Field.Index.ANALYZED));
doc3.Add(new Field("body", "blueberry pizza", Field.Store.YES, Field.Index.ANALYZED));
doc4.Add(new Field("body", "blueberry chewing gum", Field.Store.YES, Field.Index.ANALYZED));
doc5.Add(new Field("body", "piccadilly circus", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc1);
writer.AddDocument(doc2);
writer.AddDocument(doc3);
writer.AddDocument(doc4);
writer.AddDocument(doc5);
writer.Optimize();
writer.Close();
IndexSearcher searcher = new IndexSearcher(indexStore);
//PhrasePrefixQuery query1 = new PhrasePrefixQuery();
MultiPhraseQuery query1 = new MultiPhraseQuery();
//PhrasePrefixQuery query2 = new PhrasePrefixQuery();
MultiPhraseQuery query2 = new MultiPhraseQuery();
query1.Add(new Term("body", "blueberry"));
query2.Add(new Term("body", "strawberry"));
System.Collections.ArrayList termsWithPrefix = new System.Collections.ArrayList();
IndexReader ir = IndexReader.Open(indexStore);
// this TermEnum gives "piccadilly", "pie" and "pizza".
System.String prefix = "pi";
TermEnum te = ir.Terms(new Term("body", prefix + "*"));
do
{
if (te.Term().Text().StartsWith(prefix))
{
termsWithPrefix.Add(te.Term());
}
}
while (te.Next());
query1.Add((Term[]) termsWithPrefix.ToArray(typeof(Term)));
query2.Add((Term[]) termsWithPrefix.ToArray(typeof(Term)));
ScoreDoc[] result;
result = searcher.Search(query1, null, 1000).scoreDocs;
Assert.AreEqual(2, result.Length);
result = searcher.Search(query2, null, 1000).scoreDocs;
Assert.AreEqual(0, result.Length);
}
public virtual void TestDemo_Renamed_Method()
{
Analyzer analyzer = new StandardAnalyzer();
// Store the index in memory:
Directory directory = new RAMDirectory();
// To store an index on disk, use this instead (note that the
// parameter true will overwrite the index in that directory
// if one exists):
//Directory directory = FSDirectory.getDirectory("/tmp/testindex", true);
IndexWriter iwriter = new IndexWriter(directory, analyzer, true);
iwriter.SetMaxFieldLength(25000);
Document doc = new Document();
System.String text = "This is the text to be indexed.";
doc.Add(new Field("fieldname", text, Field.Store.YES, Field.Index.TOKENIZED));
iwriter.AddDocument(doc);
iwriter.Close();
// Now search the index:
IndexSearcher isearcher = new IndexSearcher(directory);
// Parse a simple query that searches for "text":
Lucene.Net.QueryParsers.QueryParser parser = new Lucene.Net.QueryParsers.QueryParser("fieldname", analyzer);
Query query = parser.Parse("text");
Hits hits = isearcher.Search(query);
Assert.AreEqual(1, hits.Length());
// Iterate through the results:
for (int i = 0; i < hits.Length(); i++)
{
Document hitDoc = hits.Doc(i);
Assert.AreEqual("This is the text to be indexed.", hitDoc.Get("fieldname"));
}
isearcher.Close();
directory.Close();
}
public virtual void TestFilterWorks()
{
Directory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
for (int i = 0; i < 500; i++)
{
Document document = new Document();
document.Add(new Field("field", English.IntToEnglish(i) + " equals " + English.IntToEnglish(i), Field.Store.NO, Field.Index.ANALYZED));
writer.AddDocument(document);
}
writer.Close();
IndexReader reader = IndexReader.Open(dir, true);
SpanTermQuery query = new SpanTermQuery(new Term("field", English.IntToEnglish(10).Trim()));
SpanQueryFilter filter = new SpanQueryFilter(query);
SpanFilterResult result = filter.BitSpans(reader);
DocIdSet docIdSet = result.DocIdSet;
Assert.IsTrue(docIdSet != null, "docIdSet is null and it shouldn't be");
AssertContainsDocId("docIdSet doesn't contain docId 10", docIdSet, 10);
var spans = result.Positions;
Assert.IsTrue(spans != null, "spans is null and it shouldn't be");
int size = GetDocIdSetSize(docIdSet);
Assert.IsTrue(spans.Count == size, "spans Size: " + spans.Count + " is not: " + size);
for (System.Collections.IEnumerator iterator = spans.GetEnumerator(); iterator.MoveNext(); )
{
SpanFilterResult.PositionInfo info = (SpanFilterResult.PositionInfo) iterator.Current;
Assert.IsTrue(info != null, "info is null and it shouldn't be");
//The doc should indicate the bit is on
AssertContainsDocId("docIdSet doesn't contain docId " + info.Doc, docIdSet, info.Doc);
//There should be two positions in each
Assert.IsTrue(info.Positions.Count == 2, "info.getPositions() Size: " + info.Positions.Count + " is not: " + 2);
}
reader.Close();
}
public virtual void TestBasic()
{
Directory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("field", "value", Field.Store.NO, Field.Index.ANALYZED));
writer.AddDocument(doc);
writer.Close();
TermQuery termQuery = new TermQuery(new Term("field", "value"));
// should not throw exception with primitive query
QueryWrapperFilter qwf = new QueryWrapperFilter(termQuery);
IndexSearcher searcher = new IndexSearcher(dir, true);
TopDocs hits = searcher.Search(new MatchAllDocsQuery(), qwf, 10);
Assert.AreEqual(1, hits.totalHits);
// should not throw exception with complex primitive query
BooleanQuery booleanQuery = new BooleanQuery();
booleanQuery.Add(termQuery, Occur.MUST);
booleanQuery.Add(new TermQuery(new Term("field", "missing")), Occur.MUST_NOT);
qwf = new QueryWrapperFilter(termQuery);
hits = searcher.Search(new MatchAllDocsQuery(), qwf, 10);
Assert.AreEqual(1, hits.totalHits);
// should not throw exception with non primitive Query (doesn't implement
// Query#createWeight)
qwf = new QueryWrapperFilter(new FuzzyQuery(new Term("field", "valu")));
hits = searcher.Search(new MatchAllDocsQuery(), qwf, 10);
Assert.AreEqual(1, hits.totalHits);
}
public void SearchFiltered(IndexWriter writer, Directory directory, Filter filter, bool optimize)
{
try
{
for (int i = 0; i < 60; i++)
{//Simple docs
Document doc = new Document();
doc.Add(new Field(FIELD, i.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
if (optimize)
writer.Optimize();
writer.Close();
BooleanQuery booleanQuery = new BooleanQuery();
booleanQuery.Add(new TermQuery(new Term(FIELD, "36")), Occur.SHOULD);
IndexSearcher indexSearcher = new IndexSearcher(directory);
ScoreDoc[] hits = indexSearcher.Search(booleanQuery, filter, 1000).ScoreDocs;
Assert.AreEqual(1, hits.Length, "Number of matched documents");
}
catch (System.IO.IOException e)
{
Assert.Fail(e.Message);
}
}
public override void SetUp()
{
base.SetUp();
directory = new RAMDirectory();
PayloadAnalyzer analyzer = new PayloadAnalyzer(this);
IndexWriter writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
writer.SetSimilarity(similarity);
//writer.infoStream = System.out;
for (int i = 0; i < 1000; i++)
{
Document doc = new Document();
Field noPayloadField = new Field(PayloadHelper.NO_PAYLOAD_FIELD, English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED);
//noPayloadField.setBoost(0);
doc.Add(noPayloadField);
doc.Add(new Field("field", English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("multiField", English.IntToEnglish(i) + " " + English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
}
writer.Optimize();
writer.Close();
searcher = new IndexSearcher(directory, true);
searcher.SetSimilarity(similarity);
}
public virtual void TestDanish()
{
/* build an index */
RAMDirectory danishIndex = new RAMDirectory();
IndexWriter writer = new IndexWriter(danishIndex, new SimpleAnalyzer(), T, IndexWriter.MaxFieldLength.LIMITED);
// Danish collation orders the words below in the given order
// (example taken from TestSort.testInternationalSort() ).
