public virtual void TestLowerCaseFilterLowSurrogateLeftover()
{
// test if the limit of the termbuffer is correctly used with supplementary
// chars
WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("BogustermBogusterm\udc16"));
LowerCaseFilter filter = new LowerCaseFilter(TEST_VERSION_CURRENT, tokenizer);
AssertTokenStreamContents(filter, new string[] { "bogustermbogusterm\udc16" });
filter.Reset();
string highSurEndingUpper = "BogustermBoguster\ud801";
string highSurEndingLower = "bogustermboguster\ud801";
tokenizer.SetReader(new StringReader(highSurEndingUpper));
AssertTokenStreamContents(filter, new string[] { highSurEndingLower });
assertTrue(filter.HasAttribute <ICharTermAttribute>());
char[] termBuffer = filter.GetAttribute <ICharTermAttribute>().Buffer;
int length = highSurEndingLower.Length;
assertEquals('\ud801', termBuffer[length - 1]);
}
public virtual void TestLowerCaseFilterLowSurrogateLeftover()
{
// test if the limit of the termbuffer is correctly used with supplementary
// chars
WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("BogustermBogusterm\udc16"));
LowerCaseFilter filter = new LowerCaseFilter(TEST_VERSION_CURRENT, tokenizer);
AssertTokenStreamContents(filter, new string[] { "bogustermbogusterm\udc16" });
filter.Reset();
string highSurEndingUpper = "BogustermBoguster\ud801";
string highSurEndingLower = "bogustermboguster\ud801";
tokenizer.Reader = new StringReader(highSurEndingUpper);
AssertTokenStreamContents(filter, new string[] { highSurEndingLower });
assertTrue(filter.HasAttribute<ICharTermAttribute>());
char[] termBuffer = filter.GetAttribute<ICharTermAttribute>().Buffer();
int length = highSurEndingLower.Length;
assertEquals('\ud801', termBuffer[length - 1]);
}
