Example using WikipediaTokenizer in Lucene

Question

I want to use WikipediaTokenizer in lucene project - http://lucene.apache.org/java/3_0_2/api/contrib-wikipedia/org/apache/lucene/wikipedia/analysis/WikipediaTokenizer.html B

Answer 1

public class WikipediaTokenizerTest { static Logger logger = Logger.getLogger(WikipediaTokenizerTest.class); protected static final String LINK_PHRASES = "click [[link here again]] click [http://lucene.apache.org here again] [[Category:a b c d]]";

public WikipediaTokenizer testSimple() throws Exception {
    String text = "This is a [[Category:foo]]";
    return new WikipediaTokenizer(new StringReader(text));
}
public static void main(String[] args){
    WikipediaTokenizerTest wtt = new WikipediaTokenizerTest();

    try {
        WikipediaTokenizer x = wtt.testSimple();

        logger.info(x.hasAttributes());

        Token token = new Token();
        int count = 0;
        int numItalics = 0;
        int numBoldItalics = 0;
        int numCategory = 0;
        int numCitation = 0;

        while (x.incrementToken() == true) {
            logger.info("seen something");
        }

    } catch(Exception e){
        logger.error("Exception while tokenizing Wiki Text: " + e.getMessage());
    }


}