System.String[] words = new System.String[] { "H\u00D8T", "H\u00C5T", "MAND" };
for (int docnum = 0; docnum < words.Length; ++docnum)
{
Document doc = new Document();
doc.Add(new Field("content", words[docnum], Field.Store.YES, Field.Index.UN_TOKENIZED));
doc.Add(new Field("body", "body", Field.Store.YES, Field.Index.UN_TOKENIZED));
writer.AddDocument(doc);
}
writer.Optimize();
writer.Close();
IndexReader reader = IndexReader.Open(danishIndex);
IndexSearcher search = new IndexSearcher(reader);
System.Globalization.CompareInfo c = new System.Globalization.CultureInfo("da" + "-" + "dk").CompareInfo;
// Unicode order would not include "H\u00C5T" in [ "H\u00D8T", "MAND" ],
// but Danish collation does.
ScoreDoc[] result = search.Search(Csrq("content", "H\u00D8T", "MAND", F, F, c), null, 1000).scoreDocs;
AssertEquals("The index Term should be included.", 1, result.Length);
result = search.Search(Csrq("content", "H\u00C5T", "MAND", F, F, c), null, 1000).scoreDocs;
AssertEquals("The index Term should not be included.", 0, result.Length);
search.Close();
}
public override void SetUp()
{
base.SetUp();
RAMDirectory directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
long theLong = System.Int64.MaxValue;
double theDouble = System.Double.MaxValue;
sbyte theByte = (sbyte)System.SByte.MaxValue;
short theShort = System.Int16.MaxValue;
int theInt = System.Int32.MaxValue;
float theFloat = System.Single.MaxValue;
for (int i = 0; i < NUM_DOCS; i++)
{
Document doc = new Document();
doc.Add(new Field("theLong", System.Convert.ToString(theLong--), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theDouble", (theDouble--).ToString("E16"), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theByte", System.Convert.ToString((sbyte)theByte--), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theShort", System.Convert.ToString(theShort--), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theInt", System.Convert.ToString(theInt--), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theFloat", (theFloat--).ToString("E8"), Field.Store.NO, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
writer.Close();
reader = IndexReader.Open(directory);
}
public void SearchFiltered(IndexWriter writer, Directory directory, Filter filter, bool optimize)
{
try
{
for (int i = 0; i < 60; i++)
{//Simple docs
Document doc = new Document();
doc.Add(new Field(FIELD, i.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
if (optimize)
{
writer.Optimize();
}
writer.Close();
BooleanQuery booleanQuery = new BooleanQuery();
booleanQuery.Add(new TermQuery(new Term(FIELD, "36")), BooleanClause.Occur.SHOULD);
IndexSearcher indexSearcher = new IndexSearcher(directory);
ScoreDoc[] hits = indexSearcher.Search(booleanQuery, filter, 1000).scoreDocs;
Assert.AreEqual(1, hits.Length, "Number of matched documents");
}
catch (System.IO.IOException e)
{
Assert.Fail(e.Message);
}
}
private void AddDoc(IndexWriter iw, int i)
{
Document d = new Document();
IFieldable f;
int scoreAndID = i + 1;
f = new Field(ID_FIELD, Id2String(scoreAndID), Field.Store.YES, Field.Index.NOT_ANALYZED); // for debug purposes
f.OmitNorms = true;
d.Add(f);
f = new Field(TEXT_FIELD, "text of doc" + scoreAndID + TextLine(i), Field.Store.NO, Field.Index.ANALYZED); // for regular search
f.OmitNorms = true;
d.Add(f);
f = new Field(INT_FIELD, "" + scoreAndID, Field.Store.NO, Field.Index.NOT_ANALYZED); // for function scoring
f.OmitNorms = true;
d.Add(f);
f = new Field(FLOAT_FIELD, scoreAndID + ".000", Field.Store.NO, Field.Index.NOT_ANALYZED); // for function scoring
f.OmitNorms = true;
d.Add(f);
iw.AddDocument(d);
Log("added: " + d);
}
public virtual void TestNullOrSubScorer()
{
Directory dir = new MockRAMDirectory();
IndexWriter w = new IndexWriter(dir, new WhitespaceAnalyzer(), IndexWriter.MaxFieldLength.UNLIMITED);
Document doc = new Document();
doc.Add(new Field("field", "a b c d", Field.Store.NO, Field.Index.ANALYZED));
w.AddDocument(doc);
IndexReader r = w.GetReader();
IndexSearcher s = new IndexSearcher(r);
BooleanQuery q = new BooleanQuery();
q.Add(new TermQuery(new Term("field", "a")), Occur.SHOULD);
// LUCENE-2617: make sure that a term not in the index still contributes to the score via coord factor
float score = s.Search(q, 10).MaxScore;
Query subQuery = new TermQuery(new Term("field", "not_in_index"));
subQuery.Boost = 0;
q.Add(subQuery, Occur.SHOULD);
float score2 = s.Search(q, 10).MaxScore;
Assert.AreEqual(score * .5, score2, 1e-6);
// LUCENE-2617: make sure that a clause not in the index still contributes to the score via coord factor
BooleanQuery qq = (BooleanQuery)q.Clone();
PhraseQuery phrase = new PhraseQuery();
phrase.Add(new Term("field", "not_in_index"));
phrase.Add(new Term("field", "another_not_in_index"));
phrase.Boost = 0;
qq.Add(phrase, Occur.SHOULD);
score2 = s.Search(qq, 10).MaxScore;
Assert.AreEqual(score * (1.0 / 3), score2, 1e-6);
// now test BooleanScorer2
subQuery = new TermQuery(new Term("field", "b"));
subQuery.Boost = 0;
q.Add(subQuery, Occur.MUST);
score2 = s.Search(q, 10).MaxScore;
Assert.AreEqual(score * (2.0 / 3), score2, 1e-6);
// PhraseQuery w/ no terms added returns a null scorer
PhraseQuery pq = new PhraseQuery();
q.Add(pq, Occur.SHOULD);
Assert.AreEqual(1, s.Search(q, 10).TotalHits);
// A required clause which returns null scorer should return null scorer to
// IndexSearcher.
