lucene-近音词查询

分析器通过Metaphone算法实现近音词查询，也可采用类似于Soundex的其它可行的算法

public void testKoolKat() throws Exceptoin{

RAMDirectory directory=new RAMDirectory();

Analyzer analyzer=new MetaphoneReplacementAnalyzer();

 

IndexWriter writer=new IndexWriter(directory,analyzer,true);

Document doc=new Document();

doc.add(Field.Text("contents","cool cat"));

writer.addDocument(doc);

writer.close();

IndexSearcher searcher=new IndexSearcher(directory);

Query query=QueryParser.parse("kool kat","contents",analyzer);

 

Hits hits=searcher.search(query);

}

public class MetaPhoneReplacementAnalyzer extends Anaylyer{

public TokenStream tokenStream(String fieldName,Reader reader){

return new MetaphoneReplacementFilter{

new LetterTokenizer(reader));

}

}

}

public class MetaphoneReplacementFilter extends TokenFilter{

publicstatic final String METAPHONE="METAPHONE";

privateMetaphone metaphoner=new Metaphone();

publicMetaphoneReplacementFilter(TokenStream input){

super(input);

}

publicToken next() throws IOException{

Token t=input.next();

if (t==null) return null;

try{

return newToken(metaphoner.encode(t.termText()),t.startOffset().t.endOffset(),METAPHONE);//设置语汇单元的token类型。

}

catch(EncodeException e){

return t;

}

}

}