public virtual void TestFarsiRangeCollating()
{
RAMDirectory ramDir = new RAMDirectory();
IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
Document doc = new Document();
doc.Add(new Field("content", "\u0633\u0627\u0628", Field.Store.YES, Field.Index.UN_TOKENIZED));
iw.AddDocument(doc);
iw.Close();
IndexSearcher is_Renamed = new IndexSearcher(ramDir);
QueryParser qp = new QueryParser("content", new WhitespaceAnalyzer());
// 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 c = new System.Globalization.CultureInfo("ar").CompareInfo;
qp.SetRangeCollator(c);
// 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 ConstantScoreRangeQuery
// with a Farsi Collator (or an Arabic one for the case when Farsi is not
// supported).
// Test ConstantScoreRangeQuery
qp.SetMultiTermRewriteMethod(MultiTermQuery.CONSTANT_SCORE_FILTER_REWRITE);
ScoreDoc[] result = is_Renamed.Search(qp.Parse("[ \u062F TO \u0698 ]"), null, 1000).ScoreDocs;
Assert.AreEqual(0, result.Length, "The index Term should not be included.");
result = is_Renamed.Search(qp.Parse("[ \u0633 TO \u0638 ]"), null, 1000).ScoreDocs;
Assert.AreEqual(1, result.Length, "The index Term should be included.");
// Test TermRangeQuery
qp.SetMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
result = is_Renamed.Search(qp.Parse("[ \u062F TO \u0698 ]"), null, 1000).ScoreDocs;
Assert.AreEqual(0, result.Length, "The index Term should not be included.");
result = is_Renamed.Search(qp.Parse("[ \u0633 TO \u0638 ]"), null, 1000).ScoreDocs;
Assert.AreEqual(1, result.Length, "The index Term should be included.");
is_Renamed.Close();
}