q = new BooleanQuery();
pq = new PhraseQuery();
q.Add(new TermQuery(new Term("field", "a")), Occur.SHOULD);
q.Add(pq, Occur.MUST);
Assert.AreEqual(0, s.Search(q, 10).TotalHits);
DisjunctionMaxQuery dmq = new DisjunctionMaxQuery(1.0f);
dmq.Add(new TermQuery(new Term("field", "a")));
dmq.Add(pq);
Assert.AreEqual(1, s.Search(dmq, 10).TotalHits);
r.Close();
w.Close();
dir.Close();
}
public virtual void TestFarsi()
{
/* build an index */
RAMDirectory farsiIndex = new RAMDirectory();
IndexWriter writer = new IndexWriter(farsiIndex, new SimpleAnalyzer(), T, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("content", "\u0633\u0627\u0628", Field.Store.YES, Field.Index.UN_TOKENIZED));
doc.Add(new Field("body", "body", Field.Store.YES, Field.Index.UN_TOKENIZED));
writer.AddDocument(doc);
writer.Optimize();
writer.Close();
IndexReader reader = IndexReader.Open(farsiIndex);
IndexSearcher search = new IndexSearcher(reader);
Query q = new TermQuery(new Term("body", "body"));
// Neither Java 1.4.2 nor 1.5.0 has Farsi Locale collation available in
// RuleBasedCollator. However, the Arabic Locale seems to order the Farsi
// characters properly.
System.Globalization.CompareInfo collator = new System.Globalization.CultureInfo("ar").CompareInfo;
// Unicode order would include U+0633 in [ U+062F - U+0698 ], but Farsi
// orders the U+0698 character before the U+0633 character, so the single
// index Term below should NOT be returned by a TermRangeFilter with a Farsi
// Collator (or an Arabic one for the case when Farsi is not supported).
Hits result = search.Search(q, new TermRangeFilter("content", "\u062F", "\u0698", T, T, collator));
Assert.AreEqual(0, result.Length(), "The index Term should not be included.");
result = search.Search(q, new TermRangeFilter("content", "\u0633", "\u0638", T, T, collator));
Assert.AreEqual(1, result.Length(), "The index Term should be included.");
search.Close();
}
public virtual void TestNullOrSubScorer()
{
Directory dir = new MockRAMDirectory();
IndexWriter w = new IndexWriter(dir, new WhitespaceAnalyzer(), IndexWriter.MaxFieldLength.UNLIMITED);
Document doc = new Document();
doc.Add(new Field("field", "a b c d", Field.Store.NO, Field.Index.ANALYZED));
w.AddDocument(doc);
IndexReader r = w.GetReader();
IndexSearcher s = new IndexSearcher(r);
BooleanQuery q = new BooleanQuery();
q.Add(new TermQuery(new Term("field", "a")), BooleanClause.Occur.SHOULD);
// PhraseQuery w/ no terms added returns a null scorer
PhraseQuery pq = new PhraseQuery();
q.Add(pq, BooleanClause.Occur.SHOULD);
Assert.AreEqual(1, s.Search(q, 10).TotalHits);
// A required clause which returns null scorer should return null scorer to
// IndexSearcher.
q = new BooleanQuery();
pq = new PhraseQuery();
q.Add(new TermQuery(new Term("field", "a")), BooleanClause.Occur.SHOULD);
q.Add(pq, BooleanClause.Occur.MUST);
Assert.AreEqual(0, s.Search(q, 10).TotalHits);
DisjunctionMaxQuery dmq = new DisjunctionMaxQuery(1.0f);
dmq.Add(new TermQuery(new Term("field", "a")));
dmq.Add(pq);
Assert.AreEqual(1, s.Search(dmq, 10).TotalHits);
r.Close();
w.Close();
dir.Close();
}
public override void SetUp()
{
base.SetUp();
RAMDirectory directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
long theLong = System.Int64.MaxValue;
double theDouble = System.Double.MaxValue;
sbyte theByte = (sbyte) System.SByte.MaxValue;
short theShort = System.Int16.MaxValue;
int theInt = System.Int32.MaxValue;
float theFloat = System.Single.MaxValue;
for (int i = 0; i < NUM_DOCS; i++)
{
Document doc = new Document();
doc.Add(new Field("theLong", System.Convert.ToString(theLong--), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theDouble", (theDouble--).ToString("E16"), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theByte", System.Convert.ToString((sbyte) theByte--), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theShort", System.Convert.ToString(theShort--), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theInt", System.Convert.ToString(theInt--), Field.Store.NO, Field.Index.NOT_ANALYZED));
doc.Add(new Field("theFloat", (theFloat--).ToString("E8"), Field.Store.NO, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
writer.Close();
reader = IndexReader.Open(directory);
}
public virtual void TestDemo_Renamed()
{
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
// Store the index in memory:
Directory directory = new RAMDirectory();
// To store an index on disk, use this instead:
//Directory directory = FSDirectory.open("/tmp/testindex");
IndexWriter iwriter = new IndexWriter(directory, analyzer, true, new IndexWriter.MaxFieldLength(25000));
Document doc = new Document();
System.String text = "This is the text to be indexed.";
doc.Add(new Field("fieldname", text, Field.Store.YES, Field.Index.ANALYZED));
iwriter.AddDocument(doc);
iwriter.Close();
// Now search the index:
IndexSearcher isearcher = new IndexSearcher(directory, true); // read-only=true
// Parse a simple query that searches for "text":
QueryParser parser = new QueryParser("fieldname", analyzer);
Query query = parser.Parse("text");
ScoreDoc[] hits = isearcher.Search(query, null, 1000).scoreDocs;
Assert.AreEqual(1, hits.Length);
// Iterate through the results:
for (int i = 0; i < hits.Length; i++)
{
Document hitDoc = isearcher.Doc(hits[i].doc);
Assert.AreEqual(hitDoc.Get("fieldname"), "This is the text to be indexed.");
}
isearcher.Close();
directory.Close();
}
public virtual void TestMmapIndex()
{
FSDirectory storeDirectory;
storeDirectory = new MMapDirectory(new System.IO.FileInfo(storePathname), null);
// plan to add a set of useful stopwords, consider changing some of the
// interior filters.
StandardAnalyzer analyzer = new StandardAnalyzer(new System.Collections.Hashtable());
// TODO: something about lock timeouts and leftover locks.
