public virtual void TestPrefixQuery() { RAMDirectory directory = new RAMDirectory(); System.String[] categories = new System.String[] { "/Computers", "/Computers/Mac", "/Computers/Windows" }; 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(); PrefixQuery query = new PrefixQuery(new Term("category", "/Computers")); IndexSearcher searcher = new IndexSearcher(directory); Hits hits = searcher.Search(query); Assert.AreEqual(3, hits.Length(), "All documents in /Computers category and below"); query = new PrefixQuery(new Term("category", "/Computers/Mac")); hits = searcher.Search(query); Assert.AreEqual(1, hits.Length(), "One in /Computers/Mac"); }
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++; }
private void AddDocumentWithDifferentFields(IndexWriter writer) { Document doc = new Document(); doc.Add(Field.Keyword("keyword2", "test1")); doc.Add(Field.Text("text2", "test1")); doc.Add(Field.UnIndexed("unindexed2", "test1")); doc.Add(Field.UnStored("unstored2", "test1")); writer.AddDocument(doc); }
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 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()); }
private Document MakeDocumentWithFields() { Document doc = new Document(); doc.Add(Field.Keyword("keyword", "test1")); doc.Add(Field.Keyword("keyword", "test2")); doc.Add(Field.Text("text", "test1")); doc.Add(Field.Text("text", "test2")); doc.Add(Field.UnIndexed("unindexed", "test1")); doc.Add(Field.UnIndexed("unindexed", "test2")); doc.Add(Field.UnStored("unstored", "test1")); doc.Add(Field.UnStored("unstored", "test2")); return(doc); }
static DocHelper() { textField1 = Field.Text(TEXT_FIELD_1_KEY, FIELD_1_TEXT, false); textField2 = Field.Text(TEXT_FIELD_2_KEY, FIELD_2_TEXT, true); keyField = Field.Keyword(KEYWORD_FIELD_KEY, KEYWORD_TEXT); unIndField = Field.UnIndexed(UNINDEXED_FIELD_KEY, UNINDEXED_FIELD_TEXT); unStoredField1 = Field.UnStored(UNSTORED_FIELD_1_KEY, UNSTORED_1_FIELD_TEXT, false); unStoredField2 = Field.UnStored(UNSTORED_FIELD_2_KEY, UNSTORED_2_FIELD_TEXT, true); { nameValues = new System.Collections.Hashtable(); nameValues[TEXT_FIELD_1_KEY] = FIELD_1_TEXT; nameValues[TEXT_FIELD_2_KEY] = FIELD_2_TEXT; nameValues[KEYWORD_FIELD_KEY] = KEYWORD_TEXT; nameValues[UNINDEXED_FIELD_KEY] = UNINDEXED_FIELD_TEXT; nameValues[UNSTORED_FIELD_1_KEY] = UNSTORED_1_FIELD_TEXT; nameValues[UNSTORED_FIELD_2_KEY] = UNSTORED_2_FIELD_TEXT; } }
/// <summary>Makes a document for a File. /// <p> /// The document has three fields: /// <ul> /// <li><code>path</code>--containing the pathname of the file, as a stored, /// tokenized Field; /// <li><code>modified</code>--containing the last modified date of the file as /// a keyword Field as encoded by <a /// href="lucene.document.DateField.html">DateField</a>; and /// <li><code>contents</code>--containing the full contents of the file, as a /// Reader Field; /// </summary> public static Document Document(System.IO.FileInfo f) { // make a new, empty document Document doc = new Document(); // Add the path of the file as a Field named "path". Use a Text Field, so // that the index stores the path, and so that the path is searchable doc.Add(Field.Text("path", f.FullName)); // Add the last modified date of the file a Field named "modified". Use a // Keyword Field, so that it's searchable, but so that no attempt is made // to tokenize the Field into words. doc.Add(Field.Keyword("modified", DateField.TimeToString(((f.LastWriteTime.Ticks - 621355968000000000) / 10000)))); // Add the contents of the file a Field named "contents". Use a Text // Field, specifying a Reader, so that the text of the file is tokenized. // ?? why doesn't FileReader work here ?? System.IO.FileStream is_Renamed = new System.IO.FileStream(f.FullName, System.IO.FileMode.Open, System.IO.FileAccess.Read); System.IO.StreamReader reader = new System.IO.StreamReader(new System.IO.StreamReader(is_Renamed, System.Text.Encoding.Default).BaseStream, new System.IO.StreamReader(is_Renamed, System.Text.Encoding.Default).CurrentEncoding); doc.Add(Field.Text("contents", reader)); // return the document return(doc); }
