tfidf算法+余弦相似度算法计算文本相似度

TF-IDF（term frequency–inverse document frequency）是一种用于信息检索与数据挖掘的常用加权技术。TF意思是词频(Term Frequency)，IDF意思是逆向文件频率(Inverse Document Frequency)。

思想：对文本进行分词，然后用tfidf算法得到文本对应的词向量，然后利用余弦算法求相似度
需要的jar :je-analysis-1.5.3.jar ,lucene-core-2.4.1.jar（高于4的版本会有冲突）

/**
 * 直接匹配2个文本
 * 
 * @author rock
 *
 */
public class GetText {
   
    private static List<String> fileList = new ArrayList<String>();
    private static HashMap<String, HashMap<String, Double>> allTheTf = new HashMap<String, HashMap<String, Double>>();
    private static HashMap<String, HashMap<String, Integer>> allTheNormalTF = new HashMap<String, HashMap<String, Integer>>();
    private static LinkedHashMap<String, Double[]> vectorMap = new LinkedHashMap<String, Double[]>();

    /**
     * 分词
     * 
     * @author create by rock
     */
    public static String[] TextcutWord(String text) throws IOException {
        String[] cutWordResult = null;
        MMAnalyzer analyzer = new MMAnalyzer();
        String tempCutWordResult = analyzer.segment(text, " ");
        cutWordResult = tempCutWordResult.split(" ");
        return cutWordResult;
    }

    public static Map<String, HashMap<String, Integer>> NormalTFOfAll(String key1, String key2, String text1,
            String text2) throws IOException {
        if (allTheNormalTF.get(key1) == null) {
            HashMap<String, Integer> dict1 = new HashMap<String, Integer>();
            dict1 = normalTF(TextcutWord(text1));
            allTheNormalTF.put(key1, dict1);
        }
        if (allTheNormalTF.get(key2) == null) {
            HashMap<String, Integer> dict2 = new HashMap<String, Integer>();
            dict2 = normalTF(TextcutWord(text2));
            allTheNormalTF.put(key2, dict2);
        }
        return allTheNormalTF;
    }

    public static Map<String, HashMap<String, Double>> tfOfAll(String key1, String key2, String text1, String text2)
            throws IOException {
            allTheTf.clear();
            HashMap<String, Double> dict1 = new HashMap<String, Double>();
            HashMap<String, Double> dict2 = new HashMap<String, Double>();
            dict1 = tf(TextcutWord(text1));
            dict2 = tf(TextcutWord(text2));
            allTheTf.put(key1, dict1);
            allTheTf.put(key2, dict2);
            return allTheTf;
    }

    /**
     * 计算词频
     * 
     * @author create by rock
     */
    public static HashMap<String, Double> tf(String[] cutWordResult) {
        HashMap<String, Double> tf = new HashMap<String, Double>();// 正规化
        int wordNum = cutWordResult.length;
        int wordtf = 0;
        for (int i = 0; i < wordNum; i++) {
            wordtf = 0;
            if (cutWordResult[i] != " ") {
                for (int j = 0; j < wordNum; j++) {
                    if (i != j) {
                        if (cutWordResult[i].equals(cutWordResult[j])) {
                            cutWordResult[j] = " ";
                            wordtf++;
                        }
                    }
                }
                tf.put(cutWordResult[i], (new Double(++wordtf)) / wordNum);
                cutWordResult[i] =