IndexWriter writer = new IndexWriter(storeDirectory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
IndexSearcher searcher = new IndexSearcher(storePathname);
for (int dx = 0; dx < 1000; dx++)
{
System.String f = RandomField();
Document doc = new Document();
doc.Add(new Field("data", f, Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
}
searcher.Close();
writer.Close();
RmDir(new System.IO.FileInfo(storePathname));
}
public override void SetUp()
{
base.SetUp();
System.String tempDir = System.IO.Path.GetTempPath();
if (tempDir == null)
{
throw new System.IO.IOException("java.io.tmpdir undefined, cannot run test");
}
indexDir = new System.IO.DirectoryInfo(Path.Combine(tempDir, "RAMDirIndex"));
Directory dir = FSDirectory.Open(indexDir);
IndexWriter writer = new IndexWriter(dir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
// add some documents
Document doc = null;
for (int i = 0; i < docsToAdd; i++)
{
doc = new Document();
doc.Add(new Field("content", English.IntToEnglish(i).Trim(), Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
Assert.AreEqual(docsToAdd, writer.MaxDoc());
writer.Close();
dir.Close();
}
public virtual void CreateRandomTerms(int nDocs, int nTerms, double power, Directory dir)
{
int[] freq = new int[nTerms];
for (int i = 0; i < nTerms; i++)
{
int f = (nTerms + 1) - i; // make first terms less frequent
freq[i] = (int) System.Math.Ceiling(System.Math.Pow(f, power));
terms[i] = new Term("f", System.Convert.ToString((char) ('A' + i)));
}
IndexWriter iw = new IndexWriter(dir, new WhitespaceAnalyzer(), true);
for (int i = 0; i < nDocs; i++)
{
Document d = new Document();
for (int j = 0; j < nTerms; j++)
{
if (r.Next(freq[j]) == 0)
{
d.Add(new Field("f", terms[j].Text(), Field.Store.NO, Field.Index.UN_TOKENIZED));
//System.out.println(d);
}
}
iw.AddDocument(d);
}
iw.Optimize();
iw.Close();
}
public virtual void SetUp()
{
directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
Document doc = new Document();
doc.Add(Field.Text("Field", "one two three four five"));
doc.Add(Field.Text("sorter", "b"));
writer.AddDocument(doc);
doc = new Document();
doc.Add(Field.Text("Field", "one two three four"));
doc.Add(Field.Text("sorter", "d"));
writer.AddDocument(doc);
doc = new Document();
doc.Add(Field.Text("Field", "one two three y"));
doc.Add(Field.Text("sorter", "a"));
writer.AddDocument(doc);
doc = new Document();
doc.Add(Field.Text("Field", "one two x"));
doc.Add(Field.Text("sorter", "c"));
writer.AddDocument(doc);
writer.Optimize();
writer.Close();
searcher = new IndexSearcher(directory);
query = new TermQuery(new Term("Field", "three"));
filter = new AnonymousClassFilter(this);
}
public static void IndexDocs(IndexWriter writer, System.IO.FileInfo file)
{
if (System.IO.Directory.Exists(file.FullName))
{
System.String[] files = System.IO.Directory.GetFileSystemEntries(file.FullName);
// an IO error could occur
if (files != null)
{
for (int i = 0; i < files.Length; i++)
{
IndexDocs(writer, new System.IO.FileInfo(files[i]));
}
}
}
else
{
System.Console.Out.WriteLine("adding " + file);
try
{
writer.AddDocument(FileDocument.Document(file));
}
// at least on windows, some temporary files raise this exception with an "access denied" message
// checking if the file can be read doesn't help
catch (System.IO.FileNotFoundException fnfe)
{
;
}
}
}
public virtual void TestMethod()
{
RAMDirectory directory = new RAMDirectory();
System.String[] values = new System.String[]{"1", "2", "3", "4"};
try
{
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
for (int i = 0; i < values.Length; i++)
{
Lucene.Net.Documents.Document doc = new Lucene.Net.Documents.Document();
doc.Add(new Field(FIELD, values[i], Field.Store.YES, Field.Index.UN_TOKENIZED));
writer.AddDocument(doc);
}
writer.Close();
BooleanQuery booleanQuery1 = new BooleanQuery();
booleanQuery1.Add(new TermQuery(new Term(FIELD, "1")), BooleanClause.Occur.SHOULD);
booleanQuery1.Add(new TermQuery(new Term(FIELD, "2")), BooleanClause.Occur.SHOULD);
BooleanQuery query = new BooleanQuery();
query.Add(booleanQuery1, BooleanClause.Occur.MUST);
query.Add(new TermQuery(new Term(FIELD, "9")), BooleanClause.Occur.MUST_NOT);
IndexSearcher indexSearcher = new IndexSearcher(directory);
Hits hits = indexSearcher.Search(query);
Assert.AreEqual(2, hits.Length(), "Number of matched documents");
}
catch (System.IO.IOException e)
{
Assert.Fail(e.Message);
}
}
/// <summary> Adds the document to the index.
///
/// </summary>
/// <param name="writer">the Lucene index writer
/// </param>
/// <param name="id">the unique id of the document
/// </param>
/// <param name="text">the text of the document
/// </param>
/// <throws> IOException </throws>
protected internal virtual void addDocument(IndexWriter writer, System.String id, System.String text)
{
Document document = new Document();
document.Add(new Field(FIELD_ID, id, Field.Store.YES, Field.Index.NOT_ANALYZED));
document.Add(new Field(FIELD_TEXT, text, Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(document, null);
}
public void TestCustomMergeScheduler()
{
// we don't really need to execute anything, just to make sure the custom MS
// compiles. But ensure that it can be used as well, e.g., no other hidden
// dependencies or something. Therefore, don't use any random API !
Directory dir = new RAMDirectory();
IndexWriterConfig conf = new IndexWriterConfig(TEST_VERSION_CURRENT, null);
conf.SetMergeScheduler(new ReportingMergeScheduler());
IndexWriter writer = new IndexWriter(dir, conf);
writer.AddDocument(new Document());
writer.Commit(); // trigger flush
writer.AddDocument(new Document());
writer.Commit(); // trigger flush
writer.ForceMerge(1);
writer.Dispose();
dir.Dispose();
}
private void Add(System.String s, System.String type, IndexWriter writer)
{
Document doc = new Document();
doc.Add(new Field("body", s, Field.Store.YES, Field.Index.ANALYZED));
doc.Add(new Field("type", type, Field.Store.YES, Field.Index.NOT_ANALYZED));
writer.AddDocument(doc);
}
// LUCENE-1404
private void AddDoc(IndexWriter writer, System.String id, System.String text)
{
Document doc = new Document();
doc.Add(new Field("id", id, Field.Store.YES, Field.Index.UN_TOKENIZED));
doc.Add(new Field("text", text, Field.Store.YES, Field.Index.TOKENIZED));
writer.AddDocument(doc);
}
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(Field.Text("Field", "bogus"));
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());
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());
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());
}
public virtual void TestIterator()
{
RAMDirectory directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("field", "iterator test doc 1", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
doc = new Document();
doc.Add(new Field("field", "iterator test doc 2", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
writer.Close();
_TestUtil.CheckIndex(directory);
IndexSearcher searcher = new IndexSearcher(directory);
Hits hits = searcher.Search(new TermQuery(new Term("field", "iterator")));
HitIterator iterator = (HitIterator) hits.Iterator();
Assert.AreEqual(2, iterator.Length());
Assert.IsTrue(iterator.MoveNext());
Hit hit = (Hit) iterator.Current;
Assert.AreEqual("iterator test doc 1", hit.Get("field"));
Assert.IsTrue(iterator.MoveNext());
hit = (Hit) iterator.Current;
Assert.AreEqual("iterator test doc 2", hit.GetDocument().Get("field"));
Assert.IsFalse(iterator.MoveNext());
bool caughtException = false;
try
{
System.Object generatedAux = iterator.Current;
}
catch (System.ArgumentOutOfRangeException e)
{
Assert.IsTrue(true);
caughtException = true;
}
Assert.IsTrue(caughtException);
}
private void AddDoc(System.String text, IndexWriter iw, float boost)
{
Document doc = new Document();
Field f = new Field("key", text, Field.Store.YES, Field.Index.ANALYZED);
f.SetBoost(boost);
doc.Add(f);
iw.AddDocument(doc);
}
public virtual void TestMutipleDocument()
