public virtual void TestCJK()
{
// Test Ideographic Space - As wide as a CJK character cell (fullwidth)
// used google to translate the word "term" to japanese -> 用語
//
// NOTE: What is printed above is not the translation of "term" into
// Japanese. Google translate currently gives:
//
// 期間
//
// Which translates to unicode characters 26399 and 38291, or
// the literals '\u671f' and '\u9593'.
//
// Unlike the second and third characters in the previous string ('\u201d' and '\u00a8')
// which fail the test for IsCharacter when tokenized by LetterTokenizer (as it should
// in Java), which causes the word to be split differently than if it actually used
// letters as defined by Unicode.
//
// Using the string "\u671f\u9593\u3000\u671f\u9593\u3000\u671f\u9593" with just the two
// characters is enough, as it uses two characters with the full width of a CJK character cell.
AssertQueryEquals("term\u3000term\u3000term", null, "term\u0020term\u0020term");
AssertQueryEquals("\u671f\u9593\u3000\u671f\u9593\u3000\u671f\u9593", null, "\u671f\u9593\u0020\u671f\u9593\u0020\u671f\u9593");
}
