Example usage for org.apache.lucene.analysis CharArraySet clear

Introduction

In this page you can find the example usage for org.apache.lucene.analysis CharArraySet clear.

Prototype

@Override
public void clear() 

Source Link

Document

Clears all entries in this set.

Usage

From source file:org.tallison.lucene.contrast.QueryToCorpusContraster.java

License:Apache License

public List<TermIDF> contrast(Query query, String fieldName, int numResults) throws IOException {
    TopScoreDocCollector results = TopScoreDocCollector.create(maxDocs, maxDocs + 10000);
    searcher.search(query, results);/*from ww w.j  a  v  a  2 s.  co m*/

    ScoreDoc[] scoreDocs = results.topDocs().scoreDocs;
    //if there are fewer documents than minTermFreq
    //return empty list now
    if (scoreDocs.length < minTermFreq) {
        return new ArrayList<TermIDF>();
    }

    //total hack
    int initialSize = scoreDocs.length * 100;
    CharArrayMap<MutableValueInt> map = new CharArrayMap<MutableValueInt>(initialSize, ignoreCase);
    CharArraySet tmpSet = new CharArraySet(100, ignoreCase);
    Set<String> selector = new HashSet<String>();
    selector.add(fieldName);

    for (ScoreDoc scoreDoc : scoreDocs) {
        //get terms from doc
        processDoc(scoreDoc.doc, fieldName, selector, tmpSet);
        //now update global doc freqs
        Iterator<Object> it = tmpSet.iterator();
        while (it.hasNext()) {
            char[] token = (char[]) it.next();
            MutableValueInt docCount = map.get(token, 0, token.length);
            if (docCount == null) {
                docCount = new MutableValueInt();
                docCount.value = 1;
            } else {
                docCount.value++;
            }
            map.put(token, docCount);
        }
        tmpSet.clear();
    }

    return getResults(fieldName, map, numResults);
}

---