{
RAMDirectory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, new KeywordAnalyzer(), true);
Document doc = new Document();
doc.Add(new Field("partnum", "Q36", Field.Store.YES, Field.Index.TOKENIZED));
writer.AddDocument(doc);
doc = new Document();
doc.Add(new Field("partnum", "Q37", Field.Store.YES, Field.Index.TOKENIZED));
writer.AddDocument(doc);
writer.Close();
IndexReader reader = IndexReader.Open(dir);
TermDocs td = reader.TermDocs(new Term("partnum", "Q36"));
Assert.IsTrue(td.Next());
td = reader.TermDocs(new Term("partnum", "Q37"));
Assert.IsTrue(td.Next());
}
private void InsertDoc(IndexWriter writer, System.String content)
{
Document doc = new Document();
doc.Add(Field.Keyword("id", "id" + docCount));
doc.Add(Field.UnStored("content", content));
writer.AddDocument(doc);
docCount++;
}
public static void IndexingArticle(Article article)
{
Lucene.Net.Index.IndexWriter lwriter = new Lucene.Net.Index.IndexWriter(HttpContext.Current.Server.MapPath(ConfigurationManager.AppSettings["IndexingArticle"]), new Lucene.Net.Analysis.Standard.StandardAnalyzer(), false);
Lucene.Net.Documents.Document doc = new Lucene.Net.Documents.Document();
doc.Add(new Lucene.Net.Documents.Field("ArticleId", article.Id.ToString(), Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.UN_TOKENIZED));
doc.Add(new Lucene.Net.Documents.Field("ArticleTitle", article.Title, Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.TOKENIZED));
doc.Add(new Lucene.Net.Documents.Field("ArticleDetail", ParseHTML(Article.GetContent(article.Id)), Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.TOKENIZED));
lwriter.AddDocument(doc);
lwriter.Close();
}
public override void SetUp()
{
base.SetUp();
RAMDirectory directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
writer.AddDocument(Doc(new Field[] { Field("id", "0"), Field("gender", "male"), Field("first", "james"), Field("last", "jones") }));
writer.AddDocument(Doc(new Field[] { Field("id", "1"), Field("gender", "male"), Field("first", "james"), Field("last", "smith"), Field("gender", "female"), Field("first", "sally"), Field("last", "jones") }));
writer.AddDocument(Doc(new Field[] { Field("id", "2"), Field("gender", "female"), Field("first", "greta"), Field("last", "jones"), Field("gender", "female"), Field("first", "sally"), Field("last", "smith"), Field("gender", "male"), Field("first", "james"), Field("last", "jones") }));
writer.AddDocument(Doc(new Field[] { Field("id", "3"), Field("gender", "female"), Field("first", "lisa"), Field("last", "jones"), Field("gender", "male"), Field("first", "bob"), Field("last", "costas") }));
writer.AddDocument(Doc(new Field[] { Field("id", "4"), Field("gender", "female"), Field("first", "sally"), Field("last", "smith"), Field("gender", "female"), Field("first", "linda"), Field("last", "dixit"), Field("gender", "male"), Field("first", "bubba"), Field("last", "jones") }));
writer.Close();
searcher = new IndexSearcher(directory);
}
public virtual void CreateDummySearcher()
{
// Create a dummy index with nothing in it.
// This could possibly fail if Lucene starts checking for docid ranges...
RAMDirectory rd = new RAMDirectory();
IndexWriter iw = new IndexWriter(rd, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
iw.AddDocument(new Document());
iw.Close();
s = new IndexSearcher(rd);
}
private void InsertDoc(IndexWriter writer, System.String content)
{
Document doc = new Document();
doc.Add(new Field("id", "id" + docCount, Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("content", content, Field.Store.NO, Field.Index.ANALYZED));
writer.AddDocument(doc);
docCount++;
}
public virtual void TestBefore()
{
// create an index
RAMDirectory indexStore = new RAMDirectory();
IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED, null);
long now = (DateTime.Now.Ticks / TimeSpan.TicksPerMillisecond);
Document doc = new Document();
// add time that is in the past
doc.Add(new Field("datefield", DateTools.TimeToString(now - 1000, DateTools.Resolution.MILLISECOND), Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("body", "Today is a very sunny day in New York City", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc, null);
writer.Optimize(null);
writer.Close();
IndexSearcher searcher = new IndexSearcher(indexStore, true, null);
// filter that should preserve matches
//DateFilter df1 = DateFilter.Before("datefield", now);
TermRangeFilter df1 = new TermRangeFilter("datefield", DateTools.TimeToString(now - 2000, DateTools.Resolution.MILLISECOND), DateTools.TimeToString(now, DateTools.Resolution.MILLISECOND), false, true);
// filter that should discard matches
//DateFilter df2 = DateFilter.Before("datefield", now - 999999);
TermRangeFilter df2 = new TermRangeFilter("datefield", DateTools.TimeToString(0, DateTools.Resolution.MILLISECOND), DateTools.TimeToString(now - 2000, DateTools.Resolution.MILLISECOND), true, false);
// search something that doesn't exist with DateFilter
Query query1 = new TermQuery(new Term("body", "NoMatchForThis"));
// search for something that does exists
Query query2 = new TermQuery(new Term("body", "sunny"));
ScoreDoc[] result;
// ensure that queries return expected results without DateFilter first
result = searcher.Search(query1, null, 1000, null).ScoreDocs;
Assert.AreEqual(0, result.Length);
result = searcher.Search(query2, null, 1000, null).ScoreDocs;
Assert.AreEqual(1, result.Length);
// run queries with DateFilter
result = searcher.Search(query1, df1, 1000, null).ScoreDocs;
Assert.AreEqual(0, result.Length);
result = searcher.Search(query1, df2, 1000, null).ScoreDocs;
Assert.AreEqual(0, result.Length);
result = searcher.Search(query2, df1, 1000, null).ScoreDocs;
Assert.AreEqual(1, result.Length);
result = searcher.Search(query2, df2, 1000, null).ScoreDocs;
Assert.AreEqual(0, result.Length);
}
public virtual void TestMethod()
{
RAMDirectory directory = new RAMDirectory();
System.String[] categories = new System.String[] { "food", "foodanddrink", "foodanddrinkandgoodtimes", "food and drink" };
Query rw1 = null;
Query rw2 = null;
try
{
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
for (int i = 0; i < categories.Length; i++)
{
Document doc = new Document();
doc.Add(Field.Keyword("category", categories[i]));
writer.AddDocument(doc);
}
writer.Close();
IndexReader reader = IndexReader.Open(directory);
PrefixQuery query = new PrefixQuery(new Term("category", "foo"));
rw1 = query.Rewrite(reader);
BooleanQuery bq = new BooleanQuery();
bq.Add(query, true, false);
rw2 = bq.Rewrite(reader);
}
catch (System.IO.IOException e)
{
Assert.Fail(e.Message);
}
BooleanQuery bq1 = null;
if (rw1 is BooleanQuery)
{
bq1 = (BooleanQuery)rw1;
}
BooleanQuery bq2 = null;
if (rw2 is BooleanQuery)
{
bq2 = (BooleanQuery)rw2;
}
else
{
Assert.Fail("Rewrite");
}
Assert.AreEqual(bq1.GetClauses().Length, bq2.GetClauses().Length, "Number of Clauses Mismatch");
}
public virtual void TestDocBoost_()
{
RAMDirectory store = new RAMDirectory();
IndexWriter writer = new IndexWriter(store, new SimpleAnalyzer(), true);
Field f1 = Field.Text("Field", "word");
Field f2 = Field.Text("Field", "word");
f2.SetBoost(2.0f);
Document d1 = new Document();
Document d2 = new Document();
Document d3 = new Document();
Document d4 = new Document();
d3.SetBoost(3.0f);
d4.SetBoost(2.0f);
d1.Add(f1); // boost = 1
d2.Add(f2); // boost = 2
d3.Add(f1); // boost = 3
d4.Add(f2); // boost = 4
writer.AddDocument(d1);
writer.AddDocument(d2);
writer.AddDocument(d3);
writer.AddDocument(d4);
writer.Optimize();
writer.Close();
float[] scores = new float[4];
new IndexSearcher(store).Search(new TermQuery(new Term("Field", "word")), new AnonymousClassHitCollector(scores, this));
float lastScore = 0.0f;
for (int i = 0; i < 4; i++)
{
Assert.IsTrue(scores[i] > lastScore);
lastScore = scores[i];
}
}
public virtual void TestWithThreads()
{
// LUCENE-5303: OrdinalsCache used the ThreadLocal BinaryDV instead of reader.getCoreCacheKey().