public virtual void TestEmptyIndex() { // creating two directories for indices Directory indexStoreA = new RAMDirectory(); Directory indexStoreB = new RAMDirectory(); // creating a document to store Document lDoc = new Document(); lDoc.Add(Field.Text("fulltext", "Once upon a time.....")); lDoc.Add(Field.Keyword("id", "doc1")); lDoc.Add(Field.Keyword("handle", "1")); // creating a document to store Document lDoc2 = new Document(); lDoc2.Add(Field.Text("fulltext", "in a galaxy far far away.....")); lDoc2.Add(Field.Keyword("id", "doc2")); lDoc2.Add(Field.Keyword("handle", "1")); // creating a document to store Document lDoc3 = new Document(); lDoc3.Add(Field.Text("fulltext", "a bizarre bug manifested itself....")); lDoc3.Add(Field.Keyword("id", "doc3")); lDoc3.Add(Field.Keyword("handle", "1")); // creating an index writer for the first index IndexWriter writerA = new IndexWriter(indexStoreA, new StandardAnalyzer(), true); // creating an index writer for the second index, but writing nothing IndexWriter writerB = new IndexWriter(indexStoreB, new StandardAnalyzer(), true); //-------------------------------------------------------------------- // scenario 1 //-------------------------------------------------------------------- // writing the documents to the first index writerA.AddDocument(lDoc); writerA.AddDocument(lDoc2); writerA.AddDocument(lDoc3); writerA.Optimize(); writerA.Close(); // closing the second index writerB.Close(); // creating the query Query query = Lucene.Net.QueryParsers.QueryParser.Parse("handle:1", "fulltext", new StandardAnalyzer()); // building the searchables Searcher[] searchers = new Searcher[2]; // VITAL STEP:adding the searcher for the empty index first, before the searcher for the populated index searchers[0] = new IndexSearcher(indexStoreB); searchers[1] = new IndexSearcher(indexStoreA); // creating the multiSearcher Searcher mSearcher = GetMultiSearcherInstance(searchers); // performing the search Hits hits = mSearcher.Search(query); Assert.AreEqual(3, hits.Length()); try { // iterating over the hit documents for (int i = 0; i < hits.Length(); i++) { Document d = hits.Doc(i); } } catch (System.IndexOutOfRangeException e) { Assert.Fail("ArrayIndexOutOfBoundsException thrown: " + e.Message); System.Console.Error.WriteLine(e.Source); } finally { mSearcher.Close(); } //-------------------------------------------------------------------- // scenario 2 //-------------------------------------------------------------------- // adding one document to the empty index writerB = new IndexWriter(indexStoreB, new StandardAnalyzer(), false); writerB.AddDocument(lDoc); writerB.Optimize(); writerB.Close(); // building the searchables Searcher[] searchers2 = new Searcher[2]; // VITAL STEP:adding the searcher for the empty index first, before the searcher for the populated index searchers2[0] = new IndexSearcher(indexStoreB); searchers2[1] = new IndexSearcher(indexStoreA); // creating the mulitSearcher Searcher mSearcher2 = GetMultiSearcherInstance(searchers2); // performing the same search Hits hits2 = mSearcher2.Search(query); Assert.AreEqual(4, hits2.Length()); try { // iterating over the hit documents for (int i = 0; i < hits2.Length(); i++) { // no exception should happen at this point Document d = hits2.Doc(i); } } catch (System.Exception e) { Assert.Fail("Exception thrown: " + e.Message); System.Console.Error.WriteLine(e.Source); } finally { mSearcher2.Close(); } //-------------------------------------------------------------------- // scenario 3 //-------------------------------------------------------------------- // deleting the document just added, this will cause a different exception to take place Term term = new Term("id", "doc1"); IndexReader readerB = IndexReader.Open(indexStoreB); readerB.Delete(term); readerB.Close(); // optimizing the index with the writer writerB = new IndexWriter(indexStoreB, new StandardAnalyzer(), false); writerB.Optimize(); writerB.Close(); // building the searchables Searcher[] searchers3 = new Searcher[2]; searchers3[0] = new IndexSearcher(indexStoreB); searchers3[1] = new IndexSearcher(indexStoreA); // creating the mulitSearcher Searcher mSearcher3 = GetMultiSearcherInstance(searchers3); // performing the same search Hits hits3 = mSearcher3.Search(query); Assert.AreEqual(3, hits3.Length()); try { // iterating over the hit documents for (int i = 0; i < hits3.Length(); i++) { Document d = hits3.Doc(i); } } catch (System.IO.IOException e) { Assert.Fail("IOException thrown: " + e.Message); System.Console.Error.WriteLine(e.Source); } finally { mSearcher3.Close(); } }