提取关键词，并排序

java 代码

//提取内容关键字！ 对关键字重要性做排序 筛选！
        TermFreqVector contentFreqVector = reader.getTermFreqVector(docId, "itemContent");
        if(contentFreqVector != null){
            //生成TermVector ArryList!
            List<termvector> contentVectorList = new ArrayList<termvector>();  </termvector></termvector>

            for (int i = 0; i < contentFreqVector.size(); i++) {
                String termWord=contentFreqVector.getTerms()[i];
                String regex="[a-zA-Z]{4,}|[\u4E00-\u9fa5]{2,5}";  //英文4个以上，中文2到5个
                boolean is = termWord.matches(regex);

                if(is==true){
                Term term = new Term("itemContent",contentFreqVector.getTerms()[i]);
                TermVector termVector = new TermVector();
                termVector.termWord = termWord;
                termVector.termFreq = contentFreqVector.getTermFrequencies()[i];

    //          termVector.docFreq = searcher.docFreq(term);
       //一般来说IDF值越大，权重越高，该词在全网出现的频率越小
                termVector.IDF = searcher.getSimilarity().idf(term, searcher);
                Similarity sim = Similarity.getDefault();
                termVector.TF = sim.tf(contentFreqVector.getTermFrequencies()[i]);
                contentVectorList.add(termVector);

            }
        }

        //按照制定的算法进行排序！ 算法还需要完善 需要考虑 TF/IDF 信息熵方面的东西！
        Comparator<termvector> comp = new TermComparator();  </termvector>
        Collections.sort(contentVectorList,comp);



   class TermComparator implements Comparator {

        public int compare(Object o1, Object o2) {
            TermVector t1 = (TermVector) o1;
            TermVector t2 = (TermVector) o2;
            if (t1.getWeight() < t2.getWeight())
                return 1;
            else
                return 0;
        }
 }
 //Document itemDoc = reader.document(docId);