Store.Directory indexDir = NewDirectory();
Store.Directory taxoDir = NewDirectory();
IndexWriterConfig conf = NewIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(Random()));
IndexWriter writer = new IndexWriter(indexDir, conf);
var taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
FacetsConfig config = new FacetsConfig();
Document doc = new Document();
doc.Add(new FacetField("A", "1"));
writer.AddDocument(config.Build(taxoWriter, doc));
doc = new Document();
doc.Add(new FacetField("A", "2"));
writer.AddDocument(config.Build(taxoWriter, doc));
var reader = DirectoryReader.Open(writer, true);
CachedOrdinalsReader ordsReader = new CachedOrdinalsReader(new DocValuesOrdinalsReader(FacetsConfig.DEFAULT_INDEX_FIELD_NAME));
ThreadClass[] threads = new ThreadClass[3];
for (int i = 0; i < threads.Length; i++)
{
threads[i] = new ThreadAnonymousInnerClassHelper(this, "CachedOrdsThread-" + i, reader, ordsReader);
}
long ramBytesUsed = 0;
foreach (ThreadClass t in threads)
{
t.Start();
t.Join();
if (ramBytesUsed == 0)
{
ramBytesUsed = ordsReader.RamBytesUsed();
}
else
{
Assert.AreEqual(ramBytesUsed, ordsReader.RamBytesUsed());
}
}
IOUtils.Close(writer, taxoWriter, reader, indexDir, taxoDir);
}
public virtual void TestDocBoost_Renamed()
{
RAMDirectory store = new RAMDirectory();
IndexWriter writer = new IndexWriter(store, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Fieldable f1 = new Field("field", "word", Field.Store.YES, Field.Index.ANALYZED);
Fieldable f2 = new Field("field", "word", Field.Store.YES, Field.Index.ANALYZED);
f2.SetBoost(2.0f);
Document d1 = new Document();
Document d2 = new Document();
Document d3 = new Document();
Document d4 = new Document();
d3.SetBoost(3.0f);
d4.SetBoost(2.0f);
d1.Add(f1); // boost = 1
d2.Add(f2); // boost = 2
d3.Add(f1); // boost = 3
d4.Add(f2); // boost = 4
writer.AddDocument(d1);
writer.AddDocument(d2);
writer.AddDocument(d3);
writer.AddDocument(d4);
writer.Optimize();
writer.Close();
float[] scores = new float[4];
new IndexSearcher(store).Search(new TermQuery(new Term("field", "word")), new AnonymousClassCollector(scores, this));
float lastScore = 0.0f;
for (int i = 0; i < 4; i++)
{
Assert.IsTrue(scores[i] > lastScore);
lastScore = scores[i];
}
}
public virtual void TestMutipleDocument()
{
RAMDirectory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, new KeywordAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("partnum", "Q36", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
doc = new Document();
doc.Add(new Field("partnum", "Q37", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
writer.Close();
IndexReader reader = IndexReader.Open(dir);
TermDocs td = reader.TermDocs(new Term("partnum", "Q36"));
Assert.IsTrue(td.Next());
td = reader.TermDocs(new Term("partnum", "Q37"));
Assert.IsTrue(td.Next());
}
public virtual void TestAfter()
{
// create an index
RAMDirectory indexStore = new RAMDirectory();
IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true);
long now = (System.DateTime.Now.Ticks - 621355968000000000) / 10000;
Document doc = new Document();
// add time that is in the future
doc.Add(Field.Keyword("datefield", DateField.TimeToString(now + 888888)));
doc.Add(Field.Text("body", "Today is a very sunny day in New York City"));
writer.AddDocument(doc);
writer.Optimize();
writer.Close();
IndexSearcher searcher = new IndexSearcher(indexStore);
// filter that should preserve matches
DateFilter df1 = DateFilter.After("datefield", now);
// filter that should discard matches
DateFilter df2 = DateFilter.After("datefield", now + 999999);
// search something that doesn't exist with DateFilter
Query query1 = new TermQuery(new Term("body", "NoMatchForThis"));
// search for something that does exists
Query query2 = new TermQuery(new Term("body", "sunny"));
Hits result;
// ensure that queries return expected results without DateFilter first
result = searcher.Search(query1);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query2);
Assert.AreEqual(1, result.Length());
// run queries with DateFilter
result = searcher.Search(query1, df1);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query1, df2);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query2, df1);
Assert.AreEqual(1, result.Length());
result = searcher.Search(query2, df2);
Assert.AreEqual(0, result.Length());
}
public virtual void TestOutOfOrderCollection()
{
Directory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, null, MaxFieldLength.UNLIMITED);
for (int i = 0; i < 10; i++)
{
writer.AddDocument(new Document());
}
writer.Commit();
writer.Close();
bool[] inOrder = new bool[]{false, true};
System.String[] actualTSDCClass = new System.String[]{"OutOfOrderTopScoreDocCollector", "InOrderTopScoreDocCollector"};
// Save the original value to set later.
bool origVal = BooleanQuery.GetAllowDocsOutOfOrder();
BooleanQuery.SetAllowDocsOutOfOrder(true);
BooleanQuery bq = new BooleanQuery();
// Add a Query with SHOULD, since bw.scorer() returns BooleanScorer2
// which delegates to BS if there are no mandatory clauses.
bq.Add(new MatchAllDocsQuery(), Occur.SHOULD);
// Set minNrShouldMatch to 1 so that BQ will not optimize rewrite to return
// the clause instead of BQ.
bq.SetMinimumNumberShouldMatch(1);
try
{
IndexSearcher searcher = new IndexSearcher(dir);
for (int i = 0; i < inOrder.Length; i++)
{
TopDocsCollector tdc = TopScoreDocCollector.create(3, inOrder[i]);
Assert.AreEqual("Lucene.Net.Search.TopScoreDocCollector+" + actualTSDCClass[i], tdc.GetType().FullName);
searcher.Search(new MatchAllDocsQuery(), tdc);
ScoreDoc[] sd = tdc.TopDocs().scoreDocs;
Assert.AreEqual(3, sd.Length);
for (int j = 0; j < sd.Length; j++)
{
Assert.AreEqual(j, sd[j].doc, "expected doc Id " + j + " found " + sd[j].doc);
}
}
}
finally
{
// Whatever happens, reset BooleanQuery.allowDocsOutOfOrder to the
// original value. Don't set it to false in case the implementation in BQ
// will change some day.
