zoukankan      html  css  js  c++  java
  • 字符串相似度匹配

    /**
        * 相似度
        * @param str1
        * @param str2
        */
       public static float levenshtein(String str1,String str2) {
           int len1 = str1.length();
           int len2 = str2.length();
           int[][] dif = new int[len1 + 1][len2 + 1];
           for (int a = 0; a <= len1; a++) {
               dif[a][0] = a;
           }
           for (int a = 0; a <= len2; a++) {
               dif[0][a] = a;
           }
           int temp;
           for (int i = 1; i <= len1; i++) {
               for (int j = 1; j <= len2; j++) {
                   if (str1.charAt(i - 1) == str2.charAt(j - 1)) {
                       temp = 0;
                   } else {
                       temp = 1;
                   }
                   dif[i][j] = min(dif[i - 1][j - 1] + temp, dif[i][j - 1] + 1,
                           dif[i - 1][j] + 1);
               }
           }
           logger.debug("字符串[{}]与[{}]比较",str1,str2);
           logger.debug("差异步骤:"+dif[len1][len2]);
           float similarity =1 - (float) dif[len1][len2] / Math.max(str1.length(), str2.length());
           logger.debug("相似度:"+similarity);
           return similarity;
       }
    
       private static int min(int... is) {
           int min = Integer.MAX_VALUE;
           for (int i : is) {
               if (min > i) {
                   min = i;
               }
           }
           return min;
       }
  • 相关阅读:
    table 如何不越过父级div
    sqlite3_column_type 与 SQLITE_NULL的区别
    lua 协程的理解
    linux 信号
    linux 查看文件夹大小
    linux 僵屍进程
    软件架构的理解
    jquery正则表达式
    linux C遍历目录下文件
    linux 进程间同步互斥
  • 原文地址:https://www.cnblogs.com/mignet/p/11562561.html
Copyright © 2011-2022 走看看