21 lines
573 B
Java
21 lines
573 B
Java
package com.star.util;
|
||
|
||
import java.util.List;
|
||
|
||
public class Normalizer {
|
||
|
||
|
||
|
||
public static String removeVersion(String str){
|
||
|
||
//现在对于2.45还不能处理,也就是点后边两个连续的后缀
|
||
return str.replaceAll("\\-*\\d+(\\.[\\d|x|X])*$","");
|
||
}
|
||
|
||
//对字符串进行规整,去除版本号后缀和连接符等
|
||
public static String normalize(String str) {
|
||
//目前可能会删除掉一些确实以数字结尾的项目;在停用词里添加‘-’
|
||
return removeVersion(str).replaceAll("[\\-]+"," ").replaceAll("'s"," ").toLowerCase();
|
||
}
|
||
}
|