本文整理汇总了Java中org.apache.lucene.analysis.PorterStemFilter类的典型用法代码示例。如果您正苦于以下问题：Java PorterStemFilter类的具体用法？Java PorterStemFilter怎么用？Java PorterStemFilter使用的例子？那么, 这里精选的类代码示例或许可以为您提供帮助。
PorterStemFilter类属于org.apache.lucene.analysis包，在下文中一共展示了PorterStemFilter类的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: reusableTokenStream
import org.apache.lucene.analysis.PorterStemFilter; //导入依赖的package包/类
/**
*
* @param fieldName
* @param reader
* @return
* @throws IOException
*/
@Override
public TokenStream reusableTokenStream(String fieldName, Reader reader) throws
IOException {
SavedStreams streams = (SavedStreams) getPreviousTokenStream();
if (streams == null) {
streams = new SavedStreams();
streams.source = new WhitespaceTokenizer(reader);
streams.result = new StopFilter(true, streams.source, stopwords, true);
streams.result = new PorterStemFilter(streams.source);
setPreviousTokenStream(streams);
} else {
streams.source.reset(reader);
}
return streams.result;
}
示例2: tokenStream
import org.apache.lucene.analysis.PorterStemFilter; //导入依赖的package包/类
@Override
public final TokenStream tokenStream(String fieldName, Reader reader) {
// Apply stop words and porter stemmer using a lower-case tokenizer.
TokenStream stream = new StopFilter(new LowerCaseTokenizer(reader),
StandardAnalyzer.STOP_WORDS);
return new PorterStemFilter(stream);
}
示例3: tokenStream
import org.apache.lucene.analysis.PorterStemFilter; //导入依赖的package包/类
@Override
public final TokenStream tokenStream(String fieldName, Reader reader) {
// Apply stop words and porter stemmer using a lower-case tokenizer.
TokenStream stream = new StopFilter(new LowerCaseTokenizer(reader),
StandardAnalyzer.STOP_WORDS);
return new PorterStemFilter(stream);
}
示例4: tokenizeGloss
import org.apache.lucene.analysis.PorterStemFilter; //导入依赖的package包/类
/**
* Takes a gloss-like string (text) and returns it tokenized.
* with:
* - stopwords
* - lower case
* - porter stemmer
*/
protected Set<String> tokenizeGloss( String s ) throws IOException {
Set<String> result = new HashSet<String>();
// I am affraid that I am reimplementing the StandardAnalizer...
TokenStream ts = new PorterStemFilter(
new StopFilter( true,
new LowerCaseTokenizer(
new StringReader( s ) ), stopWords, true ));
TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
while ( ts.incrementToken() ) {
result.add( termAtt.term() );
}
return result;
}