BooleanQuery.SetAllowDocsOutOfOrder(origVal);
}
}
public virtual void TestOutOfOrderCollection()
{
Directory dir = new RAMDirectory();
IndexWriter writer = new IndexWriter(dir, null, MaxFieldLength.UNLIMITED);
for (int i = 0; i < 10; i++)
{
writer.AddDocument(new Document());
}
writer.Commit();
writer.Close();
bool[] inOrder = new bool[] { false, true };
System.String[] actualTSDCClass = new System.String[] { "OutOfOrderTopScoreDocCollector", "InOrderTopScoreDocCollector" };
// Save the original value to set later.
bool origVal = BooleanQuery.GetAllowDocsOutOfOrder();
BooleanQuery.SetAllowDocsOutOfOrder(true);
BooleanQuery bq = new BooleanQuery();
// Add a Query with SHOULD, since bw.scorer() returns BooleanScorer2
// which delegates to BS if there are no mandatory clauses.
bq.Add(new MatchAllDocsQuery(), Occur.SHOULD);
// Set minNrShouldMatch to 1 so that BQ will not optimize rewrite to return
// the clause instead of BQ.
bq.SetMinimumNumberShouldMatch(1);
try
{
IndexSearcher searcher = new IndexSearcher(dir);
for (int i = 0; i < inOrder.Length; i++)
{
TopDocsCollector tdc = TopScoreDocCollector.create(3, inOrder[i]);
Assert.AreEqual("Lucene.Net.Search.TopScoreDocCollector+" + actualTSDCClass[i], tdc.GetType().FullName);
searcher.Search(new MatchAllDocsQuery(), tdc);
ScoreDoc[] sd = tdc.TopDocs().ScoreDocs;
Assert.AreEqual(3, sd.Length);
for (int j = 0; j < sd.Length; j++)
{
Assert.AreEqual(j, sd[j].doc, "expected doc Id " + j + " found " + sd[j].doc);
}
}
}
finally
{
// Whatever happens, reset BooleanQuery.allowDocsOutOfOrder to the
// original value. Don't set it to false in case the implementation in BQ
// will change some day.
BooleanQuery.SetAllowDocsOutOfOrder(origVal);
}
}
private static void IndexDocsNoFacets(IndexWriter indexWriter)
{
int numDocs = AtLeast(2);
for (int i = 0; i < numDocs; i++)
{
Document doc = new Document();
AddField(doc);
indexWriter.AddDocument(doc);
}
indexWriter.Commit(); // flush a segment
}
public virtual void CreateDummySearcher()
{
// Create a dummy index with nothing in it.
// This could possibly fail if Lucene starts checking for docid ranges...
RAMDirectory rd = new RAMDirectory();
IndexWriter iw = new IndexWriter(rd, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
iw.AddDocument(new Document());
iw.Close();
s = new IndexSearcher(rd);
}
void LUCENENET_100_CreateIndex()
{
Lucene.Net.Index.IndexWriter w = new Lucene.Net.Index.IndexWriter(LUCENENET_100_Dir, new Lucene.Net.Analysis.Standard.StandardAnalyzer(), true);
Lucene.Net.Documents.Field f1 = new Lucene.Net.Documents.Field("field1", "dark side of the moon", Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.TOKENIZED);
Lucene.Net.Documents.Field f2 = new Lucene.Net.Documents.Field("field2", "123", Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
Lucene.Net.Documents.Document d = new Lucene.Net.Documents.Document();
d.Add(f1);
d.Add(f2);
w.AddDocument(d);
f1 = new Lucene.Net.Documents.Field("field1", "Fly me to the moon", Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.TOKENIZED);
f2 = new Lucene.Net.Documents.Field("field2", "456", Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.UN_TOKENIZED);
d = new Lucene.Net.Documents.Document();
d.Add(f1);
d.Add(f2);
w.AddDocument(d);
w.Close();
}
public virtual void TestBefore()
{
// create an index
RAMDirectory indexStore = new RAMDirectory();
IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
long now = (DateTime.Now.Ticks / TimeSpan.TicksPerMillisecond);
Document doc = new Document();
// add time that is in the past
doc.Add(new Field("datefield", DateTools.TimeToString(now - 1000, DateTools.Resolution.MILLISECOND), Field.Store.YES, Field.Index.NOT_ANALYZED));
doc.Add(new Field("body", "Today is a very sunny day in New York City", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
writer.Optimize();
writer.Close();
IndexSearcher searcher = new IndexSearcher(indexStore, true);
// filter that should preserve matches
//DateFilter df1 = DateFilter.Before("datefield", now);
TermRangeFilter df1 = new TermRangeFilter("datefield", DateTools.TimeToString(now - 2000, DateTools.Resolution.MILLISECOND), DateTools.TimeToString(now, DateTools.Resolution.MILLISECOND), false, true);
// filter that should discard matches
//DateFilter df2 = DateFilter.Before("datefield", now - 999999);
TermRangeFilter df2 = new TermRangeFilter("datefield", DateTools.TimeToString(0, DateTools.Resolution.MILLISECOND), DateTools.TimeToString(now - 2000, DateTools.Resolution.MILLISECOND), true, false);
// search something that doesn't exist with DateFilter
Query query1 = new TermQuery(new Term("body", "NoMatchForThis"));
// search for something that does exists
Query query2 = new TermQuery(new Term("body", "sunny"));
ScoreDoc[] result;
// ensure that queries return expected results without DateFilter first
result = searcher.Search(query1, null, 1000).ScoreDocs;
Assert.AreEqual(0, result.Length);
result = searcher.Search(query2, null, 1000).ScoreDocs;
Assert.AreEqual(1, result.Length);
// run queries with DateFilter
result = searcher.Search(query1, df1, 1000).ScoreDocs;
Assert.AreEqual(0, result.Length);
result = searcher.Search(query1, df2, 1000).ScoreDocs;
Assert.AreEqual(0, result.Length);
result = searcher.Search(query2, df1, 1000).ScoreDocs;
Assert.AreEqual(1, result.Length);
result = searcher.Search(query2, df2, 1000).ScoreDocs;
Assert.AreEqual(0, result.Length);
}
public void Test_Index_ReusableStringReader()
{
Lucene.Net.Index.IndexWriter wr = new Lucene.Net.Index.IndexWriter(new Lucene.Net.Store.RAMDirectory(), new TestAnalyzer(), true);
Lucene.Net.Documents.Document doc = new Lucene.Net.Documents.Document();
Lucene.Net.Documents.Field f1 = new Lucene.Net.Documents.Field("f1", TEST_STRING, Lucene.Net.Documents.Field.Store.YES, Lucene.Net.Documents.Field.Index.TOKENIZED);
doc.Add(f1);
wr.AddDocument(doc);
wr.Close();
}
internal bool Validate = true; // set to false when doing performance testing
#endregion Fields
#region Methods
// TODO: this should be setUp()....
public virtual void CreateDummySearcher()
{
// Create a dummy index with nothing in it.
