KMP算法原理:https://blog.csdn.net/dark_cy/article/details/88698736
KMP算法是用来进行字符串匹配查找的,比如在字符串1中查找是否包含字符串2。核心是先求出Next数组。
next数组表示的是待查找的字符串的最大公共前后缀中的公共前缀的最后一个字符的下标,知道这个下标,就可以知道当匹配目标字符串出错时,目标字符串的指针怎么回退,而查找段落的指针不用回退,这样遍历一遍查找段落,就可以知道是否存在目标字符串,时间复杂度为O(n)
KMP算法的时间复杂度为O(n+m)
代码实现:
/**
* 时间复杂度O(n+m)
*/
public class KMP {
//通过计算返回字串pattern的next数组
public int[] get_next(char[] pattern){
int[] next = new int[pattern.length];
next[0] = -1;
int i = 0;
int j = -1;
while(i < pattern.length-1){
if(j == -1 || pattern[i] == pattern[j]){
++i;
++j;
next[i] = j;
}else{
//若字符不相同,则j值回溯
j = next[j];
}
}
System.out.print("next: ");
for (int i1 : next) {
System.out.print(i1+" ");
}
return next;
}
//改进版求nextval
public int[] get_nextval(char[] pattern){
int[] nextval = new int[pattern.length];
nextval[0] = -1;
int i = 0;
int j = -1;
while(i < pattern.length - 1){
if(j == -1 || pattern[i] == pattern[j]){
++i;
++j;
if(pattern[i] != pattern[j]){
nextval[i] = j;
}else{
nextval[i] = nextval[j];
}
}else{
j = nextval[j];
}
}
System.out.print("nextval: ");
for (int i1 : nextval) {
System.out.print(i1+" ");
}
System.out.println(" ");
return nextval;
}
//primary是主串,pattern是子串,匹配成功返回下标,匹配不成功返回-1
public int kmp_Index(char[] primary, char[] pattern){
int[] next = get_nextval(pattern);
int i = 0;
int j = 0;
while(i <= primary.length - 1 && j <= pattern.length - 1){
if(j == -1 || primary[i] == pattern[j]){
++i;
++j;
}else{
j = next[j];
}
}
if(j < pattern.length){
return -1;
}else{
return i - pattern.length;
}
}
public static void main(String[] args) {
KMP kmp = new KMP();
String s = "abbabbbbcab";
String ss = "babbb";
char[] s1 = s.toCharArray();
char[] ss1 = ss.toCharArray();
kmp.get_next(ss1);
System.out.println(" ");
System.out.println("主串匹配位置: "+kmp.kmp_Index(s1, ss1));
}
}