查询文档标题相似度

阅读更多

/**
* 文档相似度查询
*/
@SuppressWarnings("unchecked")
@Override
public List queryDocList(MyLibraryModel model) {
List list = new ArrayList();
List librarylist = dao.queryDocListItems(model);
for (int c = 0; c < librarylist.size(); c++) {
MyLibraryModel myModel = librarylist.get(c);
String str1 = myModel.getLibTitle();
String str2 = model.getLibTitle();
// 计算两个字符串的长度。
int len1 = str1.length();
int len2 = str2.length();

// 建立上面说的数组，比字符长度大一个空间
int[][] dif = new int[len1 + 1][len2 + 1];
// 赋初值，步骤B。
for (int a = 0; a <= len1; a++) {
dif[a][0] = a;
}
for (int a = 0; a <= len2; a++) {
dif[0][a] = a;
}
// 计算两个字符是否一样，计算左上的值
int temp;
for (int k = 1; k <= len1; k++) {
for (int j = 1; j <= len2; j++) {
if (str1.charAt(k - 1) == str2.charAt(j - 1)) {
temp = 0;
} else {
temp = 1;
}
// 取三个值中最小的
dif[k][j] = min(dif[k - 1][j - 1] + temp,
dif[k][j - 1] + 1, dif[k - 1][j] + 1);
}
}
// 取数组右下角的值，同样不同位置代表不同字符串的比较
// 计算相似度
float similarity = 1 - (float) dif[len1][len2]
/ Math.max(str1.length(), str2.length());
if (similarity > 0) {
myModel.setSimilarity(similarity);
list.add(myModel);
}
}
Collections.sort(list, new Comparator() {
public int compare(Object a, Object b) {
float one = ((MyLibraryModel) a).getSimilarity();
float two = ((MyLibraryModel) b).getSimilarity();
if (one > two)
return 0;
return 1;
}
});
if (list.size() > 4) {
return list.subList(0, 4);
}
return list;
}

/**
* 得到最小值
*
* @param is
* @return
*/
private static int min(int... is) {
int min = Integer.MAX_VALUE;
for (int i : is) {
if (min > i) {
min = i;
}
}
return min;
}