// this could possibly fail if Lucene starts checking for docid ranges...
d = NewDirectory();
IndexWriter iw = new IndexWriter(d, NewIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(Random())));
iw.AddDocument(new Document());
iw.Dispose();
r = DirectoryReader.Open(d);
s = NewSearcher(r);
}
public virtual void TestBefore()
{
// create an index
RAMDirectory indexStore = new RAMDirectory();
IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true);
long now = (long) (DateTime.UtcNow - new DateTime(1970, 1, 1)).TotalMilliseconds;
Lucene.Net.Documents.Document doc = new Lucene.Net.Documents.Document();
// add time that is in the past
doc.Add(new Field("datefield", Lucene.Net.Documents.DateTools.TimeToString(now - 1000 * 100000, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), Field.Store.YES, Field.Index.UN_TOKENIZED));
doc.Add(new Field("body", "Today is a very sunny day in New York City", Field.Store.YES, Field.Index.TOKENIZED));
writer.AddDocument(doc);
writer.Optimize();
writer.Close();
IndexSearcher searcher = new IndexSearcher(indexStore);
// filter that should preserve matches
//DateFilter df1 = DateFilter.Before("datefield", now);
RangeFilter df1 = new RangeFilter("datefield", Lucene.Net.Documents.DateTools.TimeToString(now - 2000 * 100000, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), Lucene.Net.Documents.DateTools.TimeToString(now, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), false, true);
// filter that should discard matches
//DateFilter df2 = DateFilter.Before("datefield", now - 999999);
RangeFilter df2 = new RangeFilter("datefield", Lucene.Net.Documents.DateTools.TimeToString(0, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), Lucene.Net.Documents.DateTools.TimeToString(now - 2000 * 100000, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), true, false);
// search something that doesn't exist with DateFilter
Query query1 = new TermQuery(new Term("body", "NoMatchForThis"));
// search for something that does exists
Query query2 = new TermQuery(new Term("body", "sunny"));
Hits result;
// ensure that queries return expected results without DateFilter first
result = searcher.Search(query1);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query2);
Assert.AreEqual(1, result.Length());
// run queries with DateFilter
result = searcher.Search(query1, df1);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query1, df2);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query2, df1);
Assert.AreEqual(1, result.Length());
result = searcher.Search(query2, df2);
Assert.AreEqual(0, result.Length());
}
public virtual void TestSlopScoring()
{
Directory directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("field", "foo firstname lastname foo", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc);
Document doc2 = new Document();
doc2.Add(new Field("field", "foo firstname xxx lastname foo", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc2);
Document doc3 = new Document();
doc3.Add(new Field("field", "foo firstname xxx yyy lastname foo", Field.Store.YES, Field.Index.ANALYZED));
writer.AddDocument(doc3);
writer.Optimize();
writer.Close();
Searcher searcher = new IndexSearcher(directory, true);
PhraseQuery query = new PhraseQuery();
query.Add(new Term("field", "firstname"));
query.Add(new Term("field", "lastname"));
query.Slop = System.Int32.MaxValue;
ScoreDoc[] hits = searcher.Search(query, null, 1000).ScoreDocs;
Assert.AreEqual(3, hits.Length);
// Make sure that those matches where the terms appear closer to
// each other get a higher score:
Assert.AreEqual(0.71, hits[0].Score, 0.01);
Assert.AreEqual(0, hits[0].Doc);
Assert.AreEqual(0.44, hits[1].Score, 0.01);
Assert.AreEqual(1, hits[1].Doc);
Assert.AreEqual(0.31, hits[2].Score, 0.01);
Assert.AreEqual(2, hits[2].Doc);
QueryUtils.Check(query, searcher);
}
public virtual void TestBefore()
{
// create an index
RAMDirectory indexStore = new RAMDirectory();
IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true);
long now = (System.DateTime.Now.Ticks - 621355968000000000) / 10000;
Document doc = new Document();
// add time that is in the past
doc.Add(Field.Keyword("datefield", DateField.TimeToString(now - 1000)));
doc.Add(Field.Text("body", "Today is a very sunny day in New York City"));
writer.AddDocument(doc);
writer.Optimize();
writer.Close();
IndexSearcher searcher = new IndexSearcher(indexStore);
// filter that should preserve matches
DateFilter df1 = DateFilter.Before("datefield", now);
// filter that should discard matches
DateFilter df2 = DateFilter.Before("datefield", now - 999999);
// search something that doesn't exist with DateFilter
Query query1 = new TermQuery(new Term("body", "NoMatchForThis"));
// search for something that does exists
Query query2 = new TermQuery(new Term("body", "sunny"));
Hits result;
// ensure that queries return expected results without DateFilter first
result = searcher.Search(query1);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query2);
Assert.AreEqual(1, result.Length());
// run queries with DateFilter
result = searcher.Search(query1, df1);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query1, df2);
Assert.AreEqual(0, result.Length());
result = searcher.Search(query2, df1);
Assert.AreEqual(1, result.Length());
result = searcher.Search(query2, df2);
Assert.AreEqual(0, result.Length());
}
public virtual void SetUp()
{
// Create an index writer.
directory = new RAMDirectory();
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
for (int i = 0; i < N; i++)
{
writer.AddDocument(CreateDocument(i));
}
writer.Optimize();
writer.Close();
}
public virtual void TestMethod()
{
RAMDirectory directory = new RAMDirectory();
System.String[] categories = new System.String[]{"food", "foodanddrink", "foodanddrinkandgoodtimes", "food and drink"};
Query rw1 = null;
Query rw2 = null;
try
{
IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
for (int i = 0; i < categories.Length; i++)
{
Document doc = new Document();
doc.Add(Field.Keyword("category", categories[i]));
writer.AddDocument(doc);
}
writer.Close();
IndexReader reader = IndexReader.Open(directory);
PrefixQuery query = new PrefixQuery(new Term("category", "foo"));
rw1 = query.Rewrite(reader);
BooleanQuery bq = new BooleanQuery();
bq.Add(query, true, false);
rw2 = bq.Rewrite(reader);
}
catch (System.IO.IOException e)
{
Assert.Fail(e.Message);
}
BooleanQuery bq1 = null;
if (rw1 is BooleanQuery)
{
bq1 = (BooleanQuery) rw1;
}
BooleanQuery bq2 = null;
if (rw2 is BooleanQuery)
{
bq2 = (BooleanQuery) rw2;
}
else
{
Assert.Fail("Rewrite");
}
Assert.AreEqual(bq1.GetClauses().Length, bq2.GetClauses().Length, "Number of Clauses Mismatch");
}
private static void IndexDocsWithFacetsNoTerms(IndexWriter indexWriter, TaxonomyWriter taxoWriter, IDictionary<string, int?> expectedCounts)
{
Random random = Random();
int numDocs = AtLeast(random, 2);
FacetsConfig config = Config;
for (int i = 0; i < numDocs; i++)
{
Document doc = new Document();
AddFacets(doc, config, false);
indexWriter.AddDocument(config.Build(taxoWriter, doc));
}
indexWriter.Commit(); // flush a segment
}
