Filters org.apache.lucene.analysis.standard.UAX29URLEmailTokenizer with StandardFilter, LowerCaseFilter and StopFilter, using a list of English stop words.

You must specify the required org.apache.lucene.util.Version compatibility when creating UAX29URLEmailAnalyzer

Inheritance: Lucene.Net.Analysis.Util.StopwordAnalyzerBase
UAX29URLEmailAnalyzer Class Documentation
示例#1
0
 public TokenStreamComponentsAnonymousInnerClassHelper(UAX29URLEmailAnalyzer outerInstance, UAX29URLEmailTokenizer src, TokenStream tok, TextReader reader)
     : base(src, tok)
 {
     this.outerInstance = outerInstance;
     this.reader        = reader;
     this.src           = src;
 }
示例#2
0
 public virtual void TestCombiningMarksBackwards()
 {
     Analyzer a = new UAX29URLEmailAnalyzer(LuceneVersion.LUCENE_33);
     CheckOneTerm(a, "ざ", "さ"); // hiragana Bug
     CheckOneTerm(a, "ザ", "ザ"); // katakana Works
     CheckOneTerm(a, "壹゙", "壹"); // ideographic Bug
     CheckOneTerm(a, "아゙", "아゙"); // hangul Works
 }
示例#3
0
 public TokenStreamComponentsAnonymousInnerClassHelper(UAX29URLEmailAnalyzer outerInstance, UAX29URLEmailTokenizer src, TokenStream tok, TextReader reader)
     : base(src, tok)
 {
     this.outerInstance = outerInstance;
     this.reader = reader;
     this.src = src;
 }